dl_model1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Mudit\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\smart_open\\ssh.py:34: UserWarning: paramiko missing, opening SSH/SCP/SFTP paths will be disabled.  `pip install paramiko` to suppress\n",
      "  warnings.warn('paramiko missing, opening SSH/SCP/SFTP paths will be disabled.  `pip install paramiko` to suppress')\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import nltk\n",
    "import matplotlib.pyplot as plt\n",
    "import sklearn\n",
    "import tensorflow as tf\n",
    "import gensim\n",
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Our first approach to using Deep Learning to predict the author of a text will be to use a shallow neural network \n",
    "#with non-linear activation functions\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(r'Data/dataset.csv',names=['Author','Text'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Text'] = df['Text'].map(lambda x: re.sub('\\r|\\n|\\'','',x))\n",
    "df['Text'] = df['Text'].map(lambda x: re.sub(r'--\\d\\d\\d-\\d\\d\\d-\\d\\d\\d\\d','',x))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "from nltk.corpus import stopwords\n",
    "stop_words = set(stopwords.words('english'))\n",
    "stop_words_subset = set([x for x in stop_words if 3 <= len(x) <= 5])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "#text_copy = df['Text'].copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "def remove_stopwords(x): #x is the string input\n",
    "    word_set = x.split(' ')\n",
    "    for word in word_set:\n",
    "        if word in stop_words:\n",
    "            word_set.remove(word)\n",
    "    return ' '.join(word_set)\n",
    "            \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Removing stopwords\n",
    "df['Text'] = df['Text'].map(lambda x: remove_stopwords(x))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Stratified train-test split \n",
    "\n",
    "X = df['Text']\n",
    "y = df['Author']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y,\n",
    "                                                    stratify=y, \n",
    "                                                    test_size=0.25)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "#1. Using sklearn's CountVectorizer(i.e. A Bag of words model) to get a feature vector for our article text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Building a simple bag-of-words model\n",
    "\n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "\n",
    "vectorizer = CountVectorizer(min_df=0.1, lowercase=False) #Only consider words with a minimum frequency of 0.1, dont convert words to lowercase"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "CountVectorizer(analyzer='word', binary=False, decode_error='strict',\n",
       "        dtype=<class 'numpy.int64'>, encoding='utf-8', input='content',\n",
       "        lowercase=False, max_df=1.0, max_features=None, min_df=0.1,\n",
       "        ngram_range=(1, 1), preprocessor=None, stop_words=None,\n",
       "        strip_accents=None, token_pattern='(?u)\\\\b\\\\w\\\\w+\\\\b',\n",
       "        tokenizer=None, vocabulary=None)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vectorizer.fit(df['Text'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "444"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(vectorizer.vocabulary_) #The vector has length of 444 i.e. the top 444 words in the corpus have been taken to make feature vectors out of"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train = vectorizer.transform(X_train.values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test = vectorizer.transform(X_test.values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1250, 444)"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(X_test).toarray().shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Building the neural network model. For starters, we try a simple shallow NN and observe the outcome\n",
    "\n",
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras import layers\n",
    "from tensorflow.keras.utils import plot_model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_dimension = X_train.shape[1] #This specifies the number of neurons in the input layer, in this case 444\n",
    "\n",
    "#Using Keras' sequential API\n",
    "model = Sequential()\n",
    "model.add(layers.Dense(100, input_dim=input_dimension, activation='relu'))\n",
    "model.add(layers.Dense(50, activation='softmax'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "optimizer must be an instance of tf.train.Optimizer, not a <class 'str'>",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-21-dc52499e6a70>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m model.compile(loss='categorical_crossentropy', \n\u001b[0;32m      2\u001b[0m                \u001b[0moptimizer\u001b[0m\u001b[1;33m=\u001b[0m \u001b[1;34m'adam'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m             metrics=['accuracy'])\n\u001b[0m\u001b[0;32m      4\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m \u001b[1;31m#Using Adam optimizer and the categorical cross-entropy loss function\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\tensorflow\\python\\training\\checkpointable\\base.py\u001b[0m