01-Embedding-Keras.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<img width=\"800px\" src=\"../fidle/img/00-Fidle-header-01.svg\"></img>\n",
    "\n",
    "# <!-- TITLE --> [IMDB1] - Text embedding with IMDB\n",
    "<!-- DESC --> A very classical example of word embedding for text classification (sentiment analysis)\n",
    "<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
    "\n",
    "## Objectives :\n",
    " - The objective is to guess whether film reviews are **positive or negative** based on the analysis of the text. \n",
    " - Understand the management of **textual data** and **sentiment analysis**\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": [
    {
     "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",
       "\n",
       "</style>\n",
       "\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "FIDLE 2020 - Practical Work Module\n",
      "Version              : 0.57 DEV\n",
      "Run time             : Thursday 10 September 2020, 16:34:04\n",
      "TensorFlow version   : 2.2.0\n",
      "Keras version        : 2.3.0-tf\n",
      "Current place        : Fidle at IDRIS\n",
      "Dataset dir          : /gpfswork/rech/mlh/commun/datasets\n",
      "Update keras cache   : Done\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,sys,h5py,json\n",
    "from importlib import reload\n",
    "\n",
    "sys.path.append('..')\n",
    "import fidle.pwk as ooo\n",
    "\n",
    "place, datasets_dir = 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",
    "# Choose if you want to load dataset directly from keras (small size <20M)\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, )\n",
    "# Or you can use the same pre-loaded dataset\n",
    "#\n",
    "# with  h5py.File(f'{datasets_dir}/IMDB/origine/dataset_imdb.h5','r') as f:\n",
    "#        x_train = f['x_train'][:]\n",
    "#        y_train = f['y_train'][:]\n",
    "#        x_test  = f['x_test'][:]\n",
    "#        y_test  = f['y_test'][:]"
   ]
  },
  {
   "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",
      "440 : hope\n",
      "441 : entertaining\n",
      "442 : she's\n",
      "443 : mr\n",
      "444 : overall\n",
      "445 : evil\n",
      "446 : called\n",
      "447 : loved\n",
      "448 : based\n",
      "449 : oh\n",
      "450 : several\n",
      "451 : fans\n",
      "452 : mother\n",
      "453 : drama\n",
      "454 : beginning\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",
    "for k in range(440,455):print(f'{k:2d} : {index_word[k]}' )\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 NN"
   ]
  },
  {
   "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.histplot([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 (padding)\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 (For future use but not mandatory if at GRICAD or IDRIS)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saved.\n"
     ]
    }
   ],
   "source": [
    "# ---- To write h5 dataset in a test place (optional)\n",
    "#      For small tests only !\n",
    "#\n",
    "output_dir = './data'\n",
    "ooo.mkdir(output_dir)\n",
    "\n",
    "\n",
    "with h5py.File(f'{output_dir}/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(f'{output_dir}/word_index.json', 'w') as fp:\n",
    "    json.dump(word_index, fp)\n",
    "\n",
    "with open(f'{output_dir}/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=32):\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.GlobalAveragePooling1D())\n",
    "    model.add(keras.layers.Dense(dense_vector_size, activation='relu'))\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": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential\"\n",
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "embedding (Embedding)        (None, 256, 32)           320000    \n",
      "_________________________________________________________________\n",
      "global_average_pooling1d (Gl (None, 32)                0         \n",
      "_________________________________________________________________\n",
      "dense (Dense)                (None, 32)                1056      \n",
      "_________________________________________________________________\n",
      "dense_1 (Dense)              (None, 1)                 33        \n",
      "=================================================================\n",
      "Total params: 321,089\n",
      "Trainable params: 321,089\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model = get_model(32)\n",
    "\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 5.2 - Add callback"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/30\n",
      "49/49 [==============================] - 1s 23ms/step - loss: 0.6884 - accuracy: 0.6085 - val_loss: 0.6783 - val_accuracy: 0.6292\n",
      "Epoch 2/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.6497 - accuracy: 0.7349 - val_loss: 0.6142 - val_accuracy: 0.7631\n",
      "Epoch 3/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.5548 - accuracy: 0.8092 - val_loss: 0.5105 - val_accuracy: 0.8291\n",
      "Epoch 4/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.4420 - accuracy: 0.8572 - val_loss: 0.4182 - val_accuracy: 0.8461\n",
      "Epoch 5/30\n",
      "49/49 [==============================] - 1s 17ms/step - loss: 0.3576 - accuracy: 0.8790 - val_loss: 0.3624 - val_accuracy: 0.8609\n",
      "Epoch 6/30\n",
      "49/49 [==============================] - 1s 17ms/step - loss: 0.3047 - accuracy: 0.8928 - val_loss: 0.3303 - val_accuracy: 0.8690\n",
      "Epoch 7/30\n",
      "49/49 [==============================] - 1s 17ms/step - loss: 0.2689 - accuracy: 0.9030 - val_loss: 0.3116 - val_accuracy: 0.8744\n",
      "Epoch 8/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.2426 - accuracy: 0.9122 - val_loss: 0.3002 - val_accuracy: 0.8775\n",
      "Epoch 9/30\n",
      "49/49 [==============================] - 1s 17ms/step - loss: 0.2219 - accuracy: 0.9204 - val_loss: 0.2924 - val_accuracy: 0.8802\n",
