diff --git a/BHPD/01-DNN-Regression.ipynb b/BHPD/01-DNN-Regression.ipynb
index 48dcbae6f509efe63e510c24d6a4a5e1771582ec..b8ee713cd35a0caf62534e7df26f79eb519fbedf 100644
--- a/BHPD/01-DNN-Regression.ipynb
+++ b/BHPD/01-DNN-Regression.ipynb
@@ -43,9 +43,9 @@
"output_type": "stream",
"text": [
"IDLE 2020 - Practical Work Module\n",
- " Version : 0.2\n",
- " Run time : Thursday 30 January 2020, 13:57:24\n",
- " Matplotlib style : fidle/talk.mplstyle\n",
+ " Version : 0.2.4\n",
+ " Run time : Sunday 2 February 2020, 15:17:29\n",
+ " Matplotlib style : ../fidle/talk.mplstyle\n",
" TensorFlow version : 2.0.0\n",
" Keras version : 2.2.4-tf\n"
]
@@ -58,12 +58,14 @@
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import pandas as pd\n",
- "import os\n",
+ "import os,sys\n",
"\n",
"from IPython.display import display, Markdown\n",
- "import fidle.pwk as ooo\n",
"from importlib import reload\n",
"\n",
+ "sys.path.append('..')\n",
+ "import fidle.pwk as ooo\n",
+ "\n",
"ooo.init()"
]
},
@@ -94,116 +96,9 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<style type=\"text/css\" >\n",
- "</style><table id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddf\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >crim</th> <th class=\"col_heading level0 col1\" >zn</th> <th class=\"col_heading level0 col2\" >indus</th> <th class=\"col_heading level0 col3\" >chas</th> <th class=\"col_heading level0 col4\" >nox</th> <th class=\"col_heading level0 col5\" >rm</th> <th class=\"col_heading level0 col6\" >age</th> <th class=\"col_heading level0 col7\" >dis</th> <th class=\"col_heading level0 col8\" >rad</th> <th class=\"col_heading level0 col9\" >tax</th> <th class=\"col_heading level0 col10\" >ptratio</th> <th class=\"col_heading level0 col11\" >b</th> <th class=\"col_heading level0 col12\" >lstat</th> <th class=\"col_heading level0 col13\" >medv</th> </tr></thead><tbody>\n",
- " <tr>\n",
- " <th id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddflevel0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col0\" class=\"data row0 col0\" >0.01</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col1\" class=\"data row0 col1\" >18.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col2\" class=\"data row0 col2\" >2.31</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col3\" class=\"data row0 col3\" >0.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col4\" class=\"data row0 col4\" >0.54</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col5\" class=\"data row0 col5\" >6.58</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col6\" class=\"data row0 col6\" >65.20</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col7\" class=\"data row0 col7\" >4.09</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col8\" class=\"data row0 col8\" >1.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col9\" class=\"data row0 col9\" >296.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col10\" class=\"data row0 col10\" >15.30</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col11\" class=\"data row0 col11\" >396.90</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col12\" class=\"data row0 col12\" >4.98</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow0_col13\" class=\"data row0 col13\" >24.00</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddflevel0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col0\" class=\"data row1 col0\" >0.03</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col1\" class=\"data row1 col1\" >0.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col2\" class=\"data row1 col2\" >7.07</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col3\" class=\"data row1 col3\" >0.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col4\" class=\"data row1 col4\" >0.47</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col5\" class=\"data row1 col5\" >6.42</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col6\" class=\"data row1 col6\" >78.90</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col7\" class=\"data row1 col7\" >4.97</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col8\" class=\"data row1 col8\" >2.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col9\" class=\"data row1 col9\" >242.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col10\" class=\"data row1 col10\" >17.80</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col11\" class=\"data row1 col11\" >396.90</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col12\" class=\"data row1 col12\" >9.14</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow1_col13\" class=\"data row1 col13\" >21.60</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddflevel0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col0\" class=\"data row2 col0\" >0.03</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col1\" class=\"data row2 col1\" >0.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col2\" class=\"data row2 col2\" >7.07</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col3\" class=\"data row2 col3\" >0.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col4\" class=\"data row2 col4\" >0.47</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col5\" class=\"data row2 col5\" >7.18</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col6\" class=\"data row2 col6\" >61.10</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col7\" class=\"data row2 col7\" >4.97</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col8\" class=\"data row2 col8\" >2.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col9\" class=\"data row2 col9\" >242.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col10\" class=\"data row2 col10\" >17.80</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col11\" class=\"data row2 col11\" >392.83</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col12\" class=\"data row2 col12\" >4.03</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow2_col13\" class=\"data row2 col13\" >34.70</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddflevel0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col0\" class=\"data row3 col0\" >0.03</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col1\" class=\"data row3 col1\" >0.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col2\" class=\"data row3 col2\" >2.18</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col3\" class=\"data row3 col3\" >0.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col4\" class=\"data row3 col4\" >0.46</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col5\" class=\"data row3 col5\" >7.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col6\" class=\"data row3 col6\" >45.80</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col7\" class=\"data row3 col7\" >6.06</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col8\" class=\"data row3 col8\" >3.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col9\" class=\"data row3 col9\" >222.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col10\" class=\"data row3 col10\" >18.70</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col11\" class=\"data row3 col11\" >394.63</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col12\" class=\"data row3 col12\" >2.94</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow3_col13\" class=\"data row3 col13\" >33.40</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddflevel0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col0\" class=\"data row4 col0\" >0.07</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col1\" class=\"data row4 col1\" >0.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col2\" class=\"data row4 col2\" >2.18</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col3\" class=\"data row4 col3\" >0.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col4\" class=\"data row4 col4\" >0.46</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col5\" class=\"data row4 col5\" >7.15</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col6\" class=\"data row4 col6\" >54.20</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col7\" class=\"data row4 col7\" >6.06</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col8\" class=\"data row4 col8\" >3.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col9\" class=\"data row4 col9\" >222.00</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col10\" class=\"data row4 col10\" >18.70</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col11\" class=\"data row4 col11\" >396.90</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col12\" class=\"data row4 col12\" >5.33</td>\n",
- " <td id=\"T_1413a27e_4360_11ea_8817_9fb1a1a03ddfrow4_col13\" class=\"data row4 col13\" >36.20</td>\n",
- " </tr>\n",
- " </tbody></table>"
- ],
- "text/plain": [
- "<pandas.io.formats.style.Styler at 0x7f66b1797890>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Données manquantes : 0 Shape is : (506, 14)\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"data = pd.read_csv('./data/BostonHousing.csv', header=0)\n",
"\n",
@@ -223,19 +118,9 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Original data shape was : (506, 14)\n",
- "x_train : (354, 13) y_train : (354,)\n",
- "x_test : (152, 13) y_test : (152,)\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"# ---- Split => train, test\n",
"#\n",
@@ -268,294 +153,9 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<style type=\"text/css\" >\n",
- "</style><table id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddf\" ><caption>Before normalization :</caption><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >crim</th> <th class=\"col_heading level0 col1\" >zn</th> <th class=\"col_heading level0 col2\" >indus</th> <th class=\"col_heading level0 col3\" >chas</th> <th class=\"col_heading level0 col4\" >nox</th> <th class=\"col_heading level0 col5\" >rm</th> <th class=\"col_heading level0 col6\" >age</th> <th class=\"col_heading level0 col7\" >dis</th> <th class=\"col_heading level0 col8\" >rad</th> <th class=\"col_heading level0 col9\" >tax</th> <th class=\"col_heading level0 col10\" >ptratio</th> <th class=\"col_heading level0 col11\" >b</th> <th class=\"col_heading level0 col12\" >lstat</th> </tr></thead><tbody>\n",
- " <tr>\n",
- " <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col0\" class=\"data row0 col0\" >354.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col1\" class=\"data row0 col1\" >354.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col2\" class=\"data row0 col2\" >354.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col3\" class=\"data row0 col3\" >354.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col4\" class=\"data row0 col4\" >354.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col5\" class=\"data row0 col5\" >354.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col6\" class=\"data row0 col6\" >354.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col7\" class=\"data row0 col7\" >354.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col8\" class=\"data row0 col8\" >354.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col9\" class=\"data row0 col9\" >354.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col10\" class=\"data row0 col10\" >354.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col11\" class=\"data row0 col11\" >354.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow0_col12\" class=\"data row0 col12\" >354.00</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col0\" class=\"data row1 col0\" >3.69</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col1\" class=\"data row1 col1\" >10.39</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col2\" class=\"data row1 col2\" >11.51</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col3\" class=\"data row1 col3\" >0.07</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col4\" class=\"data row1 col4\" >0.55</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col5\" class=\"data row1 col5\" >6.27</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col6\" class=\"data row1 col6\" >69.52</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col7\" class=\"data row1 col7\" >3.76</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col8\" class=\"data row1 col8\" >9.82</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col9\" class=\"data row1 col9\" >412.81</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col10\" class=\"data row1 col10\" >18.59</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col11\" class=\"data row1 col11\" >358.13</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow1_col12\" class=\"data row1 col12\" >12.80</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col0\" class=\"data row2 col0\" >8.49</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col1\" class=\"data row2 col1\" >22.21</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col2\" class=\"data row2 col2\" >6.94</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col3\" class=\"data row2 col3\" >0.25</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col4\" class=\"data row2 col4\" >0.11</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col5\" class=\"data row2 col5\" >0.68</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col6\" class=\"data row2 col6\" >27.74</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col7\" class=\"data row2 col7\" >2.06</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col8\" class=\"data row2 col8\" >8.83</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col9\" class=\"data row2 col9\" >171.63</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col10\" class=\"data row2 col10\" >2.13</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col11\" class=\"data row2 col11\" >88.80</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow2_col12\" class=\"data row2 col12\" >7.07</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col0\" class=\"data row3 col0\" >0.01</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col1\" class=\"data row3 col1\" >0.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col2\" class=\"data row3 col2\" >1.21</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col3\" class=\"data row3 col3\" >0.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col4\" class=\"data row3 col4\" >0.39</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col5\" class=\"data row3 col5\" >3.56</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col6\" class=\"data row3 col6\" >2.90</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col7\" class=\"data row3 col7\" >1.13</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col8\" class=\"data row3 col8\" >1.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col9\" class=\"data row3 col9\" >188.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col10\" class=\"data row3 col10\" >12.60</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col11\" class=\"data row3 col11\" >0.32</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow3_col12\" class=\"data row3 col12\" >1.92</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col0\" class=\"data row4 col0\" >0.08</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col1\" class=\"data row4 col1\" >0.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col2\" class=\"data row4 col2\" >5.32</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col3\" class=\"data row4 col3\" >0.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col4\" class=\"data row4 col4\" >0.45</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col5\" class=\"data row4 col5\" >5.88</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col6\" class=\"data row4 col6\" >46.40</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col7\" class=\"data row4 col7\" >2.10</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col8\" class=\"data row4 col8\" >4.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col9\" class=\"data row4 col9\" >279.50</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col10\" class=\"data row4 col10\" >17.40</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col11\" class=\"data row4 col11\" >376.12</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow4_col12\" class=\"data row4 col12\" >7.21</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col0\" class=\"data row5 col0\" >0.25</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col1\" class=\"data row5 col1\" >0.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col2\" class=\"data row5 col2\" >9.90</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col3\" class=\"data row5 col3\" >0.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col4\" class=\"data row5 col4\" >0.54</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col5\" class=\"data row5 col5\" >6.17</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col6\" class=\"data row5 col6\" >78.80</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col7\" class=\"data row5 col7\" >3.11</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col8\" class=\"data row5 col8\" >5.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col9\" class=\"data row5 col9\" >336.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col10\" class=\"data row5 col10\" >19.10</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col11\" class=\"data row5 col11\" >391.26</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow5_col12\" class=\"data row5 col12\" >12.02</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col0\" class=\"data row6 col0\" >4.18</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col1\" class=\"data row6 col1\" >9.38</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col2\" class=\"data row6 col2\" >18.10</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col3\" class=\"data row6 col3\" >0.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col4\" class=\"data row6 col4\" >0.62</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col5\" class=\"data row6 col5\" >6.60</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col6\" class=\"data row6 col6\" >94.45</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col7\" class=\"data row6 col7\" >5.19</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col8\" class=\"data row6 col8\" >24.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col9\" class=\"data row6 col9\" >666.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col10\" class=\"data row6 col10\" >20.20</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col11\" class=\"data row6 col11\" >396.17</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow6_col12\" class=\"data row6 col12\" >17.25</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddflevel0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col0\" class=\"data row7 col0\" >73.53</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col1\" class=\"data row7 col1\" >100.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col2\" class=\"data row7 col2\" >27.74</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col3\" class=\"data row7 col3\" >1.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col4\" class=\"data row7 col4\" >0.87</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col5\" class=\"data row7 col5\" >8.72</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col6\" class=\"data row7 col6\" >100.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col7\" class=\"data row7 col7\" >10.71</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col8\" class=\"data row7 col8\" >24.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col9\" class=\"data row7 col9\" >711.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col10\" class=\"data row7 col10\" >22.00</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col11\" class=\"data row7 col11\" >396.90</td>\n",
- " <td id=\"T_182f41ce_4360_11ea_8817_9fb1a1a03ddfrow7_col12\" class=\"data row7 col12\" >36.98</td>\n",
- " </tr>\n",
- " </tbody></table>"
- ],
- "text/plain": [
- "<pandas.io.formats.style.Styler at 0x7f66b277cc90>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "text/html": [
- "<style type=\"text/css\" >\n",
- "</style><table id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddf\" ><caption>After normalization :</caption><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >crim</th> <th class=\"col_heading level0 col1\" >zn</th> <th class=\"col_heading level0 col2\" >indus</th> <th class=\"col_heading level0 col3\" >chas</th> <th class=\"col_heading level0 col4\" >nox</th> <th class=\"col_heading level0 col5\" >rm</th> <th class=\"col_heading level0 col6\" >age</th> <th class=\"col_heading level0 col7\" >dis</th> <th class=\"col_heading level0 col8\" >rad</th> <th class=\"col_heading level0 col9\" >tax</th> <th class=\"col_heading level0 col10\" >ptratio</th> <th class=\"col_heading level0 col11\" >b</th> <th class=\"col_heading level0 col12\" >lstat</th> </tr></thead><tbody>\n",
- " <tr>\n",
- " <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col0\" class=\"data row0 col0\" >354.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col1\" class=\"data row0 col1\" >354.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col2\" class=\"data row0 col2\" >354.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col3\" class=\"data row0 col3\" >354.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col4\" class=\"data row0 col4\" >354.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col5\" class=\"data row0 col5\" >354.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col6\" class=\"data row0 col6\" >354.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col7\" class=\"data row0 col7\" >354.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col8\" class=\"data row0 col8\" >354.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col9\" class=\"data row0 col9\" >354.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col10\" class=\"data row0 col10\" >354.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col11\" class=\"data row0 col11\" >354.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow0_col12\" class=\"data row0 col12\" >354.00</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col0\" class=\"data row1 col0\" >0.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col1\" class=\"data row1 col1\" >0.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col2\" class=\"data row1 col2\" >0.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col3\" class=\"data row1 col3\" >-0.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col4\" class=\"data row1 col4\" >-0.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col5\" class=\"data row1 col5\" >0.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col6\" class=\"data row1 col6\" >0.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col7\" class=\"data row1 col7\" >-0.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col8\" class=\"data row1 col8\" >0.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col9\" class=\"data row1 col9\" >-0.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col10\" class=\"data row1 col10\" >0.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col11\" class=\"data row1 col11\" >0.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow1_col12\" class=\"data row1 col12\" >0.00</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col0\" class=\"data row2 col0\" >1.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col1\" class=\"data row2 col1\" >1.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col2\" class=\"data row2 col2\" >1.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col3\" class=\"data row2 col3\" >1.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col4\" class=\"data row2 col4\" >1.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col5\" class=\"data row2 col5\" >1.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col6\" class=\"data row2 col6\" >1.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col7\" class=\"data row2 col7\" >1.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col8\" class=\"data row2 col8\" >1.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col9\" class=\"data row2 col9\" >1.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col10\" class=\"data row2 col10\" >1.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col11\" class=\"data row2 col11\" >1.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow2_col12\" class=\"data row2 col12\" >1.00</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col0\" class=\"data row3 col0\" >-0.43</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col1\" class=\"data row3 col1\" >-0.47</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col2\" class=\"data row3 col2\" >-1.49</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col3\" class=\"data row3 col3\" >-0.27</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col4\" class=\"data row3 col4\" >-1.50</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col5\" class=\"data row3 col5\" >-4.