{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<img width=\"800px\" src=\"../fidle/img/00-Fidle-header-01.svg\"></img>\n",
"\n",
"# <!-- TITLE --> [SYNOP2] - Time series with RNN - Try a prediction\n",
"<!-- DESC --> Episode 2 : Training session and first predictions\n",
"<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
"\n",
"## Objectives :\n",
" - Make a simple prediction (3h)\n",
" - Understanding the use of a recurrent neural network\n",
"\n",
"\n",
"SYNOP meteorological data, available at: https://public.opendatasoft.com\n",
"\n",
"## What we're going to do :\n",
"\n",
" - Read our dataset\n",
" - Select our data and normalize it\n",
" - Doing our training\n",
" - Making simple predictions\n",
"\n",
"## Step 1 - Import and init\n",
"### 1.1 - Python"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style>\n",
"\n",
"div.warn { \n",
" background-color: #fcf2f2;\n",
" border-color: #dFb5b4;\n",
" border-left: 5px solid #dfb5b4;\n",
" padding: 0.5em;\n",
" font-weight: bold;\n",
" font-size: 1.1em;;\n",
" }\n",
"\n",
"\n",
"\n",
"div.nota { \n",
" background-color: #DAFFDE;\n",
" border-left: 5px solid #92CC99;\n",
" padding: 0.5em;\n",
" }\n",
"\n",
"div.todo:before { content:url(data:image/svg+xml;base64,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);\n",
" float:left;\n",
" margin-right:20px;\n",
" margin-top:-20px;\n",
" margin-bottom:20px;\n",
"}\n",
"div.todo{\n",
" font-weight: bold;\n",
" font-size: 1.1em;\n",
" margin-top:40px;\n",
"}\n",
"div.todo ul{\n",
" margin: 0.2em;\n",
"}\n",
"div.todo li{\n",
" margin-left:60px;\n",
" margin-top:0;\n",
" margin-bottom:0;\n",
"}\n",
"\n",
"div .comment{\n",
" font-size:0.8em;\n",
" color:#696969;\n",
"}\n",
"\n",
"\n",
"\n",
"</style>\n",
"\n"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": [
"**FIDLE 2020 - Practical Work Module**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Version : 0.6.1 DEV\n",
"Notebook id : SYNOP2\n",
"Run time : Saturday 19 December 2020, 11:22:47\n",
"TensorFlow version : 2.0.0\n",
"Keras version : 2.2.4-tf\n",
"Datasets dir : /home/pjluc/datasets/fidle\n",
"Running mode : full\n",
"Update keras cache : False\n",
"Save figs : True\n",
"Path figs : ./run/figs\n"
]
}
],
"source": [
"import tensorflow as tf\n",
"from tensorflow import keras\n",
"from tensorflow.keras.callbacks import TensorBoard\n",
"from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator\n",
"\n",
"import numpy as np\n",
"import math, random\n",
"import matplotlib.pyplot as plt\n",
"\n",
"import pandas as pd\n",
"import h5py, json\n",
"import os,time,sys\n",
"\n",
"from importlib import reload\n",
"\n",
"sys.path.append('..')\n",
"import fidle.pwk as pwk\n",
"\n",
"datasets_dir = pwk.init('SYNOP2')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 2 - Read and prepare dataset\n",
"### 2.1 - Read it"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"<br>**Train dataset example :**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"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>tend</th>\n",
" <th>cod_tend</th>\n",
" <th>dd</th>\n",
" <th>ff</th>\n",
" <th>td</th>\n",
" <th>u</th>\n",
" <th>ww</th>\n",
" <th>pres</th>\n",
" <th>rafper</th>\n",
" <th>rr1</th>\n",
" <th>rr3</th>\n",
" <th>tc</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>-120.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>278.75</td>\n",
" <td>88.0</td>\n",
" <td>60.0</td>\n",
" <td>96250.0</td>\n",
" <td>4.1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>7.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>-150.0</td>\n",
" <td>6.0</td>\n",
" <td>60.0</td>\n",
" <td>1.0</td>\n",
" <td>278.65</td>\n",
" <td>93.0</td>\n",
" <td>61.0</td>\n",
" <td>96100.0</td>\n",
" <td>2.6</td>\n",
" <td>0.2</td>\n",
" <td>0.6</td>\n",
" <td>6.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>10.0</td>\n",
