is_dnn/labworks/LW4/new.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "#device_name=tf.test.gpu_device_name()\n",
    "#if device_name != '/device:GPU:0':\n",
    "  #raise SystemError('GPUdevicenotfound')\n",
    "#print('FoundGPUat:{}'.format(device_name))\n",
    "#загрузкадатасета\n",
    "from keras.datasets import imdb\n",
    "vocabulary_size=5000\n",
    "index_from=3\n",
    "(X_train,y_train),(X_test,y_test)=imdb.load_data(path=\"imdb.npz\",\n",
    "                                                 num_words=vocabulary_size,\n",
    "                                                 skip_top=0,\n",
    "                                                 maxlen=None,\n",
    "                                                 seed=4*8 - 1,\n",
    "                                                 start_char=1,\n",
    "                                                 oov_char=2,\n",
    "                                                 index_from=index_from)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(X_train.shape)\n",
    "print(y_train.shape)\n",
    "print(X_test.shape)\n",
    "print(y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "word_to_id=imdb.get_word_index()\n",
    "#уточнениесловаря\n",
    "word_to_id={key:(value + index_from) for key,value in word_to_id.items()}\n",
    "word_to_id[\"<PAD>\"]=0\n",
    "word_to_id[\"<START>\"]=1\n",
    "word_to_id[\"<UNK>\"]=2\n",
    "word_to_id[\"<UNUSED>\"]=3\n",
    "#созданиеобратногословаря\"индекс:слово\"\n",
    "id_to_word={value:key for key,value in word_to_id.items()}\n",
    "some_number=4*8-1\n",
    "review_as_text=''.join(id_to_word[id] for id in X_train[some_number])\n",
    "print(X_train[some_number])\n",
    "print(review_as_text)\n",
    "print(len(X_train[some_number]))\n",
    "if y_train[some_number] == 1:\n",
    "  class_label='Positive'\n",
    "else:\n",
    "  class_label='Negative'\n",
    "print('Review class:', y_train[some_number], f'({class_label})')\n",
    "print(len(max(X_train, key=len)))\n",
    "print(len(min(X_train, key=len)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "from keras.preprocessing import sequence\n",
    "max_words=500\n",
    "X_train=sequence.pad_sequences(X_train, maxlen=max_words, value=0, padding='pre', truncating='post')\n",
    "X_test=sequence.pad_sequences(X_test, maxlen=max_words, value=0, padding='pre', truncating='post')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.preprocessing import sequence\n",
    "max_words=500\n",
    "X_train=sequence.pad_sequences(X_train, maxlen=max_words, value=0, padding='pre', truncating='post')\n",
    "X_test=sequence.pad_sequences(X_test, maxlen=max_words, value=0, padding='pre', truncating='post')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "word_to_id=imdb.get_word_index()\n",
    "#уточнениесловаря\n",
    "word_to_id={key:(value + index_from) for key,value in word_to_id.items()}\n",
    "word_to_id[\"<PAD>\"]=0\n",
    "word_to_id[\"<START>\"]=1\n",
    "word_to_id[\"<UNK>\"]=2\n",
    "word_to_id[\"<UNUSED>\"]=3\n",
    "#созданиеобратногословаря\"индекс:слово\"\n",
    "id_to_word={value:key for key,value in word_to_id.items()}\n",
    "some_number=4*8-1\n",
    "review_as_text=''.join(id_to_word[id] for id in X_train[some_number])\n",
    "print(X_train[some_number])\n",
    "print(review_as_text)\n",
    "print(len(X_train[some_number]))\n",
    "if y_train[some_number] == 1:\n",
    "  class_label='Positive'\n",
    "else:\n",
    "  class_label='Negative'\n",
    "print('Review class:', y_train[some_number], f'({class_label})')\n",
    "print(len(max(X_train, key=len)))\n",
    "print(len(min(X_train, key=len)))\n",
    "\n",
    "print(\"x_train: \", X_train)\n",
    "print(X_train.shape)\n",
    "print(\"x_test: \", X_test)\n",
    "print(X_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.models import Sequential\n",
    "from keras.layers import Embedding, LSTM, Dropout, Dense\n",
    "\n",
    "model=Sequential()\n",
    "model.add(Embedding(input_dim=len(word_to_id), output_dim=32, input_length=500))\n",
    "model.add(LSTM(units=90))\n",
    "model.add(Dropout(rate=0.4))\n",
    "model.add(Dense(units=1, activation='sigmoid'))\n",
    "model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n",
    "H=model.fit(X_train, y_train, validation_split=0.1, epochs=5, batch_size=32)\n",
    "print(model.summary())\n",
    "scores=model.evaluate(X_test, y_test)\n",
    "print(\"LOss: \", scores[0])\n",
    "print(\"Accuracy: \", scores[1])\n",
    "test_result=model.predict(X_test)\n",
    "predicted_labels=[1 if test_result[i,0]>=0.5 else 0 for i in range(len(test_result))]\n",
    "from sklearn.metrics import classification_report\n",
    "print(classification_report(y_test, predicted_labels, labels=[0,1], target_names=[\"Negative\", \"Positive\"]))"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}