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col6\" class=\"data row3 col6\" >-2.40</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col7\" class=\"data row3 col7\" >-1.28</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col8\" class=\"data row3 col8\" >-1.00</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col9\" class=\"data row3 col9\" >-1.31</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col10\" class=\"data row3 col10\" >-2.81</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col11\" class=\"data row3 col11\" >-4.03</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow3_col12\" class=\"data row3 col12\" >-1.54</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col0\" class=\"data row4 col0\" >-0.42</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col1\" class=\"data row4 col1\" >-0.47</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col2\" class=\"data row4 col2\" >-0.89</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col3\" class=\"data row4 col3\" >-0.27</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col4\" class=\"data row4 col4\" >-0.93</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col5\" class=\"data row4 col5\" >-0.58</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col6\" class=\"data row4 col6\" >-0.83</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col7\" class=\"data row4 col7\" >-0.81</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col8\" class=\"data row4 col8\" >-0.66</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col9\" class=\"data row4 col9\" >-0.78</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col10\" class=\"data row4 col10\" >-0.56</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col11\" class=\"data row4 col11\" >0.20</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow4_col12\" class=\"data row4 col12\" >-0.79</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col0\" class=\"data row5 col0\" >-0.40</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col1\" class=\"data row5 col1\" >-0.47</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col2\" class=\"data row5 col2\" >-0.23</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col3\" class=\"data row5 col3\" >-0.27</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col4\" class=\"data row5 col4\" >-0.14</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col5\" class=\"data row5 col5\" >-0.15</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col6\" class=\"data row5 col6\" >0.33</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col7\" class=\"data row5 col7\" >-0.32</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col8\" class=\"data row5 col8\" >-0.55</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col9\" class=\"data row5 col9\" >-0.45</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col10\" class=\"data row5 col10\" >0.24</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col11\" class=\"data row5 col11\" >0.37</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow5_col12\" class=\"data row5 col12\" >-0.11</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col0\" class=\"data row6 col0\" >0.06</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col1\" class=\"data row6 col1\" >-0.05</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col2\" class=\"data row6 col2\" >0.95</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col3\" class=\"data row6 col3\" >-0.27</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col4\" class=\"data row6 col4\" >0.62</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col5\" class=\"data row6 col5\" >0.49</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col6\" class=\"data row6 col6\" >0.90</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col7\" class=\"data row6 col7\" >0.69</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col8\" class=\"data row6 col8\" >1.61</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col9\" class=\"data row6 col9\" >1.48</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col10\" class=\"data row6 col10\" >0.76</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col11\" class=\"data row6 col11\" >0.43</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow6_col12\" class=\"data row6 col12\" >0.63</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddflevel0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col0\" class=\"data row7 col0\" >8.23</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col1\" class=\"data row7 col1\" >4.04</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col2\" class=\"data row7 col2\" >2.34</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col3\" class=\"data row7 col3\" >3.70</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col4\" class=\"data row7 col4\" >2.82</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col5\" class=\"data row7 col5\" >3.62</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col6\" class=\"data row7 col6\" >1.10</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col7\" class=\"data row7 col7\" >3.37</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col8\" class=\"data row7 col8\" >1.61</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col9\" class=\"data row7 col9\" >1.74</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col10\" class=\"data row7 col10\" >1.60</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col11\" class=\"data row7 col11\" >0.44</td>\n",
- " <td id=\"T_18500710_4360_11ea_8817_9fb1a1a03ddfrow7_col12\" class=\"data row7 col12\" >3.42</td>\n",
- " </tr>\n",
- " </tbody></table>"
- ],
- "text/plain": [
- "<pandas.io.formats.style.Styler at 0x7f66b0230290>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
"source": [
"display(x_train.describe().style.format(\"{0:.2f}\").set_caption(\"Before normalization :\"))\n",
"\n",
@@ -584,7 +184,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -610,30 +210,9 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Model: \"sequential\"\n",
- "_________________________________________________________________\n",
- "Layer (type) Output Shape Param # \n",
- "=================================================================\n",
- "dense (Dense) (None, 64) 896 \n",
- "_________________________________________________________________\n",
- "dense_1 (Dense) (None, 64) 4160 \n",
- "_________________________________________________________________\n",
- "dense_2 (Dense) (None, 1) 65 \n",
- "=================================================================\n",
- "Total params: 5,121\n",
- "Trainable params: 5,121\n",
- "Non-trainable params: 0\n",
- "_________________________________________________________________\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"model=get_model_v1( (13,) )\n",
"\n",
@@ -649,217 +228,9 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Train on 354 samples, validate on 152 samples\n",
- "Epoch 1/100\n",
- "354/354 [==============================] - 1s 2ms/sample - loss: 458.8973 - mae: 19.4424 - mse: 458.8973 - val_loss: 318.9800 - val_mae: 15.9424 - val_mse: 318.9801\n",
- "Epoch 2/100\n",
- "354/354 [==============================] - 0s 229us/sample - loss: 213.7796 - mae: 12.2567 - mse: 213.7796 - val_loss: 101.1658 - val_mae: 8.0594 - val_mse: 101.1658\n",
- "Epoch 3/100\n",
- "354/354 [==============================] - 0s 208us/sample - loss: 72.5785 - mae: 6.2987 - mse: 72.5785 - val_loss: 44.4772 - val_mae: 5.2539 - val_mse: 44.4771\n",
- "Epoch 4/100\n",
- "354/354 [==============================] - 0s 197us/sample - loss: 37.8617 - mae: 4.3850 - mse: 37.8617 - val_loss: 26.7013 - val_mae: 4.0062 - val_mse: 26.7013\n",
- "Epoch 5/100\n",
- "354/354 [==============================] - 0s 213us/sample - loss: 28.4107 - mae: 3.7569 - mse: 28.4106 - val_loss: 22.1095 - val_mae: 3.6372 - val_mse: 22.1095\n",
- "Epoch 6/100\n",
- "354/354 [==============================] - 0s 200us/sample - loss: 23.1609 - mae: 3.4180 - mse: 23.1609 - val_loss: 23.2152 - val_mae: 3.7587 - val_mse: 23.2152\n",
- "Epoch 7/100\n",
- "354/354 [==============================] - 0s 212us/sample - loss: 20.4846 - mae: 3.2105 - mse: 20.4846 - val_loss: 19.2353 - val_mae: 3.2211 - val_mse: 19.2353\n",
- "Epoch 8/100\n",
- "354/354 [==============================] - 0s 182us/sample - loss: 18.0685 - mae: 3.0027 - mse: 18.0685 - val_loss: 18.5149 - val_mae: 3.1562 - val_mse: 18.5149\n",
- "Epoch 9/100\n",
- "354/354 [==============================] - 0s 192us/sample - loss: 16.9782 - mae: 2.9048 - mse: 16.9782 - val_loss: 17.4633 - val_mae: 2.8894 - val_mse: 17.4633\n",
- "Epoch 10/100\n",
- "354/354 [==============================] - 0s 184us/sample - loss: 15.3535 - mae: 2.7671 - mse: 15.3535 - val_loss: 17.4349 - val_mae: 2.9033 - val_mse: 17.4349\n",
- "Epoch 11/100\n",
- "354/354 [==============================] - 0s 211us/sample - loss: 14.0626 - mae: 2.6465 - mse: 14.0626 - val_loss: 18.2428 - val_mae: 3.0016 - val_mse: 18.2428\n",
- "Epoch 12/100\n",
- "354/354 [==============================] - 0s 213us/sample - loss: 13.5890 - mae: 2.5958 - mse: 13.5890 - val_loss: 16.3660 - val_mae: 2.6599 - val_mse: 16.3660\n",
- "Epoch 13/100\n",
- "354/354 [==============================] - 0s 193us/sample - loss: 13.0816 - mae: 2.5412 - mse: 13.0816 - val_loss: 16.1545 - val_mae: 2.6357 - val_mse: 16.1545\n",
- "Epoch 14/100\n",
- "354/354 [==============================] - 0s 179us/sample - loss: 12.4630 - mae: 2.4577 - mse: 12.4630 - val_loss: 18.6261 - val_mae: 2.8769 - val_mse: 18.6261\n",
- "Epoch 15/100\n",
- "354/354 [==============================] - 0s 180us/sample - loss: 11.8046 - mae: 2.4121 - mse: 11.8046 - val_loss: 16.6238 - val_mae: 2.6581 - val_mse: 16.6238\n",
- "Epoch 16/100\n",
- "354/354 [==============================] - 0s 203us/sample - loss: 11.5041 - mae: 2.3948 - mse: 11.5042 - val_loss: 19.4839 - val_mae: 2.9697 - val_mse: 19.4839\n",
- "Epoch 17/100\n",
- "354/354 [==============================] - 0s 207us/sample - loss: 11.4561 - mae: 2.4221 - mse: 11.4561 - val_loss: 15.4893 - val_mae: 2.5344 - val_mse: 15.4893\n",
- "Epoch 18/100\n",
- "354/354 [==============================] - 0s 201us/sample - loss: 11.2035 - mae: 2.3512 - mse: 11.2035 - val_loss: 16.1624 - val_mae: 2.6216 - val_mse: 16.1624\n",
- "Epoch 19/100\n",
- "354/354 [==============================] - 0s 205us/sample - loss: 10.8601 - mae: 2.3359 - mse: 10.8601 - val_loss: 16.6674 - val_mae: 2.6028 - val_mse: 16.6674\n",
- "Epoch 20/100\n",
- "354/354 [==============================] - 0s 204us/sample - loss: 10.5051 - mae: 2.2677 - mse: 10.5051 - val_loss: 15.9863 - val_mae: 2.5769 - val_mse: 15.9863\n",
- "Epoch 21/100\n",
- "354/354 [==============================] - 0s 186us/sample - loss: 10.2899 - mae: 2.2877 - mse: 10.2899 - val_loss: 16.1491 - val_mae: 2.5465 - val_mse: 16.1491\n",
- "Epoch 22/100\n",
- "354/354 [==============================] - 0s 197us/sample - loss: 10.1146 - mae: 2.2151 - mse: 10.1146 - val_loss: 16.0190 - val_mae: 2.5167 - val_mse: 16.0190\n",
- "Epoch 23/100\n",
- "354/354 [==============================] - 0s 208us/sample - loss: 10.0647 - mae: 2.2372 - mse: 10.0647 - val_loss: 16.0099 - val_mae: 2.5391 - val_mse: 16.0099\n",
- "Epoch 24/100\n",
- "354/354 [==============================] - 0s 205us/sample - loss: 9.7932 - mae: 2.2132 - mse: 9.7932 - val_loss: 15.0919 - val_mae: 2.4853 - val_mse: 15.0919\n",
- "Epoch 25/100\n",
- "354/354 [==============================] - 0s 200us/sample - loss: 9.7249 - mae: 2.1589 - mse: 9.7249 - val_loss: 16.0316 - val_mae: 2.5151 - val_mse: 16.0316\n",
- "Epoch 26/100\n",
- "354/354 [==============================] - 0s 208us/sample - loss: 9.4263 - mae: 2.1743 - mse: 9.4263 - val_loss: 14.8897 - val_mae: 2.4844 - val_mse: 14.8897\n",
- "Epoch 27/100\n",
- "354/354 [==============================] - 0s 196us/sample - loss: 9.2317 - mae: 2.1075 - mse: 9.2317 - val_loss: 16.4898 - val_mae: 2.5348 - val_mse: 16.4898\n",
- "Epoch 28/100\n",
- "354/354 [==============================] - 0s 193us/sample - loss: 8.9923 - mae: 2.1092 - mse: 8.9923 - val_loss: 15.7991 - val_mae: 2.5335 - val_mse: 15.7991\n",
- "Epoch 29/100\n",
- "354/354 [==============================] - 0s 205us/sample - loss: 8.9679 - mae: 2.1287 - mse: 8.9679 - val_loss: 17.9783 - val_mae: 2.6815 - val_mse: 17.9783\n",
- "Epoch 30/100\n",
- "354/354 [==============================] - 0s 189us/sample - loss: 8.9394 - mae: 2.1013 - mse: 8.9394 - val_loss: 16.0569 - val_mae: 2.5941 - val_mse: 16.0569\n",
- "Epoch 31/100\n",
- "354/354 [==============================] - 0s 195us/sample - loss: 8.6655 - mae: 2.0745 - mse: 8.6655 - val_loss: 15.6427 - val_mae: 2.5280 - val_mse: 15.6427\n",
- "Epoch 32/100\n",
- "354/354 [==============================] - 0s 193us/sample - loss: 8.5800 - mae: 2.0763 - mse: 8.5800 - val_loss: 17.5586 - val_mae: 2.6977 - val_mse: 17.5586\n",
- "Epoch 33/100\n",
- "354/354 [==============================] - 0s 212us/sample - loss: 8.2374 - mae: 2.0580 - mse: 8.2374 - val_loss: 14.9162 - val_mae: 2.4350 - val_mse: 14.9162\n",
- "Epoch 34/100\n",
- "354/354 [==============================] - 0s 203us/sample - loss: 8.1720 - mae: 2.0231 - mse: 8.1720 - val_loss: 15.2634 - val_mae: 2.4622 - val_mse: 15.2634\n",
- "Epoch 35/100\n",
- "354/354 [==============================] - 0s 203us/sample - loss: 8.2398 - mae: 1.9970 - mse: 8.2398 - val_loss: 14.5321 - val_mae: 2.4526 - val_mse: 14.5321\n",
- "Epoch 36/100\n",
- "354/354 [==============================] - 0s 191us/sample - loss: 8.1026 - mae: 2.0228 - mse: 8.1026 - val_loss: 14.5209 - val_mae: 2.4306 - val_mse: 14.5209\n",
- "Epoch 37/100\n",
- "354/354 [==============================] - 0s 189us/sample - loss: 8.0507 - mae: 2.0038 - mse: 8.0507 - val_loss: 14.2053 - val_mae: 2.4105 - val_mse: 14.2053\n",
- "Epoch 38/100\n",
- "354/354 [==============================] - 0s 180us/sample - loss: 7.9693 - mae: 1.9907 - mse: 7.9693 - val_loss: 15.1895 - val_mae: 2.4466 - val_mse: 15.1895\n",
- "Epoch 39/100\n",
- "354/354 [==============================] - 0s 190us/sample - loss: 8.0358 - mae: 1.9684 - mse: 8.0358 - val_loss: 14.1343 - val_mae: 2.4152 - val_mse: 14.1343\n",
- "Epoch 40/100\n",
- "354/354 [==============================] - 0s 187us/sample - loss: 7.5035 - mae: 1.9196 - mse: 7.5035 - val_loss: 17.4994 - val_mae: 2.6633 - val_mse: 17.4994\n",
- "Epoch 41/100\n",
- "354/354 [==============================] - 0s 215us/sample - loss: 7.6546 - mae: 1.9187 - mse: 7.6546 - val_loss: 16.1207 - val_mae: 2.5874 - val_mse: 16.1207\n",
- "Epoch 42/100\n",
- "354/354 [==============================] - 0s 191us/sample - loss: 7.5702 - mae: 1.9474 - mse: 7.5702 - val_loss: 16.0411 - val_mae: 2.5549 - val_mse: 16.0411\n",
- "Epoch 43/100\n",
- "354/354 [==============================] - 0s 199us/sample - loss: 7.2741 - mae: 1.8964 - mse: 7.2741 - val_loss: 18.3190 - val_mae: 2.9024 - val_mse: 18.3190\n",
- "Epoch 44/100\n",
- "354/354 [==============================] - 0s 192us/sample - loss: 7.3155 - mae: 1.9052 - mse: 7.3155 - val_loss: 14.6721 - val_mae: 2.5076 - val_mse: 14.6721\n",
- "Epoch 45/100\n",
- "354/354 [==============================] - 0s 180us/sample - loss: 7.2273 - mae: 1.9336 - mse: 7.2273 - val_loss: 16.3598 - val_mae: 2.6645 - val_mse: 16.3598\n",
- "Epoch 46/100\n",
- "354/354 [==============================] - 0s 175us/sample - loss: 7.0535 - mae: 1.9014 - mse: 7.0535 - val_loss: 12.9086 - val_mae: 2.3502 - val_mse: 12.9086\n",
- "Epoch 47/100\n",
- "354/354 [==============================] - 0s 197us/sample - loss: 7.0074 - mae: 1.8563 - mse: 7.0074 - val_loss: 16.8070 - val_mae: 2.6346 - val_mse: 16.8070\n",
- "Epoch 48/100\n",
- "354/354 [==============================] - 0s 182us/sample - loss: 7.0550 - mae: 1.9165 - mse: 7.0550 - val_loss: 14.6369 - val_mae: 2.3841 - val_mse: 14.6369\n",
- "Epoch 49/100\n",
- "354/354 [==============================] - 0s 194us/sample - loss: 6.8742 - mae: 1.8599 - mse: 6.8742 - val_loss: 13.6704 - val_mae: 2.3694 - val_mse: 13.6704\n",
- "Epoch 50/100\n",
- "354/354 [==============================] - 0s 188us/sample - loss: 6.7243 - mae: 1.8279 - mse: 6.7243 - val_loss: 16.2202 - val_mae: 2.7116 - val_mse: 16.2202\n",
- "Epoch 51/100\n",
- "354/354 [==============================] - 0s 182us/sample - loss: 6.6542 - mae: 1.8333 - mse: 6.6542 - val_loss: 13.2996 - val_mae: 2.4556 - val_mse: 13.2996\n",
- "Epoch 52/100\n",
- "354/354 [==============================] - 0s 185us/sample - loss: 6.6939 - mae: 1.7798 - mse: 6.6939 - val_loss: 12.5869 - val_mae: 2.3476 - val_mse: 12.5869\n",
- "Epoch 53/100\n",
- "354/354 [==============================] - 0s 181us/sample - loss: 6.4587 - mae: 1.7806 - mse: 6.4587 - val_loss: 12.8318 - val_mae: 2.3455 - val_mse: 12.8318\n",
- "Epoch 54/100\n",
- "354/354 [==============================] - 0s 200us/sample - loss: 6.3607 - mae: 1.8065 - mse: 6.3607 - val_loss: 12.5530 - val_mae: 2.3419 - val_mse: 12.5530\n",
- "Epoch 55/100\n",
- "354/354 [==============================] - 0s 193us/sample - loss: 6.4998 - mae: 1.7788 - mse: 6.4998 - val_loss: 15.9603 - val_mae: 2.6778 - val_mse: 15.9603\n",
- "Epoch 56/100\n",
- "354/354 [==============================] - 0s 214us/sample - loss: 6.3887 - mae: 1.7788 - mse: 6.3887 - val_loss: 13.8484 - val_mae: 2.3625 - val_mse: 13.8484\n",
- "Epoch 57/100\n",
- "354/354 [==============================] - 0s 200us/sample - loss: 6.1759 - mae: 1.7890 - mse: 6.1759 - val_loss: 13.8605 - val_mae: 2.4015 - val_mse: 13.8605\n",
- "Epoch 58/100\n",
- "354/354 [==============================] - 0s 196us/sample - loss: 6.0961 - mae: 1.7153 - mse: 6.0961 - val_loss: 12.4883 - val_mae: 2.3339 - val_mse: 12.4883\n",
- "Epoch 59/100\n",
- "354/354 [==============================] - 0s 193us/sample - loss: 6.1896 - mae: 1.7431 - mse: 6.1896 - val_loss: 14.4011 - val_mae: 2.5137 - val_mse: 14.4011\n",
- "Epoch 60/100\n",
- "354/354 [==============================] - 0s 206us/sample - loss: 5.9512 - mae: 1.7174 - mse: 5.9512 - val_loss: 12.7580 - val_mae: 2.3765 - val_mse: 12.7580\n",
- "Epoch 61/100\n",
- "354/354 [==============================] - 0s 182us/sample - loss: 5.9029 - mae: 1.6871 - mse: 5.9029 - val_loss: 12.7280 - val_mae: 2.3057 - val_mse: 12.7280\n",
- "Epoch 62/100\n",
- "354/354 [==============================] - 0s 217us/sample - loss: 5.8361 - mae: 1.6887 - mse: 5.8361 - val_loss: 12.3790 - val_mae: 2.3095 - val_mse: 12.3790\n",
- "Epoch 63/100\n",
- "354/354 [==============================] - 0s 203us/sample - loss: 5.9223 - mae: 1.6781 - mse: 5.9223 - val_loss: 12.8838 - val_mae: 2.3390 - val_mse: 12.8838\n",
- "Epoch 64/100\n",
- "354/354 [==============================] - 0s 188us/sample - loss: 5.6987 - mae: 1.6582 - mse: 5.6987 - val_loss: 15.2329 - val_mae: 2.5214 - val_mse: 15.2329\n",
- "Epoch 65/100\n",
- "354/354 [==============================] - 0s 200us/sample - loss: 5.7098 - mae: 1.6895 - mse: 5.7098 - val_loss: 15.4004 - val_mae: 2.6585 - val_mse: 15.4004\n",
- "Epoch 66/100\n",
- "354/354 [==============================] - 0s 217us/sample - loss: 5.6926 - mae: 1.7027 - mse: 5.6926 - val_loss: 13.3976 - val_mae: 2.4128 - val_mse: 13.3976\n",
- "Epoch 67/100\n",
- "354/354 [==============================] - 0s 200us/sample - loss: 5.5392 - mae: 1.6788 - mse: 5.5392 - val_loss: 12.1396 - val_mae: 2.3543 - val_mse: 12.1396\n",
- "Epoch 68/100\n",
- "354/354 [==============================] - 0s 204us/sample - loss: 5.6455 - mae: 1.6395 - mse: 5.6455 - val_loss: 12.3876 - val_mae: 2.2912 - val_mse: 12.3876\n",
- "Epoch 69/100\n",
- "354/354 [==============================] - 0s 193us/sample - loss: 5.5486 - mae: 1.6507 - mse: 5.5486 - val_loss: 11.8058 - val_mae: 2.2785 - val_mse: 11.8058\n",
- "Epoch 70/100\n",
- "354/354 [==============================] - 0s 196us/sample - loss: 5.2014 - mae: 1.6158 - mse: 5.2014 - val_loss: 12.3587 - val_mae: 2.3669 - val_mse: 12.3587\n",
- "Epoch 71/100\n",
- "354/354 [==============================] - 0s 206us/sample - loss: 5.3234 - mae: 1.6188 - mse: 5.3234 - val_loss: 12.7164 - val_mae: 2.3158 - val_mse: 12.7164\n",
- "Epoch 72/100\n",
- "354/354 [==============================] - 0s 194us/sample - loss: 5.2484 - mae: 1.6042 - mse: 5.2484 - val_loss: 12.3865 - val_mae: 2.3693 - val_mse: 12.3865\n",
- "Epoch 73/100\n",
- "354/354 [==============================] - 0s 196us/sample - loss: 5.0747 - mae: 1.6102 - mse: 5.0747 - val_loss: 12.4433 - val_mae: 2.3377 - val_mse: 12.4433\n",
- "Epoch 74/100\n",
- "354/354 [==============================] - 0s 211us/sample - loss: 5.0366 - mae: 1.5948 - mse: 5.0366 - val_loss: 12.8354 - val_mae: 2.4892 - val_mse: 12.8354\n",
- "Epoch 75/100\n",
- "354/354 [==============================] - 0s 195us/sample - loss: 5.1710 - mae: 1.6385 - mse: 5.1710 - val_loss: 12.3743 - val_mae: 2.3796 - val_mse: 12.3743\n",
- "Epoch 76/100\n",
- "354/354 [==============================] - 0s 206us/sample - loss: 5.0850 - mae: 1.5859 - mse: 5.0850 - val_loss: 13.4606 - val_mae: 2.4595 - val_mse: 13.4606\n",
- "Epoch 77/100\n",
- "354/354 [==============================] - 0s 197us/sample - loss: 5.0708 - mae: 1.6001 - mse: 5.0708 - val_loss: 13.3754 - val_mae: 2.3588 - val_mse: 13.3754\n",
- "Epoch 78/100\n",
- "354/354 [==============================] - 0s 186us/sample - loss: 4.8250 - mae: 1.5805 - mse: 4.8250 - val_loss: 12.2387 - val_mae: 2.2988 - val_mse: 12.2387\n",
- "Epoch 79/100\n",
- "354/354 [==============================] - 0s 194us/sample - loss: 4.8951 - mae: 1.5868 - mse: 4.8951 - val_loss: 11.8498 - val_mae: 2.3508 - val_mse: 11.8498\n",
- "Epoch 80/100\n",
- "354/354 [==============================] - 0s 183us/sample - loss: 4.9441 - mae: 1.5494 - mse: 4.9441 - val_loss: 13.9550 - val_mae: 2.5396 - val_mse: 13.9550\n",
- "Epoch 81/100\n",
- "354/354 [==============================] - 0s 203us/sample - loss: 4.8870 - mae: 1.5427 - mse: 4.8870 - val_loss: 12.1051 - val_mae: 2.3690 - val_mse: 12.1051\n",
- "Epoch 82/100\n",
- "354/354 [==============================] - 0s 190us/sample - loss: 4.7350 - mae: 1.5419 - mse: 4.7350 - val_loss: 13.7286 - val_mae: 2.5262 - val_mse: 13.7286\n",
- "Epoch 83/100\n",
- "354/354 [==============================] - 0s 238us/sample - loss: 4.9354 - mae: 1.5685 - mse: 4.9354 - val_loss: 12.9193 - val_mae: 2.4904 - val_mse: 12.9193\n",
- "Epoch 84/100\n",
- "354/354 [==============================] - 0s 191us/sample - loss: 4.6636 - mae: 1.5551 - mse: 4.6636 - val_loss: 12.1324 - val_mae: 2.4348 - val_mse: 12.1324\n",
- "Epoch 85/100\n",
- "354/354 [==============================] - 0s 195us/sample - loss: 4.7957 - mae: 1.5276 - mse: 4.7957 - val_loss: 12.3749 - val_mae: 2.3330 - val_mse: 12.3749\n",
- "Epoch 86/100\n",
- "354/354 [==============================] - 0s 204us/sample - loss: 4.6654 - mae: 1.5355 - mse: 4.6654 - val_loss: 11.5430 - val_mae: 2.3188 - val_mse: 11.5430\n",
- "Epoch 87/100\n",
- "354/354 [==============================] - 0s 179us/sample - loss: 4.5632 - mae: 1.5194 - mse: 4.5632 - val_loss: 11.3675 - val_mae: 2.2698 - val_mse: 11.3675\n",
- "Epoch 88/100\n",
- "354/354 [==============================] - 0s 196us/sample - loss: 4.5784 - mae: 1.4623 - mse: 4.5784 - val_loss: 14.0622 - val_mae: 2.4995 - val_mse: 14.0622\n",
- "Epoch 89/100\n",
- "354/354 [==============================] - 0s 205us/sample - loss: 4.4661 - mae: 1.4873 - mse: 4.4661 - val_loss: 12.3719 - val_mae: 2.3247 - val_mse: 12.3719\n",
- "Epoch 90/100\n",
- "354/354 [==============================] - 0s 200us/sample - loss: 4.4662 - mae: 1.5005 - mse: 4.4662 - val_loss: 12.6654 - val_mae: 2.3659 - val_mse: 12.6654\n",
- "Epoch 91/100\n",
- "354/354 [==============================] - 0s 190us/sample - loss: 4.3980 - mae: 1.4574 - mse: 4.3980 - val_loss: 12.4609 - val_mae: 2.3459 - val_mse: 12.4609\n",
- "Epoch 92/100\n",
- "354/354 [==============================] - 0s 192us/sample - loss: 4.5533 - mae: 1.5108 - mse: 4.5533 - val_loss: 12.7677 - val_mae: 2.4253 - val_mse: 12.7677\n",
- "Epoch 93/100\n",
- "354/354 [==============================] - 0s 197us/sample - loss: 4.4988 - mae: 1.4931 - mse: 4.4988 - val_loss: 12.2878 - val_mae: 2.3648 - val_mse: 12.2878\n",
- "Epoch 94/100\n",
- "354/354 [==============================] - 0s 196us/sample - loss: 4.5069 - mae: 1.4879 - mse: 4.5069 - val_loss: 12.9163 - val_mae: 2.4027 - val_mse: 12.9163\n",
- "Epoch 95/100\n",
- "354/354 [==============================] - 0s 192us/sample - loss: 4.2032 - mae: 1.4314 - mse: 4.2032 - val_loss: 11.4810 - val_mae: 2.2678 - val_mse: 11.4810\n",
