{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\scipy\\__init__.py:155: UserWarning: A NumPy version >=1.18.5 and <1.25.0 is required for this version of SciPy (detected version 1.26.3\n",
      "  warnings.warn(f\"A NumPy version >={np_minversion} and <{np_maxversion}\"\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From C:\\Users\\Admin\\AppData\\Roaming\\Python\\Python39\\site-packages\\keras\\src\\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import classification_report, confusion_matrix\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "vocab_size = 10000"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Vocab Size is the unique words (approximation) contained in the dataset. (https://www.tensorflow.org/api_docs/python/tf/keras/datasets/imdb/load_data#:~:text=only%20consider%20the%20top%2010%2C000%20most%20common%20words%2C)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "(x_train, y_train), (x_test, y_test) = tf.keras.datasets.imdb.load_data(num_words=vocab_size)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(((25000,), (25000,)), ((25000,), (25000,)))"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(x_train.shape, y_train.shape), (x_test.shape, y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1,\n",
       " 14,\n",
       " 22,\n",
       " 16,\n",
       " 43,\n",
       " 530,\n",
       " 973,\n",
       " 1622,\n",
       " 1385,\n",
       " 65,\n",
       " 458,\n",
       " 4468,\n",
       " 66,\n",
       " 3941,\n",
       " 4,\n",
       " 173,\n",
       " 36,\n",
       " 256,\n",
       " 5,\n",
       " 25,\n",
       " 100,\n",
       " 43,\n",
       " 838,\n",
       " 112,\n",
       " 50,\n",
       " 670,\n",
       " 2,\n",
       " 9,\n",
       " 35,\n",
       " 480,\n",
       " 284,\n",
       " 5,\n",
       " 150,\n",
       " 4,\n",
       " 172,\n",
       " 112,\n",
       " 167,\n",
       " 2,\n",
       " 336,\n",
       " 385,\n",
       " 39,\n",
       " 4,\n",
       " 172,\n",
       " 4536,\n",
       " 1111,\n",
       " 17,\n",
       " 546,\n",
       " 38,\n",
       " 13,\n",
       " 447,\n",
       " 4,\n",
       " 192,\n",
       " 50,\n",
       " 16,\n",
       " 6,\n",
       " 147,\n",
       " 2025,\n",
       " 19,\n",
       " 14,\n",
       " 22,\n",
       " 4,\n",
       " 1920,\n",
       " 4613,\n",
       " 469,\n",
       " 4,\n",
       " 22,\n",
       " 71,\n",
       " 87,\n",
       " 12,\n",
       " 16,\n",
       " 43,\n",
       " 530,\n",
       " 38,\n",
       " 76,\n",
       " 15,\n",
       " 13,\n",
       " 1247,\n",
       " 4,\n",
       " 22,\n",
       " 17,\n",
       " 515,\n",
       " 17,\n",
       " 12,\n",
       " 16,\n",
       " 626,\n",
       " 18,\n",
       " 2,\n",
       " 5,\n",
       " 62,\n",
       " 386,\n",
       " 12,\n",
       " 8,\n",
       " 316,\n",
       " 8,\n",
       " 106,\n",
       " 5,\n",
       " 4,\n",
       " 2223,\n",
       " 5244,\n",
       " 16,\n",
       " 480,\n",
       " 66,\n",
       " 3785,\n",
       " 33,\n",
       " 4,\n",
       " 130,\n",
       " 12,\n",
       " 16,\n",
       " 38,\n",
       " 619,\n",
       " 5,\n",
       " 25,\n",
       " 124,\n",
       " 51,\n",
       " 36,\n",
       " 135,\n",
       " 48,\n",
       " 25,\n",
       " 1415,\n",
       " 33,\n",
       " 6,\n",
       " 22,\n",
       " 12,\n",
       " 215,\n",
       " 28,\n",
       " 77,\n",
       " 52,\n",
       " 5,\n",
       " 14,\n",
       " 407,\n",
       " 16,\n",
       " 82,\n",
       " 2,\n",
       " 8,\n",
       " 4,\n",
       " 107,\n",
       " 117,\n",
       " 5952,\n",
       " 15,\n",
       " 256,\n",
       " 4,\n",
       " 2,\n",
       " 7,\n",
       " 3766,\n",
       " 5,\n",
       " 723,\n",
       " 36,\n",
       " 71,\n",
       " 43,\n",
       " 530,\n",
       " 476,\n",
       " 26,\n",
       " 400,\n",
       " 317,\n",
       " 46,\n",
       " 7,\n",
       " 4,\n",
       " 2,\n",
       " 1029,\n",
       " 13,\n",
       " 104,\n",
       " 88,\n",
       " 4,\n",
       " 381,\n",
       " 15,\n",
       " 297,\n",
       " 98,\n",
       " 32,\n",
       " 2071,\n",
       " 56,\n",
       " 26,\n",
       " 141,\n",
       " 6,\n",
       " 194,\n",
       " 7486,\n",
       " 18,\n",
       " 4,\n",
       " 226,\n",
       " 22,\n",
       " 21,\n",
       " 134,\n",
       " 476,\n",
       " 26,\n",
       " 480,\n",
       " 5,\n",
       " 144,\n",
       " 30,\n",
       " 5535,\n",
       " 18,\n",
       " 51,\n",
       " 36,\n",
       " 28,\n",
       " 224,\n",
       " 92,\n",
       " 25,\n",
       " 104,\n",
       " 4,\n",
       " 226,\n",
       " 65,\n",
       " 16,\n",
       " 38,\n",
       " 1334,\n",
       " 88,\n",
       " 12,\n",
       " 16,\n",
       " 283,\n",
       " 5,\n",
       " 16,\n",
       " 4472,\n",
       " 113,\n",
       " 103,\n",
       " 32,\n",
       " 15,\n",
       " 16,\n",
       " 5345,\n",
       " 19,\n",
       " 178,\n",
       " 32]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "239"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "int(np.mean(np.array([len(row) for row in x_train])).round())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is the average length of a review in the dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "max_length = int(np.mean(np.array([len(row) for row in x_train])).round())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train = tf.keras.preprocessing.sequence.pad_sequences(x_train, maxlen=max_length)\n",