" <td>3.0</td>\n",
" <td>280.0</td>\n",
" <td>2.1</td>\n",
" <td>278.85</td>\n",
" <td>95.0</td>\n",
" <td>58.0</td>\n",
" <td>96110.0</td>\n",
" <td>2.6</td>\n",
" <td>0.0</td>\n",
" <td>0.4</td>\n",
" <td>6.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>230.0</td>\n",
" <td>3.0</td>\n",
" <td>310.0</td>\n",
" <td>2.6</td>\n",
" <td>279.15</td>\n",
" <td>96.0</td>\n",
" <td>50.0</td>\n",
" <td>96340.0</td>\n",
" <td>5.7</td>\n",
" <td>0.0</td>\n",
" <td>3.0</td>\n",
" <td>6.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>280.0</td>\n",
" <td>1.0</td>\n",
" <td>330.0</td>\n",
" <td>4.6</td>\n",
" <td>278.15</td>\n",
" <td>94.0</td>\n",
" <td>21.0</td>\n",
" <td>96620.0</td>\n",
" <td>8.7</td>\n",
" <td>0.4</td>\n",
" <td>0.8</td>\n",
" <td>5.9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>480.0</td>\n",
" <td>3.0</td>\n",
" <td>350.0</td>\n",
" <td>5.1</td>\n",
" <td>276.95</td>\n",
" <td>91.0</td>\n",
" <td>60.0</td>\n",
" <td>97100.0</td>\n",
" <td>8.2</td>\n",
" <td>0.2</td>\n",
" <td>0.4</td>\n",
" <td>5.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>530.0</td>\n",
" <td>2.0</td>\n",
" <td>350.0</td>\n",
" <td>3.1</td>\n",
" <td>274.05</td>\n",
" <td>83.0</td>\n",
" <td>21.0</td>\n",
" <td>97630.0</td>\n",
" <td>7.2</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>3.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>450.0</td>\n",
" <td>2.0</td>\n",
" <td>340.0</td>\n",
" <td>6.2</td>\n",
" <td>272.15</td>\n",
" <td>81.0</td>\n",
" <td>2.0</td>\n",
" <td>98080.0</td>\n",
" <td>9.3</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>280.0</td>\n",
" <td>1.0</td>\n",
" <td>320.0</td>\n",
" <td>6.2</td>\n",
" <td>270.15</td>\n",
" <td>74.0</td>\n",
" <td>2.0</td>\n",
" <td>98360.0</td>\n",
" <td>10.3</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>220.0</td>\n",
" <td>1.0</td>\n",
" <td>290.0</td>\n",
" <td>2.6</td>\n",
" <td>269.65</td>\n",
" <td>72.0</td>\n",
" <td>2.0</td>\n",
" <td>98580.0</td>\n",
" <td>5.1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>100.0</td>\n",
" <td>1.0</td>\n",
" <td>350.0</td>\n",
" <td>3.1</td>\n",
" <td>270.45</td>\n",
" <td>79.0</td>\n",
" <td>2.0</td>\n",
" <td>98680.0</td>\n",
" <td>4.1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>300.0</td>\n",
" <td>3.0</td>\n",
" <td>350.0</td>\n",
" <td>5.1</td>\n",
" <td>268.55</td>\n",
" <td>70.0</td>\n",
" <td>2.0</td>\n",
" <td>98980.0</td>\n",
" <td>6.7</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>-0.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>130.0</td>\n",
" <td>1.0</td>\n",
" <td>10.0</td>\n",
" <td>4.6</td>\n",
" <td>267.45</td>\n",
" <td>60.0</td>\n",
" <td>2.0</td>\n",
" <td>99110.0</td>\n",
" <td>7.7</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>150.0</td>\n",
" <td>3.0</td>\n",
" <td>10.0</td>\n",
" <td>5.7</td>\n",
" <td>267.45</td>\n",
" <td>59.0</td>\n",
" <td>2.0</td>\n",
" <td>99260.0</td>\n",
" <td>8.7</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>140.0</td>\n",
" <td>1.0</td>\n",
" <td>50.0</td>\n",
" <td>2.6</td>\n",
" <td>268.15</td>\n",
" <td>70.0</td>\n",
" <td>2.0</td>\n",
" <td>99400.0</td>\n",
" <td>5.7</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>-0.8</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" tend cod_tend dd ff td u ww pres rafper rr1 \\\n",
"0 -120.0 6.0 0.0 0.0 278.75 88.0 60.0 96250.0 4.1 0.0 \n",
"1 -150.0 6.0 60.0 1.0 278.65 93.0 61.0 96100.0 2.6 0.2 \n",
"2 10.0 3.0 280.0 2.1 278.85 95.0 58.0 96110.0 2.6 0.0 \n",
"3 230.0 3.0 310.0 2.6 279.15 96.0 50.0 96340.0 5.7 0.0 \n",
"4 280.0 1.0 330.0 4.6 278.15 94.0 21.0 96620.0 8.7 0.4 \n",
"5 480.0 3.0 350.0 5.1 276.95 91.0 60.0 97100.0 8.2 0.2 \n",
"6 530.0 2.0 350.0 3.1 274.05 83.0 21.0 97630.0 7.2 0.0 \n",
"7 450.0 2.0 340.0 6.2 272.15 81.0 2.0 98080.0 9.3 0.0 \n",