- "Epoch 96/100\n",
- "354/354 [==============================] - 0s 191us/sample - loss: 4.3565 - mae: 1.4812 - mse: 4.3565 - val_loss: 11.7690 - val_mae: 2.3530 - val_mse: 11.7690\n",
- "Epoch 97/100\n",
- "354/354 [==============================] - 0s 193us/sample - loss: 4.2132 - mae: 1.4641 - mse: 4.2132 - val_loss: 11.7643 - val_mae: 2.3037 - val_mse: 11.7643\n",
- "Epoch 98/100\n",
- "354/354 [==============================] - 0s 184us/sample - loss: 4.2685 - mae: 1.4209 - mse: 4.2685 - val_loss: 13.5426 - val_mae: 2.4505 - val_mse: 13.5426\n",
- "Epoch 99/100\n",
- "354/354 [==============================] - 0s 193us/sample - loss: 4.2273 - mae: 1.4354 - mse: 4.2273 - val_loss: 11.9713 - val_mae: 2.3091 - val_mse: 11.9713\n",
- "Epoch 100/100\n",
- "354/354 [==============================] - 0s 204us/sample - loss: 4.0932 - mae: 1.4115 - mse: 4.0932 - val_loss: 12.6829 - val_mae: 2.3742 - val_mse: 12.6829\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"history = model.fit(x_train,\n",
" y_train,\n",
@@ -881,19 +252,9 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "x_test / loss : 12.6829\n",
- "x_test / mae : 2.3742\n",
- "x_test / mse : 12.6829\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"score = model.evaluate(x_test, y_test, verbose=0)\n",
"\n",
@@ -912,132 +273,9 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>loss</th>\n",
- " <th>mae</th>\n",
- " <th>mse</th>\n",
- " <th>val_loss</th>\n",
- " <th>val_mae</th>\n",
- " <th>val_mse</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>count</th>\n",
- " <td>100.000000</td>\n",
- " <td>100.000000</td>\n",
- " <td>100.000000</td>\n",
- " <td>100.000000</td>\n",
- " <td>100.000000</td>\n",
- " <td>100.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>mean</th>\n",
- " <td>15.358750</td>\n",
- " <td>2.269137</td>\n",
- " <td>15.358750</td>\n",
- " <td>18.906837</td>\n",
- " <td>2.754277</td>\n",
- " <td>18.906838</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>std</th>\n",
- " <td>49.946002</td>\n",
- " <td>2.123399</td>\n",
- " <td>49.945997</td>\n",
- " <td>31.760275</td>\n",
- " <td>1.495250</td>\n",
- " <td>31.760280</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>min</th>\n",
- " <td>4.093166</td>\n",
- " <td>1.411523</td>\n",
- " <td>4.093166</td>\n",
- " <td>11.367452</td>\n",
- " <td>2.267774</td>\n",
- " <td>11.367453</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>25%</th>\n",
- " <td>5.073712</td>\n",
- " <td>1.598796</td>\n",
- " <td>5.073712</td>\n",
- " <td>12.645807</td>\n",
- " <td>2.361604</td>\n",
- " <td>12.645807</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>50%</th>\n",
- " <td>6.709099</td>\n",
- " <td>1.830622</td>\n",
- " <td>6.709099</td>\n",
- " <td>14.303193</td>\n",
- " <td>2.460818</td>\n",
- " <td>14.303193</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>75%</th>\n",
- " <td>9.500961</td>\n",
- " <td>2.162759</td>\n",
- " <td>9.500960</td>\n",
- " <td>16.156455</td>\n",
- " <td>2.624831</td>\n",
- " <td>16.156455</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>max</th>\n",
- " <td>458.897337</td>\n",
- " <td>19.442396</td>\n",
- " <td>458.897278</td>\n",
- " <td>318.980021</td>\n",
- " <td>15.942373</td>\n",
- " <td>318.980072</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
- "text/plain": [
- " loss mae mse val_loss val_mae val_mse\n",
- "count 100.000000 100.000000 100.000000 100.000000 100.000000 100.000000\n",
- "mean 15.358750 2.269137 15.358750 18.906837 2.754277 18.906838\n",
- "std 49.946002 2.123399 49.945997 31.760275 1.495250 31.760280\n",
- "min 4.093166 1.411523 4.093166 11.367452 2.267774 11.367453\n",
- "25% 5.073712 1.598796 5.073712 12.645807 2.361604 12.645807\n",
- "50% 6.709099 1.830622 6.709099 14.303193 2.460818 14.303193\n",
- "75% 9.500961 2.162759 9.500960 16.156455 2.624831 16.156455\n",
- "max 458.897337 19.442396 458.897278 318.980021 15.942373 318.980072"
- ]
- },
- "execution_count": 9,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
+ "outputs": [],
"source": [
"\n",
"df=pd.DataFrame(data=history.history)\n",
@@ -1046,63 +284,18 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "min( val_mae ) : 2.2678\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"print(\"min( val_mae ) : {:.4f}\".format( min(history.history[\"val_mae\"]) ) )"
]
},
{
"cell_type": "code",
- "execution_count": 11,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 576x432 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 576x432 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 576x432 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
"source": [
"ooo.plot_history(history, plot={'MSE' :['mse', 'val_mse'],\n",
" 'MAE' :['mae', 'val_mae'],\n",
@@ -1118,7 +311,7 @@
},
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -1132,18 +325,9 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Prédiction : 10.45 K$\n",
- "Reality : 10.40 K$\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"\n",
"predictions = model.predict( my_data )\n",
diff --git a/BHPD/02-DNN-Regression Premium.ipynb b/BHPD/02-DNN-Regression Premium.ipynb
index 9f387f191fc27d23de20a3ede32e9a521635d4ca..9e37920a82080d75aca0db53da92c6e51cb502a4 100644
--- a/BHPD/02-DNN-Regression Premium.ipynb
+++ b/BHPD/02-DNN-Regression Premium.ipynb
@@ -37,22 +37,9 @@
},
{
"cell_type": "code",
- "execution_count": 1,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "IDLE 2020 - Practical Work Module\n",
- " Version : 0.2\n",
- " Run time : Monday 27 January 2020, 15:48:21\n",
- " Matplotlib style : fidle/talk.mplstyle\n",
- " TensorFlow version : 2.0.0\n",
- " Keras version : 2.2.4-tf\n"
- ]
- }
- ],
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
"source": [
"import tensorflow as tf\n",
"from tensorflow import keras\n",
@@ -60,12 +47,14 @@
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import pandas as pd\n",
- "import os\n",
+ "import os,sys\n",
"\n",
"from IPython.display import display, Markdown\n",
- "import fidle.pwk as ooo\n",
"from importlib import reload\n",
"\n",
+ "sys.path.append('..')\n",
+ "import fidle.pwk as ooo\n",
+ "\n",
"ooo.init()"
]
},
@@ -96,116 +85,9 @@
},
{
"cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<style type=\"text/css\" >\n",
- "</style><table id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afb\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >crim</th> <th class=\"col_heading level0 col1\" >zn</th> <th class=\"col_heading level0 col2\" >indus</th> <th class=\"col_heading level0 col3\" >chas</th> <th class=\"col_heading level0 col4\" >nox</th> <th class=\"col_heading level0 col5\" >rm</th> <th class=\"col_heading level0 col6\" >age</th> <th class=\"col_heading level0 col7\" >dis</th> <th class=\"col_heading level0 col8\" >rad</th> <th class=\"col_heading level0 col9\" >tax</th> <th class=\"col_heading level0 col10\" >ptratio</th> <th class=\"col_heading level0 col11\" >b</th> <th class=\"col_heading level0 col12\" >lstat</th> <th class=\"col_heading level0 col13\" >medv</th> </tr></thead><tbody>\n",
- " <tr>\n",
- " <th id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afblevel0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col0\" class=\"data row0 col0\" >0.01</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col1\" class=\"data row0 col1\" >18.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col2\" class=\"data row0 col2\" >2.31</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col3\" class=\"data row0 col3\" >0.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col4\" class=\"data row0 col4\" >0.54</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col5\" class=\"data row0 col5\" >6.58</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col6\" class=\"data row0 col6\" >65.20</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col7\" class=\"data row0 col7\" >4.09</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col8\" class=\"data row0 col8\" >1.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col9\" class=\"data row0 col9\" >296.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col10\" class=\"data row0 col10\" >15.30</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col11\" class=\"data row0 col11\" >396.90</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col12\" class=\"data row0 col12\" >4.98</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow0_col13\" class=\"data row0 col13\" >24.00</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afblevel0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col0\" class=\"data row1 col0\" >0.03</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col1\" class=\"data row1 col1\" >0.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col2\" class=\"data row1 col2\" >7.07</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col3\" class=\"data row1 col3\" >0.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col4\" class=\"data row1 col4\" >0.47</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col5\" class=\"data row1 col5\" >6.42</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col6\" class=\"data row1 col6\" >78.90</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col7\" class=\"data row1 col7\" >4.97</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col8\" class=\"data row1 col8\" >2.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col9\" class=\"data row1 col9\" >242.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col10\" class=\"data row1 col10\" >17.80</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col11\" class=\"data row1 col11\" >396.90</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col12\" class=\"data row1 col12\" >9.14</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow1_col13\" class=\"data row1 col13\" >21.60</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afblevel0_row2\" class=\"row_heading level0 row2\" >2</th>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col0\" class=\"data row2 col0\" >0.03</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col1\" class=\"data row2 col1\" >0.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col2\" class=\"data row2 col2\" >7.07</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col3\" class=\"data row2 col3\" >0.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col4\" class=\"data row2 col4\" >0.47</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col5\" class=\"data row2 col5\" >7.18</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col6\" class=\"data row2 col6\" >61.10</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col7\" class=\"data row2 col7\" >4.97</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col8\" class=\"data row2 col8\" >2.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col9\" class=\"data row2 col9\" >242.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col10\" class=\"data row2 col10\" >17.80</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col11\" class=\"data row2 col11\" >392.83</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col12\" class=\"data row2 col12\" >4.03</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow2_col13\" class=\"data row2 col13\" >34.70</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afblevel0_row3\" class=\"row_heading level0 row3\" >3</th>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col0\" class=\"data row3 col0\" >0.03</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col1\" class=\"data row3 col1\" >0.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col2\" class=\"data row3 col2\" >2.18</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col3\" class=\"data row3 col3\" >0.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col4\" class=\"data row3 col4\" >0.46</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col5\" class=\"data row3 col5\" >7.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col6\" class=\"data row3 col6\" >45.80</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col7\" class=\"data row3 col7\" >6.06</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col8\" class=\"data row3 col8\" >3.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col9\" class=\"data row3 col9\" >222.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col10\" class=\"data row3 col10\" >18.70</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col11\" class=\"data row3 col11\" >394.63</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col12\" class=\"data row3 col12\" >2.94</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow3_col13\" class=\"data row3 col13\" >33.40</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afblevel0_row4\" class=\"row_heading level0 row4\" >4</th>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col0\" class=\"data row4 col0\" >0.07</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col1\" class=\"data row4 col1\" >0.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col2\" class=\"data row4 col2\" >2.18</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col3\" class=\"data row4 col3\" >0.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col4\" class=\"data row4 col4\" >0.46</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col5\" class=\"data row4 col5\" >7.15</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col6\" class=\"data row4 col6\" >54.20</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col7\" class=\"data row4 col7\" >6.06</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col8\" class=\"data row4 col8\" >3.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col9\" class=\"data row4 col9\" >222.00</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col10\" class=\"data row4 col10\" >18.70</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col11\" class=\"data row4 col11\" >396.90</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col12\" class=\"data row4 col12\" >5.33</td>\n",
- " <td id=\"T_13ff0f06_4114_11ea_af1b_698ca2e84afbrow4_col13\" class=\"data row4 col13\" >36.20</td>\n",
- " </tr>\n",
- " </tbody></table>"
- ],
- "text/plain": [
- "<pandas.io.formats.style.Styler at 0x7f5fda4af110>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Données manquantes : 0 Shape is : (506, 14)\n"
- ]
- }
- ],
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
"source": [
"data = pd.read_csv('./data/BostonHousing.csv', header=0)\n",
"\n",
@@ -225,19 +107,9 @@
},
{
"cell_type": "code",
- "execution_count": 3,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Original data shape was : (506, 14)\n",
- "x_train : (354, 13) y_train : (354,)\n",
- "x_test : (152, 13) y_test : (152,)\n"
- ]
- }
- ],
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
"source": [
"# ---- Split => train, test\n",
"#\n",
@@ -270,294 +142,9 @@
},
{
"cell_type": "code",
- "execution_count": 4,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<style type=\"text/css\" >\n",
- "</style><table id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afb\" ><caption>Before normalization :</caption><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >crim</th> <th class=\"col_heading level0 col1\" >zn</th> <th class=\"col_heading level0 col2\" >indus</th> <th class=\"col_heading level0 col3\" >chas</th> <th class=\"col_heading level0 col4\" >nox</th> <th class=\"col_heading level0 col5\" >rm</th> <th class=\"col_heading level0 col6\" >age</th> <th class=\"col_heading level0 col7\" >dis</th> <th class=\"col_heading level0 col8\" >rad</th> <th class=\"col_heading level0 col9\" >tax</th> <th class=\"col_heading level0 col10\" >ptratio</th> <th class=\"col_heading level0 col11\" >b</th> <th class=\"col_heading level0 col12\" >lstat</th> </tr></thead><tbody>\n",
- " <tr>\n",
- " <th id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afblevel0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow0_col0\" class=\"data row0 col0\" >354.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow0_col1\" class=\"data row0 col1\" >354.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow0_col2\" class=\"data row0 col2\" >354.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow0_col3\" class=\"data row0 col3\" >354.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow0_col4\" class=\"data row0 col4\" >354.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow0_col5\" class=\"data row0 col5\" >354.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow0_col6\" class=\"data row0 col6\" >354.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow0_col7\" class=\"data row0 col7\" >354.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow0_col8\" class=\"data row0 col8\" >354.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow0_col9\" class=\"data row0 col9\" >354.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow0_col10\" class=\"data row0 col10\" >354.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow0_col11\" class=\"data row0 col11\" >354.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow0_col12\" class=\"data row0 col12\" >354.00</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afblevel0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow1_col0\" class=\"data row1 col0\" >3.50</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow1_col1\" class=\"data row1 col1\" >11.26</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow1_col2\" class=\"data row1 col2\" >10.98</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow1_col3\" class=\"data row1 col3\" >0.05</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow1_col4\" class=\"data row1 col4\" >0.55</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow1_col5\" class=\"data row1 col5\" >6.30</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow1_col6\" class=\"data row1 col6\" >68.18</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow1_col7\" class=\"data row1 col7\" >3.83</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow1_col8\" class=\"data row1 col8\" >9.29</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow1_col9\" class=\"data row1 col9\" >403.31</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow1_col10\" class=\"data row1 col10\" >18.54</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow1_col11\" class=\"data row1 col11\" >359.90</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow1_col12\" class=\"data row1 col12\" >12.38</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afblevel0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow2_col0\" class=\"data row2 col0\" >8.57</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow2_col1\" class=\"data row2 col1\" >23.21</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow2_col2\" class=\"data row2 col2\" >6.82</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow2_col3\" class=\"data row2 col3\" >0.22</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow2_col4\" class=\"data row2 col4\" >0.11</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow2_col5\" class=\"data row2 col5\" >0.66</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow2_col6\" class=\"data row2 col6\" >28.04</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow2_col7\" class=\"data row2 col7\" >2.10</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow2_col8\" class=\"data row2 col8\" >8.59</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow2_col9\" class=\"data row2 col9\" >167.27</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow2_col10\" class=\"data row2 col10\" >2.13</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow2_col11\" class=\"data row2 col11\" >88.19</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow2_col12\" class=\"data row2 col12\" >6.61</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afblevel0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow3_col0\" class=\"data row3 col0\" >0.01</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow3_col1\" class=\"data row3 col1\" >0.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow3_col2\" class=\"data row3 col2\" >0.74</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow3_col3\" class=\"data row3 col3\" >0.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow3_col4\" class=\"data row3 col4\" >0.39</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow3_col5\" class=\"data row3 col5\" >3.86</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow3_col6\" class=\"data row3 col6\" >2.90</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow3_col7\" class=\"data row3 col7\" >1.13</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow3_col8\" class=\"data row3 col8\" >1.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow3_col9\" class=\"data row3 col9\" >187.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow3_col10\" class=\"data row3 col10\" >12.60</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow3_col11\" class=\"data row3 col11\" >2.52</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow3_col12\" class=\"data row3 col12\" >1.92</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afblevel0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow4_col0\" class=\"data row4 col0\" >0.08</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow4_col1\" class=\"data row4 col1\" >0.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow4_col2\" class=\"data row4 col2\" >5.19</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow4_col3\" class=\"data row4 col3\" >0.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow4_col4\" class=\"data row4 col4\" >0.45</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow4_col5\" class=\"data row4 col5\" >5.89</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow4_col6\" class=\"data row4 col6\" >45.18</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow4_col7\" class=\"data row4 col7\" >2.12</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow4_col8\" class=\"data row4 col8\" >4.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow4_col9\" class=\"data row4 col9\" >279.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow4_col10\" class=\"data row4 col10\" >17.40</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow4_col11\" class=\"data row4 col11\" >377.59</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow4_col12\" class=\"data row4 col12\" >7.19</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afblevel0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow5_col0\" class=\"data row5 col0\" >0.23</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow5_col1\" class=\"data row5 col1\" >0.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow5_col2\" class=\"data row5 col2\" >8.56</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow5_col3\" class=\"data row5 col3\" >0.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow5_col4\" class=\"data row5 col4\" >0.54</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow5_col5\" class=\"data row5 col5\" >6.22</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow5_col6\" class=\"data row5 col6\" >76.50</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow5_col7\" class=\"data row5 col7\" >3.21</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow5_col8\" class=\"data row5 col8\" >5.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow5_col9\" class=\"data row5 col9\" >329.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow5_col10\" class=\"data row5 col10\" >19.10</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow5_col11\" class=\"data row5 col11\" >391.81</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow5_col12\" class=\"data row5 col12\" >11.17</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afblevel0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow6_col0\" class=\"data row6 col0\" >2.89</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow6_col1\" class=\"data row6 col1\" >12.50</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow6_col2\" class=\"data row6 col2\" >18.10</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow6_col3\" class=\"data row6 col3\" >0.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow6_col4\" class=\"data row6 col4\" >0.62</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow6_col5\" class=\"data row6 col5\" >6.61</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow6_col6\" class=\"data row6 col6\" >93.57</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow6_col7\" class=\"data row6 col7\" >5.12</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow6_col8\" class=\"data row6 col8\" >8.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow6_col9\" class=\"data row6 col9\" >666.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow6_col10\" class=\"data row6 col10\" >20.20</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow6_col11\" class=\"data row6 col11\" >396.21</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow6_col12\" class=\"data row6 col12\" >16.57</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afblevel0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow7_col0\" class=\"data row7 col0\" >88.98</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow7_col1\" class=\"data row7 col1\" >95.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow7_col2\" class=\"data row7 col2\" >27.74</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow7_col3\" class=\"data row7 col3\" >1.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow7_col4\" class=\"data row7 col4\" >0.87</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow7_col5\" class=\"data row7 col5\" >8.72</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow7_col6\" class=\"data row7 col6\" >100.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow7_col7\" class=\"data row7 col7\" >12.13</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow7_col8\" class=\"data row7 col8\" >24.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow7_col9\" class=\"data row7 col9\" >711.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow7_col10\" class=\"data row7 col10\" >22.00</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow7_col11\" class=\"data row7 col11\" >396.90</td>\n",