      "Epoch 10/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.2054 - accuracy: 0.9275 - val_loss: 0.2883 - val_accuracy: 0.8826\n",
      "Epoch 11/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.1910 - accuracy: 0.9310 - val_loss: 0.2881 - val_accuracy: 0.8820\n",
      "Epoch 12/30\n",
      "49/49 [==============================] - 1s 17ms/step - loss: 0.1784 - accuracy: 0.9374 - val_loss: 0.2873 - val_accuracy: 0.8830\n",
      "Epoch 13/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.1663 - accuracy: 0.9423 - val_loss: 0.2919 - val_accuracy: 0.8810\n",
      "Epoch 14/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.1570 - accuracy: 0.9472 - val_loss: 0.2921 - val_accuracy: 0.8826\n",
      "Epoch 15/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.1478 - accuracy: 0.9508 - val_loss: 0.2968 - val_accuracy: 0.8816\n",
      "Epoch 16/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.1401 - accuracy: 0.9532 - val_loss: 0.3015 - val_accuracy: 0.8815\n",
      "Epoch 17/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.1326 - accuracy: 0.9566 - val_loss: 0.3077 - val_accuracy: 0.8782\n",
      "Epoch 18/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.1254 - accuracy: 0.9595 - val_loss: 0.3155 - val_accuracy: 0.8795\n",
      "Epoch 19/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.1192 - accuracy: 0.9627 - val_loss: 0.3214 - val_accuracy: 0.8761\n",
      "Epoch 20/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.1129 - accuracy: 0.9647 - val_loss: 0.3292 - val_accuracy: 0.8745\n",
      "Epoch 21/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.1074 - accuracy: 0.9672 - val_loss: 0.3374 - val_accuracy: 0.8735\n",
      "Epoch 22/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.1019 - accuracy: 0.9698 - val_loss: 0.3483 - val_accuracy: 0.8698\n",
      "Epoch 23/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.0975 - accuracy: 0.9715 - val_loss: 0.3538 - val_accuracy: 0.8726\n",
      "Epoch 24/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.0924 - accuracy: 0.9731 - val_loss: 0.3640 - val_accuracy: 0.8701\n",
      "Epoch 25/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.0883 - accuracy: 0.9755 - val_loss: 0.3732 - val_accuracy: 0.8703\n",
      "Epoch 26/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.0838 - accuracy: 0.9776 - val_loss: 0.3825 - val_accuracy: 0.8686\n",
      "Epoch 27/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.0800 - accuracy: 0.9792 - val_loss: 0.3939 - val_accuracy: 0.8678\n",
      "Epoch 28/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.0765 - accuracy: 0.9807 - val_loss: 0.4021 - val_accuracy: 0.8666\n",
      "Epoch 29/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.0730 - accuracy: 0.9821 - val_loss: 0.4218 - val_accuracy: 0.8646\n",
      "Epoch 30/30\n",
      "49/49 [==============================] - 1s 16ms/step - loss: 0.0696 - accuracy: 0.9835 - val_loss: 0.4242 - val_accuracy: 0.8646\n",
      "CPU times: user 37.1 s, sys: 1.5 s, total: 38.6 s\n",
      "Wall time: 25.7 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "\n",
    "n_epochs   = 30\n",
    "batch_size = 512\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": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "x_test / loss      : 0.2873\n",
      "x_test / accuracy  : 0.8830\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_08c4932e_f373_11ea_b3b0_0cc47af5c729row0_col0 {\n",
       "            background-color:  #ebf3eb;\n",
       "            color:  #000000;\n",
       "            font-size:  12pt;\n",
       "        }    #T_08c4932e_f373_11ea_b3b0_0cc47af5c729row0_col1 {\n",
       "            background-color:  #ebf3eb;\n",
       "            color:  #000000;\n",
       "            font-size:  12pt;\n",
       "        }    #T_08c4932e_f373_11ea_b3b0_0cc47af5c729row1_col0 {\n",
       "            background-color:  #ebf3eb;\n",
       "            color:  #000000;\n",
       "            font-size:  12pt;\n",
       "        }    #T_08c4932e_f373_11ea_b3b0_0cc47af5c729row1_col1 {\n",
       "            background-color:  #ebf3eb;\n",
       "            color:  #000000;\n",
       "            font-size:  12pt;\n",
       "        }</style><table id=\"T_08c4932e_f373_11ea_b3b0_0cc47af5c729\" ><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_08c4932e_f373_11ea_b3b0_0cc47af5c729level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
       "                        <td id=\"T_08c4932e_f373_11ea_b3b0_0cc47af5c729row0_col0\" class=\"data row0 col0\" >1.00</td>\n",
       "                        <td id=\"T_08c4932e_f373_11ea_b3b0_0cc47af5c729row0_col1\" class=\"data row0 col1\" >0.00</td>\n",
       "            </tr>\n",
       "            <tr>\n",
       "                        <th id=\"T_08c4932e_f373_11ea_b3b0_0cc47af5c729level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
       "                        <td id=\"T_08c4932e_f373_11ea_b3b0_0cc47af5c729row1_col0\" class=\"data row1 col0\" >1.00</td>\n",
       "                        <td id=\"T_08c4932e_f373_11ea_b3b0_0cc47af5c729row1_col1\" class=\"data row1 col1\" >0.00</td>\n",
       "            </tr>\n",
       "    </tbody></table>"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x14d92668afd0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "model = keras.models.load_model('./run/models/best_model.h5')\n",
    "\n",
    "# ---- Evaluate\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)           Deprecated after 01/01/2021 !!\n",
    "\n",
    "y_sigmoid = model.predict(x_test)\n",
    "y_pred    = np.argmax(y_sigmoid, axis=-1)\n",
    "\n",
    "# ooo.display_confusion_matrix(y_test,y_pred,labels=range(2),color='orange',font_size='20pt')\n",
    "ooo.display_confusion_matrix(y_test,y_pred,labels=range(2))\n"
   ]
  },
  {
   "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
}