"8 280.0 1.0 320.0 6.2 270.15 74.0 2.0 98360.0 10.3 0.0 \n",
"9 220.0 1.0 290.0 2.6 269.65 72.0 2.0 98580.0 5.1 0.0 \n",
"10 100.0 1.0 350.0 3.1 270.45 79.0 2.0 98680.0 4.1 0.0 \n",
"11 300.0 3.0 350.0 5.1 268.55 70.0 2.0 98980.0 6.7 0.0 \n",
"12 130.0 1.0 10.0 4.6 267.45 60.0 2.0 99110.0 7.7 0.0 \n",
"13 150.0 3.0 10.0 5.7 267.45 59.0 2.0 99260.0 8.7 0.0 \n",
"14 140.0 1.0 50.0 2.6 268.15 70.0 2.0 99400.0 5.7 0.0 \n",
"\n",
" rr3 tc \n",
"0 0.0 7.5 \n",
"1 0.6 6.6 \n",
"2 0.4 6.4 \n",
"3 3.0 6.6 \n",
"4 0.8 5.9 \n",
"5 0.4 5.2 \n",
"6 0.0 3.5 \n",
"7 0.0 1.9 \n",
"8 0.0 1.1 \n",
"9 0.0 1.0 \n",
"10 0.0 0.5 \n",
"11 0.0 -0.3 \n",
"12 0.0 1.2 \n",
"13 0.0 1.5 \n",
"14 0.0 -0.8 "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": [
"<br>**After normalization :**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
"</style><table id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >tend</th> <th class=\"col_heading level0 col1\" >cod_tend</th> <th class=\"col_heading level0 col2\" >dd</th> <th class=\"col_heading level0 col3\" >ff</th> <th class=\"col_heading level0 col4\" >td</th> <th class=\"col_heading level0 col5\" >u</th> <th class=\"col_heading level0 col6\" >ww</th> <th class=\"col_heading level0 col7\" >pres</th> <th class=\"col_heading level0 col8\" >rafper</th> <th class=\"col_heading level0 col9\" >rr1</th> <th class=\"col_heading level0 col10\" >rr3</th> <th class=\"col_heading level0 col11\" >tc</th> </tr></thead><tbody>\n",
" <tr>\n",
" <th id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22level0_row0\" class=\"row_heading level0 row0\" >count</th>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row0_col0\" class=\"data row0 col0\" >25000.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row0_col1\" class=\"data row0 col1\" >25000.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row0_col2\" class=\"data row0 col2\" >25000.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row0_col3\" class=\"data row0 col3\" >25000.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row0_col4\" class=\"data row0 col4\" >25000.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row0_col5\" class=\"data row0 col5\" >25000.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row0_col6\" class=\"data row0 col6\" >25000.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row0_col7\" class=\"data row0 col7\" >25000.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row0_col8\" class=\"data row0 col8\" >25000.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row0_col9\" class=\"data row0 col9\" >25000.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row0_col10\" class=\"data row0 col10\" >25000.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row0_col11\" class=\"data row0 col11\" >25000.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22level0_row1\" class=\"row_heading level0 row1\" >mean</th>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row1_col0\" class=\"data row1 col0\" >-0.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row1_col1\" class=\"data row1 col1\" >-0.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row1_col2\" class=\"data row1 col2\" >0.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row1_col3\" class=\"data row1 col3\" >0.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row1_col4\" class=\"data row1 col4\" >-0.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row1_col5\" class=\"data row1 col5\" >0.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row1_col6\" class=\"data row1 col6\" >0.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row1_col7\" class=\"data row1 col7\" >-0.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row1_col8\" class=\"data row1 col8\" >-0.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row1_col9\" class=\"data row1 col9\" >-0.