    "x_test = tf.keras.preprocessing.sequence.pad_sequences(x_test, maxlen=max_length)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(((25000, 239), (25000,)), ((25000, 239), (25000,)))"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(x_train.shape, y_train.shape), (x_test.shape, y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From C:\\Users\\Admin\\AppData\\Roaming\\Python\\Python39\\site-packages\\keras\\src\\backend.py:873: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "model = tf.keras.Sequential([\n",
    "    tf.keras.layers.Embedding(vocab_size, 512, input_length=max_length),\n",
    "    tf.keras.layers.Flatten(),\n",
    "    tf.keras.layers.Dense(16, activation=tf.keras.activations.relu),\n",
    "    tf.keras.layers.Dense(1, activation='sigmoid')\n",
    "])"
   ]
  },
  {
   "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",
      " embedding (Embedding)       (None, 239, 512)          5120000   \n",
      "                                                                 \n",
      " flatten (Flatten)           (None, 122368)            0         \n",
      "                                                                 \n",
      " dense (Dense)               (None, 16)                1957904   \n",
      "                                                                 \n",
      " dense_1 (Dense)             (None, 1)                 17        \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 7077921 (27.00 MB)\n",
      "Trainable params: 7077921 (27.00 MB)\n",
      "Non-trainable params: 0 (0.00 Byte)\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.0001), loss='binary_crossentropy', metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/5\n",
      "WARNING:tensorflow:From C:\\Users\\Admin\\AppData\\Roaming\\Python\\Python39\\site-packages\\keras\\src\\utils\\tf_utils.py:492: The name tf.ragged.RaggedTensorValue is deprecated. Please use tf.compat.v1.ragged.RaggedTensorValue instead.\n",
      "\n",
      "WARNING:tensorflow:From C:\\Users\\Admin\\AppData\\Roaming\\Python\\Python39\\site-packages\\keras\\src\\engine\\base_layer_utils.py:384: The name tf.executing_eagerly_outside_functions is deprecated. Please use tf.compat.v1.executing_eagerly_outside_functions instead.\n",
      "\n",
      "196/196 [==============================] - 32s 155ms/step - loss: 0.6753 - accuracy: 0.5732 - val_loss: 0.6068 - val_accuracy: 0.6938\n",
      "Epoch 2/5\n",
      "196/196 [==============================] - 29s 150ms/step - loss: 0.4221 - accuracy: 0.8478 - val_loss: 0.3719 - val_accuracy: 0.8502\n",
      "Epoch 3/5\n",
      "196/196 [==============================] - 30s 153ms/step - loss: 0.2378 - accuracy: 0.9257 - val_loss: 0.3230 - val_accuracy: 0.8629\n",
      "Epoch 4/5\n",
      "196/196 [==============================] - 30s 151ms/step - loss: 0.1558 - accuracy: 0.9598 - val_loss: 0.2968 - val_accuracy: 0.8725\n",
      "Epoch 5/5\n",
      "196/196 [==============================] - 29s 147ms/step - loss: 0.1029 - accuracy: 0.9812 - val_loss: 0.2958 - val_accuracy: 0.8728\n"
     ]
    }
   ],
   "source": [
    "history = model.fit(x_train, y_train, batch_size=128, epochs=5, validation_data=(x_test, y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "782/782 [==============================] - 6s 7ms/step - loss: 0.2958 - accuracy: 0.8728\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[0.2958017885684967, 0.8728399872779846]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "results = model.evaluate(x_test, y_test)\n",
    "results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x700 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame(history.history)[['loss', 'val_loss']].plot(figsize=(10,7))\n",
    "plt.title(\"Loss Curves\")\n",
    "plt.xticks([0, 1, 2, 3, 4])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x700 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame(history.history)[['accuracy', 'val_accuracy']].plot(figsize=(10,7))\n",
    "plt.title(\"Accuracy Curves\")\n",
    "plt.xticks([0, 1, 2, 3, 4])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "782/782 [==============================] - 6s 7ms/step\n"
     ]
    }
   ],
   "source": [
    "y_pred = model.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "predicted_labels = (y_pred > 0.5).astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "    Negative       0.90      0.84      0.87     12500\n",
      "    Positive       0.85      0.90      0.88     12500\n",
      "\n",
      "    accuracy                           0.87     25000\n",
      "   macro avg       0.87      0.87      0.87     25000\n",
      "weighted avg       0.87      0.87      0.87     25000\n",
      "\n"
     ]
    }
   ],
   "source": [
    "report = classification_report(y_test, predicted_labels, target_names=['Negative', 'Positive'])\n",
    "print(report)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cm = confusion_matrix(y_test, predicted_labels)\n",
    "sns.heatmap(cm, cmap='crest', annot=True, fmt=\".0f\")\n",
    "plt.title(\"Confusion Matrix\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}