{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "3f0e4dc5",
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow_datasets as tfds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "cf67fff4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1mDownloading and preparing dataset Unknown size (download: Unknown size, generated: Unknown size, total: Unknown size) to C:\\Users\\PC\\tensorflow_datasets\\imdb_reviews\\plain_text\\1.0.0...\u001b[0m\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a7b64b1fc98b43e5b89b9e528ea07b25",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Dl Completed...: 0 url [00:00, ? url/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "21c118e765e44287a6d29c1d9921d7a3",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Dl Size...: 0 MiB [00:00, ? MiB/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating splits...:   0%|          | 0/3 [00:00<?, ? splits/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating train examples...: 0 examples [00:00, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Shuffling imdb_reviews-train.tfrecord...:   0%|          | 0/25000 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating test examples...: 0 examples [00:00, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Shuffling imdb_reviews-test.tfrecord...:   0%|          | 0/25000 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating unsupervised examples...: 0 examples [00:00, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Shuffling imdb_reviews-unsupervised.tfrecord...:   0%|          | 0/50000 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1mDataset imdb_reviews downloaded and prepared to C:\\Users\\PC\\tensorflow_datasets\\imdb_reviews\\plain_text\\1.0.0. Subsequent calls will reuse this data.\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "#imdb, info= tfds.load('imdb_reviews', with_info=True, as_supervised=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "16309217",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_data, test_data= imdb['train'], imdb['test']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "acf53763",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e9169c88",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e0af2f79",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "training_sentences = []\n",
    "training_labels = []\n",
    "\n",
    "testing_sentences = []\n",
    "testing_labels = []\n",
    "\n",
    "# str(s.tonumpy()) is needed in Python3 instead of just s.numpy()\n",
    "for s,l in train_data:\n",
    "    training_sentences.append(s.numpy().decode('utf8'))\n",
    "    training_labels.append(l.numpy())\n",
    "  \n",
    "for s,l in test_data:\n",
    "    testing_sentences.append(s.numpy().decode('utf8'))\n",
    "    testing_labels.append(l.numpy())\n",
    "  \n",
    "training_labels_final = np.array(training_labels)\n",
    "testing_labels_final = np.array(testing_labels)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d6a9c40c",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "72cec8f1",
   "metadata": {},
   "outputs": [],
   "source": [
    "vocab_size = 10000\n",
    "embedding_dim = 16\n",
    "max_length = 120\n",
    "trunc_type='post'\n",
    "oov_tok = \"<OOV>\"\n",
    "\n",
    "\n",
    "from tensorflow.keras.preprocessing.text import Tokenizer\n",
    "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
    "\n",
    "tokenizer = Tokenizer(num_words = vocab_size, oov_token=oov_tok)\n",
    "tokenizer.fit_on_texts(training_sentences)\n",
    "word_index = tokenizer.word_index\n",
    "sequences = tokenizer.texts_to_sequences(training_sentences)\n",
    "padded = pad_sequences(sequences,maxlen=max_length, truncating=trunc_type)\n",
    "\n",
    "testing_sequences = tokenizer.texts_to_sequences(testing_sentences)\n",
    "testing_padded = pad_sequences(testing_sequences,maxlen=max_length)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "c0dcf0fb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? this is the kind of film for a snowy sunday afternoon when the rest of the world can go ahead with its own business as you <OOV> into a big arm chair and <OOV> for a couple of hours wonderful performances from cher and nicolas cage as always gently row the plot along there are no <OOV> to cross no dangerous waters just a warm and witty <OOV> through new york life at its best a family film in every sense and one that deserves the praise it received\n",
      "This is the kind of film for a snowy Sunday afternoon when the rest of the world can go ahead with its own business as you descend into a big arm-chair and mellow for a couple of hours. Wonderful performances from Cher and Nicolas Cage (as always) gently row the plot along. There are no rapids to cross, no dangerous waters, just a warm and witty paddle through New York life at its best. A family film in every sense and one that deserves the praise it received.\n"