- " <td id=\"T_1878bc44_4114_11ea_af1b_698ca2e84afbrow7_col12\" class=\"data row7 col12\" >36.98</td>\n",
- " </tr>\n",
- " </tbody></table>"
- ],
- "text/plain": [
- "<pandas.io.formats.style.Styler at 0x7f5fd31583d0>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "text/html": [
- "<style type=\"text/css\" >\n",
- "</style><table id=\"T_188108ae_4114_11ea_af1b_698ca2e84afb\" ><caption>After normalization :</caption><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >crim</th> <th class=\"col_heading level0 col1\" >zn</th> <th class=\"col_heading level0 col2\" >indus</th> <th class=\"col_heading level0 col3\" >chas</th> <th class=\"col_heading level0 col4\" >nox</th> <th class=\"col_heading level0 col5\" >rm</th> <th class=\"col_heading level0 col6\" >age</th> <th class=\"col_heading level0 col7\" >dis</th> <th class=\"col_heading level0 col8\" >rad</th> <th class=\"col_heading level0 col9\" >tax</th> <th class=\"col_heading level0 col10\" >ptratio</th> <th class=\"col_heading level0 col11\" >b</th> <th class=\"col_heading level0 col12\" >lstat</th> </tr></thead><tbody>\n",
- " <tr>\n",
- " <th id=\"T_188108ae_4114_11ea_af1b_698ca2e84afblevel0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow0_col0\" class=\"data row0 col0\" >354.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow0_col1\" class=\"data row0 col1\" >354.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow0_col2\" class=\"data row0 col2\" >354.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow0_col3\" class=\"data row0 col3\" >354.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow0_col4\" class=\"data row0 col4\" >354.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow0_col5\" class=\"data row0 col5\" >354.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow0_col6\" class=\"data row0 col6\" >354.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow0_col7\" class=\"data row0 col7\" >354.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow0_col8\" class=\"data row0 col8\" >354.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow0_col9\" class=\"data row0 col9\" >354.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow0_col10\" class=\"data row0 col10\" >354.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow0_col11\" class=\"data row0 col11\" >354.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow0_col12\" class=\"data row0 col12\" >354.00</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_188108ae_4114_11ea_af1b_698ca2e84afblevel0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow1_col0\" class=\"data row1 col0\" >-0.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow1_col1\" class=\"data row1 col1\" >-0.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow1_col2\" class=\"data row1 col2\" >0.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow1_col3\" class=\"data row1 col3\" >0.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow1_col4\" class=\"data row1 col4\" >-0.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow1_col5\" class=\"data row1 col5\" >0.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow1_col6\" class=\"data row1 col6\" >-0.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow1_col7\" class=\"data row1 col7\" >-0.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow1_col8\" class=\"data row1 col8\" >-0.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow1_col9\" class=\"data row1 col9\" >0.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow1_col10\" class=\"data row1 col10\" >0.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow1_col11\" class=\"data row1 col11\" >0.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow1_col12\" class=\"data row1 col12\" >-0.00</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_188108ae_4114_11ea_af1b_698ca2e84afblevel0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow2_col0\" class=\"data row2 col0\" >1.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow2_col1\" class=\"data row2 col1\" >1.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow2_col2\" class=\"data row2 col2\" >1.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow2_col3\" class=\"data row2 col3\" >1.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow2_col4\" class=\"data row2 col4\" >1.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow2_col5\" class=\"data row2 col5\" >1.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow2_col6\" class=\"data row2 col6\" >1.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow2_col7\" class=\"data row2 col7\" >1.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow2_col8\" class=\"data row2 col8\" >1.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow2_col9\" class=\"data row2 col9\" >1.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow2_col10\" class=\"data row2 col10\" >1.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow2_col11\" class=\"data row2 col11\" >1.00</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow2_col12\" class=\"data row2 col12\" >1.00</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_188108ae_4114_11ea_af1b_698ca2e84afblevel0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow3_col0\" class=\"data row3 col0\" >-0.41</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow3_col1\" class=\"data row3 col1\" >-0.49</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow3_col2\" class=\"data row3 col2\" >-1.50</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow3_col3\" class=\"data row3 col3\" >-0.23</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow3_col4\" class=\"data row3 col4\" >-1.47</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow3_col5\" class=\"data row3 col5\" >-3.68</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow3_col6\" class=\"data row3 col6\" >-2.33</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow3_col7\" class=\"data row3 col7\" >-1.29</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow3_col8\" class=\"data row3 col8\" >-0.96</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow3_col9\" class=\"data row3 col9\" >-1.29</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow3_col10\" class=\"data row3 col10\" >-2.79</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow3_col11\" class=\"data row3 col11\" >-4.05</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow3_col12\" class=\"data row3 col12\" >-1.58</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_188108ae_4114_11ea_af1b_698ca2e84afblevel0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow4_col0\" class=\"data row4 col0\" >-0.40</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow4_col1\" class=\"data row4 col1\" >-0.49</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow4_col2\" class=\"data row4 col2\" >-0.85</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow4_col3\" class=\"data row4 col3\" >-0.23</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow4_col4\" class=\"data row4 col4\" >-0.92</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow4_col5\" class=\"data row4 col5\" >-0.61</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow4_col6\" class=\"data row4 col6\" >-0.82</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow4_col7\" class=\"data row4 col7\" >-0.81</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow4_col8\" class=\"data row4 col8\" >-0.62</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow4_col9\" class=\"data row4 col9\" >-0.74</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow4_col10\" class=\"data row4 col10\" >-0.54</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow4_col11\" class=\"data row4 col11\" >0.20</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow4_col12\" class=\"data row4 col12\" >-0.78</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_188108ae_4114_11ea_af1b_698ca2e84afblevel0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow5_col0\" class=\"data row5 col0\" >-0.38</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow5_col1\" class=\"data row5 col1\" >-0.49</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow5_col2\" class=\"data row5 col2\" >-0.35</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow5_col3\" class=\"data row5 col3\" >-0.23</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow5_col4\" class=\"data row5 col4\" >-0.11</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow5_col5\" class=\"data row5 col5\" >-0.12</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow5_col6\" class=\"data row5 col6\" >0.30</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow5_col7\" class=\"data row5 col7\" >-0.30</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow5_col8\" class=\"data row5 col8\" >-0.50</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow5_col9\" class=\"data row5 col9\" >-0.44</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow5_col10\" class=\"data row5 col10\" >0.26</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow5_col11\" class=\"data row5 col11\" >0.36</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow5_col12\" class=\"data row5 col12\" >-0.18</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_188108ae_4114_11ea_af1b_698ca2e84afblevel0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow6_col0\" class=\"data row6 col0\" >-0.07</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow6_col1\" class=\"data row6 col1\" >0.05</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow6_col2\" class=\"data row6 col2\" >1.04</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow6_col3\" class=\"data row6 col3\" >-0.23</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow6_col4\" class=\"data row6 col4\" >0.65</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow6_col5\" class=\"data row6 col5\" >0.48</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow6_col6\" class=\"data row6 col6\" >0.91</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow6_col7\" class=\"data row6 col7\" >0.61</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow6_col8\" class=\"data row6 col8\" >-0.15</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow6_col9\" class=\"data row6 col9\" >1.57</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow6_col10\" class=\"data row6 col10\" >0.78</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow6_col11\" class=\"data row6 col11\" >0.41</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow6_col12\" class=\"data row6 col12\" >0.63</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_188108ae_4114_11ea_af1b_698ca2e84afblevel0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow7_col0\" class=\"data row7 col0\" >9.98</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow7_col1\" class=\"data row7 col1\" >3.61</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow7_col2\" class=\"data row7 col2\" >2.46</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow7_col3\" class=\"data row7 col3\" >4.31</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow7_col4\" class=\"data row7 col4\" >2.93</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow7_col5\" class=\"data row7 col5\" >3.67</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow7_col6\" class=\"data row7 col6\" >1.13</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow7_col7\" class=\"data row7 col7\" >3.95</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow7_col8\" class=\"data row7 col8\" >1.71</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow7_col9\" class=\"data row7 col9\" >1.84</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow7_col10\" class=\"data row7 col10\" >1.62</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow7_col11\" class=\"data row7 col11\" >0.42</td>\n",
- " <td id=\"T_188108ae_4114_11ea_af1b_698ca2e84afbrow7_col12\" class=\"data row7 col12\" >3.72</td>\n",
- " </tr>\n",
- " </tbody></table>"
- ],
- "text/plain": [
- "<pandas.io.formats.style.Styler at 0x7f5fd2d75f50>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
"source": [
"display(x_train.describe().style.format(\"{0:.2f}\").set_caption(\"Before normalization :\"))\n",
"\n",
@@ -586,7 +173,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -613,30 +200,9 @@
},
{
"cell_type": "code",
- "execution_count": 6,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Model: \"sequential\"\n",
- "_________________________________________________________________\n",
- "Layer (type) Output Shape Param # \n",
- "=================================================================\n",
- "dense (Dense) (None, 64) 896 \n",
- "_________________________________________________________________\n",
- "dense_1 (Dense) (None, 64) 4160 \n",
- "_________________________________________________________________\n",
- "dense_2 (Dense) (None, 1) 65 \n",
- "=================================================================\n",
- "Total params: 5,121\n",
- "Trainable params: 5,121\n",
- "Non-trainable params: 0\n",
- "_________________________________________________________________\n"
- ]
- }
- ],
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
"source": [
"model=get_model_v1( (13,) )\n",
"\n",
@@ -652,7 +218,7 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -670,7 +236,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -695,19 +261,9 @@
},
{
"cell_type": "code",
- "execution_count": 9,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "x_test / loss : 14.2504\n",
- "x_test / mae : 2.4316\n",
- "x_test / mse : 14.2504\n"
- ]
- }
- ],
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
"source": [
"score = model.evaluate(x_test, y_test, verbose=0)\n",
"\n",
@@ -726,63 +282,18 @@
},
{
"cell_type": "code",
- "execution_count": 10,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "min( val_mae ) : 2.2208\n"
- ]
- }
- ],
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
"source": [
"print(\"min( val_mae ) : {:.4f}\".format( min(history.history[\"val_mae\"]) ) )"
]
},
{
"cell_type": "code",
- "execution_count": 11,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 576x432 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 576x432 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 576x432 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
"source": [
"reload(ooo)\n",
"ooo.plot_history(history, plot={'MSE' :['mse', 'val_mse'],\n",
@@ -806,31 +317,9 @@
},
{
"cell_type": "code",
- "execution_count": 12,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Model: \"sequential\"\n",
- "_________________________________________________________________\n",
- "Layer (type) Output Shape Param # \n",
- "=================================================================\n",
- "dense (Dense) (None, 64) 896 \n",
- "_________________________________________________________________\n",
- "dense_1 (Dense) (None, 64) 4160 \n",
- "_________________________________________________________________\n",
- "dense_2 (Dense) (None, 1) 65 \n",
- "=================================================================\n",
- "Total params: 5,121\n",
- "Trainable params: 5,121\n",
- "Non-trainable params: 0\n",
- "_________________________________________________________________\n",
- "Loaded.\n"
- ]
- }
- ],
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
"source": [
"loaded_model = tf.keras.models.load_model('./run/models/best_model.h5')\n",
"loaded_model.summary()\n",
@@ -846,19 +335,9 @@
},
{
"cell_type": "code",
- "execution_count": 13,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "x_test / loss : 12.2278\n",
- "x_test / mae : 2.2441\n",
- "x_test / mse : 12.2278\n"
- ]
- }
- ],
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
"source": [
"score = loaded_model.evaluate(x_test, y_test, verbose=0)\n",
"\n",
@@ -876,7 +355,7 @@
},
{
"cell_type": "code",
- "execution_count": 23,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -889,17 +368,9 @@
},
{
"cell_type": "code",
- "execution_count": 24,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Prédiction : 8.66 K$ Reality : 10.20 K$\n"
- ]
- }
- ],
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
"source": [
"\n",
"predictions = loaded_model.predict( mon_test )\n",
diff --git a/BHPD/fidle/pwk.py b/BHPD/fidle/pwk.py
deleted file mode 100644
index fd7bc208cc25b092430d6b75439e341c253fd702..0000000000000000000000000000000000000000
--- a/BHPD/fidle/pwk.py
+++ /dev/null
@@ -1,217 +0,0 @@
-
-# ==================================================================
-# ____ _ _ _ __ __ _
-# | _ \ _ __ __ _ ___| |_(_) ___ __ _| | \ \ / /__ _ __| | __
-# | |_) | '__/ _` |/ __| __| |/ __/ _` | | \ \ /\ / / _ \| '__| |/ /
-# | __/| | | (_| | (__| |_| | (_| (_| | | \ V V / (_) | | | <
-# |_| |_| \__,_|\___|\__|_|\___\__,_|_| \_/\_/ \___/|_| |_|\_\
-# module pwk
-# ==================================================================
-# A simple module to host some common functions for practical work
-# pjluc 2020
-
-import os
-import glob
-from datetime import datetime
-import itertools
-import datetime, time
-
-import math
-import numpy as np
-
-import tensorflow as tf
-from tensorflow import keras
-
-import matplotlib
-import matplotlib.pyplot as plt
-import seaborn as sn
-
-VERSION='0.2'
-
-
-# -------------------------------------------------------------
-# init_all
-# -------------------------------------------------------------
-#
-def init(mplstyle='fidle/talk.mplstyle'):
- global VERSION
- # ---- matplotlib
- matplotlib.style.use(mplstyle)
- # ---- Hello world
-# now = datetime.datetime.now()
- print('IDLE 2020 - Practical Work Module')
- print(' Version :', VERSION)
- print(' Run time : {}'.format(time.strftime("%A %-d %B %Y, %H:%M:%S")))
- print(' Matplotlib style :', mplstyle)
- print(' TensorFlow version :',tf.__version__)
- print(' Keras version :',tf.keras.__version__)
-
-# -------------------------------------------------------------
-# Folder cooking
-# -------------------------------------------------------------
-#
-def tag_now():
- return datetime.datetime.now().strftime("%Y-%m-%d_%Hh%Mm%Ss")
-
-def mkdir(path):
- os.makedirs(path, mode=0o750, exist_ok=True)
-
-def get_directory_size(path):
- """
- Return the directory size, but only 1 level
- args:
- path : directory path
- return:
- size in Mo
- """
- size=0
- for f in os.listdir(path):
- if os.path.isfile(path+'/'+f):
- size+=os.path.getsize(path+'/'+f)
- return size/(1024*1024)
-
-# -------------------------------------------------------------
-# shuffle_dataset
-# -------------------------------------------------------------
-#
-def shuffle_np_dataset(x, y):
- assert (len(x) == len(y)), "x and y must have same size"
- p = np.random.permutation(len(x))
- return x[p], y[p]
-
-
-def update_progress(what,i,imax):
- bar_length = min(40,imax)
- if (i%int(imax/bar_length))!=0 and i<imax:
- return
- progress = float(i/imax)
- block = int(round(bar_length * progress))
- endofline = '\r' if progress<1 else '\n'
- text = "{:16s} [{}] {:>5.1f}% of {}".format( what, "#"*block+"-"*(bar_length-block), progress*100, imax)
- print(text, end=endofline)
-
-
-# -------------------------------------------------------------
-# show_images
-# -------------------------------------------------------------
-#
-def plot_images(x,y, indices, columns=12, x_size=1, y_size=1, colorbar=False, y_pred=None, cm='binary'):
- """
- Show some images in a grid, with legends
- args:
- X: images - Shapes must be (-1 lx,ly,1) or (-1 lx,ly,3)
- y: real classes
- indices: indices of images to show
- columns: number of columns (12)
- x_size,y_size: figure size
- colorbar: show colorbar (False)
- y_pred: predicted classes (None)
- cm: Matplotlib olor map
- returns:
- nothing
- """
- rows = math.ceil(len(indices)/columns)
- fig=plt.figure(figsize=(columns*x_size, rows*(y_size+0.35)))
- n=1
- errors=0
- if np.any(y_pred)==None:
- y_pred=y
- for i in indices:
- axs=fig.add_subplot(rows, columns, n)
- n+=1
- # ---- Shape is (lx,ly)
- if len(x[i].shape)==2:
- xx=x[i]
- # ---- Shape is (lx,ly,n)
- if len(x[i].shape)==3:
- (lx,ly,lz)=x[i].shape
- if lz==1:
- xx=x[i].reshape(lx,ly)
- else:
- xx=x[i]
- img=axs.imshow(xx, cmap = cm, interpolation='lanczos')
- axs.spines['right'].set_visible(True)
- axs.spines['left'].set_visible(True)
- axs.spines['top'].set_visible(True)
- axs.spines['bottom'].set_visible(True)
- axs.set_yticks([])
- axs.set_xticks([])
- if y[i]!=y_pred[i]:
- axs.set_xlabel('{} ({})'.format(y_pred[i],y[i]))
- axs.xaxis.label.set_color('red')
- errors+=1
- else:
- axs.set_xlabel(y[i])
- if colorbar:
- fig.colorbar(img,orientation="vertical", shrink=0.65)
- plt.show()
-
-def plot_image(x,cm='binary', figsize=(4,4)):
- (lx,ly,lz)=x.shape
- plt.figure(figsize=figsize)
- if lz==1:
- plt.imshow(x.reshape(lx,ly), cmap = cm, interpolation='lanczos')
- else:
- plt.imshow(x.reshape(lx,ly,lz),cmap = cm, interpolation='lanczos')
- plt.show()
-
-
-# -------------------------------------------------------------
-# show_history
-# -------------------------------------------------------------
-#
-def plot_history(history, figsize=(8,6),
- plot={"Accuracy":['accuracy','val_accuracy'], 'Loss':['loss', 'val_loss']}):
- """
- Show history
- args:
- history: history
- figsize: fig size
- plot: list of data to plot : {<title>:[<metrics>,...], ...}
- """
- for title,curves in plot.items():
- plt.figure(figsize=figsize)
- plt.title(title)
- plt.ylabel(title)
- plt.xlabel('Epoch')
- for c in curves:
- plt.plot(history.history[c])
- plt.legend(curves, loc='upper left')
- plt.show()
-
-
-
-# -------------------------------------------------------------
-# plot_confusion_matrix
-# -------------------------------------------------------------
-#
-def plot_confusion_matrix(cm,
- title='Confusion matrix',
- figsize=(12,8),
- cmap="gist_heat_r",
- vmin=0,
- vmax=1,
- xticks=5,yticks=5):
- """
- given a sklearn confusion matrix (cm), make a nice plot
-
- Args:
- cm: confusion matrix from sklearn.metrics.confusion_matrix
- title: the text to display at the top of the matrix
- figsize: Figure size (12,8)
- cmap: color map (gist_heat_r)
- vmi,vmax: Min/max 0 and 1
-
- """
-
- accuracy = np.trace(cm) / float(np.sum(cm))
- misclass = 1 - accuracy
-
- plt.figure(figsize=figsize)
- sn.heatmap(cm, linewidths=1, linecolor="#ffffff",square=True,
- cmap=cmap, xticklabels=xticks, yticklabels=yticks,
- vmin=vmin,vmax=vmax)
- plt.ylabel('True label')
- plt.xlabel('Predicted label\naccuracy={:0.4f}; misclass={:0.4f}'.format(accuracy, misclass))
-
- plt.show()
diff --git a/GTSRB/01-Preparation-of-data.ipynb b/GTSRB/01-Preparation-of-data.ipynb
index c1ec4fc7b18984cdab67975728702eb33beb2aa0..1c0cabf5dface27d23884d6243d9bebf20739b17 100644
--- a/GTSRB/01-Preparation-of-data.ipynb
+++ b/GTSRB/01-Preparation-of-data.ipynb
@@ -25,22 +25,9 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "IDLE 2020 - Practical Work Module\n",
- " Version : 0.1.5\n",
- " Run time : Wednesday 22 January 2020, 19:21:15\n",
- " Matplotlib style : fidle/talk.mplstyle\n",
- " TensorFlow version : 2.0.0\n",
- " Keras version : 2.2.4-tf\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"import os, time, sys\n",
"import csv\n",
@@ -54,9 +41,11 @@
"from skimage.filters import rank\n",
"from skimage import io, color, exposure, transform\n",
"\n",
- "import fidle.pwk as ooo\n",
"from importlib import reload\n",
"\n",
+ "sys.path.append('..')\n",
+ "import fidle.pwk as ooo\n",
+ "\n",
"ooo.init()"
]
},
diff --git a/GTSRB/02-First-convolutions.ipynb b/GTSRB/02-First-convolutions.ipynb