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row1_col10\" class=\"data row1 col10\" >0.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row1_col11\" class=\"data row1 col11\" >-0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22level0_row2\" class=\"row_heading level0 row2\" >std</th>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row2_col0\" class=\"data row2 col0\" >1.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row2_col1\" class=\"data row2 col1\" >1.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row2_col2\" class=\"data row2 col2\" >1.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row2_col3\" class=\"data row2 col3\" >1.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row2_col4\" class=\"data row2 col4\" >1.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row2_col5\" class=\"data row2 col5\" >1.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row2_col6\" class=\"data row2 col6\" >1.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row2_col7\" class=\"data row2 col7\" >1.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row2_col8\" class=\"data row2 col8\" >1.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row2_col9\" class=\"data row2 col9\" >1.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row2_col10\" class=\"data row2 col10\" >1.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row2_col11\" class=\"data row2 col11\" >1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22level0_row3\" class=\"row_heading level0 row3\" >min</th>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row3_col0\" class=\"data row3 col0\" >-6.80</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row3_col1\" class=\"data row3 col1\" >-1.59</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row3_col2\" class=\"data row3 col2\" >-1.75</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row3_col3\" class=\"data row3 col3\" >-1.37</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row3_col4\" class=\"data row3 col4\" >-5.18</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row3_col5\" class=\"data row3 col5\" >-3.82</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row3_col6\" class=\"data row3 col6\" >-0.52</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row3_col7\" class=\"data row3 col7\" >-4.94</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row3_col8\" class=\"data row3 col8\" >-1.64</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row3_col9\" class=\"data row3 col9\" >-0.31</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row3_col10\" class=\"data row3 col10\" >-0.27</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row3_col11\" class=\"data row3 col11\" >-3.03</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22level0_row4\" class=\"row_heading level0 row4\" >25%</th>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row4_col0\" class=\"data row4 col0\" >-0.64</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row4_col1\" class=\"data row4 col1\" >-0.85</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row4_col2\" class=\"data row4 col2\" >-0.64</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row4_col3\" class=\"data row4 col3\" >-0.76</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row4_col4\" class=\"data row4 col4\" >-0.72</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row4_col5\" class=\"data row4 col5\" >-0.71</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row4_col6\" class=\"data row4 col6\" >-0.42</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row4_col7\" class=\"data row4 col7\" >-0.55</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row4_col8\" class=\"data row4 col8\" >-0.69</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row4_col9\" class=\"data row4 