     ]
    }
   ],
   "source": [
    "reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])\n",
    "\n",
    "def decode_review(text):\n",
    "    return ' '.join([reverse_word_index.get(i, '?') for i in text])\n",
    "\n",
    "print(decode_review(padded[3]))\n",
    "print(training_sentences[3])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e686566e",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "d1eb1544",
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "37439b38",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential\"\n",
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "embedding (Embedding)        (None, 120, 16)           160000    \n",
      "_________________________________________________________________\n",
      "flatten (Flatten)            (None, 1920)              0         \n",
      "_________________________________________________________________\n",
      "dense (Dense)                (None, 6)                 11526     \n",
      "_________________________________________________________________\n",
      "dense_1 (Dense)              (None, 1)                 7         \n",
      "=================================================================\n",
      "Total params: 171,533\n",
      "Trainable params: 171,533\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model = tf.keras.Sequential([\n",
    "    tf.keras.layers.Embedding(vocab_size, embedding_dim, input_length=max_length),\n",
    "    tf.keras.layers.Flatten(),\n",
    "    tf.keras.layers.Dense(6, activation='relu'),\n",
    "    tf.keras.layers.Dense(1, activation='sigmoid')\n",
    "])\n",
    "model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])\n",
    "model.summary()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ec82f16a",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "8f99ce40",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n",
      "782/782 [==============================] - 3s 4ms/step - loss: 0.4897 - accuracy: 0.7482 - val_loss: 0.3403 - val_accuracy: 0.8504\n",
      "Epoch 2/10\n",
      "782/782 [==============================] - 4s 5ms/step - loss: 0.2309 - accuracy: 0.9116 - val_loss: 0.3690 - val_accuracy: 0.8396\n",
      "Epoch 3/10\n",
      "782/782 [==============================] - 4s 5ms/step - loss: 0.0766 - accuracy: 0.9824 - val_loss: 0.4656 - val_accuracy: 0.8250\n",
      "Epoch 4/10\n",
      "782/782 [==============================] - 4s 4ms/step - loss: 0.0169 - accuracy: 0.9982 - val_loss: 0.5381 - val_accuracy: 0.8250\n",
      "Epoch 5/10\n",
      "782/782 [==============================] - 3s 4ms/step - loss: 0.0044 - accuracy: 0.9997 - val_loss: 0.5966 - val_accuracy: 0.8249\n",
      "Epoch 6/10\n",
      "782/782 [==============================] - 3s 4ms/step - loss: 0.0015 - accuracy: 1.0000 - val_loss: 0.6405 - val_accuracy: 0.8264\n",
      "Epoch 7/10\n",
      "782/782 [==============================] - 3s 4ms/step - loss: 7.7152e-04 - accuracy: 1.0000 - val_loss: 0.6814 - val_accuracy: 0.8265\n",
      "Epoch 8/10\n",
      "782/782 [==============================] - 4s 5ms/step - loss: 5.2565e-04 - accuracy: 1.0000 - val_loss: 0.7277 - val_accuracy: 0.8255\n",
      "Epoch 9/10\n",
      "782/782 [==============================] - 4s 5ms/step - loss: 2.6606e-04 - accuracy: 1.0000 - val_loss: 0.7623 - val_accuracy: 0.8263\n",
      "Epoch 10/10\n",
      "782/782 [==============================] - 3s 4ms/step - loss: 1.4898e-04 - accuracy: 1.0000 - val_loss: 0.7965 - val_accuracy: 0.8258\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<tensorflow.python.keras.callbacks.History at 0x202067b78e0>"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "num_epochs = 10\n",
    "model.fit(padded, training_labels_final, epochs=num_epochs, validation_data=(testing_padded, testing_labels_final))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bfbc9d49",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "82624b40",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "5f51dcbc",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(10000, 16)\n"
     ]
    }
   ],
   "source": [
    "e = model.layers[0]\n",
    "weights = e.get_weights()[0]\n",
    "print(weights.shape) # shape: (vocab_size, embedding_dim)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d80bb061",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "3819a423",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[11, 64, 102, 12, 7, 478, 1200]]\n"
     ]
    }
   ],
   "source": [
    "sentence = \"I really think this is amazing. honest.\"\n",
    "sequence = tokenizer.texts_to_sequences([sentence])\n",
    "print(sequence)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "27fe916d",
   "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}