index 3aa129a7d42897958da1aa8d9fad9a9ae59bfe1e..ac8dd91e596b4645ef010340ce2eb49adbdb1a9c 100644
--- a/GTSRB/02-First-convolutions.ipynb
+++ b/GTSRB/02-First-convolutions.ipynb
@@ -33,11 +33,13 @@
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import h5py\n",
- "import os,time\n",
+ "import os,time,sys\n",
"\n",
- "import fidle.pwk as ooo\n",
"from importlib import reload\n",
"\n",
+ "sys.path.append('..')\n",
+ "import fidle.pwk as ooo\n",
+ "\n",
"ooo.init()"
]
},
diff --git a/GTSRB/03-Tracking-and-visualizing.ipynb b/GTSRB/03-Tracking-and-visualizing.ipynb
index 204e784a88e5335f5e21c0d6087428f440e9fb42..2aa572ff0c0cae4f81d24bffb8f899e5300d1536 100644
--- a/GTSRB/03-Tracking-and-visualizing.ipynb
+++ b/GTSRB/03-Tracking-and-visualizing.ipynb
@@ -37,11 +37,13 @@
"\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sn\n",
- "import os, time, random\n",
+ "import os, sys, time, random\n",
"\n",
- "import fidle.pwk as ooo\n",
"from importlib import reload\n",
"\n",
+ "sys.path.append('..')\n",
+ "import fidle.pwk as ooo\n",
+ "\n",
"ooo.init()"
]
},
diff --git a/GTSRB/04-Data-augmentation.ipynb b/GTSRB/04-Data-augmentation.ipynb
index 2b87edc465153e7a7a15be329b32a4a345f2656b..e8c9079b7b49bca3069cbb5b40d5dbc96442d851 100644
--- a/GTSRB/04-Data-augmentation.ipynb
+++ b/GTSRB/04-Data-augmentation.ipynb
@@ -34,11 +34,13 @@
"\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sn\n",
- "import os, time, random\n",
+ "import os, sys, time, random\n",
"\n",
- "import fidle.pwk as ooo\n",
"from importlib import reload\n",
"\n",
+ "sys.path.append('..')\n",
+ "import fidle.pwk as ooo\n",
+ "\n",
"ooo.init()"
]
},
diff --git a/GTSRB/05-Full-convolutions.ipynb b/GTSRB/05-Full-convolutions.ipynb
index 4ae5fb20e5e031a01aad98423bd7cb1d3e483398..6e2220a2615d4abf1bc9b512b321dd19f5089a3d 100644
--- a/GTSRB/05-Full-convolutions.ipynb
+++ b/GTSRB/05-Full-convolutions.ipynb
@@ -21,7 +21,7 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -47,26 +47,9 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n",
- "Full Convolutions Notebook\n",
- " Version : 1.6\n",
- " Now is : Tuesday 21 January 2020 - 00h11m24s\n",
- " OAR id : ???\n",
- " Tag id : 077605\n",
- " Working directory : /home/pjluc/dev/fidle/GTSRB\n",
- " TensorFlow version : 2.0.0\n",
- " Keras version : 2.2.4-tf\n",
- " for tensorboard : --logdir /home/pjluc/dev/fidle/GTSRB/run/logs_077605\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"# ---- Where I am ?\n",
"now = time.strftime(\"%A %d %B %Y - %Hh%Mm%Ss\")\n",
@@ -100,7 +83,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -129,7 +112,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -213,7 +196,7 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
diff --git a/GTSRB/99 Scripts-Tensorboard.ipynb b/GTSRB/99 Scripts-Tensorboard.ipynb
index 2db0f8bd965552bdec9f03abb08d53933f0cde1a..dc8c2c0f84b1e1b524641cb5e45f0a216d4a5e8d 100644
--- a/GTSRB/99 Scripts-Tensorboard.ipynb
+++ b/GTSRB/99 Scripts-Tensorboard.ipynb
@@ -15,158 +15,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "## 1/ Méthode 1 : Shell execute\n",
- "### 1.1/ Start/stop"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Tensorbord started - pid is 9934\n",
- "12399\n"
- ]
- }
- ],
- "source": [
- "%%bash\n",
- "tensorboard_start --logdir ./run/logs"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 7,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Tensorboard status - not found...\n"
- ]
- }
- ],
- "source": [
- "%%bash\n",
- "tensorboard_status"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Tensorbord stopped - pid was 9934\n"
- ]
- }
- ],
- "source": [
- "%%bash\n",
- "tensorboard_stop"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 1.3/ Scripts"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Overwriting /home/paroutyj/bin/tensorboard_start\n"
- ]
- }
- ],
- "source": [
- "%%writefile \"~/bin/tensorboard_start\"\n",
- "\n",
- "#!/bin/bash\n",
- "#\n",
- "# -----------------------------------------------------------\n",
- "# _____ _ _ \n",
- "# |_ _|__ _ __ ___ ___ _ __| |__ ___ __ _ _ __ __| |\n",
- "# | |/ _ \\ '_ \\/ __|/ _ \\| '__| '_ \\ / _ \\ / _` | '__/ _` |\n",
- "# | | __/ | | \\__ \\ (_) | | | |_) | (_) | (_| | | | (_| |\n",
- "# |_|\\___|_| |_|___/\\___/|_| |_.__/ \\___/ \\__,_|_| \\__,_|\n",
- "# Start\n",
- "# -----------------------------------------------------------\n",
- "# Start tensorboard, with calculate port number and good host\n",
- "# -----------------------------------------------------------\n",
- "# Jean-Luc Parouty CNRS/SIMaP Janvier 2020 - version 1.02\n",
- "\n",
- "VERSION='1.2'\n",
- "CONDA_ENV='GPU'\n",
- "HOST_FRONT='f-dahu'\n",
- "\n",
- "# ---- Usage\n",
- "#\n",
- "if [ \"$1\" == \"-?\" ] || [ $# -eq 0 ]; then\n",
- " echo -e \"Start tensorboard in GRICAD environment. (v$VERSION)\"\n",
- " echo -e \"Usage: $(basename $0) -h | --logdir <logdir> [tensorboard args]\"\n",
- " echo -e \"Exemple : $(basename $0) --logdir ./run/logs\\n\"\n",
- " exit\n",
- "fi\n",
- " \n",
- "# ---- Conda activate\n",
- "#\n",
- "source /applis/environments/conda.sh\n",
- "conda activate \"$CONDA_ENV\" >/dev/null 2>&1\n",
- "status=$?\n",
- "if [ $status -ne 0 ]; then\n",
- " echo -e \"Oups ! Conda environment is not available... contact your support ;-(\\n\"\n",
- " exit 1\n",
- "fi\n",
- " \n",
- "# ---- Port number\n",
- "#\n",
- "PORT_JPY=\"$(/usr/bin/id -u)\"\n",
- "PORT_TSB=\"$(( $PORT_JPY + 10000 ))\"\n",
- " \n",
- "# ---- tmpdir (tmp bug)\n",
- "#\n",
- "export TMPDIR=\"/tmp/$(/usr/bin/id -un)\"\n",
- "/bin/mkdir -p \"$TMPDIR\"\n",
- "\n",
- "# ---- Start it\n",
- "#\n",
- "tensorboard --port $PORT_TSB --host 0.0.0.0 $@ &>/dev/null &\n",
- " \n",
- "# ---- Where is it ?\n",
- "#\n",
- "sleep 5\n",
- "p=\"$(/bin/ps ax | /bin/grep \"tensorboard --port $PORT_TSB\" | /bin/grep -v grep | awk '{print $1}')\"\n",
- "if [ -z \"$p\" ]; then\n",
- " echo \"Tensorboard didn't start... check your parameters !\"\n",
- " exit\n",
- "else\n",
- " echo \"Tensorbord started - pid is $p\"\n",
- "fi\n",
- " \n",
- "# ---- Not on a node ? we give the tunnel\n",
- "#\n",
- "if [ \"$(hostname)\" == $HOST_FRONT ]\n",
- "then\n",
- " SSH_CMD=\"/usr/bin/ssh -NL 6006:$HOST_FRONT:$PORT_TSB dahu.ciment\"\n",
- " echo -e \"SSH Tunnel : \\e[93m$SSH_CMD \\e[0m\\n\"\n",
- "fi\n",
- " "
+ "## 1/ Méthode 1 : Shell command"
]
},
{
@@ -175,46 +24,8 @@
"metadata": {},
"outputs": [],
"source": [
- "%%writefile \"~/bin/tensorboard_status\"\n",
- "\n",
- "#!/bin/bash\n",
- "#\n",
- "# -----------------------------------------------------------\n",
- "# _____ _ _ \n",
- "# |_ _|__ _ __ ___ ___ _ __| |__ ___ __ _ _ __ __| |\n",
- "# | |/ _ \\ '_ \\/ __|/ _ \\| '__| '_ \\ / _ \\ / _` | '__/ _` |\n",
- "# | | __/ | | \\__ \\ (_) | | | |_) | (_) | (_| | | | (_| |\n",
- "# |_|\\___|_| |_|___/\\___/|_| |_.__/ \\___/ \\__,_|_| \\__,_|\n",
- "# Status\n",
- "# -----------------------------------------------------------\n",
- "# Stop tensorboard previously started with tensorboard_start\n",
- "# -----------------------------------------------------------\n",
- "# Jean-Luc Parouty CNRS/SIMaP Janvier 2020\n",
- "\n",
- "VERSION=\"1.02\"\n",
- "\n",
- "# ---- Usage\n",
- "#\n",
- "if [ \"$1\" == \"-?\" ] ; then\n",
- " echo -e \"Tensorboard status in GRICAD environment. (v$VERSION)\"\n",
- " echo -e \"Usage: $(basename $0) [-h ]\"\n",
- " echo -e \"Exemple : $(basename $0)\\n\"\n",
- " exit\n",
- "fi\n",
- "\n",
- "# ---- Process id\n",
- "#\n",
- "PORT_JPY=\"$(id -u)\"\n",
- "PORT_TSB=\"$(( $PORT_JPY + 10000 ))\"\n",
- "\n",
- "# ---- Where is it ?\n",
- "#\n",
- "p=\"$(ps ax | grep \"tensorboard --port $PORT_TSB\" | grep -v grep | awk '{print $1}')\"\n",
- "if [ -z \"$p\" ]; then\n",
- " echo \"Tensorboard status - not found...\"\n",
- "else\n",
- " echo \"Tensorboard status - pid is $p\"\n",
- "fi"
+ "%%bash\n",
+ "tensorboard_start --logdir ./run/logs"
]
},
{
@@ -223,54 +34,8 @@
"metadata": {},
"outputs": [],
"source": [
- "%%writefile \"~/bin/tensorboard_stop\"\n",
- "\n",
- "#!/bin/bash\n",
- "#\n",
- "# -----------------------------------------------------------\n",
- "# _____ _ _ \n",
- "# |_ _|__ _ __ ___ ___ _ __| |__ ___ __ _ _ __ __| |\n",
- "# | |/ _ \\ '_ \\/ __|/ _ \\| '__| '_ \\ / _ \\ / _` | '__/ _` |\n",
- "# | | __/ | | \\__ \\ (_) | | | |_) | (_) | (_| | | | (_| |\n",
- "# |_|\\___|_| |_|___/\\___/|_| |_.__/ \\___/ \\__,_|_| \\__,_|\n",
- "# Stop\n",
- "# -----------------------------------------------------------\n",
- "# Stop tensorboard previously started with tensorboard_start\n",
- "# -----------------------------------------------------------\n",
- "# Jean-Luc Parouty CNRS/SIMaP Janvier 2020\n",
- "\n",
- "VERSION=\"1.02\"\n",
- "\n",
- "# ---- Usage\n",
- "#\n",
- "if [ \"$1\" == \"-?\" ] ; then\n",
- " echo -e \"Stop tensorboard in GRICAD environment. (v$VERSION)\"\n",
- " echo -e \"Usage: $(basename $0) [-h ]\"\n",
- " echo -e \"Exemple : $(basename $0)\\n\"\n",
- " exit\n",
- "fi\n",
- "\n",
- "# ---- Process id\n",
- "#\n",
- "PORT_JPY=\"$(id -u)\"\n",
- "PORT_TSB=\"$(( $PORT_JPY + 10000 ))\"\n",
- "\n",
- "# ---- Where is it ?\n",
- "#\n",
- "p=\"$(ps ax | grep \"tensorboard --port $PORT_TSB\" | grep -v grep | awk '{print $1}')\"\n",
- "if [ -z \"$p\" ]; then\n",
- " echo \"Tensorboard process not found...\"\n",
- "else\n",
- " kill $p\n",
- " echo \"Tensorbord stopped - pid was $p\"\n",
- "fi"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "**Set scripts privileges :**"
+ "%%bash\n",
+ "tensorboard_status"
]
},
{
@@ -280,15 +45,7 @@
"outputs": [],
"source": [
"%%bash\n",
- "/bin/chmod 755 ~/bin/tensorboard_* 2>/dev/null\n",
- "/bin/ls -l ~/bin/tensorboard_* 2>/dev/null"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "**Check**"
+ "tensorboard_stop"
]
},
{
diff --git a/GTSRB/fidle/__init__.py b/GTSRB/fidle/__init__.py
deleted file mode 100644
index 098c126cc59c579c3cc9a4fd398f3899b823d0d8..0000000000000000000000000000000000000000
--- a/GTSRB/fidle/__init__.py
+++ /dev/null
@@ -1,2 +0,0 @@
-
-VERSION='0.1a'
\ No newline at end of file
diff --git a/GTSRB/fidle/pwk.py b/GTSRB/fidle/pwk.py
deleted file mode 100644
index fd7bc208cc25b092430d6b75439e341c253fd702..0000000000000000000000000000000000000000
--- a/GTSRB/fidle/pwk.py
+++ /dev/null
@@ -1,217 +0,0 @@
-
-# ==================================================================
-# ____ _ _ _ __ __ _
-# | _ \ _ __ __ _ ___| |_(_) ___ __ _| | \ \ / /__ _ __| | __
-# | |_) | '__/ _` |/ __| __| |/ __/ _` | | \ \ /\ / / _ \| '__| |/ /
-# | __/| | | (_| | (__| |_| | (_| (_| | | \ V V / (_) | | | <
-# |_| |_| \__,_|\___|\__|_|\___\__,_|_| \_/\_/ \___/|_| |_|\_\
-# module pwk
-# ==================================================================
-# A simple module to host some common functions for practical work
-# pjluc 2020
-
-import os
-import glob
-from datetime import datetime
-import itertools
-import datetime, time
-
-import math
-import numpy as np
-
-import tensorflow as tf
-from tensorflow import keras
-
-import matplotlib
-import matplotlib.pyplot as plt
-import seaborn as sn
-
-VERSION='0.2'
-
-
-# -------------------------------------------------------------
-# init_all
-# -------------------------------------------------------------
-#
-def init(mplstyle='fidle/talk.mplstyle'):
- global VERSION
- # ---- matplotlib
- matplotlib.style.use(mplstyle)
- # ---- Hello world
-# now = datetime.datetime.now()
- print('IDLE 2020 - Practical Work Module')
- print(' Version :', VERSION)
- print(' Run time : {}'.format(time.strftime("%A %-d %B %Y, %H:%M:%S")))
- print(' Matplotlib style :', mplstyle)
- print(' TensorFlow version :',tf.__version__)
- print(' Keras version :',tf.keras.__version__)
-
-# -------------------------------------------------------------
-# Folder cooking
-# -------------------------------------------------------------
-#
-def tag_now():
- return datetime.datetime.now().strftime("%Y-%m-%d_%Hh%Mm%Ss")
-
-def mkdir(path):
- os.makedirs(path, mode=0o750, exist_ok=True)
-
-def get_directory_size(path):
- """
- Return the directory size, but only 1 level
- args:
- path : directory path
- return:
- size in Mo
- """
- size=0
- for f in os.listdir(path):
- if os.path.isfile(path+'/'+f):
- size+=os.path.getsize(path+'/'+f)
- return size/(1024*1024)
-
-# -------------------------------------------------------------
-# shuffle_dataset
-# -------------------------------------------------------------
-#
-def shuffle_np_dataset(x, y):
- assert (len(x) == len(y)), "x and y must have same size"
- p = np.random.permutation(len(x))
- return x[p], y[p]
-
-
-def update_progress(what,i,imax):
- bar_length = min(40,imax)
- if (i%int(imax/bar_length))!=0 and i<imax:
- return
- progress = float(i/imax)
- block = int(round(bar_length * progress))
- endofline = '\r' if progress<1 else '\n'
- text = "{:16s} [{}] {:>5.1f}% of {}".format( what, "#"*block+"-"*(bar_length-block), progress*100, imax)
- print(text, end=endofline)
-
-
-# -------------------------------------------------------------
-# show_images
-# -------------------------------------------------------------
-#
-def plot_images(x,y, indices, columns=12, x_size=1, y_size=1, colorbar=False, y_pred=None, cm='binary'):
- """
- Show some images in a grid, with legends
- args:
- X: images - Shapes must be (-1 lx,ly,1) or (-1 lx,ly,3)
- y: real classes
- indices: indices of images to show
- columns: number of columns (12)
- x_size,y_size: figure size
- colorbar: show colorbar (False)
- y_pred: predicted classes (None)
- cm: Matplotlib olor map
- returns:
- nothing
- """
- rows = math.ceil(len(indices)/columns)
- fig=plt.figure(figsize=(columns*x_size, rows*(y_size+0.35)))
- n=1
- errors=0
- if np.any(y_pred)==None:
- y_pred=y
- for i in indices:
- axs=fig.add_subplot(rows, columns, n)
- n+=1
- # ---- Shape is (lx,ly)
- if len(x[i].shape)==2:
- xx=x[i]
- # ---- Shape is (lx,ly,n)
- if len(x[i].shape)==3:
- (lx,ly,lz)=x[i].shape
- if lz==1:
- xx=x[i].reshape(lx,ly)
- else:
- xx=x[i]
- img=axs.imshow(xx, cmap = cm, interpolation='lanczos')
- axs.spines['right'].set_visible(True)
- axs.spines['left'].set_visible(True)
- axs.spines['top'].set_visible(True)
- axs.spines['bottom'].set_visible(True)
- axs.set_yticks([])
- axs.set_xticks([])
- if y[i]!=y_pred[i]:
- axs.set_xlabel('{} ({})'.format(y_pred[i],y[i]))
- axs.xaxis.label.set_color('red')
- errors+=1
- else:
- axs.set_xlabel(y[i])
- if colorbar:
- fig.colorbar(img,orientation="vertical", shrink=0.65)
- plt.show()
-
-def plot_image(x,cm='binary', figsize=(4,4)):
- (lx,ly,lz)=x.shape
- plt.figure(figsize=figsize)
- if lz==1:
- plt.imshow(x.reshape(lx,ly), cmap = cm, interpolation='lanczos')
- else:
- plt.imshow(x.reshape(lx,ly,lz),cmap = cm, interpolation='lanczos')
- plt.show()
-
-
-# -------------------------------------------------------------
-# show_history
-# -------------------------------------------------------------
-#
-def plot_history(history, figsize=(8,6),
- plot={"Accuracy":['accuracy','val_accuracy'], 'Loss':['loss', 'val_loss']}):
- """
- Show history
- args:
- history: history
- figsize: fig size
- plot: list of data to plot : {<title>:[<metrics>,...], ...}
- """
- for title,curves in plot.items():
- plt.figure(figsize=figsize)
- plt.title(title)
- plt.ylabel(title)
- plt.xlabel('Epoch')
- for c in curves:
- plt.plot(history.history[c])
- plt.legend(curves, loc='upper left')
- plt.show()
-
-
-
-# -------------------------------------------------------------
-# plot_confusion_matrix
-# -------------------------------------------------------------
-#
-def plot_confusion_matrix(cm,
- title='Confusion matrix',
- figsize=(12,8),
- cmap="gist_heat_r",
- vmin=0,
- vmax=1,
- xticks=5,yticks=5):
- """
- given a sklearn confusion matrix (cm), make a nice plot
-
- Args:
- cm: confusion matrix from sklearn.metrics.confusion_matrix
- title: the text to display at the top of the matrix
- figsize: Figure size (12,8)
- cmap: color map (gist_heat_r)
- vmi,vmax: Min/max 0 and 1
-
- """
-
- accuracy = np.trace(cm) / float(np.sum(cm))
- misclass = 1 - accuracy
-
- plt.figure(figsize=figsize)
- sn.heatmap(cm, linewidths=1, linecolor="#ffffff",square=True,
- cmap=cmap, xticklabels=xticks, yticklabels=yticks,
- vmin=vmin,vmax=vmax)
- plt.ylabel('True label')
- plt.xlabel('Predicted label\naccuracy={:0.4f}; misclass={:0.4f}'.format(accuracy, misclass))
-
- plt.show()
diff --git a/GTSRB/fidle/talk.mplstyle b/GTSRB/fidle/talk.mplstyle
deleted file mode 100644
index edf3fed3a5f6f7c0a1b76a4195f74ea9d68aa966..0000000000000000000000000000000000000000
--- a/GTSRB/fidle/talk.mplstyle
+++ /dev/null
@@ -1,33 +0,0 @@
-
-# See : https://matplotlib.org/users/customizing.html
-
-axes.titlesize : 24
-axes.labelsize : 20
-axes.edgecolor : dimgrey
-axes.labelcolor : dimgrey
-axes.linewidth : 2
-axes.grid : False
-
-axes.prop_cycle : cycler('color', ['steelblue', 'tomato', '2ca02c', 'd62728', '9467bd', '8c564b', 'e377c2', '7f7f7f', 'bcbd22', '17becf'])
-
-lines.linewidth : 3
-lines.markersize : 10
-
-xtick.color : black
-xtick.labelsize : 18
-ytick.color : black
-ytick.labelsize : 18
-
-axes.spines.left : True
-axes.spines.bottom : True
-axes.spines.top : False
-axes.spines.right : False
-
-savefig.dpi : 300 # figure dots per inch or 'figure'
-savefig.facecolor : white # figure facecolor when saving
-savefig.edgecolor : white # figure edgecolor when saving
-savefig.format : svg
-savefig.bbox : tight
-savefig.pad_inches : 0.1
-savefig.transparent : True
-savefig.jpeg_quality: 95
diff --git a/IMDB/.~03-LSTM-Keras.ipynb b/IMDB/.~03-LSTM-Keras.ipynb
deleted file mode 100644
index db8bfb1cd617395f31e23ccc4bafd633b7c2e180..0000000000000000000000000000000000000000
--- a/IMDB/.~03-LSTM-Keras.ipynb
+++ /dev/null
@@ -1,679 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "Text Embedding - IMDB dataset\n",
- "=============================\n",
- "---\n",
- "Introduction au Deep Learning (IDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020 \n",
- "\n",
- "## Text classification using **Text embedding** :\n",
- "\n",
- "The objective is to guess whether film reviews are **positive or negative** based on the analysis of the text. \n",
- "\n",
- "Original dataset can be find **[there](http://ai.stanford.edu/~amaas/data/sentiment/)** \n",
- "Note that [IMDb.com](https://imdb.com) offers several easy-to-use [datasets](https://www.imdb.com/interfaces/) \n",
- "For simplicity's sake, we'll use the dataset directly [embedded in Keras](https://www.tensorflow.org/api_docs/python/tf/keras/datasets)\n",
- "\n",
- "What we're going to do:\n",
- "\n",
- " - Retrieve data\n",
- " - Preparing the data\n",
- " - Build a model\n",
- " - Train the model\n",
- " - Evaluate the result\n"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Step 1 - Init python stuff"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 1,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "IDLE 2020 - Practical Work Module\n",
- " Version : 0.2.4\n",
- " Run time : Wednesday 29 January 2020, 13:22:54\n",
- " Matplotlib style : fidle/talk.mplstyle\n",
- " TensorFlow version : 2.0.0\n",
- " Keras version : 2.2.4-tf\n"
- ]
- }
- ],
- "source": [
- "import numpy as np\n",
- "\n",
- "import tensorflow as tf\n",
- "import tensorflow.keras as keras\n",
- "import tensorflow.keras.datasets.imdb as imdb\n",
- "\n",
- "import matplotlib.pyplot as plt\n",
- "import matplotlib\n",
- "import seaborn as sns\n",
- "\n",
- "import os,h5py,json\n",
- "\n",
- "import fidle.pwk as ooo\n",
- "from importlib import reload\n",
- "\n",
- "ooo.init()"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Step 2 - Retrieve data\n",
- "\n",
- "**From Keras :**\n",
- "This IMDb dataset can bet get directly from [Keras datasets](https://www.tensorflow.org/api_docs/python/tf/keras/datasets) \n",
- "\n",
- "Due to their nature, textual data can be somewhat complex.\n",
- "\n",
- "### 2.1 - Data structure : \n",
- "The dataset is composed of 2 parts: **reviews** and **opinions** (positive/negative), with a **dictionary**\n",
- "\n",
- " - dataset = (reviews, opinions)\n",
- " - reviews = \\[ review_0, review_1, ...\\]\n",
- " - review_i = [ int1, int2, ...] where int_i is the index of the word in the dictionary.\n",
- " - opinions = \\[ int0, int1, ...\\] where int_j == 0 if opinion is negative or 1 if opinion is positive.\n",
- " - dictionary = \\[ mot1:int1, mot2:int2, ... ]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 2.2 - Get dataset\n",
- "For simplicity, we will use a pre-formatted dataset. \n",
- "See : https://www.tensorflow.org/api_docs/python/tf/keras/datasets/imdb/load_data \n",
- "\n",
- "However, Keras offers some usefull tools for formatting textual data. \n",
- "See : https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/text"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [],
- "source": [
- "vocab_size = 10000\n",
- "\n",
- "# ----- Retrieve x,y\n",
- "#\n",
- "(x_train, y_train), (x_test, y_test) = imdb.load_data( num_words = vocab_size,\n",
- " skip_top = 0,\n",
- " maxlen = None,\n",
- " seed = 42,\n",
- " start_char = 1,\n",
- " oov_char = 2,\n",
- " index_from = 3, )"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- " Max(x_train,x_test) : 9999\n",
- " x_train : (25000,) y_train : (25000,)\n",
- " x_test : (25000,) y_test : (25000,)\n",
- "\n",
- "Review example (x_train[12]) :\n",
- "\n",
- " [1, 14, 22, 1367, 53, 206, 159, 4, 636, 898, 74, 26, 11, 436, 363, 108, 7, 14, 432, 14, 22, 9, 1055, 34, 8599, 2, 5, 381, 3705, 4509, 14, 768, 47, 839, 25, 111, 1517, 2579, 1991, 438, 2663, 587, 4, 280, 725, 6, 58, 11, 2714, 201, 4, 206, 16, 702, 5, 5176, 19, 480, 5920, 157, 13, 64, 219, 4, 2, 11, 107, 665, 1212, 39, 4, 206, 4, 65, 410, 16, 565, 5, 24, 43, 343, 17, 5602, 8, 169, 101, 85, 206, 108, 8, 3008, 14, 25, 215, 168, 18, 6, 2579, 1991, 438, 2, 11, 129, 1609, 36, 26, 66, 290, 3303, 46, 5, 633, 115, 4363]\n"
- ]
- }
- ],
- "source": [
- "print(\" Max(x_train,x_test) : \", ooo.rmax([x_train,x_test]) )\n",
- "print(\" x_train : {} y_train : {}\".format(x_train.shape, y_train.shape))\n",
- "print(\" x_test : {} y_test : {}\".format(x_test.shape, y_test.shape))\n",
- "\n",
- "print('\\nReview example (x_train[12]) :\\n\\n',x_train[12])"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 2.3 - Have a look for humans (optional)\n",
- "When we loaded the dataset, we asked for using \\<start\\> as 1, \\<unknown word\\> as 2 \n",
- "So, we shifted the dataset by 3 with the parameter index_from=3"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "metadata": {},
- "outputs": [],
- "source": [
- "# ---- Retrieve dictionary {word:index}, and encode it in ascii\n",
- "\n",
- "word_index = imdb.get_word_index()\n",
- "\n",
- "# ---- Shift the dictionary from +3\n",
- "\n",
- "word_index = {w:(i+3) for w,i in word_index.items()}\n",
- "\n",
- "# ---- Add <pad>, <start> and unknown tags\n",
- "\n",
- "word_index.update( {'<pad>':0, '<start>':1, '<unknown>':2} )\n",
- "\n",
- "# ---- Create a reverse dictionary : {index:word}\n",
- "\n",
- "index_word = {index:word for word,index in word_index.items()} \n",
- "\n",
- "# ---- Add a nice function to transpose :\n",
- "#\n",
- "def dataset2text(review):\n",
- " return ' '.join([index_word.get(i, '?') for i in review])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n",
- "Dictionary size : 88587\n",
- "\n",
- "Review example (x_train[12]) :\n",
- "\n",
- " [1, 14, 22, 1367, 53, 206, 159, 4, 636, 898, 74, 26, 11, 436, 363, 108, 7, 14, 432, 14, 22, 9, 1055, 34, 8599, 2, 5, 381, 3705, 4509, 14, 768, 47, 839, 25, 111, 1517, 2579, 1991, 438, 2663, 587, 4, 280, 725, 6, 58, 11, 2714, 201, 4, 206, 16, 702, 5, 5176, 19, 480, 5920, 157, 13, 64, 219, 4, 2, 11, 107, 665, 1212, 39, 4, 206, 4, 65, 410, 16, 565, 5, 24, 43, 343, 17, 5602, 8, 169, 101, 85, 206, 108, 8, 3008, 14, 25, 215, 168, 18, 6, 2579, 1991, 438, 2, 11, 129, 1609, 36, 26, 66, 290, 3303, 46, 5, 633, 115, 4363]\n",
- "\n",
- "In real words :\n",
- "\n",
- " <start> this film contains more action before the opening credits than are in entire hollywood films of this sort this film is produced by tsui <unknown> and stars jet li this team has brought you many worthy hong kong cinema productions including the once upon a time in china series the action was fast and furious with amazing wire work i only saw the <unknown> in two shots aside from the action the story itself was strong and not just used as filler to find any other action films to rival this you must look for a hong kong cinema <unknown> in your area they are really worth checking out and usually never disappoint\n"
- ]
- }
- ],
- "source": [
- "print('\\nDictionary size : ', len(word_index))\n",
- "print('\\nReview example (x_train[12]) :\\n\\n',x_train[12])\n",