col9\" >-0.15</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row4_col10\" class=\"data row4 col10\" >-0.20</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row4_col11\" class=\"data row4 col11\" >-0.75</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22level0_row5\" class=\"row_heading level0 row5\" >50%</th>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row5_col0\" class=\"data row5 col0\" >-0.00</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row5_col1\" class=\"data row5 col1\" >-0.48</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row5_col2\" class=\"data row5 col2\" >-0.12</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row5_col3\" class=\"data row5 col3\" >-0.19</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row5_col4\" class=\"data row5 col4\" >0.05</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row5_col5\" class=\"data row5 col5\" >0.18</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row5_col6\" class=\"data row5 col6\" >-0.42</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row5_col7\" class=\"data row5 col7\" >0.03</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row5_col8\" class=\"data row5 col8\" >-0.27</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row5_col9\" class=\"data row5 col9\" >-0.15</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row5_col10\" class=\"data row5 col10\" >-0.20</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row5_col11\" class=\"data row5 col11\" >-0.01</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22level0_row6\" class=\"row_heading level0 row6\" >75%</th>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row6_col0\" class=\"data row6 col0\" >0.63</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row6_col1\" class=\"data row6 col1\" >0.99</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row6_col2\" class=\"data row6 col2\" >1.08</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row6_col3\" class=\"data row6 col3\" >0.50</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row6_col4\" class=\"data row6 col4\" >0.79</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row6_col5\" class=\"data row6 col5\" >0.84</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row6_col6\" class=\"data row6 col6\" >-0.37</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row6_col7\" class=\"data row6 col7\" >0.61</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row6_col8\" class=\"data row6 col8\" >0.52</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row6_col9\" class=\"data row6 col9\" >-0.15</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row6_col10\" class=\"data row6 col10\" >-0.20</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row6_col11\" class=\"data row6 col11\" >0.72</td>\n",
" </tr>\n",
" <tr>\n",
" <th id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22level0_row7\" class=\"row_heading level0 row7\" >max</th>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row7_col0\" class=\"data row7 col0\" >7.16</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row7_col1\" class=\"data row7 col1\" >1.36</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row7_col2\" class=\"data row7 col2\" >1.34</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row7_col3\" class=\"data row7 col3\" >6.28</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row7_col4\" class=\"data row7 col4\" >2.40</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row7_col5\" class=\"data row7 col5\" >1.62</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row7_col6\" class=\"data row7 col6\" >4.46</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row7_col7\" class=\"data row7 col7\" >3.10</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row7_col8\" class=\"data row7 col8\" >6.29</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row7_col9\" class=\"data row7 col9\" >30.36</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row7_col10\" class=\"data row7 col10\" >31.27</td>\n",
" <td id=\"T_0b3f8a90_41e4_11eb_8992_174cdf497e22row7_col11\" class=\"data row7 col11\" >3.02</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
"<pandas.io.formats.style.Styler at 0x7f3858235d50>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": [
"<br>**Shapes :**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dataset : (29165, 14)\n",
"Train dataset : (25000, 12)\n",
"Test dataset : (4165, 12)\n"
]
}
],
"source": [
"dataset_dir = './data'\n",
"dataset_filename = 'synop-LYS.csv'\n",
"schema_filename = 'synop.json'\n",
"train_len = 25000\n",
"features = ['tend', 'cod_tend', 'dd', 'ff', 'td', 'u', 'ww', 'pres', 'rafper', 'rr1', 'rr3', 'tc']\n",
"features_len = len(features)\n",
"\n",
"# ---- Read dataset from ./data\n",
"\n",
"df = pd.read_csv(f'{dataset_dir}/{dataset_filename}', header=0, sep=';')\n",
"\n",
"# ---- Train / Test\n",
"\n",
"dataset_train = df.loc[ :train_len-1, features ]\n",
"dataset_test = df.loc[train_len:, features ]\n",
"pwk.subtitle('Train dataset example :')\n",
"display(dataset_train.head(15))\n",
"\n",
"# ---- Normalize, and convert to numpy array\n",
"\n",
"mean = dataset_train.mean()\n",
"std = dataset_train.std()\n",
"dataset_train = (dataset_train - mean) / std\n",
"dataset_test = (dataset_test - mean) / std\n",
"\n",
"pwk.subtitle('After normalization :')\n",
"display(dataset_train.describe().style.format(\"{0:.2f}\"))\n",
"\n",
"dataset_train = dataset_train.to_numpy()\n",
"dataset_test = dataset_test.to_numpy()\n",
"\n",
"pwk.subtitle('Shapes :')\n",
"print('Dataset : ',df.shape)\n",
"print('Train dataset : ',dataset_train.shape)\n",
"print('Test dataset : ',dataset_test.shape)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 2.2 - Prepare data generator"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"<br>**About the splitting of our dataset :**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Nombre de train batchs disponibles : 781\n",
"batch x shape : (32, 16, 12)\n",
"batch y shape : (32, 12)\n"
]
},
{
"data": {
"text/markdown": [
"<br>**What a batch looks like (x) :**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[-1.089 0.623 -1.753 -1.371 -0.22 0.952 2.56 -3.502 -0.56 -0.154 -0.199 -0.64 ]\n",
" [-1.361 0.623 -1.237 -0.964 -0.237 1.229 2.611 -3.702 -0.954 0.167 0.221 -0.75 ]\n",
" [ 0.089 -0.482 0.654 -0.517 -0.203 1.34 2.457 -3.688 -0.954 -0.154 0.081 -0.775]\n",
" [ 2.082 -0.482 0.912 -0.314 -0.153 1.396 2.046 -3.382 -0.14 -0.154 1.899 -0.75 ]\n",
" [ 2.535 -1.218 1.084 0.5 -0.321 1.285 0.557 -3.009 0.648 0.488 0.36 -0.836]\n",
" [ 4.347 -0.482 1.256 0.704 -0.522 1.118 2.56 -2.37 0.516 0.167 0.081 -0.921]\n",
" [ 4.801 -0.85 1.256 -0.11 -1.01 0.675 0.557 -1.664 0.254 -0.154 -0.199 -1.129]\n",
" [ 4.076 -0.85 1.17 1.151 -1.329 0.564 -0.418 -1.065 0.805 -0.154 -0.199 -1.324]\n",
" [ 2.535 -1.218 0.998 1.151 -1.665 0.176 -0.418 -0.692 1.068 -0.154 -0.199 -1.422]\n",
" [ 1.992 -1.218 0.74 -0.314 -1.749 0.065 -0.418 -0.399 -0.298 -0.154 -0.199 -1.434]\n",
" [ 0.904 -1.218 1.256 -0.11 -1.615 0.453 -0.418 -0.266 -0.56 -0.154 -0.199 -1.495]\n",
" [ 2.717 -0.482 1.256 0.704 -1.934 -0.046 -0.418 0.134 0.122 -0.154 -0.199 -1.593]\n",
" [ 1.176 -1.218 -1.667 0.5 -2.119 -0.601 -0.418 0.307 0.385 -0.154 -0.199 -1.41 ]\n",
" [ 1.357 -0.482 -1.667 0.948 -2.119 -0.656 -0.418 0.507 0.648 -0.154 -0.199 -1.373]\n",
" [ 1.267 -1.218 -1.323 -0.314 -2.001 -0.046 -0.418 0.693 -0.14 -0.154 -0.199 -1.654]\n",
" [-0.183 0.255 0.654 -0.964 -2.052 0.453 -0.418 0.666 -1.243 -0.154 -0.199 -1.861]]\n"
]
},
{
"data": {
"text/markdown": [
"<br>**What a batch looks like (y) :**"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[ 0.18 -1.218 0.568 -0.761 -2.052 0.675 -0.418 0.693 -1.243 -0.154 -0.199 -1.935]\n"