- "print('\\nIn real words :\\n\\n', dataset2text(x_train[12]))"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 2.4 - Have a look for neurons"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 6,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 864x432 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
- "source": [
- "plt.figure(figsize=(12, 6))\n",
- "ax=sns.distplot([len(i) for i in x_train],bins=60)\n",
- "ax.set_title('Distribution of reviews by size')\n",
- "plt.xlabel(\"Review's sizes\")\n",
- "plt.ylabel('Density')\n",
- "ax.set_xlim(0, 1500)\n",
- "plt.show()"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Step 3 - Preprocess the data\n",
- "In order to be processed by an NN, all entries must have the same length. \n",
- "We chose a review length of **review_len** \n",
- "We will therefore complete them with a padding (of \\<pad\\>\\) "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 7,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n",
- "Review example (x_train[12]) :\n",
- "\n",
- " [ 1 14 22 1367 53 206 159 4 636 898 74 26 11 436\n",
- " 363 108 7 14 432 14 22 9 1055 34 8599 2 5 381\n",
- " 3705 4509 14 768 47 839 25 111 1517 2579 1991 438 2663 587\n",
- " 4 280 725 6 58 11 2714 201 4 206 16 702 5 5176\n",
- " 19 480 5920 157 13 64 219 4 2 11 107 665 1212 39\n",
- " 4 206 4 65 410 16 565 5 24 43 343 17 5602 8\n",
- " 169 101 85 206 108 8 3008 14 25 215 168 18 6 2579\n",
- " 1991 438 2 11 129 1609 36 26 66 290 3303 46 5 633\n",
- " 115 4363 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0]\n",
- "\n",
- "In real words :\n",
- "\n",
- " <start> this film contains more action before the opening credits than are in entire hollywood films of this sort this film is produced by tsui <unknown> and stars jet li this team has brought you many worthy hong kong cinema productions including the once upon a time in china series the action was fast and furious with amazing wire work i only saw the <unknown> in two shots aside from the action the story itself was strong and not just used as filler to find any other action films to rival this you must look for a hong kong cinema <unknown> in your area they are really worth checking out and usually never disappoint <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad>\n"
- ]
- }
- ],
- "source": [
- "review_len = 256\n",
- "\n",
- "x_train = keras.preprocessing.sequence.pad_sequences(x_train,\n",
- " value = 0,\n",
- " padding = 'post',\n",
- " maxlen = review_len)\n",
- "\n",
- "x_test = keras.preprocessing.sequence.pad_sequences(x_test,\n",
- " value = 0 ,\n",
- " padding = 'post',\n",
- " maxlen = review_len)\n",
- "\n",
- "print('\\nReview example (x_train[12]) :\\n\\n',x_train[12])\n",
- "print('\\nIn real words :\\n\\n', dataset2text(x_train[12]))"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Save dataset and dictionary (can be usefull)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 8,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Saved.\n"
- ]
- }
- ],
- "source": [
- "os.makedirs('./data', mode=0o750, exist_ok=True)\n",
- "\n",
- "with h5py.File('./data/dataset_imdb.h5', 'w') as f:\n",
- " f.create_dataset(\"x_train\", data=x_train)\n",
- " f.create_dataset(\"y_train\", data=y_train)\n",
- " f.create_dataset(\"x_test\", data=x_test)\n",
- " f.create_dataset(\"y_test\", data=y_test)\n",
- "\n",
- "with open('./data/word_index.json', 'w') as fp:\n",
- " json.dump(word_index, fp)\n",
- "\n",
- "with open('./data/index_word.json', 'w') as fp:\n",
- " json.dump(index_word, fp)\n",
- "\n",
- "print('Saved.')"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Step 4 - Build the model\n",
- "Few remarks :\n",
- "1. We'll choose a dense vector size for the embedding output with **dense_vector_size**\n",
- "2. **GlobalAveragePooling1D** do a pooling on the last dimension : (None, lx, ly) -> (None, ly) \n",
- "In other words: we average the set of vectors/words of a sentence\n",
- "3. L'embedding de Keras fonctionne de manière supervisée. Il s'agit d'une couche de *vocab_size* neurones vers *n_neurons* permettant de maintenir une table de vecteurs (les poids constituent les vecteurs). Cette couche ne calcule pas de sortie a la façon des couches normales, mais renvois la valeur des vecteurs. n mots => n vecteurs (ensuite empilés par le pooling) \n",
- "Voir : https://stats.stackexchange.com/questions/324992/how-the-embedding-layer-is-trained-in-keras-embedding-layer\n",
- "\n",
- "A SUIVRE : https://www.liip.ch/en/blog/sentiment-detection-with-keras-word-embeddings-and-lstm-deep-learning-networks\n",
- "### 4.1 - Build\n",
- "More documentation about :\n",
- " - [Embedding](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Embedding)\n",
- " - [GlobalAveragePooling1D](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling1D)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 9,
- "metadata": {},
- "outputs": [],
- "source": [
- "def get_model(dense_vector_size=128):\n",
- " \n",
- " model = keras.Sequential()\n",
- " model.add(keras.layers.Embedding(input_dim = vocab_size, \n",
- " output_dim = dense_vector_size, \n",
- " input_length = review_len))\n",
- " model.add(keras.layers.LSTM(128, dropout=0.2, recurrent_dropout=0.2))\n",
- " model.add(keras.layers.Dense(1, activation='sigmoid'))\n",
- "\n",
- " model.compile(optimizer = 'adam',\n",
- " loss = 'binary_crossentropy',\n",
- " metrics = ['accuracy'])\n",
- " return model"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Step 5 - Train the model\n",
- "### 5.1 - Get it"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 15,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Model: \"sequential_1\"\n",
- "_________________________________________________________________\n",
- "Layer (type) Output Shape Param # \n",
- "=================================================================\n",
- "embedding_1 (Embedding) (None, 256, 128) 1280000 \n",
- "_________________________________________________________________\n",
- "lstm_1 (LSTM) (None, 128) 131584 \n",
- "_________________________________________________________________\n",
- "dense_1 (Dense) (None, 1) 129 \n",
- "=================================================================\n",
- "Total params: 1,411,713\n",
- "Trainable params: 1,411,713\n",
- "Non-trainable params: 0\n",
- "_________________________________________________________________\n"
- ]
- }
- ],
- "source": [
- "model = get_model()\n",
- "\n",
- "model.summary()"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 5.2 - Add callback"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 16,
- "metadata": {},
- "outputs": [],
- "source": [
- "os.makedirs('./run/models', mode=0o750, exist_ok=True)\n",
- "save_dir = \"./run/models/best_model.h5\"\n",
- "savemodel_callback = tf.keras.callbacks.ModelCheckpoint(filepath=save_dir, verbose=0, save_best_only=True)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 5.1 - Train it\n",
- "GPU : batch_size=512 : 305s"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Train on 25000 samples, validate on 25000 samples\n",
- "Epoch 1/10\n",
- "25000/25000 [==============================] - 206s 8ms/sample - loss: 0.6684 - accuracy: 0.5654 - val_loss: 0.6667 - val_accuracy: 0.5606\n",
- "Epoch 2/10\n",
- " 9120/25000 [=========>....................] - ETA: 1:42 - loss: 0.6228 - accuracy: 0.5968"
- ]
- }
- ],
- "source": [
- "%%time\n",
- "\n",
- "n_epochs = 10\n",
- "batch_size = 32\n",
- "\n",
- "history = model.fit(x_train,\n",
- " y_train,\n",
- " epochs = n_epochs,\n",
- " batch_size = batch_size,\n",
- " validation_data = (x_test, y_test),\n",
- " verbose = 1,\n",
- " callbacks = [savemodel_callback])\n"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Step 6 - Evaluate\n",
- "### 6.1 - Training history"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 13,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 576x432 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 576x432 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
- "source": [
- "ooo.plot_history(history)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 6.2 - Reload and evaluate best model"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 14,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "x_test / loss : 0.4452\n",
- "x_test / accuracy : 0.8282\n"
- ]
- },
- {
- "data": {
- "text/markdown": [
- "#### Accuracy donut is :"
- ],
- "text/plain": [
- "<IPython.core.display.Markdown object>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "iVBORw0KGgoAAAANSUhEUgAAAaUAAAGoCAYAAADmTPpwAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8QZhcZAAAgAElEQVR4nOzdd5hcVfnA8e+ZmZ2d7b2lF0IqIQmEEulIUwEFRaQozYZYfxZAURTFAgiioNKlCAIKSJeeUAOk97LZlO29T7+/P+5usjtzZ+uUe2fez/Pss5tz78682d2575xzz3mP0jQNIYQQwgxsiQ5ACCGE6CdJSQghhGlIUhJCCGEakpSEEEKYhiQlIYQQpiFJSQghhGlIUhJCCGEakpSEEEKYhiQlIYQQpiFJSQghhGlIUhJCCGEakpSEEEKYhiQlIYQQpiFJSQghhGlIUhJCCGEakpSEEEKYhiQlIYQQpiFJSQghhGlIUhJCCGEakpSEEEKYhiQlIYQQpiFJSQghhGlIUhJCCGEakpSEEEKYhiQlIYQQpiFJSQghhGlIUhJCCGEakpSEEEKYhiQlIYQQpiFJSQghhGlIUhJCCGEakpSEEEKYhiQlIYQQpiFJSQghhGlIUhJCCGEakpSEEEKYhiQlIYQQpiFJSQghhGlIUhJCCGEakpSEEEKYhiQlIYQQpiFJSQghhGlIUhJCCGEakpSEEEKYhiQlIYQQpiFJSQghhGlIUhJCCGEakpSEEEKYhiQlIYQQpuFIdABCJCkFZAF5Az5yB3ydCQSBQN9HcMBnN9AD9IZ87gTqAX8c/x9CxJUkJSFGJwOYARwEzOz7PBnIZ3DiySU2IxFB9MRUPcxHRwyeW4iYU5qmJToGIcwmlwMJp/9z/9eTEhjXaHShJ6cqYC2wBlgNbEfvkQlhSpKURKrLAY4Aju77OBwoTWhEsdULrENPUGv6PtajDw8KkXCSlEQqUei9naOBZX2fD0Em/ASBrRxIUu/3fXgTGZRITZKURDLLBJZyIAkdBZTE68n9gSD+QBCfP4g/oOELBPH7g/gCQQKBICiFApQCNeBrm01ht9mw2xR2m8JmUzjsijSHnfQ0e7zC7wLeAP4HvAzsAORiIWJOkpJINjOATwOfAU4AnNF8cE3T6PUE6Hb7+j78dLt9eH3BQUnHHwgSi5eWTSlcTjsup52MdEff1w4y0vXP/f+221S0n7oKPUH9D3gNaIv2EwgBkpSE9dmBT6Anoc8Ac8f7gEFNo6cv2XS7/XT3HkhAPW4/QQu8ZpwOGxnpDnIyneRlHfhwRqenFQQ+4ECSWolMUxdRIklJWFEacCLweeCzjHNIrtvto6XDQ2unm5ZODx093pj0cswgw2knLzt9UKLKdKWN92HbgaeAR4HXkQQlxkGSkrAKJ3AqcC5wNlAwlgcJBIK0dXlp6UtArZ0ePL7UniGdZreR25egCnNdlOS7cDrG3KNqAN5Dvx/1F2T6uRglSUrC7GYAXwUuYwxTtd1eP03tblo7PbR0umnvTt5eUDQVZKdTkp9BaUEGBTnp2NSY7lEF0If5fgs8j0yUECMgSUmYURpwJvB19N7RqLR2eqhr7aG+pYf2bpnVPF4Ou6I4L4PSviSVNbbhvo+BvwJPINUmxBAkKQkzmYreK7ocKB/pNwUCQRraeqlr6aG+tTflh+NiLdPl0BNUfgYl+Rk47KNa5tUD/BO4DdgYkwCFpUlSEonmQJ/C/XXgdPQFrsPyB4LUt/ZQ09RDfWsPgaD8HSeCzaYoK8hgUnE2ZYUZ2G2jSlAvA7eiz+CTX6AAJCmJxCkHvgFcAUwcyTcEgxq1Ld3sa+ymoa2XoCQiUzloQi7zpxeN5Vs3ovecHkEvgyRSmCQlEW/lwI+BbwKukXxDd6+PqvpO9jR04vUFYxqcGLuTlkwkJyNkrbLfB44R34NqQr/vdCdQF9XghGVIUhLxMqpkFAxq1LX0UFXXQWO7O+bBifFxOGx86ogpqNBZek/eAi21sOhkWHgcuLJG8nBe9PtOv0OvySdSiCQlEWujSkbdbh+76zvZU98lExYsZMG0QmZOzBvc6OmBmy8FX98MSKcLFp0ER30GCitG8rAB4AHgl8DeaMYrzEuSkoiVESejoKZR39JDVV0nDW1yS8GKTls6BZczZMHt6tfgmb+En6xscPDhcPSZMG3BSB7egz6k91ugcdzBClOTpCSibcTJyB8Isqu2g8raDtxe6RVZVXaGg5MWTwofuvvHz2HX+qG/uWIGHHUmLDgG7MNuhN0F3AL8EVnrlLQkKYloKQB+BlzJCJPRjup2vH6ZuGB1S2eXMqE45F5RexPc9jVGXD4jpxCOOAMOOw0yc4Y7uxm913QnMlsv6UhSEuOlgC8DNzFMYVRJRsnp00dNDV9Au+Lf8NrDo3+wtHQ44lNwzOcgY9jkVA38ArgfvXK5SAKSlMR4HIL+bvWYoU6SZJS8SgsyOHqeQfGNO74NjfvG/sCuTFj2OX1ShHPY+THvow8Xrxn7EwqzkKQkxiIHuB74Lvp+RoYkGSW/Yw6poCg3JGnU7IS7fhidJ8jKg+M+D4efBvYh1zsFgT+h95w6o/PkIhEkKYnRUMAX0EvDTIh0kiSj1HHmsmnhFcRfuhfefy66T5RfAiecDwuPB9uQ22pUo79Z+g9SusiSJCmJkZqNvj/OJ4c6qbqpiw27WmQ2XQqYUZHLITNCygoFA3DL5dDdHpsnLZkEJ14A844e7swXgauAytgEImJFkpIYTiZwLfo074jjJ129PtbtbJLqCynk5CUTyQ4tK7TtI/jnb2L/5FPnwae/DqVThjrLDfwauBl9rZOwAElKYignAvcB0yKdEAgE2bavjR3V7Uh91NQxZFmhDW/HJwi7A44+C44/T5+1F9kW4GLgo/gEJsZjVHXmRcpIR5/i/RpDJKTalm5eX13Ntn2SkFLNnMn54QnJ0wNbVsYviIAf3v6PPtNv64dDnTkHfYv2qxliYo4wB+kpiVDz0YthLox0Qrfbx/rKZupbZd1iqhpVWaF4mXMEnPFVyCse6qy30HtNUkvPpKSnJPrZgO+gb1ttmJACQY2te1t5Y3W1JKQUlpPhID3N4NKx9s24xzLIlpV6r+mdp/UJF8aOB9ahzyIVJiQ9JQF6JYYH0Xd+NdTU3suaHU10u/3xi0qYknFZoUa47esjLysUa2VT4exvw4SZQ531APobMVnXZCLSUxLHo6+EN0xIwaDGxqoW3tlQJwlJAHoVhzDr3jJPQgKo3w33Xq3fc9IirpW7BFgNHBm3uMSwJCmlLjtwHfA6ERbCdvR4Wb6uhh3VMVpzIiynrCAjvM4dwNq34h/McAJ+ePUhePB66GiKdNZM4B30ZQ9yPTQB+SWkpnLgZeBXRPgb2FnTzltra2jv9sY1MGFuB0/KD2+s2QFN46hzF2u71sNffwCb3o10hh34DfA4kB23uIQhSUqpZwn6ZIaTjQ56fAHe21THhl0tBGWetwiRn2OwHsiMvaRQvZ3w+E367EBvxEk656L3mqbFLS4RRpJSajkLWEGE4bqmdjdvrqmmQWbWCQMzJ+SG17kLBmDDisQENBarX4O//R9Ub490xkLgQ+C4+AUlBpKklBoU8D3gafSyQYNomsbWvW28u6FWataJiKaV54Y37lgduzp3sdJSC/deo0+CMFaMvnD86/ELSvSTpJT8HOiFVG9FT06DeLwB3ttYx5Y9rVJSWUSU5rCR5TLYrjzRa5PGKhjQJ0E8cTP4DMviOYC/AXcwRM1HEX2SlJJbLvBf9C3Kw7R3e3lrbbUUURXDMiwr5O4erryP+W18B+67Vl9nZexK4H/ovScRB5KUktdk4G3gDKOD9a09vL2+hl4ZrhMjMLHYYFLapvfAnwSzM2sr4a4fwZ7Nkc44AViJvn2LiDFJSsnpcPQX0SFGB3fVdvDBpnr8ARmwE8PLyXDgNCortO7NuMcSM93t8I+fw6pXIp0xHX2S0KL4BZWaJCkln88Cy9HXIg2iaRrrK5tZV9ks94/EiM2ZUhg+dNfWALs3JSagWAn44b93wgt3R6qdVwK8CXwirnGlGElKyeXb6NtAh9WB8QeCrNzSQGVtR/yjEpZmWFZo/XJzlRWKppUvwMO/0tc2hctDv8d0anyDSh2SlJLH94DbMZhh1+vx8/b6WupaeuIflbC0ciuVFYqmynVw90/0HmG4TOA59MW2caGUOkEppQ3xkTSFKQ3meAoL+jb6lO8w7V0e3t9cL+uPxJjMMiorVL3d3GWFoqWlVp+Zd/H1UDIp9Ggaelmiy9GrjcfLo8ALBu0Rq85ajSQl6/sWeg8pTF1LDx9va5AJDWLMDMsKrUvyXtJAHc1w/0/h4p9DRdg2GDbgfvQhvT/FKaJVmqY9PNpvUkrlaJpmOB6plMoAfJqmjbu3NdTzjJQM31nblegLY8Psbehk5WaZYSfGLnJZobcTE1Ci9HTAAz8famLHbcDPMRg6jzel1LS+4bzrlVJfVEp9rJTqBf7cd/yBvuMlSqn7lFL1QDcwqe+4Qyn1E6XUJqWUWynVrJR6Sil1yCifZ3Lf4+9WSnmUUg1KqXeVUl8Z7v8gPSXr+gb6avMwexu6WLU9Yql+IUYkacoKRYOnBx7+JZz3E5i1xOiMXwI+4LcxjiRTKWW0kNeradrAWUyfRd/A8K/olSlCZzi9AtQBNwBZQFdf+yPAeX3H/4o+i/dbwHtKqWM1TVsd8jhhz6OUcvR9/0TgTmAbem9yIXAs8I+h/oOSlKzpa+h/BGH2NnaxanvE1elCjEjkskJvxD8Ys/B54bHfwjnfg/mGs8JvBFrRL86x8su+j1DPA58Z8O/5wEJN0yKtCN6gadpFAxuUUqegJ6THgfO1vm3JlVL/Alah3yY4NuRxwp5HKbUQfaHxTzRN+8NI/2P9JClZzxXA340O7GvsYvU2SUhm4rArXE4H6Wl20tPs2G0KpUAp/XP/8FhQ09A0fS1ZUNN3/PX4Ari9ftzeAIE4byMSuazQR3GNw3QCfnjyj3rPackpRmfcCbQBj8UogruAJwzaQ1/4zw+RkABuNmj7XN/n3/QnJABN09YppZ4DzlZKlWiaNvC5jJ6nvyt9olLqAU3TDKcwRiJJyVouA+42OrCvsYtV2xplUWwcOeyK3CwnmekOXE4HLqeeePq/djntxtOpx8AfCOL2HkhS/V97fAF63H7au71RTVzGZYXeTY6yQuOlBfVFtj4vHPnp0KMKeAh9uMxoltx4bdc07dURnLdtDMeno8/iM0pmG4Cz+84ZmJTCHkfTtN1Kqd8A1wC1Sqk16FXXn9A0bdhiiZKUrOMS4B6jA9VNkpBizWFX5GWlk5/tJD9b/5zlSgvvTcTs+W1kZ9jIzjAuWK1pGl29Ptq6vLR1eWjr9tDeNbZElZOZZlxWKNnXJo3WS/eCKxMOPTH0iAP4N/oC20RtNjXkokRN04yOj+WP2fB5NE37mVLqPuDT6EN+VwA/Ukr9QdO0nwz1gJKUrOFU9IQU9kdT3dTFx1slIUWTzaYoyE5cAhoLpRQ5mU5yMp1MLtV7OUaJqq3TS3CYSgxzphQYlxXak2RlhcZL0+CZOyA9C+YcEXrUhb7A9gQgdHKAWe0ETgPmAutCjs3r+7xrpA+maVol+my8PyulXMDLwI+VUrcMNaQnScn85qGPIdtDD9Q0dfOx9JCiIj3NTnlhJuWFmRTnuaI27JZIRonKHwjS2NZLXUsPdS09eP3hay5L8w3KCq1L4rJC4xEMwJM3w4XXwfSw+se56BfiYxh+OM0MnkZfZnKNUuqCARMdFqDvWv12yP0kQ0qpPKBH0zRff5umaW6l1Gb0HX0LAElKFlWC/m4rbG5uTXM3H21rkOvEOORmpu1PRPnZ6abuCUWLw26joiiLiqIsNE2jpdOzP0F19foilxVKporg0eb3waM3wld+BRNnhR4tAV5FL+K6NwrPtkQpdVGEY0+P54E1TXtFKfU4cD5Q0De5oX9KuBt96vdInAjcpZT6N7AVfbr5YehDeB9omrZ1qG+WpGRe6ejFVaeHHmhs6+WjrZKQRkspKM51UV6YSVlhJlmu1N5QVClFUa6LolwX86cV0tXrw24zSMzV26GpOv4BWonXDY/cAJfeaFSSaDLwLHqPqSvse0fnS30fRmYB463KcCH69O9LgFvQF9a+BVynadr6ET7GWvRr1wl9j2cH9qBPmb9luG9WmlzZzEih19P6cuiBrl4vy9fW4gskTamrmMtMdzCtPIcpZTmkp4WNgorhvHC3XjlbDC+3CC67EfJLjY4+BXyeJKpTFwuSlMzpagxWhnt9AZavq6HbnTQFgWOqrCCDaeW5lBVkpMTQXExoGmxfBe8/C5VrEx2NNRRW6Ikp26CYLfwauC7OEVmKJCXzOQd9OukgwaDGuxvraO5wJyAk63A6bEwpy2FaeU7KD89FXVM1fPQyrHkN3LINypAqZuiJKc2goC1cgF7tWxiQpGQuh6Gvawib/rR6eyN7GsY7HJ28CrLTmV6Rw4TiLOw268+cMzWvWy/K+uGLUFuZ6GjMa/4y+MKPjI640Sc+rIpvQNYgSck8JgIrgQmhB7ZXt7GpqjX+EVlAcZ6LuVMKKMx1JTqU1FS1EV57CPYOOaEqdZ3wRTjhfKMju4HDAamcHEKSkjlkAm8Di0MP1DZ3s3LLqEpHpYS8LCfzphZQWpCZ6FAEwNaV8Noj0LAn0ZGYi1Lw+f+LVMD1VeAMxj9jLqlIUjKHu9Hn8A/S3uVhxfrauBfjNLMsl4M5UwqYWJwlkxfMJhjQF9m+8Si0S2Hg/dKccPnvoDxsdQfAH4Ahy+6kGklKifdFDCoKu71+3lpbI9uY90lPszN7cj5Ty3KwGa2lEebh98KHL8GKJ6FnXJuQJo+CMvjaTZCRY3T0c4xz4WsykaSUWDPQ62INqtgQCAR5e0MtbV1SkdlhV8yamM+MCblJUfonpXh64N1n4L3/6pMjUt3MRXDRdaDC/o6bgUOA2vgHZT6SlBInDf0+UlglxzU7mthdL+8wp5RmM39aIU5Z8GptXW16Re1U20bdyDHnwCcvNjryMvApZGGtJKUE+j3w49DG6qYuPtqa2uPxLqedQ2cWU14okxiSyqZ34fm7UnM79YG+dA3MDnsvCnptuT/HORrTkaSUGCejz7wZpNvt4801NfhTuITQlNJs5k8vxOmQ3lFS6m7XyxZtfCfRkSROZi5ceRtkF4Qe8aCvVdwY/6DMQ5JS/OUD64FBVRuDQY2319fS2uVJTFQJJr2jFBOFXtNvV2xjVV0bH9e0sauth6l5GVR977Sw86raupn+p1eGfKyHP3cYFy6cPOQ5/91ay1Nbanlvbwt7O3rJS09jXkkOP1x2EKcfVDboXH8wyM/f2MKDa/fQ4wtw6sxS/nzGQkqy+io8zFoCF17HRx99xLJly1i+fDlHHXUU6MVMj0RPUClJklL8PQSElZ7fWNXCjurUHNaYXJrNAukdpZ5x9prUL5+mMCONJRX5fFzTRm66wzApdXv9PLXFeA7BVS+spdcfpPoHp1GcaVgSaL/ym18kN93B2bMrmF2cTUuvj/vX7GZLUxe/PnEuPz1u9v5zb3pnO9e+vokfLZtFaZaT3729naUT83n2S0fvP8d/6mUcfuV1HHfccdx+++0Dn+pmwLAURCqQpBRfn0ffsG+QxvZe3t1Ql4BwEkt6RwIYc6+psrWbGQVZACy48zW6vH7DpBTJe3tbWHbfcj4/bwJPfMHwHs8gr+9q5KTpJYPaenx+Fv/9TXa1dlP/wzMoyHACcPS9bzG7KJsHPnsYAPev3s0Vz66m+9ozcfW9+frduzu5c1MzGzdvISdn0FRxDfgk8PqI/zNJRObYxk8F8PfQRp8/yOrtqVdppKwggxMXT5SEJGDeMrjyT0Y7tw6pPyGN1T2rqgC4YvHUEZ0fmpAAMtMcfGZWGb6gxtbmA7Upe30BCvsSFEBhhpOgBm6/vu5wR0sXv3pjE3ecvZSczLASWQr4B/oOrSlHklJ8KPSEVBh6YH1lM72e1KoyMmtiHkfOLZPhOnFAVh5c9HM48tNxebour5/HN9UwJS+DU2Ya7n00Yvs69TVYpVkHhv+OnlTIoxv28c6eZrY2dXLTu9uZW5xDvktPVF9/bg1nzi7nzBIFrxsWDJ8E3DquwCxKklJ8nNn3MUhNUzd7G1On8rfNpjjs4BLmTSuUEkEinN0BZ1wBZ16pfx1D/9qwjy6vn8sWTcU2jr/FtXXt/GdzDcdOKRrUc/vliXOZnJvBMfevYM4dr1HZ2sM9Zy0C9KG8VbXt/On0vp7hu89A1Qajh/8KcNyYg7Mo2Q499jKAP4U2ur1+1u5MnWE7l9POkXPLyM8e+mayEBx2ir6l+L9+H7M1Tfes3o1NwaWLp4z5MRq7PZzz+AdkOOzcc9bgWsqlWem8f8XxbG3qoscXYH5pDi6HnYZuDz98ZQM3nzKf8mwX/95UzW9WbKPh1pc44Ywzuf2OOyksHDSgcid6oWbfmAO1GOkpxd6PgWmhjesqm/H6U2M9UkFOOscfOkESkhi5KXP1WnHGRUzHZVNjB+/va+WUGaVMyRvbPc2WXi+nPPQONZ1unj7/SA4uyg47x6YUc0tyOGxC/v7JDd99aR0Ly/K4bPFUPtjXwhee+JDLFk/lP19YyraP3+eii8Im5s5HX1SbMiQpxdZ09K3NB2lo66W2OTV27pxSms0nFpTjckqnXIxSXom+e+v8ZVF92HtX7QbgiiUjm+AQqqXXyycffIctTV089cUjDSdAGHlhex1Pb6nlrs8sQinFvat3s2xyIVcdMYMjJhZw41GTefHFF6mtDZu+/ktC1jUmM0lKsXUbMGhqTTCosb6yOUHhxNeC6YUsnlUiO8GKsXO69N1bT7ogKg/nCwR5aN1eSjKdnD27YtTf39rXQ9rY2MlTXzwybNFsJF1eP998fi3XHTebWX29qn0dbibnHdhkenKuPpKwd8/u0G/PIoUmPcjVInY+BZwV2rizpp2u3uQeHrYpOGJuKTMn5CU6FJEsjvsCfP4HMM43OM9sraWxx8vFCyeTFqHqfI/Pz5amTmo7B1c2b+318smH3mFDQyf/Pu8Izpg1soQE8LPXN5GXnsaPls3a3zYhx8WGhgOFl9c3dOjtDduMHuLzwMgXYVmYjKnERjoGkxt6PX627WtLQDjxY7MpjpxTRmlBxvAnCzEaC44Fexo8eQsE/Dy0dg+723sBaOzx4g0E+fVyfVv2qXkZXHxo+CSGe1f3D91Ni/g0K6tbOfEf7/CVQyfvX/wKcMpD77Kqtp0vLZhEm9vHw+v2Dvq+ZZMLDddOraxu5c4Pd7Hi0mMHJcKLFk7i3tW7+fJTH7N0Qj6/e2c7J0wrZtLGl+HEsyA7P/Sh/oK+xUVS7wMiSSk2fggcFNq4saoFfyB5K2jYbYqj5pVRnCcJScTI3KPg/KvhX7/n3tW7eWv34KHw697YDMDxU4vCktK+jl7+t7OBZZMLmVtiuNnekD6u1d9QPrphH49u2Bd2/P6zF4clJX8wyFefXc03D5/OkZMGL1M8YVoJ9561mN++vY1nttZywrRi/vbpReDugf89AOd8L/QpDkKfOPWrUQdvIVJmKPqmAFvQp4Lvl+ylhBx2xdHzyinMDVudLkT0Va6FR28EXxJvhHnJDTBtQWirB5gNhN14ShZyTyn6/khIQgpqyT25QRKSiLsZh8IFPwOHc/hzrer5uyAQVu0lHfh5AqKJG0lK0XUycG5oY2VNB509yTm5wW5THDlXEpJIgOmHwPk/iXn1h4Rp3KtvJR/uK+i9paQkSSl6FPDr0Ea318/Wva0JCCf2bEpx5NwyivMkIYkEOWiJPmXclqR1FFc8CT2doa129LVLSUmSUvScDBwV2rixqjUpJzcoBUfMKaUkXyY1iASbcwSc+wNQSXg58/TCO/8xOvJF4NA4RxMXSfhbTAgF/CK0sb3Lw74kLbi6aGYxZbLthDCL+cvg9EsTHUVsrHwBOluMjtwQ71DiQZJSdBwPHBPauHVvcq5Jmjkhlyllo59SK0RMHfkZWPLJREcRfT6vPowX7kwMRmesTpJSdITNhuno9lLbknz17UryM5g3LWxbKCHM4VNfg8lzEh1F9H38CrQ1GB0Ju49tdZKUxu8Y4MTQxq1JWLkhy+Xg8Nkl49p/RoiYcqTBF38CuUWJjiS6An5463GjIydjcP2xMklK43ddaENnj5eapu5ExBIzDruS3WKFNWTnw5eugbQkW8O09g1oqjY68hv0+9pJQZLS+BwJnBramIz17Q4/uJSczCR7kYvkVTETzv52oqOIrmAQ3nzM6MjRJFFvSZLS+IT1krp6fVQ3Jlcvad60AplpJ6xnwTFw3OcTHUV0bXwH6nYZHfluvEOJFUlKY3cY8OnQxm372kimVUmTSrKZNTGsWrEQ1nDil2D2EYmOIno0DZZHnIkXVgTaiiQpjV1YL6nb7UuqdUm5mU4WzUyyG8YitSibXm27cPQb+pnWlveNZuIpICnGKyUpjc084OzQxu372kmWoutKwZJZxdgjbIQmhGWkZ8Bnv63/USeDYBBWvmh05FIgN87RRJ1cccbma6ENPR4/exrCalRZ1sGT8snLTk90GEJEx5S5+uLaZLHqFfCG7fWXA1yWgGiiSpLS6LmAi0Mbd1YnTy8pN8vJwZPkPpJIMidfmDzDeO5uWPOG0ZHvoBdstSxJSqP3OWBQSYNAIMjehuS4l6QULDmoGJstSYY6hOiXlp5cw3gfPGfUOh190oNlSVIava+GNtQ0d+MLBBMRS9TJsJ1Iask0jNdcA9s+MjoSto+6lUhSGp2DMFikVlWfHPeSZNhOpIRkGsZ737C3dDywKM6RRI0kpdG5IrShs8dLS4cnEbFElQzbiZSRTMN4lWuhYY/RkbBrlVVIUhq5NOCS0MbdSdJLkmE7kVKSaRjvg+eNWs9Hv2ZZjiSlkfsMUDawIRjUkmKCQ05GmgzbidRz8oWQX5LoKMZvwwrwhY3WFAGnJSCacZOkNHJhExxqW7rx+q0/wWHu1AIZthOpJy1dL0NkdZ5e2LrS6MhF8Q4lGiQpjcwU4PTQxt311u8lFeSkU1GUleNKj0wAACAASURBVOgwhEiMQ46D0imJjmL81i03aj0bC1Z4kKQ0MpcRsl9Jt9tHY1tvgsKJnnlTZRdZkcJsdjjZkh2KwXashp6O0FYXcE4CohkXSUrDs6HXlBpkTxL0ksoKMijOcyU6DCESa/ZSfeKDlQUDsOFtoyOWy7iSlIa3FH34bj9N05Kizt3cqQWJDkEIc/hkWOUw6zEewjsJmBjnSMZFktLwPhfa0NjWi9sbSEQsUTOpJIu8LJkCLgSg95RmL010FOOzbyu01IW2KsBSszkkKQ1NYZCUapp7EhBK9CgFc6ZIL0mIQU660PoLate9ZdRqqSE8SUpDmwscPLBB0zTqWqydlKaV55LlsuS6OiFip2wqLDwh0VGMz3rDIbxDgVlxjmTMJCkNLayX1NLpweOz7tCd3aZkoawQkZx4PtgdiY5i7JproHq70ZEz4h3KWElSGlpYUqpt7k5EHFEztSwHl9PS260IETv5pfraJSvb+qFRqySlJDABOCy0sdbi95OmleckOgQhzG1p2Dp5a9mxyqj1BCAjvoGMjSSlyML+Mju6vfR4/ImIJSqK81zkZDoTHYYQ5jZxFkw4KNFRjF1tJXS3h7a60BOT6UlSiuxToQ31rdbuJU0vt1zFESESw8q9JU3TKzyEs8R/SpKSsTTglNDG+lbrlhVyOe2UF2YmOgwhrGHBMZCRnegoxs54CM8S95UkKRlbRkghQ58/SEunO0HhjN/UshypBC7ESKWlw6KTEh3F2O1cA1rYDgazgJkJiGZUJCkZCxu6a2jrRdMSEcr4KSUTHIQYtcMtuR2RrqfTslPDJSkZC3uL1GDh+0kVhVm4nBZeeyFEIhRNgJmLEh3F2G235hCeJKVwGUDYX2KDhbepmF4hvSQhxmSp6a/hkRlPdjgRMPUUXElK4RYDg7oVvR6/ZQuw5mSkUZxnieUJQpjPwYdBXnGioxibmh1GeyxloJcdMi1JSuGODG1o7fQkIo6omFRi4RlEQiSaza7PxLMiTYO9W4yOHBHvUEZDklK48KTUZd2kVCbTwIUYn9mmvoYPbZ/hZIewa5yZSFIKlzQ9pYx0B3lZph4+FsL8Jh0MmRa9L2s8A8/UWVaS0mBlwLSBDZqm0WbRnlKF9JKEGD+bHWYdnugoxqbGMCnNBky7oZokpcHCekkdPV4CQWsuUJIKDkJEiVV3pXX3QNM+oyOm/Q9JUhosaYbuHHZFUa4r0WEIkRxmLrLuPkvG95VMO4QnSWmwpElKpQWZUlZIiGhJz4DpCxMdxdgY31cy7WQHSUoH2DDo0lo1KcnQnRBRZtUhvOptRq1HAKZ81ypJ6YA5GBRh7ez1JSicsVNAWb4smBUiqmZbdLJD/W7we0NbS4GpCYhmWJKUDgjrzlp11l1Rngtnmmx5LkRU5RZDxYxERzF6AT/U7jI6siTeoYyEJKUD5oU2WHXRbKn0koSIjYMWJzqCsakzTEqz4x3GSEhSOmB6aENXj/WG7gDys9MTHYIQycmq26Q3VRu1SlIyubB+ebfHmkkpL1uqOAgRExNMv0deOJsdPIZb73w23qGMhEUn3kedwmBHxh63PwGhjE+my4HTIfeThIiJvBLIzDWqvp1YNjsUlEFhORRO0D8XVehf55fox8PloV/7TFUdQJKSroCQmXeBYNCS21XkZ8nQnRAxNWFmpL2KYstmh/zSA8lmf+Kp0NuNE89w5gMbohzpuEhS0oXdT7JiLwkgX4buhIitihgmpUGJp+9j/IlnKMciScmUwu4nWTcpSU9JiJga732l/sQzMOH0fx2bxDOUw+L5ZCMhSUlnMMnBmklJJjkIEWMjSUphiafvXk9iEg+apqFpGJUeM6zWmkiSlHQGPSXrzbyTSQ5CxEH/ZAd3tz6JoD/ZDJxkUFCWkMTjD2h4fAF63D46eny0dXloau/F4wsyoyKXQ2YUhX7bpLgGOQKSlHRh95S6LTh8J5MchIiTb/wRsvLiXjk8UuJp7ujF7Q0O+b09xqM/Yde+RJOkpEuKnpJMchAiTnLDehxRE5Z4en20dY4s8Qyl2/iaJknJhBwYFCaM8K7C1LIz0hIdghBiBAYnHj8dvd6oJJ6h9Bpf0ybG5MnGQZKSPqY66Ofg8QXwB0y1nmxE0p1yP0kIswhNPJ29XlpjnHiG4g9oBINa6GQHJ+AC3HEPKAJJShDWD3dbsJcE4EqTX6cQ8TQo8Xj8dPYkNvEMxxcIkh4+ASMPSUqmkhPa4LNgLwmkpyREvPgDQV5btdeUiWcoPn+Q9PBtbfKB+gSEY0gKshokJX/AWn9oAE6HDbtsfy5EXDjsNrw+610nIlzb8uIdx1AkKUF2aIMVk5JLeklCxFW603oDTT6/4bUtP95xDEWSkkFPKRC03vCdFV8gQliZFd8IRkhK0lMymaQYvrPiC0QIK3OF35sxPZ/xtU16SiYjSUkIMWpWfM1JT8kaDJKS9YbvrPiuTQgrc1lwyDzCG27pKZlMkkx0sN4LRAgrs+ISDOkpWUNSDN/Z7TIdXIh4cljwNSez76whKYbvbMp6LxAhrMyKr7kIEx2kp2QySdFTsuDrQwhLUxZ80UVY7uKKdxxDkaSUJPeUrPgCEcLKrPiSi1D0xVT79EhSMvgZaNYbvbPkUIIQVmbF11yEmL3xjmMokpQM3iVY8Y/NgiELIeIswoiK9JRMJmyfCite4INW7N4JYWFWfMnZjK/4kpRMJrynZMFq21Z8gQhhZZoFX3QRRoEkKZlM2C/EeinJmi8QIawsiPVeczJ8Zw0Gw3fWS0sWLGwuhKVp1pukG2n2nUx0MJmwX4glh+8kKwkRV1a8j6uMr23SUzKZ7tAGK5YP8RqXDxFCxEiEkj2mJveUrKErtMEeYYqKmbl9YaOQQogYcnsDiQ5h1GTxrDUkRU/JY8EXiBBWZsU3gjLRwRrCe0p26/1YrPiuTQgrs+JrTio6WENYUnJYcKKDFV8gQliZFUcn0tIML/lh18BEkqRkOHxnvR+L22u9oQQhrMyKr7kIW7jXxDuOoVjv6ht9jaENrnTr7SgpPSUh4ieoaXh81pt9l2G8Q7UkJZPZG9oQ4RdnaoGgZsktN4SwIisO3UHEnlJ1vOMYiiQlo6SUbr2kBNYcThDCiqw4MqGA9DTDpFQb51CGJElJ/4UM6mKkp9mxy2QHIUQEVpwOnu60G00JbwY8CQgnIklKeu27sDHVCN1cU+uVpCREXLg91nutWWGSA0hS6pcUQ3id3aZabiBE0urosd5rzWWBSQ4gSalfUiSlti5T9cKFSFrtXVZMSuaf5ACSlPolxQy8NukpCRFzwaBGuwVfa9JTshaDnpL17in5/EG63aYqYyVE0uns9Vpy2wq5p2QtSTF8B9BmwWEFIazEqq8xSUrWkhTDdwDtcl9JiJiy6r3bCG+0JSmZVBL1lKz5ghHCKqw4yUEpyHalGR2qinMow5KkpGsgpHx7msOG07iirqnJZAchYseqkxyyXWnYwgsC1GNQ+zPRrHfVjY0gsCW0MT8rPQGhjI9MdhAidqw6ySEn02nUvDHecYyEJKUDVoU25GUb/iJNz6o3YoUwO6u+tnKzDIfuNsQ7jpGQpHTAx6ENVuwpAbR2uhMdghBJqbXTmvdsI/SUJCmZXNL0lOpbexMdghBJR9M06lt7Eh3GmOTK8J0lrQUGDRZnudJIc1jvR9TV66Or15rDDEKYVVuX15KV+B12RZbLcDaxJCWT68ZgskNeljV7S7Ut1nxHJ4RZ1Vn0NZWXlW60ZcVOoD0B4QxLktJg4feVsq15X8mqLyAhzMqqr6l849sQYdc6s5CkNFj4fSWL9pRaOjx4fNYbahDCjHrcPktuVwGQZ/zGWpKSRYQlJav2lAAaLHpTVgizsWovCSDf+I21JCWLWBPakJ2RhsNuva3RQe4rCREtdRad0eqwK7IzDNcohb0BNwtJSoO1A9tDG/Msul6psa2XQNB6q8+FMBOfP0hTuzWTUmGOK9Ikh9YEhDMikpTCGQzhWfO+kj+g0WzRF5MQZtHQ1oMFKwsBUJKfYdT8TrzjGA1JSuHCxloj/GItQYbwhBgfK99PKjW+dr0S7zhGQ5JSuNdCG4pzXUYVdi1hX2M3/kAw0WEIYUleX4CaZmsmJZfTTq7xJIdX4x3LaEhSCrcGfSuL/ex2G8W5rgSFMz7+QJDqpu5EhyGEJe1p6CJo0fuyJXmGvaR1QF2cQxkVSUrhgsDLoY2lBdYdwttV25HoEISwHE3TqKqz7msnwm0HUw/dgSSlSF4KbSizcFJq7/bSIpXDhRiVxjY33W5/osMYs5J8w9Gd/8U7jtGSpGTsf4QUZ83OcJJp0S3SAapqOxMdghCWssvCvaTczDRczrDrlQdYkYBwRkWSkrEm4MPQRisP4VU3dUnZISFGqMfjt/SsuwhDd28Dpl8jIkkpsrAhPCsnpaAGe+qltyTESOyus/ZrJcJUcNMP3YEkpaG8GNpQkpeBRWeGA1BV14lm1VWAQsRJMKixu966Q3c2pSgyni1s+kkOIElpKB8SUorDYbdRaNGp4aAPSTRYtIaXEPFS09yNx2fdtX2FuenY7WGX9kb0jUxNT5JSZAEMurtWHsIDqLTwzVsh4sHqSyjKCzONml9FX+5iepKUhhY2hFeWb/gLt4yG1l6ZHi5EBA1tvbR0ehIdxpgpYGJxttEhS9xPAklKwwn7ReZmOckxLgVvGZuqTFsgWIiE0TSNTVUtiQ5jXEryM3A57aHNXuDpBIQzJpKUhlaLwdTwSSWG70Qso7nDTb1sACjEIDXN3bR3W3N32X6TSg2vTc8CbXEOZcwkKQ3vkdCGSSVZiYgjqjbtbpWZeEL0CQY1Nu+29giCw66oML6f9HC8YxkPSUrD+xchNwgzXWkU5lhz479+Hd1eKdQqRJ/dDZ2WLikEUFGYhSN81l0L8EICwhkzSUrDq8Ngfn+EbrKlbN7TatkKyEJEiz8QZOsey4xuRRThtsLj6PeULEOS0siEDeFNLMqy9EJagB63n91S5UGkuMqaDsuX4HI57ZEKsFpq6A4kKY3U04TUjHKm2SOtB7CUrXvbZBNAkbK8vgDbq63fS5pYnIVSYe+Sq4B34x/N+EhSGplO4KnQxillOQkIJbo8vgA7a6y9WFCIsdpe3Y4/YP0h7AhDdw8TstuBFUhSGrn7QhtK8zPIsPB2Fv12VLfR67H2TV4hRqur10tlErwhy8lMIz/bcOKV5YbuQJLSaLwB7BrYoJRiShJMePAHNNbsaEp0GELEjaZprN7eRDAJlkVE6CV9CGyNcyhRIUlp5IIY9JamlFp/CA/08ioy6UGkip01HZYuJ9TPFvmNsSV7SSBJabQeIGzNkiPS3iWWs2FXswzjiaTX1etl8x5rL5TtN6kky2iH2QD6+kpLkqQ0Ovsw2Pxv5sS8BIQSfTKMJ5Ld/mG7JFmfd5DxtedJoD7OoUSNJKXRuzu0oTQ/g/xsZyJiiToZxhPJLFmG7QDKCjLIyTS87twc71iiSZLS6D0LbAttPGhifgJCiQ0ZxhPJKJmG7SBiL+lN4KP4RhJdkpRGLwD8IbRxQlEmWS7rTw8HGcYTySfZhu3ys50U5xney74p3rFEmySlsXkYqBnYoJSK9M7FkmQYTySTZBq2g4i9pE0Y3PO2GklKY+MB/hjaOLk0x2iDLcvasKuZzh5L1XIUIkxblyephu0y0x1MKDLcPudmLLLl+VAkKY3dXYRsnGW3KWZU5CYonOjzBzRWbmnA57d2sUqRutzeACs31yfNsB3AzAm5RnXuaoF/JiCcqJOkNHadwF9CG6dX5JIWvqeJZXX1+vhoa6NsCCgsJxjU+HBLPb3e5HlTleawRaq5eTv6CI7lJc/VMzFuJ6R6uMNuY1pFclR56NfQ1svGqpZEhyHEqKytbEqq+0gA08tzjDby6wL+loBwYkKS0vg0YlB6aGZFHjarb7YUYmdNB3saZOKDsIbKmnb21HclOoyostsU041vD9xDyK0EK5OkNH63oE8T3y/daU+KQq2h1u5ooqXTnegwhBhSY1svG3YlX89+RkVupJJCtyUgnJiRpDR+u4DHQhsPnpSPPcl6S0ENVm5ukIW1wrS6e318uLXBepsIDSPNYWPWJMNp4I8Du+McTkxJUoqO34c2ZKQ7kmrdUj+PL8DKLfUEZLdaYTI+f5APNtfj8yff3+bBk/JJc4QtNwkAv0xAODElSSk61qNvmT7IQRPzkmrdUr+2Li+rdzTJjDxhGkFNY9X2Rjp7fYkOJeoy0h1D3Uuy5J5JQ5GkFD0/Bga9Ihx2G/OmFiYonNiqbupmfWVzosMQAk3TWLO9ibqWnkSHEhNzJhveCughCXtJIEkpmrYDfw5tnFyaTYHxVsWWt6uukw27JDGJxFq7s5m9jck1065fXpaTycaTpm5FXzCbdCQpRdcNQFgl0wUzkrO3BPpU8c27k6eEi7CW9ZXNSV2jccH0QqPqDc0kQeHVSJKjrLV5tAHXAX8d2FiY42JicRbVTd3723p7unnuyQdY8eqzNNRWk+Z0MmHydE4963xOOuNclFJ4PR7efPkpPnr3dXbt2Ex7SxMFRaUcPO9Qzrv0O0yedtCIA9tTuY0nHryDLRtW0dbSSH5BMXMWLOGci77J9FlzB8V1/19u5IMV/wPg6ONP45JvXYsrI3PQ473/1svcesMPuP2hlwGw2WD25ILR/ryEGLONVS1U1nYkOoyYqSjKjFQJ/AagPc7hxI2Sm9VR5wBWAYcMbOz1+Hlt1T4CQY1gMMhPrzqfrRtWceLp53Dw/MV4PL2seOVZtm9ey+cu+BpfufJq9u3eyVUXnsLchYez6IhjKSwupb56Ly89/Qhudy+/uOV+Dlly9LAB7dq+mZ9841yyc/I49azzKSotp656D/975lHc7h5+/7d/M+Pg+QD8/Zaf88ZLT3Huxd8A4N8P/Y2TPnUuX/v+9fsfr7urg29fdBpnn385Z59/xf72gyfnM3eKJCYRe+srm5M6IdlsipMXTyTTlRZ6aCuwEEjaSsnSU4o+P/B94NWBjf1TxLfubWPbpjVsXvcRZ553KZd/57r955zxuYu46oJTePm/j/KVK68mN7+QP97/HDNmzRv0BMefejbfv+xMHrjjt9xy73+HDejFpx7G63Fz3d/+PahXtHDJ0fzi+1/m9RcPJKX3l7/M2edfzhe+/C39P+Pz8sqzjw9KSg/+9fcUFJXwmS9cOuh5tu1tIxjUmD8teYcrRWJpmsa6ymaq6pJ3yA7goAm5RgkJ4AckcUICuacUK68BYdmif4p4b7d+U7awuGzQ8bQ0J7n5Bbhc+lBZbl5BWEICmDx9FlOmH8yeXWEb4Brq7e7se77SQe39z9//fAAej5uc3AO76Gbn5ON2H5jVtGnth7z2/JN86ye/xW4Pn+6+o7qddZXNMl1cRJ2m6ZtPJntCcjntzJpkuJP1S8ALcQ4n7iQpxc4PiTBFfNbcQ8nKzuWpf97FO6+/QGNdNdV7Knnob39g59YNnH/Zd4d84GAwSGtzA/kFxSMKZNGRxwFw2w3/x7aNa2hurGPj2pX85ffXUFBUymmfvWD/uXPmL+GlZ/7Jru2bqdy+iZeefoQ5C5YA4PN5ufMP13LmeZfu71kZ2VXbwZodybPLp0i8QDDIx9sa2dOQnLPsBlo0s9io6GoAvZeU9OSeUmzdDPxfaOO7G2p5c/ly7vjdNdTs3bW/PSMzm+/+7GaOOu7UIR/0hX8/yF23Xs95l3ybC674/rBBaJrGY/fdxjOP3Ye798Bki1lzD+Wa3/5tUI+tek8lv/nxFdTsqwJgwqRp/PQP9zBxygwevfdW3nz5GW5/6CXS013DPm9Rroulc0pJT0u+BcQiftxePys3N9DalVwVv41MKc1m8awSo0O3A0O/W00SkpRiKx99/dKgLk2vx8/dj73Mo/f/mfIJU5izYAmdnW28+J+H2bd7J9f+7u8sWnqs4QNuWf8x1333QiZOnsEf7noKZ/rI1kC9+NTDrFzxKkuPOZmiknJ2bd/EM4/dy8Qp0/nlbQ+RlX1gxbjf72Pvrh0ATJ5+EA5HGnt3bef7l53JdX+4h0OXHsML/3mIl556hN6eLpYe80m+cuXVhokqI93BkXPLyMtyjvBHJsQBrZ0eVm6px51EeyJF4nLaOWnxJNIcYb2kOmAekBJrLyQpxd7XgL8PbFi/fj1LjziCS6/6Kad/9sL97R53L9+5+HSCWpC//evNsHs2O7as5xffu5jsnDxuvPNfFJWUjyiAR+66hef/8yB3PPIqBUUH3oWtev8tfvXDS/nCl7/FhV8L69Dtp2ka11x5HhWTpvHdn97E2689x+2/+RHfuvp3FJdVcPtvfsziI47lGz+8wfD77TbFkoNLIm3hLIShvQ1d+jBwilyjjppXRllBptGhs4Bn4xxOwsg9pdi7B3hjYMOtt96Kx+3mnHPOHXRiuiuDw5adSGNdNQ11+wYd27l1A9d//8tkZudww5//OeKE5Pf7ePqxu5m3cOmghASw5KjjycjMZsOaD4Z8jBefepjavVVcetW1ALzy3OMcfcLpHH/q2cw/9Ag+f/E3ef2FJwkGjQthBoIaH25pYMueVpkAIYalaRobq1pYtb0xZRLSlNLsSAnpQVIoIYEkpXgIApeib58OQHV1NaDXtHKmDf4VBAP+vs8Hhisqt23k+u9/mYzMLH59+z8pLZ844ifvaGvF5/USDIYPf2iaRjAYGPRcoZob63j47zdx2Xd+Rm5ewf624tKK/ecUl1bg9XroaB96D5ute9v4cGsDfqkwLiLw+QO8v7meHdVJuzY0TIbTzoLpRUaHaoDvxTmchJOkFB+7ge/0/2PePH2a96P/fIhFMw/cburq7OCDFa+SnZNH+YQpgJ6QfvG9i0l3ZXDD7f+kbMLkiE/icfeyb/dOWpoa9rflFxaTk1fAprUfUl+zd9D577z+PB53LwfNXRjxMf/+x18wZ8FhHH/q2fvbCotK2V15oDjx7p1bcaQ5yc0bfn1SbXMPK9bV0uNOvmrOYny6en0sX1dLQ2tvokOJq0UHlRjdRwJ96D8l7iMNZL/++usTHUOqWAssBmbPnTuXBx98kOeee476mj10tjXz3ttv8NebfkpzQy2XXHUts+cvpqGummuuPI+uznbO+uJluN29VO3cMuijfOIUHGn6IrvN6z7mR1/9LB3trftn8CmlSHdlsHLFK6x45Vl6e7qp2VvFq889zj/vuZXs3Hy+e+1NgyY69Hv3zRf577/u5Wc33Ud2zoHjQS3IM4/eQ1dnO3sqt/H4P/7MJ076FEcdd9qIfhAeX4B9jV3kZjrJzjBcIChSTE1TN+9vTo0JDQNNLcthpvG+a/8gievbDUUqOsSPhv7OZ9nUqVOLV65cya9+9Stee+016h97DGe6i2kHzeXSq67l6ONPB6C+Zi+d7fobpcfu+5Phg/79ieVhdelCffrcL1NQVMLzTz7Ic0/cj8ftJje/kGNO/gxfuvx7lBgMB3Z3dXD3rb/kgiu+T1nFpEHHTjrjXFqbG3jpqUfwuHs58thTueK7Px/VD8PrD/L+5nqmlGazYHqh0QZmIgV4fAHWVTZTM6AuZKrISHewYLrh6EJKDtv1k9l38Xcu8GRoY2NbL+9urEtAOInnctpZNLOYssKhk6tILjVN3aytbMLrS817jMvml1OSb1hw9VPAi3EOxzQkKSXGQ8BFoY3rKpvZlcRFJocjvabUkMq9o34zJ+RGmtxwP3BZnMMxFUlKiZEPbAAGjZv5A0GWr61Jyi2dR0p6Tckt1XtHAMV5LpbNLzfaJ6kaWIC+BU7KkqSUOKcCL4c2dvZ4Wb6uBn8gtX8v0mtKLh5fgPWVzYP2FEtFGU47xy+aGKn01hnoRVdTmiSlxLoDuDK0sba5m5VbGgxOTy0up5350wqZWJxl9K5SWICmaext6GLj7paU7h2BvkfSsYdUkJ9tWBrsT6Tw5IaBJCklVhbwMTA79MCmqha2p9ACwqHkZTmZN7WAUuMV78Kkalu62by7lc6e1B2OHmjxQcVMKcsxOvQWcAohuwqkKklKiTcXWAlkD2zUNI33NtXT2JZaCwmHUpznYt7UAgpyhq9QLhKnud3Npt0ttHQmf1XvkZpWnsOhMw23mtkHHAbI0EgfSUrmcA7w79BGry/AW2tr6PH4ExCSeVUUZTJ3SgE5mVJ53Ezau71s3t1CfYpVZBhOYU46n1hQgc0WNgTtBY5Ff1Mq+khSMo/fAleHNnb0eFkhEx8MTSnLZs7kAjLSZQ14InW7fWzZ08a+xuTfgG+0XE47xx86AZfT8G/0cuC+OIdkepKUzMOOPvPmk6EH6lt7+GBTPfKbCmdTiukVOcyoyCXTJSWL4qmr10dlbQdVdR3IZSScUnDMggoKcw2Hm/8GfDPOIVmCJCVzKQI+AqaFHthZ086GXUNX4U51ZQUZTK/IpTQ/Q2brxYimadS19lBV20mD3O8c0sIZRUyvCK8pCbwHnIA+fCdCSFIynwXof7TZoQfW7Ghid31n+HeIQTJdDqaX5zKlNBunbMUeFW5vgD31nVTVd9Ir9ziHNUTFhjr0iQ018Y3IOkaVlJRSBUAtkA5crGnaw7EKLMV9BvgvMOjtfjCo8f5mmZE3UjalmFiSxfTyXApyRrZtvBisucPNrtoOapq7ZYhuhKaUZrN4VonRIT96D+mduAZkMaNNSlcBtwNVwG5N006MUVwCfohB6Xp/IMj7m+pp7nAnICTrys92Mq08l/LCzEir6UUftzdAbXM3VXUddMgao1GZUJTJ4bNLIw0fXwn8Nc4hWc5ok9JqoAV4BrgNmKVp2s4YxRYVSqkcTdOsOOalgHvRd60dxB8I8u6GOlq7ZB3IWBTmplNemElFYSbZGTKtHKCj20tdSw91rT20yvqiMSnNz+DIuWVGU79BT0bfApmvNJwR7zyrlFoCLELf33X8mAAAEXJJREFUfOoR9NXHYRfMvnNPVEo9r5RqVkq5lVKVSql7lVLFIeedq5R6QynVppTqUUptVUrdrpRy9h2/RCmlKaVOMHiON5VSVSFtVX3ti5VSLyul2oF1fcdylFK/Vkp9oJRqUkp5lFI7lFK/U0qFlQpQuq/2nd/V97FeKfWrvuPn9MV2RYSfwca+xx/rHXcNfXbO8tADDruNo+aXkZslF9SxaOnwsKmqlddWVfPqx3vZsKuZpnY3wRQanwoGNRrbellf2cwrH+3ljTXVbN7TKglpjApz0lk6pzRSQnoM+DaSkEZkxD0lpdQdwFeAMk3TupVS/wGWAlM1TQsOOO/r6O8KqtET2G5gCnAmcImmaWv6zvsNcC2wCXgc/V7VTPT9hg7XNK1NKXUJein3EzVNezMknjeBaZqmTRvQVgUEgQLgCfSZbNmapv1RKTUHeBN9keo29PHd44HPA69omjZo21Sl1MPAhcAH6D3DNmAOcIqmafOUUg5gL1CladrRId97FPpkhZ9qmnbjiH7AkeUBrwKHhx7w+AK8vb6WrhSuKh5NaQ4b5QWZlBdmUpTnSrphPrfXT1O7m7qWHupbe/EHUrsWXbTkZjk5ZkF5pOLBzwOfQ0oIjdiIkpJSyoU+W+S/mqZd0td2NvA08ClN017sa5sE7Oz7WKZpWlvI49g0TQsqpY5Av9i/0ff97gHnKABN07QxJqWpwFc1Tbsn5Hxn38P6QtpvAH4GHKlp2sq+tvOAfwEPA18JSbq2/n8rpW4ErgHma5q2acA5d6P3IqdomhaNWTZF6Al1QegBt9fPivW19LhlRlS0ZTjt5Genk5edTn62k/ysdNKd1khUbq+fti4vbV0e2rv1z6m21Xg8ZLkcHHvIhEh/F8uB0wGZmTQKI10Kfw567+MfA9qeR6/XdBkHdkn8AuAEfhmakAAGXNwv7Pt8zcCE1HfOeLu4LeiJLPS5968J6Ovl5KAvWH2VvqTEgXIf/fH9cGBCCvk/ANyNXoXhcuD/+h47C/gi8GKUEhJAM/qi2uXAwQMPuJwOPjG/nBXra+WiE2W93gC9LT3UtvTsb3P1Jar8vkSVl+WMtFo/LjRNw+MLSAJKgAynnWULKiIlpI/RR4ckIY3SSF9NlwONwD6l1EED2l8BvqCUKtY0rQmY1de+epjHm4U+vrp2NMGO0E5N0wxfkUqpK4FvAPMJv59WEBJfraZp9UM9kaZpu5RSrwIXK6Wu7uuFnYee8O4Z6nvHoB44GVhByOLaTFcan1hQwdvra/H45GIUS25vQJ8QMCBR2RSkOx24nHb9I82Oq+/f6c4DXzsdthEv6tU0Da8viNvnx+0N7P/weAf+24/bF5Cp2gngTLOxbEE5mcYlrrag95BSdxvpcRg2KSmlpgMnos8G2xbhtIvQZ+P1v+KGe5moEZwz3ONEir3HqFEp9QPgFuB/6NPaa9BXVE8EHmBwkhppfAB3od+/Ogv9ftXl6Avknh/h94/GPg4kpgkDD2RnpLFsfjlvb6jF55d7BfEU1KDX4x/RolKbTWFToFAoxf4kpWkamgYaGsEgKTXpwmqcaTaWzSuPNHNzN/o2FE3xjSp5jKSndCn6RfqrGG/T+2v0C/FtwNa+tsXA9iEecyv6O4mFDF0ht7+uTqHBsemM7ubhxejrq84IuUd0eoT4zlZKlQ3XW0KfBNEAXK6U2gB8Avi9pmmxuslTiZ6YlgODVujlZjlZNr+c9zbW4ZXEZErBoIb+m5GkY0X6kF3EhFSPPsy+L75RJZchp4QrpWzAJcB6TdPu0TTtydAP4FFggVJqKfAkeu/jF0qpsKJPA6ZH/7Pv841KqbCl9gPO6++ZfTLk+JcI6SmMQAD9SrB//KTv3lJYZW70Ke8Af+j7GRjFBkDfkN0DwGnAL/qa7x1lbKO1Bf3dWGvogfzsdI5dOCHSsIIQYoyyM9I4ZuGESAmpDTgV2BHfqJLPcOuUTgUmY7DXzwD9xy7XNG0f+pa+c4H1SqkblFJXKKV+oZRaBRwK0DfL7ffo7/g/Vkpd17cm6Eal1Db0adBomrYVfSLC15VSf1VKfV0p9VfgVkb/y38SvXf1olLqG0qpH6NPGc8KPVHTtCfQZ999GXhbKXV133PfAqw3eOy70ZPdl4C3NE0bqpcYLWvRe5thC4OzM9I4duEE8mQdkxBRkZfl5JgFFZHe7HUDn6JvTaQYn+GS0uV9n/8T6QRN0zag92jOV0plaJr2V/SL5TbgO8Bf0Nc3fYy+rqf/+64GLgDagR+jD/+dA7zA4PtCF/c9/4Xo94Smod/jqh7Jf3CAm9DXRc0A/oS+uvp/6InHyAXAVYAL+DlwM3rv5InQEzVN24E+vR1i30saaCXwaQxm+Licdo45pILS/Iw4hiNE8inKdfGJyLPs2tCvC+/FN6rkJVXCo0Qp9QJwNDBB07R4TwM9Dv3eVn7ogaCmsWZHE3sbZAM2IUZrQlEmSw4uwW4zfP9ejz6aJD2kKBpxmSERWd80+dOAhxKQkECf9HAMBjdYbUqxZFYJB08Ky1dCiCHMmJDL4bNLIyWkKvTXnCSkKJOe0jgopY5Ev3/2nb7PczVNq0pgSBPRFzIfYnSwqq6DdTubZd6XEMNYML2QmRPyIh3ehN5DGu0tBDEC0lMan28C9wG5wIUJTkigv0iO5cD9rUGmleeydG4pduOikUKkPJtNcfjs0qES0vvoNTMlIcWI9JSSUzp6qaUvGR1s6XTzwaZ6WcskxACZLgdLZ5eSnx1xQ8hn0CdAGS7QF9EhSSl52YDfAT8yOtjj8fPR1gbZqkAIoLwwkyWziiNV+ga4E32YXup4xZgkpeT3HQaXgNovGNTYtLuFnTVSokukJgXMnVrArKEnAl0N/AEpwxEXkpRSw7noVSoMxyVqW7pZvb1JauaJlJKeZufw2SUU50Vcy+dBX6v5SKQTRPRJUkodx6Lvf2VUR5Aet4+PtjbKFusiJRTlujh8dslQ247sQt8AdFX8ohIgSSnVTEEvn3SU0cFgUGPj7hYqZThPJLGZE3KZN60QW+RtRJ5Fr0ITVltSxJ4kpdTjBH4L/CDSCbXNfcN5sl22SCIOu76QvKIorNxlvyD6hp+/7/taJIAkpdR1Nnp1c8M7vN1uHx9tbaCty2t0WAhLyc92ctjB/9/evcW2eRUAHP/bsR3n0qQXd12brmu7lW2atnEZCIZAXF4REmIT4xk0kACBBBIPCMGExAMPPHCReOIJwQAhIV7giY2bxANoE7RMY6Xd1i7t1jhp7Fwc3z4ejr1FXey4qe2cJP+fZDltPzunUup/P/t859zG5Fi20yGvA4/T4Ro/DY9R2ttOEt7Oe89Gf+jsPO10I+kU95zYz93Hprvt+vs3wo7Rs8MbmToxSsoRprt+udMB86UKz56fY2n1ZvZUlLZXYTrPQ3cVup0dAXyfMOXbH+5IGCW1fYKwCsSG66s0mgn/vbTAi68u4o+MYpYZSXP/yQOcvP0t+4yuVybsqt1trzhtA6Ok9U4DvwLe1emAxaU1nj0/x+KynzUpPrcfHOfB04cY677z8nPAp3hzZ2tFxCjpRqOE2Ucd385rJgkXZku8cGmBesOfH22/0WyaB04fYqYw2e2wNeBJwoadvl0XKaOkTj5A2EX3TKcDVtfqnL1YZLbo+pTaPscPT/LAqYPksh3XrQP4K/BZ4IXhjEpbZZTUzRjwbeBrdNnm5LWFFf59ochypT6scUnsG8ty/6mDHDkw3u2wJeDrwE/w2qMdwSipFw8Tzpoe7HRAo9nkf7Mlzl9e9KJbDVQ+N8K9Jw5w4rbJbtO8IWx4+XngleGMTP1glNSrHPBV4JuEM6gN1eoNXnx1kQuzJRpNf7bUP9lMmjMz05w+NtVpi/K2IuEz0Z/jyt47jlHSzToJ/BD4WLeDKtUGL16+zktXS9gm3YqRdIpTR6c4c3yaXOf9jtp+QQjStcGPTINglLQVKcIyRT8A7uh24EqlzguXFrj0+pL/ZdVNSQF3HJnk3jsObDbFG+AS8AXCYqrawYySbsUE4e28r9Bhr6a2pdUqz798ndni8lAGpp3t6MFx7rvzAPvGc5sdOg98F/gxUBn4wDRwRkn9cJwQp88AXd9fub60xvOvLPD6wupQBqad5bYDY9xzfD8Hp/KbHbpK2FH5e8D1gQ9MQ2OU1E93Ey5O/DQbbL++3kK5woUrJV6dW3bZoj0unQrXGt01M83U5mdGDcJM0CdxAdVdyShpEB4EvgN8fLMDK9U6L10t8/JrZSrVxuBHpmhkM2lO3r6P00enuu0Au95vgG/gBbC7mlHSIL2P8H7/hzY7sNlMmC0uc/FKifmyW7LvZlPjWU4dneL44UkyI12ndrf9ibCS998HOzLFwChp0FLARwlxencvD7i+tMbFKyUuzy3TdD75rpBKwdGDE5w6uo/CdMfL3G70L0KM/oDXG+0ZRknD0p5G/i3g7b08oFpr8PJrZS5eLbO65hJGO9HkWJaZwgR3HtnXy7TutmcIi6b+HpcG2nOMkoYtBbwf+CLwSWDTV6okSbi2WGF2bpkrxWWqdV+nYjY2mmGmMMFMYYL9k12vFFivCfyaEKN/DGxwip5R0naaAZ4APgcc6eUBSZIwt1hhtrjMbHGZas1AxSCfG+HYoRCiHqZzr1cGfkqY3v3SIMamncUoKQajhLOmLwHv7fVBSZIwV2qfQa2wVnP23jDlMmmOtc6IDk3lN1sc9UbnCBe8/owQJgkwSorPw4S39h5nk1Ui1kuShGIrULMGamDGRjMcns5zrDDB4f1jpG8uRA3gt8CPCDPqfPHRWxglxeowYVO2JwiLwPYsSRKuL1WZW1zl2mKF+VLFFcu3KJ8boTCdpzA9RmE6z0Q+u5Wn+SfwVOt2ua8D1K5jlBS7FOHs6VHgMeDUzT5Bs5mwUF7j2uIqxVKFhfKakepgNJt+I0CF6TEmx7YUIYCzhAj9EjjftwFq1zNK2klSwDsJcXoMOL2VJ2kmCaXlKsVShfnyGvOlyp5dTWJ8NMP0ZO6NEPWwzE8353kzRGf7MkDtOUZJO1UKeAdvnkHdfStPVqnWKa/UKK9UWVqtUV6tsbRa2zWxyudGmBrPsW8827oPX/e4okI3rxAi9BTwLH5OpFtklLQbpICHCHF6FHhbv564Vm+ytFoNwWqFqrxSZaVSj+7VN5WCfHaEybFsKzo5psbD19nMLcenrUm4juhp4HeEpX+cl6++MUraje4EPgx8pHWb6fc3aDYTKrUG1VqDWr3J2gb31XqTWr3BWi3c1xvd/621J7KlWr9IAelUilw2TS4zQjaTfuPrXDbNaDZDPjfSumUYzaZvdlp2LxLgOUKEngb+Aiz2+5tIbUZJu10KOEOI0wcJq0mc2I6BNJMEknXx6X9A+uUs8EdChP5M2EhPGgqjpL3oOPAIIVCPED6b6ro54S5WJkSofTb0DHBtOwekvc0oSZAnTJS4D7i3dX8fcA/Q85LWkVsB/kMI0LnW7SzhuiFfBBQNoyR1lia81dcO1fr7w9s4rm7mCKFZH55zhHXlnJCg6BklaWumgENAYYP7jX7vEN2XTUpat+YN9zXCZzrzQHHdbR64StgS/Err/ipQ7d9fURo+oyQNRwrI8db4tG+SMEqSpIj07Yo6SZJulVGSJEXDKEmSomGUJEnRMEqSpGgYJUlSNIySJCkaRkmSFA2jJEmKhlGSJEXDKEmSomGUJEnRMEqSpGgYJUlSNIySJCkaRkmSFA2jJEmKhlGSJEXDKEmSomGUJEnRMEqSpGgYJUlSNIySJCkaRkmSFA2jJEmKhlGSJEXDKEmSomGUJEnRMEqSpGgYJUlSNIySJCkaRkmSFA2jJEmKhlGSJEXDKEmSomGUJEnRMEqSpGgYJUlSNIySJCkaRkmSFA2jJEmKhlGSJEXDKEmSomGUJEnRMEqSpGgYJUlSNIySJCkaRkmSFA2jJEmKhlGSJEXj/8Gc/4bK72XVAAAAAElFTkSuQmCC\n",
- "text/plain": [
- "<Figure size 432x432 with 1 Axes>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "text/markdown": [
- "#### Confusion matrix is :"
- ],
- "text/plain": [
- "<IPython.core.display.Markdown object>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "text/html": [
- "<style type=\"text/css\" >\n",
- " #T_7ebbbdc8_4293_11ea_ab68_4df1eb20668drow0_col0 {\n",
- " background-color: #ffa500;\n",
- " color: #000000;\n",
- " font-size: 20pt;\n",
- " } #T_7ebbbdc8_4293_11ea_ab68_4df1eb20668drow0_col1 {\n",
- " background-color: #fff6e5;\n",
- " color: #000000;\n",
- " font-size: 20pt;\n",
- " } #T_7ebbbdc8_4293_11ea_ab68_4df1eb20668drow1_col0 {\n",
- " background-color: #fff6e5;\n",
- " color: #000000;\n",
- " font-size: 20pt;\n",
- " } #T_7ebbbdc8_4293_11ea_ab68_4df1eb20668drow1_col1 {\n",
- " background-color: #ffa500;\n",
- " color: #000000;\n",
- " font-size: 20pt;\n",
- " }</style><table id=\"T_7ebbbdc8_4293_11ea_ab68_4df1eb20668d\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >0</th> <th class=\"col_heading level0 col1\" >1</th> </tr></thead><tbody>\n",
- " <tr>\n",
- " <th id=\"T_7ebbbdc8_4293_11ea_ab68_4df1eb20668dlevel0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
- " <td id=\"T_7ebbbdc8_4293_11ea_ab68_4df1eb20668drow0_col0\" class=\"data row0 col0\" >0.81</td>\n",
- " <td id=\"T_7ebbbdc8_4293_11ea_ab68_4df1eb20668drow0_col1\" class=\"data row0 col1\" >0.19</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_7ebbbdc8_4293_11ea_ab68_4df1eb20668dlevel0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
- " <td id=\"T_7ebbbdc8_4293_11ea_ab68_4df1eb20668drow1_col0\" class=\"data row1 col0\" >0.15</td>\n",
- " <td id=\"T_7ebbbdc8_4293_11ea_ab68_4df1eb20668drow1_col1\" class=\"data row1 col1\" >0.85</td>\n",
- " </tr>\n",
- " </tbody></table>"
- ],
- "text/plain": [
- "<pandas.io.formats.style.Styler at 0x7f879daa7750>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
- "source": [
- "model = keras.models.load_model('./run/models/best_model.h5')\n",
- "\n",
- "# ---- Evaluate\n",
- "reload(ooo)\n",
- "score = model.evaluate(x_test, y_test, verbose=0)\n",
- "\n",
- "print('x_test / loss : {:5.4f}'.format(score[0]))\n",
- "print('x_test / accuracy : {:5.4f}'.format(score[1]))\n",
- "\n",
- "values=[score[1], 1-score[1]]\n",
- "ooo.plot_donut(values,[\"Accuracy\",\"Errors\"], title=\"#### Accuracy donut is :\")\n",
- "\n",
- "# ---- Confusion matrix\n",
- "\n",
- "y_pred = model.predict_classes(x_test)\n",
- "\n",
- "ooo.display_confusion_matrix(y_test,y_pred,labels=range(2),color='orange',font_size='20pt')\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- }
- ],
- "metadata": {
- "kernelspec": {
- "display_name": "Python 3",
- "language": "python",
- "name": "python3"
- },
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.7.5"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}
diff --git a/IMDB/01-Embedding-Keras.ipynb b/IMDB/01-Embedding-Keras.ipynb
index b5cd9d3552214f8d3acf5488d3eaf0af276484d7..75ee361fae078ca33e9d5b2200b5ee2e9774544d 100644
--- a/IMDB/01-Embedding-Keras.ipynb
+++ b/IMDB/01-Embedding-Keras.ipynb
@@ -7,7 +7,7 @@
"Text Embedding - IMDB dataset\n",
"=============================\n",
"---\n",
- "Introduction au Deep Learning (IDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020 \n",
+ "Formation Introduction au Deep Learning (FIDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020 \n",
"\n",
"## Text classification using **Text embedding** :\n",
"\n",
@@ -35,22 +35,9 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "IDLE 2020 - Practical Work Module\n",
- " Version : 0.2.4\n",
- " Run time : Monday 27 January 2020, 23:33:47\n",
- " Matplotlib style : fidle/talk.mplstyle\n",
- " TensorFlow version : 2.0.0\n",
- " Keras version : 2.2.4-tf\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"import numpy as np\n",
"\n",
@@ -62,11 +49,13 @@
"import matplotlib\n",
"import seaborn as sns\n",
"\n",
- "import os,h5py,json\n",
+ "import os,sys,h5py,json\n",
"\n",
- "import fidle.pwk as ooo\n",
"from importlib import reload\n",
"\n",
+ "sys.path.append('..')\n",
+ "import fidle.pwk as ooo\n",
+ "\n",
"ooo.init()"
]
},
@@ -105,7 +94,7 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -124,23 +113,9 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- " Max(x_train,x_test) : 9999\n",
- " x_train : (25000,) y_train : (25000,)\n",
- " x_test : (25000,) y_test : (25000,)\n",
- "\n",
- "Review example (x_train[12]) :\n",
- "\n",
- " [1, 14, 22, 1367, 53, 206, 159, 4, 636, 898, 74, 26, 11, 436, 363, 108, 7, 14, 432, 14, 22, 9, 1055, 34, 8599, 2, 5, 381, 3705, 4509, 14, 768, 47, 839, 25, 111, 1517, 2579, 1991, 438, 2663, 587, 4, 280, 725, 6, 58, 11, 2714, 201, 4, 206, 16, 702, 5, 5176, 19, 480, 5920, 157, 13, 64, 219, 4, 2, 11, 107, 665, 1212, 39, 4, 206, 4, 65, 410, 16, 565, 5, 24, 43, 343, 17, 5602, 8, 169, 101, 85, 206, 108, 8, 3008, 14, 25, 215, 168, 18, 6, 2579, 1991, 438, 2, 11, 129, 1609, 36, 26, 66, 290, 3303, 46, 5, 633, 115, 4363]\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"print(\" Max(x_train,x_test) : \", ooo.rmax([x_train,x_test]) )\n",
"print(\" x_train : {} y_train : {}\".format(x_train.shape, y_train.shape))\n",
@@ -160,7 +135,7 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -188,26 +163,9 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n",
- "Dictionary size : 88587\n",
- "\n",
- "Review example (x_train[12]) :\n",
- "\n",
- " [1, 14, 22, 1367, 53, 206, 159, 4, 636, 898, 74, 26, 11, 436, 363, 108, 7, 14, 432, 14, 22, 9, 1055, 34, 8599, 2, 5, 381, 3705, 4509, 14, 768, 47, 839, 25, 111, 1517, 2579, 1991, 438, 2663, 587, 4, 280, 725, 6, 58, 11, 2714, 201, 4, 206, 16, 702, 5, 5176, 19, 480, 5920, 157, 13, 64, 219, 4, 2, 11, 107, 665, 1212, 39, 4, 206, 4, 65, 410, 16, 565, 5, 24, 43, 343, 17, 5602, 8, 169, 101, 85, 206, 108, 8, 3008, 14, 25, 215, 168, 18, 6, 2579, 1991, 438, 2, 11, 129, 1609, 36, 26, 66, 290, 3303, 46, 5, 633, 115, 4363]\n",
- "\n",
- "In real words :\n",
- "\n",
- " <start> this film contains more action before the opening credits than are in entire hollywood films of this sort this film is produced by tsui <unknown> and stars jet li this team has brought you many worthy hong kong cinema productions including the once upon a time in china series the action was fast and furious with amazing wire work i only saw the <unknown> in two shots aside from the action the story itself was strong and not just used as filler to find any other action films to rival this you must look for a hong kong cinema <unknown> in your area they are really worth checking out and usually never disappoint\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"print('\\nDictionary size : ', len(word_index))\n",
"print('\\nReview example (x_train[12]) :\\n\\n',x_train[12])\n",
@@ -223,22 +181,9 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 864x432 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
"source": [
"plt.figure(figsize=(12, 6))\n",
"ax=sns.distplot([len(i) for i in x_train],bins=60)\n",
@@ -261,42 +206,9 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n",
- "Review example (x_train[12]) :\n",
- "\n",
- " [ 1 14 22 1367 53 206 159 4 636 898 74 26 11 436\n",
- " 363 108 7 14 432 14 22 9 1055 34 8599 2 5 381\n",
- " 3705 4509 14 768 47 839 25 111 1517 2579 1991 438 2663 587\n",
- " 4 280 725 6 58 11 2714 201 4 206 16 702 5 5176\n",
- " 19 480 5920 157 13 64 219 4 2 11 107 665 1212 39\n",
- " 4 206 4 65 410 16 565 5 24 43 343 17 5602 8\n",
- " 169 101 85 206 108 8 3008 14 25 215 168 18 6 2579\n",
- " 1991 438 2 11 129 1609 36 26 66 290 3303 46 5 633\n",
- " 115 4363 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
- " 0 0 0 0]\n",
- "\n",
- "In real words :\n",
- "\n",
- " <start> this film contains more action before the opening credits than are in entire hollywood films of this sort this film is produced by tsui <unknown> and stars jet li this team has brought you many worthy hong kong cinema productions including the once upon a time in china series the action was fast and furious with amazing wire work i only saw the <unknown> in two shots aside from the action the story itself was strong and not just used as filler to find any other action films to rival this you must look for a hong kong cinema <unknown> in your area they are really worth checking out and usually never disappoint <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad> <pad>\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"review_len = 256\n",
"\n",
@@ -323,17 +235,9 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Saved.\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"os.makedirs('./data', mode=0o750, exist_ok=True)\n",
"\n",
@@ -373,7 +277,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -421,7 +325,7 @@
},
{
"cell_type": "code",
- "execution_count": 11,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -439,21 +343,9 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "ename": "NameError",
- "evalue": "name 'model' is not defined",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
- "\u001b[0;32m<timed exec>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n",
- "\u001b[0;31mNameError\u001b[0m: name 'model' is not defined"
- ]
- }
- ],
+ "outputs": [],
"source": [
"%%time\n",
"\n",
@@ -479,34 +371,9 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 576x432 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 576x432 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
"source": [
"ooo.plot_history(history)"
]
@@ -520,92 +387,9 @@
},
{
"cell_type": "code",
- "execution_count": 14,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "x_test / loss : 0.2869\n",
- "x_test / accuracy : 0.8834\n"
- ]
- },
- {
- "data": {
- "text/markdown": [
- "#### Accuracy donut is :"
- ],
- "text/plain": [
- "<IPython.core.display.Markdown object>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 432x432 with 1 Axes>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "text/markdown": [
- "#### Confusion matrix is :"
- ],
- "text/plain": [
- "<IPython.core.display.Markdown object>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "text/html": [
- "<style type=\"text/css\" >\n",
- " #T_65f76824_414d_11ea_86c3_492c802c4115row0_col0 {\n",
- " background-color: #ffa500;\n",
- " color: #000000;\n",
- " font-size: 20pt;\n",
- " } #T_65f76824_414d_11ea_86c3_492c802c4115row0_col1 {\n",
- " background-color: #fff6e5;\n",
- " color: #000000;\n",
- " font-size: 20pt;\n",
- " } #T_65f76824_414d_11ea_86c3_492c802c4115row1_col0 {\n",
- " background-color: #fff6e5;\n",
- " color: #000000;\n",
- " font-size: 20pt;\n",
- " } #T_65f76824_414d_11ea_86c3_492c802c4115row1_col1 {\n",
- " background-color: #ffa500;\n",
- " color: #000000;\n",
- " font-size: 20pt;\n",
- " }</style><table id=\"T_65f76824_414d_11ea_86c3_492c802c4115\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >0</th> <th class=\"col_heading level0 col1\" >1</th> </tr></thead><tbody>\n",
- " <tr>\n",
- " <th id=\"T_65f76824_414d_11ea_86c3_492c802c4115level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
- " <td id=\"T_65f76824_414d_11ea_86c3_492c802c4115row0_col0\" class=\"data row0 col0\" >0.89</td>\n",
- " <td id=\"T_65f76824_414d_11ea_86c3_492c802c4115row0_col1\" class=\"data row0 col1\" >0.11</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_65f76824_414d_11ea_86c3_492c802c4115level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
- " <td id=\"T_65f76824_414d_11ea_86c3_492c802c4115row1_col0\" class=\"data row1 col0\" >0.12</td>\n",
- " <td id=\"T_65f76824_414d_11ea_86c3_492c802c4115row1_col1\" class=\"data row1 col1\" >0.88</td>\n",
- " </tr>\n",
- " </tbody></table>"
- ],
- "text/plain": [
- "<pandas.io.formats.style.Styler at 0x7f9bc836a9d0>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
"source": [
"model = keras.models.load_model('./run/models/best_model.h5')\n",
"\n",
diff --git a/IMDB/02-Prediction.ipynb b/IMDB/02-Prediction.ipynb
index a932667c3949b42e3c7cef5d5199920f8a4c9416..07393e244e27bed52133e105ec699a59113f4391 100644
--- a/IMDB/02-Prediction.ipynb
+++ b/IMDB/02-Prediction.ipynb
@@ -30,22 +30,9 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "IDLE 2020 - Practical Work Module\n",
- " Version : 0.2.4\n",
- " Run time : Monday 27 January 2020, 21:57:44\n",
- " Matplotlib style : fidle/talk.mplstyle\n",
- " TensorFlow version : 2.0.0\n",
- " Keras version : 2.2.4-tf\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"import numpy as np\n",
"\n",
@@ -58,11 +45,13 @@
"import seaborn as sns\n",
"import pandas as pd\n",
"\n",
- "import os,h5py,json,re\n",
+ "import os,sys,h5py,json,re\n",
"\n",
- "import fidle.pwk as ooo\n",
"from importlib import reload\n",
"\n",
+ "sys.path.append('..')\n",
+ "import fidle.pwk as ooo\n",
+ "\n",
"ooo.init()"
]
},
@@ -76,7 +65,7 @@
},
{
"cell_type": "code",
- "execution_count": 79,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -94,7 +83,7 @@
},
{
"cell_type": "code",
- "execution_count": 80,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -112,7 +101,7 @@
},
{
"cell_type": "code",
- "execution_count": 102,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -154,28 +143,9 @@
},
{
"cell_type": "code",