]
}
],
"source": [
"sequence_len = 16\n",
"batch_size = 32\n",
"\n",
"# ---- Train generator\n",
"train_generator = TimeseriesGenerator(dataset_train, dataset_train, length=sequence_len, batch_size=batch_size)\n",
"test_generator = TimeseriesGenerator(dataset_test, dataset_test, length=sequence_len, batch_size=batch_size)\n",
"\n",
"# ---- About\n",
"\n",
"pwk.subtitle('About the splitting of our dataset :')\n",
"\n",
"x,y=train_generator[0]\n",
"print(f'Nombre de train batchs disponibles : ', len(train_generator))\n",
"print('batch x shape : ',x.shape)\n",
"print('batch y shape : ',y.shape)\n",
"\n",
"x,y=train_generator[0]\n",
"pwk.subtitle('What a batch looks like (x) :')\n",
"np_print2(x[0] )\n",
"pwk.subtitle('What a batch looks like (y) :')\n",
"np_print2(y[0])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 3 - Create a model"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model: \"sequential\"\n",
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"lstm (LSTM) (None, 100) 45200 \n",
"_________________________________________________________________\n",
"dropout (Dropout) (None, 100) 0 \n",
"_________________________________________________________________\n",
"dense (Dense) (None, 12) 1212 \n",
"=================================================================\n",
"Total params: 46,412\n",
"Trainable params: 46,412\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
]
}
],
"source": [
"model = keras.models.Sequential()\n",
"model.add( keras.layers.InputLayer(input_shape=(sequence_len, features_len)) )\n",
"model.add( keras.layers.LSTM(100, activation='relu') )\n",
"model.add( keras.layers.Dropout(0.2) )\n",
"model.add( keras.layers.Dense(features_len) )\n",
"\n",
"model.summary()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Step 4 - Compile and run"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 4.1 - Callback"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"pwk.mkdir('./run/models')\n",
"save_dir = './run/models/best_model.h5'\n",
"bestmodel_callback = tf.keras.callbacks.ModelCheckpoint(filepath=save_dir, verbose=0, save_best_only=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 4.2 - Compile"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"model.compile(optimizer='adam', \n",
" loss='mse', \n",
" metrics = ['mae'] )"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 4.3 - Fit\n",
"6' with a CPU (laptop) \n",
"2' with a GPU"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/10\n",
"781/781 [==============================] - 39s 49ms/step - loss: 0.5982 - mae: 0.5025 - val_loss: 0.4670 - val_mae: 0.4259\n",
"Epoch 2/10\n",
"781/781 [==============================] - 38s 49ms/step - loss: 0.5033 - mae: 0.4368 - val_loss: 0.4431 - val_mae: 0.4058\n",
"Epoch 3/10\n",
"781/781 [==============================] - 38s 48ms/step - loss: 0.4817 - mae: 0.4189 - val_loss: 0.4261 - val_mae: 0.3870\n",
"Epoch 4/10\n",
"781/781 [==============================] - 38s 48ms/step - loss: 0.4699 - mae: 0.4088 - val_loss: 0.4176 - val_mae: 0.3818\n",
"Epoch 5/10\n",
"781/781 [==============================] - 38s 49ms/step - loss: 0.4604 - mae: 0.4013 - val_loss: 0.4106 - val_mae: 0.3738\n",
"Epoch 6/10\n",
"781/781 [==============================] - 38s 49ms/step - loss: 0.4512 - mae: 0.3962 - val_loss: 0.4073 - val_mae: 0.3690\n",
"Epoch 7/10\n",
"781/781 [==============================] - 38s 49ms/step - loss: 0.4454 - mae: 0.3923 - val_loss: 0.4077 - val_mae: 0.3703\n",
"Epoch 8/10\n",
"781/781 [==============================] - 38s 48ms/step - loss: 0.4395 - mae: 0.3899 - val_loss: 0.4099 - val_mae: 0.3703\n",
"Epoch 9/10\n",
"781/781 [==============================] - 38s 48ms/step - loss: 0.4350 - mae: 0.3865 - val_loss: 0.4125 - val_mae: 0.3709\n",