- "execution_count": 91,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n",
- "Text review : This film is particularly nice, a must see.\n",
- "x_train[0] : [1, 2, 22, 9, 572, 2, 6, 215, 2, 0, 0, 0, 0, 0] (...)\n",
- "Translation : <start> <unknown> film is particularly <unknown> a must <unknown> <pad> <pad> <pad> <pad> <pad> (...)\n",
- "\n",
- "Text review : Some films are classics and cannot be ignored.\n",
- "x_train[1] : [1, 2, 108, 26, 2239, 5, 566, 30, 2, 0, 0, 0, 0, 0] (...)\n",
- "Translation : <start> <unknown> films are classics and cannot be <unknown> <pad> <pad> <pad> <pad> <pad> (...)\n",
- "\n",
- "Text review : This movie is just abominable and doesn't deserve to be seen!\n",
- "x_train[2] : [1, 2, 20, 9, 43, 2, 5, 152, 1833, 8, 30, 2, 0, 0, 0, 0, 0] (...)\n",
- "Translation : <start> <unknown> movie is just <unknown> and doesn't deserve to be <unknown> <pad> <pad> <pad> <pad> <pad> (...)\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"def translate(x):\n",
" return ' '.join( [index_word.get(i,'?') for i in x] )\n",
@@ -196,7 +166,7 @@
},
{
"cell_type": "code",
- "execution_count": 83,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -212,7 +182,7 @@
},
{
"cell_type": "code",
- "execution_count": 86,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -228,22 +198,9 @@
},
{
"cell_type": "code",
- "execution_count": 89,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n",
- "This film is particularly nice, a must see. => POSITIVE (0.62)\n",
- "\n",
- "Some films are classics and cannot be ignored. => POSITIVE (0.57)\n",
- "\n",
- "This movie is just abominable and doesn't deserve to be seen! => NEGATIVE (0.42)\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"for i in range(nb_reviews):\n",
" print(f'\\n{reviews[i]:<70} =>',('NEGATIVE' if y_pred[i][0]<0.5 else 'POSITIVE'),f'({y_pred[i][0]:.2f})')"
@@ -251,20 +208,9 @@
},
{
"cell_type": "code",
- "execution_count": 101,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "[1, 0, 1, 2]"
- ]
- },
- "execution_count": 101,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
+ "outputs": [],
"source": [
"a=[1]+[i for i in range(3)]\n",
"a"
diff --git a/IMDB/03-LSTM-Keras.ipynb b/IMDB/03-LSTM-Keras.ipynb
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..42a2639408384500e4e26c26ab0574836f15f856 100644
--- a/IMDB/03-LSTM-Keras.ipynb
+++ b/IMDB/03-LSTM-Keras.ipynb
@@ -0,0 +1,442 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Text Embedding - IMDB dataset\n",
+ "=============================\n",
+ "---\n",
+ "Introduction au Deep Learning (IDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020 \n",
+ "\n",
+ "## Text classification using **Text embedding** :\n",
+ "\n",
+ "The objective is to guess whether film reviews are **positive or negative** based on the analysis of the text. \n",
+ "\n",
+ "Original dataset can be find **[there](http://ai.stanford.edu/~amaas/data/sentiment/)** \n",
+ "Note that [IMDb.com](https://imdb.com) offers several easy-to-use [datasets](https://www.imdb.com/interfaces/) \n",
+ "For simplicity's sake, we'll use the dataset directly [embedded in Keras](https://www.tensorflow.org/api_docs/python/tf/keras/datasets)\n",
+ "\n",
+ "What we're going to do:\n",
+ "\n",
+ " - Retrieve data\n",
+ " - Preparing the data\n",
+ " - Build a model\n",
+ " - Train the model\n",
+ " - Evaluate the result\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 1 - Init python stuff"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import numpy as np\n",
+ "\n",
+ "import tensorflow as tf\n",
+ "import tensorflow.keras as keras\n",
+ "import tensorflow.keras.datasets.imdb as imdb\n",
+ "\n",
+ "import matplotlib.pyplot as plt\n",
+ "import matplotlib\n",
+ "import seaborn as sns\n",
+ "\n",
+ "import os,sys,h5py,json\n",
+ "\n",
+ "from importlib import reload\n",
+ "\n",
+ "sys.path.append('..')\n",
+ "import fidle.pwk as ooo\n",
+ "\n",
+ "ooo.init()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 2 - Retrieve data\n",
+ "\n",
+ "**From Keras :**\n",
+ "This IMDb dataset can bet get directly from [Keras datasets](https://www.tensorflow.org/api_docs/python/tf/keras/datasets) \n",
+ "\n",
+ "Due to their nature, textual data can be somewhat complex.\n",
+ "\n",
+ "### 2.1 - Data structure : \n",
+ "The dataset is composed of 2 parts: **reviews** and **opinions** (positive/negative), with a **dictionary**\n",
+ "\n",
+ " - dataset = (reviews, opinions)\n",
+ " - reviews = \\[ review_0, review_1, ...\\]\n",
+ " - review_i = [ int1, int2, ...] where int_i is the index of the word in the dictionary.\n",
+ " - opinions = \\[ int0, int1, ...\\] where int_j == 0 if opinion is negative or 1 if opinion is positive.\n",
+ " - dictionary = \\[ mot1:int1, mot2:int2, ... ]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 2.2 - Get dataset\n",
+ "For simplicity, we will use a pre-formatted dataset. \n",
+ "See : https://www.tensorflow.org/api_docs/python/tf/keras/datasets/imdb/load_data \n",
+ "\n",
+ "However, Keras offers some usefull tools for formatting textual data. \n",
+ "See : https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/text"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "vocab_size = 10000\n",
+ "\n",
+ "# ----- Retrieve x,y\n",
+ "#\n",
+ "(x_train, y_train), (x_test, y_test) = imdb.load_data( num_words = vocab_size,\n",
+ " skip_top = 0,\n",
+ " maxlen = None,\n",
+ " seed = 42,\n",
+ " start_char = 1,\n",
+ " oov_char = 2,\n",
+ " index_from = 3, )"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(\" Max(x_train,x_test) : \", ooo.rmax([x_train,x_test]) )\n",
+ "print(\" x_train : {} y_train : {}\".format(x_train.shape, y_train.shape))\n",
+ "print(\" x_test : {} y_test : {}\".format(x_test.shape, y_test.shape))\n",
+ "\n",
+ "print('\\nReview example (x_train[12]) :\\n\\n',x_train[12])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 2.3 - Have a look for humans (optional)\n",
+ "When we loaded the dataset, we asked for using \\<start\\> as 1, \\<unknown word\\> as 2 \n",
+ "So, we shifted the dataset by 3 with the parameter index_from=3"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# ---- Retrieve dictionary {word:index}, and encode it in ascii\n",
+ "\n",
+ "word_index = imdb.get_word_index()\n",
+ "\n",
+ "# ---- Shift the dictionary from +3\n",
+ "\n",
+ "word_index = {w:(i+3) for w,i in word_index.items()}\n",
+ "\n",
+ "# ---- Add <pad>, <start> and unknown tags\n",
+ "\n",
+ "word_index.update( {'<pad>':0, '<start>':1, '<unknown>':2} )\n",
+ "\n",
+ "# ---- Create a reverse dictionary : {index:word}\n",
+ "\n",
+ "index_word = {index:word for word,index in word_index.items()} \n",
+ "\n",
+ "# ---- Add a nice function to transpose :\n",
+ "#\n",
+ "def dataset2text(review):\n",
+ " return ' '.join([index_word.get(i, '?') for i in review])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print('\\nDictionary size : ', len(word_index))\n",
+ "print('\\nReview example (x_train[12]) :\\n\\n',x_train[12])\n",
+ "print('\\nIn real words :\\n\\n', dataset2text(x_train[12]))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 2.4 - Have a look for neurons"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "plt.figure(figsize=(12, 6))\n",
+ "ax=sns.distplot([len(i) for i in x_train],bins=60)\n",
+ "ax.set_title('Distribution of reviews by size')\n",
+ "plt.xlabel(\"Review's sizes\")\n",
+ "plt.ylabel('Density')\n",
+ "ax.set_xlim(0, 1500)\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 3 - Preprocess the data\n",
+ "In order to be processed by an NN, all entries must have the same length. \n",
+ "We chose a review length of **review_len** \n",
+ "We will therefore complete them with a padding (of \\<pad\\>\\) "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "review_len = 256\n",
+ "\n",
+ "x_train = keras.preprocessing.sequence.pad_sequences(x_train,\n",
+ " value = 0,\n",
+ " padding = 'post',\n",
+ " maxlen = review_len)\n",
+ "\n",
+ "x_test = keras.preprocessing.sequence.pad_sequences(x_test,\n",
+ " value = 0 ,\n",
+ " padding = 'post',\n",
+ " maxlen = review_len)\n",
+ "\n",
+ "print('\\nReview example (x_train[12]) :\\n\\n',x_train[12])\n",
+ "print('\\nIn real words :\\n\\n', dataset2text(x_train[12]))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Save dataset and dictionary (can be usefull)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "os.makedirs('./data', mode=0o750, exist_ok=True)\n",
+ "\n",
+ "with h5py.File('./data/dataset_imdb.h5', 'w') as f:\n",
+ " f.create_dataset(\"x_train\", data=x_train)\n",
+ " f.create_dataset(\"y_train\", data=y_train)\n",
+ " f.create_dataset(\"x_test\", data=x_test)\n",
+ " f.create_dataset(\"y_test\", data=y_test)\n",
+ "\n",
+ "with open('./data/word_index.json', 'w') as fp:\n",
+ " json.dump(word_index, fp)\n",
+ "\n",
+ "with open('./data/index_word.json', 'w') as fp:\n",
+ " json.dump(index_word, fp)\n",
+ "\n",
+ "print('Saved.')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 4 - Build the model\n",
+ "Few remarks :\n",
+ "1. We'll choose a dense vector size for the embedding output with **dense_vector_size**\n",
+ "2. **GlobalAveragePooling1D** do a pooling on the last dimension : (None, lx, ly) -> (None, ly) \n",
+ "In other words: we average the set of vectors/words of a sentence\n",
+ "3. L'embedding de Keras fonctionne de manière supervisée. Il s'agit d'une couche de *vocab_size* neurones vers *n_neurons* permettant de maintenir une table de vecteurs (les poids constituent les vecteurs). Cette couche ne calcule pas de sortie a la façon des couches normales, mais renvois la valeur des vecteurs. n mots => n vecteurs (ensuite empilés par le pooling) \n",
+ "Voir : https://stats.stackexchange.com/questions/324992/how-the-embedding-layer-is-trained-in-keras-embedding-layer\n",
+ "\n",
+ "A SUIVRE : https://www.liip.ch/en/blog/sentiment-detection-with-keras-word-embeddings-and-lstm-deep-learning-networks\n",
+ "### 4.1 - Build\n",
+ "More documentation about :\n",
+ " - [Embedding](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Embedding)\n",
+ " - [GlobalAveragePooling1D](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling1D)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def get_model(dense_vector_size=128):\n",
+ " \n",
+ " model = keras.Sequential()\n",
+ " model.add(keras.layers.Embedding(input_dim = vocab_size, \n",
+ " output_dim = dense_vector_size, \n",
+ " input_length = review_len))\n",
+ " model.add(keras.layers.LSTM(128, dropout=0.2, recurrent_dropout=0.2))\n",
+ " model.add(keras.layers.Dense(1, activation='sigmoid'))\n",
+ "\n",
+ " model.compile(optimizer = 'adam',\n",
+ " loss = 'binary_crossentropy',\n",
+ " metrics = ['accuracy'])\n",
+ " return model"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 5 - Train the model\n",
+ "### 5.1 - Get it"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model = get_model()\n",
+ "\n",
+ "model.summary()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 5.2 - Add callback"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "os.makedirs('./run/models', mode=0o750, exist_ok=True)\n",
+ "save_dir = \"./run/models/best_model.h5\"\n",
+ "savemodel_callback = tf.keras.callbacks.ModelCheckpoint(filepath=save_dir, verbose=0, save_best_only=True)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 5.1 - Train it\n",
+ "GPU : batch_size=512 : 305s"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "%%time\n",
+ "\n",
+ "n_epochs = 10\n",
+ "batch_size = 32\n",
+ "\n",
+ "history = model.fit(x_train,\n",
+ " y_train,\n",
+ " epochs = n_epochs,\n",
+ " batch_size = batch_size,\n",
+ " validation_data = (x_test, y_test),\n",
+ " verbose = 1,\n",
+ " callbacks = [savemodel_callback])\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 6 - Evaluate\n",
+ "### 6.1 - Training history"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "ooo.plot_history(history)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 6.2 - Reload and evaluate best model"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model = keras.models.load_model('./run/models/best_model.h5')\n",
+ "\n",
+ "# ---- Evaluate\n",
+ "reload(ooo)\n",
+ "score = model.evaluate(x_test, y_test, verbose=0)\n",
+ "\n",
+ "print('x_test / loss : {:5.4f}'.format(score[0]))\n",
+ "print('x_test / accuracy : {:5.4f}'.format(score[1]))\n",
+ "\n",
+ "values=[score[1], 1-score[1]]\n",
+ "ooo.plot_donut(values,[\"Accuracy\",\"Errors\"], title=\"#### Accuracy donut is :\")\n",
+ "\n",
+ "# ---- Confusion matrix\n",
+ "\n",
+ "y_pred = model.predict_classes(x_test)\n",
+ "\n",
+ "ooo.display_confusion_matrix(y_test,y_pred,labels=range(2),color='orange',font_size='20pt')\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.7.5"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/IMDB/fidle/__init__.py b/IMDB/fidle/__init__.py
deleted file mode 100644
index 098c126cc59c579c3cc9a4fd398f3899b823d0d8..0000000000000000000000000000000000000000
--- a/IMDB/fidle/__init__.py
+++ /dev/null
@@ -1,2 +0,0 @@
-
-VERSION='0.1a'
\ No newline at end of file
diff --git a/IMDB/fidle/talk.mplstyle b/IMDB/fidle/talk.mplstyle
deleted file mode 100644
index edf3fed3a5f6f7c0a1b76a4195f74ea9d68aa966..0000000000000000000000000000000000000000
--- a/IMDB/fidle/talk.mplstyle
+++ /dev/null
@@ -1,33 +0,0 @@
-
-# See : https://matplotlib.org/users/customizing.html
-
-axes.titlesize : 24
-axes.labelsize : 20
-axes.edgecolor : dimgrey
-axes.labelcolor : dimgrey
-axes.linewidth : 2
-axes.grid : False
-
-axes.prop_cycle : cycler('color', ['steelblue', 'tomato', '2ca02c', 'd62728', '9467bd', '8c564b', 'e377c2', '7f7f7f', 'bcbd22', '17becf'])
-
-lines.linewidth : 3
-lines.markersize : 10
-
-xtick.color : black
-xtick.labelsize : 18
-ytick.color : black
-ytick.labelsize : 18
-
-axes.spines.left : True
-axes.spines.bottom : True
-axes.spines.top : False
-axes.spines.right : False
-
-savefig.dpi : 300 # figure dots per inch or 'figure'
-savefig.facecolor : white # figure facecolor when saving
-savefig.edgecolor : white # figure edgecolor when saving
-savefig.format : svg
-savefig.bbox : tight
-savefig.pad_inches : 0.1
-savefig.transparent : True
-savefig.jpeg_quality: 95
diff --git a/VAE/01-VAE with MNIST.ipynb b/VAE/01-VAE with MNIST.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..4a2a0dba8571dc9c3f28e029ef06f5bdad5b1e63
--- /dev/null
+++ b/VAE/01-VAE with MNIST.ipynb
@@ -0,0 +1,224 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Text Embedding - IMDB dataset\n",
+ "=============================\n",
+ "---\n",
+ "Formation Introduction au Deep Learning (FIDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020 \n",
+ "\n",
+ "## Variational AutoEncoder (VAE), with MNIST Dataset\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 1 - Init python stuff"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "IDLE 2020 - Practical Work Module\n",
+ " Version : 0.2.4\n",
+ " Run time : Sunday 2 February 2020, 19:30:36\n",
+ " Matplotlib style : ../fidle/talk.mplstyle\n",
+ " TensorFlow version : 2.0.0\n",
+ " Keras version : 2.2.4-tf\n"
+ ]
+ }
+ ],
+ "source": [
+ "import numpy as np\n",
+ "\n",
+ "import tensorflow as tf\n",
+ "import tensorflow.keras as keras\n",
+ "import tensorflow.keras.datasets.imdb as imdb\n",
+ "\n",
+ "import models.VAE\n",
+ "from models.VAE import VariationalAutoencoder\n",
+ "\n",
+ "import matplotlib.pyplot as plt\n",
+ "import matplotlib\n",
+ "import seaborn as sns\n",
+ "\n",
+ "import os,sys,h5py,json\n",
+ "\n",
+ "from importlib import reload\n",
+ "\n",
+ "\n",
+ "\n",
+ "sys.path.append('..')\n",
+ "import fidle.pwk as ooo\n",
+ "\n",
+ "ooo.init()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "reload(models.VAE)\n",
+ "input_shape = (28,28,1)\n",
+ "z_dim = 2\n",
+ "\n",
+ "encoder= [ {'type':'Conv2D', 'filters':32, 'kernel_size':(3,3), 'strides':1, 'padding':'same', 'activation':'relu'},\n",
+ " {'type':'Conv2D', 'filters':64, 'kernel_size':(3,3), 'strides':2, 'padding':'same', 'activation':'relu'},\n",
+ " {'type':'Conv2D', 'filters':64, 'kernel_size':(3,3), 'strides':2, 'padding':'same', 'activation':'relu'},\n",
+ " {'type':'Conv2D', 'filters':64, 'kernel_size':(3,3), 'strides':1, 'padding':'same', 'activation':'relu'}\n",
+ " ]\n",
+ "\n",
+ "decoder= [ {'type':'Conv2DT', 'filters':64, 'kernel_size':(3,3), 'strides':1, 'padding':'same', 'activation':'relu'},\n",
+ " {'type':'Conv2DT', 'filters':64, 'kernel_size':(3,3), 'strides':2, 'padding':'same', 'activation':'relu'},\n",
+ " {'type':'Conv2DT', 'filters':32, 'kernel_size':(3,3), 'strides':2, 'padding':'same', 'activation':'relu'},\n",
+ " {'type':'Conv2DT', 'filters':1, 'kernel_size':(3,3), 'strides':1, 'padding':'same', 'activation':'sigmoid'}\n",
+ " ]\n",
+ "\n",
+ "vae = models.VAE.VariationalAutoencoder(input_shape, encoder, decoder, z_dim)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Model: \"model_29\"\n",
+ "__________________________________________________________________________________________________\n",
+ "Layer (type) Output Shape Param # Connected to \n",
+ "==================================================================================================\n",
+ "encoder_input (InputLayer) [(None, 28, 28, 1)] 0 \n",
+ "__________________________________________________________________________________________________\n",
+ "Layer_1 (Conv2D) (None, 28, 28, 32) 320 encoder_input[0][0] \n",
+ "__________________________________________________________________________________________________\n",
+ "Layer_2 (Conv2D) (None, 14, 14, 64) 18496 Layer_1[0][0] \n",
+ "__________________________________________________________________________________________________\n",
+ "Layer_3 (Conv2D) (None, 7, 7, 64) 36928 Layer_2[0][0] \n",
+ "__________________________________________________________________________________________________\n",
+ "Layer_4 (Conv2D) (None, 7, 7, 64) 36928 Layer_3[0][0] \n",
+ "__________________________________________________________________________________________________\n",
+ "flatten_7 (Flatten) (None, 3136) 0 Layer_4[0][0] \n",
+ "__________________________________________________________________________________________________\n",
+ "mu (Dense) (None, 2) 6274 flatten_7[0][0] \n",
+ "__________________________________________________________________________________________________\n",
+ "log_var (Dense) (None, 2) 6274 flatten_7[0][0] \n",
+ "__________________________________________________________________________________________________\n",
+ "encoder_output (Lambda) (None, 2) 0 mu[0][0] \n",
+ " log_var[0][0] \n",
+ "==================================================================================================\n",
+ "Total params: 105,220\n",
+ "Trainable params: 105,220\n",
+ "Non-trainable params: 0\n",
+ "__________________________________________________________________________________________________\n"
+ ]
+ }
+ ],
+ "source": [
+ "vae.encoder.summary()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Model: \"model_30\"\n",
+ "_________________________________________________________________\n",
+ "Layer (type) Output Shape Param # \n",
+ "=================================================================\n",
+ "decoder_input (InputLayer) [(None, 2)] 0 \n",
+ "_________________________________________________________________\n",
+ "dense_7 (Dense) (None, 3136) 9408 \n",
+ "_________________________________________________________________\n",
+ "reshape_7 (Reshape) (None, 7, 7, 64) 0 \n",
+ "_________________________________________________________________\n",
+ "Layer_1 (Conv2DTranspose) (None, 7, 7, 64) 36928 \n",
+ "_________________________________________________________________\n",
+ "Layer_2 (Conv2DTranspose) (None, 14, 14, 64) 36928 \n",
+ "_________________________________________________________________\n",
+ "Layer_3 (Conv2DTranspose) (None, 28, 28, 32) 18464 \n",
+ "_________________________________________________________________\n",
+ "Layer_4 (Conv2DTranspose) (None, 28, 28, 1) 289 \n",
+ "=================================================================\n",
+ "Total params: 102,017\n",
+ "Trainable params: 102,017\n",
+ "Non-trainable params: 0\n",
+ "_________________________________________________________________\n"
+ ]
+ }
+ ],
+ "source": [
+ "vae.decoder.summary()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{'b': 2}"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "a={'a':1, 'b':2}\n",
+ "del a['a']\n",
+ "a"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.7.5"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/VAE/models/VAE.py b/VAE/models/VAE.py
new file mode 100644
index 0000000000000000000000000000000000000000..380c3469b0978078132315eff05e6e3a52276b0a
--- /dev/null
+++ b/VAE/models/VAE.py
@@ -0,0 +1,114 @@
+import numpy as np
+
+import tensorflow as tf
+import tensorflow.keras as keras
+from tensorflow.keras import backend as K
+from tensorflow.keras.layers import Input, Conv2D, Flatten, Dense, Conv2DTranspose, Reshape, Lambda, Activation, BatchNormalization, LeakyReLU, Dropout
+from tensorflow.keras.models import Model
+
+import tensorflow.keras.datasets.imdb as imdb
+
+
+
+
+class VariationalAutoencoder():
+
+
+ def __init__(self, input_shape, encoder_layers, decoder_layers, z_dim):
+
+ self.name = 'Variational AutoEncoder'
+ self.input_shape = input_shape
+ self.encoder_layers = encoder_layers
+ self.decoder_layers = decoder_layers
+ self.z_dim = z_dim
+
+ # ==== Encoder ================================================================
+
+ # ---- Input layer
+ encoder_input = Input(shape=self.input_shape, name='encoder_input')
+ x = encoder_input
+
+ # ---- Add next layers
+ i=1
+ for params in encoder_layers:
+ t=params['type']
+ params.pop('type')
+ if t=='Conv2D':
+ layer = Conv2D(**params, name=f"Layer_{i}")
+ if t=='Dropout':
+ layer = Dropout(**params)
+ x = layer(x)
+ i+=1
+
+ # ---- Flatten
+ shape_before_flattening = K.int_shape(x)[1:]
+ x = Flatten()(x)
+
+ # ---- mu / log_var
+ self.mu = Dense(self.z_dim, name='mu')(x)
+ self.log_var = Dense(self.z_dim, name='log_var')(x)
+
+ self.encoder_mu_log_var = Model(encoder_input, (self.mu, self.log_var))
+
+ # ---- output layer
+ def sampling(args):
+ mu, log_var = args
+ epsilon = K.random_normal(shape=K.shape(mu), mean=0., stddev=1.)
+ return mu + K.exp(log_var / 2) * epsilon
+
+ encoder_output = Lambda(sampling, name='encoder_output')([self.mu, self.log_var])
+
+ self.encoder = Model(encoder_input, encoder_output)
+
+ # ==== Decoder ================================================================
+
+ # ---- Input layer
+ decoder_input = Input(shape=(self.z_dim,), name='decoder_input')
+
+ # ---- First dense layer
+ x = Dense(np.prod(shape_before_flattening))(decoder_input)
+ x = Reshape(shape_before_flattening)(x)
+
+ # ---- Add next layers
+ i=1
+ for params in decoder_layers:
+ t=params['type']
+ params.pop('type')
+ if t=='Conv2DT':
+ layer = Conv2DTranspose(**params, name=f"Layer_{i}")
+ if t=='Dropout':
+ layer = Dropout(**params)
+ x = layer(x)
+ i+=1
+
+ decoder_output = x
+
+ self.decoder = Model(decoder_input, decoder_output)
+
+ # ==== Encoder-Decoder ========================================================
+
+ model_input = encoder_input
+ model_output = self.decoder(encoder_output)
+
+ self.model = Model(model_input, model_output)
+
+
+ def compile(self, learning_rate, r_loss_factor):
+ self.learning_rate = learning_rate
+ self.r_loss_factor = r_loss_factor
+
+ def vae_r_loss(y_true, y_pred):
+ r_loss = K.mean(K.square(y_true - y_pred), axis = [1,2,3])
+ return r_loss_factor * r_loss
+
+ def vae_kl_loss(y_true, y_pred):
+ kl_loss = -0.5 * K.sum(1 + self.log_var - K.square(self.mu) - K.exp(self.log_var), axis = 1)
+ return kl_loss
+
+ def vae_loss(y_true, y_pred):
+ r_loss = vae_r_loss(y_true, y_pred)
+ kl_loss = vae_kl_loss(y_true, y_pred)
+ return r_loss + kl_loss
+
+ optimizer = Adam(lr=learning_rate)
+ self.model.compile(optimizer=optimizer, loss = vae_loss, metrics = [vae_r_loss, vae_kl_loss], experimental_run_tf_function=False)
diff --git a/BHPD/fidle/__init__.py b/fidle/__init__.py
similarity index 100%
rename from BHPD/fidle/__init__.py
rename to fidle/__init__.py
diff --git a/IMDB/fidle/pwk.py b/fidle/pwk.py
similarity index 99%
rename from IMDB/fidle/pwk.py
rename to fidle/pwk.py
index 8cdba2c56fabc3d865fa816057aa9f5c06c5ed88..fd2939d33d14ecf0fbb1fa3a73854388be62b46f 100644
--- a/IMDB/fidle/pwk.py
+++ b/fidle/pwk.py
@@ -38,7 +38,7 @@ VERSION='0.2.4'
# init_all
# -------------------------------------------------------------
#
-def init(mplstyle='fidle/talk.mplstyle'):
+def init(mplstyle='../fidle/talk.mplstyle'):
global VERSION
# ---- matplotlib
matplotlib.style.use(mplstyle)
diff --git a/BHPD/fidle/talk.mplstyle b/fidle/talk.mplstyle
similarity index 100%
rename from BHPD/fidle/talk.mplstyle
rename to fidle/talk.mplstyle