"Epoch 10/10\n",
"781/781 [==============================] - 37s 48ms/step - loss: 0.4314 - mae: 0.3854 - val_loss: 0.4090 - val_mae: 0.3749\n",
"CPU times: user 8min 37s, sys: 1min 38s, total: 10min 15s\n",
"Wall time: 6min 19s\n"
]
}
],
"source": [
"%%time\n",
"\n",
"history=model.fit_generator(train_generator, \n",
" epochs=10, \n",
" verbose=1,\n",
" validation_data = test_generator,\n",
" callbacks = [bestmodel_callback])"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div class=\"comment\">Saved: ./run/figs/SYNOP2-01-history_0</div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"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": {
"text/html": [
"<div class=\"comment\">Saved: ./run/figs/SYNOP2-01-history_1</div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"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": [
"pwk.plot_history(history,plot={'loss':['loss','val_loss'], 'mae':['mae','val_mae']}, save_as='01-history')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 5 - Predict"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 5.1 - Load model"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [],
"source": [
"loaded_model = tf.keras.models.load_model('./run/models/best_model.h5')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 5.2 Make a prediction\n",
"A basic prediction, with normalized values (so humanly not very understandable)"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div class=\"comment\">Saved: ./run/figs/SYNOP2-02-prediction-norm</div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1080x1152 with 12 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"s=random.randint(0,len(dataset_test)-sequence_len)\n",
"\n",
"sequence = dataset_test[s:s+sequence_len]\n",
"sequence_true = dataset_test[s:s+sequence_len+1]\n",
"\n",
"pred = loaded_model.predict( np.array([sequence]) )\n",
"\n",
"# ---- Show result\n",
"pwk.plot_multivariate_serie(sequence_true, predictions=pred, labels=features, save_as='02-prediction-norm')\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 5.3 Real prediction\n",
"We are now going to make a true prediction, with an un-normalized result"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div class=\"comment\">Saved: ./run/figs/SYNOP2-03-prediction</div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 3024x2304 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Gap between prediction and reality : 0.40 °C\n"
]
}
],
"source": [
"def denormalize(mean,std,seq):\n",
" nseq = seq.copy()\n",
" for i,s in enumerate(nseq):\n",
" s = s*std + mean\n",
" nseq[i]=s\n",
" return nseq\n",
"\n",
"\n",
"# ---- Get a sequence\n",
"\n",
"i=random.randint(0,len(dataset_test)-sequence_len)\n",
"sequence = dataset_test[i:i+sequence_len]\n",
"sequence_true = dataset_test[i:i+sequence_len+1]\n",
"\n",
"# ---- Prediction\n",
"\n",
"pred = loaded_model.predict( np.array([sequence]) )\n",
"\n",
"# ---- De-normalization\n",
"\n",
"sequence_true = denormalize(mean,std, sequence_true)\n",
"pred = denormalize(mean,std, pred)\n",
"\n",
"# ---- Show it\n",
"feat=11\n",
"\n",
"pwk.plot_multivariate_serie(sequence_true, predictions=pred, labels=features, only_features=[feat],width=14, height=8, save_as='03-prediction')\n",
"\n",
"delta_deg=abs(sequence_true[-1][feat]-pred[-1][feat])\n",
"print(f'Gap between prediction and reality : {delta_deg:.2f} °C')\n"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"End time is : Saturday 19 December 2020, 11:24:13\n",
"Duration is : 00:01:25 329ms\n",
"This notebook ends here\n"
]
}
],
"source": [
"pwk.end()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"<img width=\"80px\" src=\"../fidle/img/00-Fidle-logo-01.svg\"></img>"
]
}
],
"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": "3.7.7"
}
},
"nbformat": 4,
"nbformat_minor": 4
}