in \u001b[0;36m_method_wrapper\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m    472\u001b[0m     \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_setattr_tracking\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mFalse\u001b[0m  \u001b[1;31m# pylint: disable=protected-access\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    473\u001b[0m     \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 474\u001b[1;33m       \u001b[0mmethod\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    475\u001b[0m     \u001b[1;32mfinally\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    476\u001b[0m       \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_setattr_tracking\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mprevious_value\u001b[0m  \u001b[1;31m# pylint: disable=protected-access\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\tensorflow\\python\\keras\\engine\\training.py\u001b[0m in \u001b[0;36mcompile\u001b[1;34m(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, target_tensors, distribute, **kwargs)\u001b[0m\n\u001b[0;32m    408\u001b[0m       raise ValueError(\n\u001b[0;32m    409\u001b[0m           \u001b[1;34m'optimizer must be an instance of tf.train.Optimizer, not '\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 410\u001b[1;33m           'a %s' % type(optimizer))\n\u001b[0m\u001b[0;32m    411\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    412\u001b[0m     \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0moptimizer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0moptimizers\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0moptimizer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mValueError\u001b[0m: optimizer must be an instance of tf.train.Optimizer, not a <class 'str'>"
     ]
    }
   ],
   "source": [
    "model.compile(loss='categorical_crossentropy', \n",
    "               optimizer= 'adam', \n",
    "            metrics=['accuracy'])\n",
    "\n",
    "#Using Adam optimizer and the categorical cross-entropy loss function"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "dense (Dense)                (None, 100)               44500     \n",
      "_________________________________________________________________\n",
      "dense_1 (Dense)              (None, 50)                5050      \n",
      "=================================================================\n",
      "Total params: 49,550\n",
      "Trainable params: 49,550\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LabelBinarizer(neg_label=0, pos_label=1, sparse_output=False)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#The target column has string categorical values. Convert this to discrete numeric values using Keras' LabelEncoder\n",
    "from sklearn.preprocessing import LabelBinarizer\n",
    "encoder = LabelBinarizer()\n",
    "encoder.fit(df['Author'].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "#encoder.transform(df['Author'])\n",
    "#author_copy = df['Author'].copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_train = encoder.transform(y_train)\n",
    "y_test = encoder.transform(y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "history = model.fit(X_train, y_train,\n",
    "                     epochs=100,\n",
    "                     verbose=False,\n",
    "                     validation_data=(X_test, y_test),\n",
    "                    batch_size=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'batch_size': 10,\n",
       " 'epochs': 100,\n",
       " 'steps': None,\n",
       " 'samples': 3750,\n",
       " 'verbose': False,\n",
       " 'do_validation': True,\n",
       " 'metrics': ['loss', 'acc', 'val_loss', 'val_acc'],\n",
       " 'validation_steps': None}"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#dir(history)\n",
    "#history.model\n",
    "history.params"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "loss, accuracy = model.evaluate(X_train, y_train, verbose=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "On the training set: loss of 3.085614833253203e-07 and accuracy achieved: 1.0\n"
     ]
    }
   ],
   "source": [
    "print(f'On the training set: loss of {loss} and accuracy achieved: {accuracy}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Testing Accuracy:  0.7528\n"
     ]
    }
   ],
   "source": [
    "#A validation set accuracy of 100% suggests that our model has overfitted. \n",
    "#The accuracy on the testing set comes out to be:\n",
    "loss, accuracy = model.evaluate(X_test, y_test, verbose=False)\n",
    "print(\"Testing Accuracy:  {:.4f}\".format(accuracy))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "SHALLOW NEURAL NETWORK WITH RELU ACTIVATION AT THE HIDDEN LAYER AND SOFTMAX AT THE OUTPUT LAYER ACHIEVES 98.9% ACCURACY"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Trying a model with two hidden layers:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_two = Sequential()\n",
    "model_two.add(layers.Dense(100,input_dim = input_dimension, activation = 'relu'))\n",
    "model_two.add(layers.Dense(75,activation = 'relu'))\n",
    "model_two.add(layers.Dense(50, activation='softmax'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_two.compile(loss='categorical_crossentropy', \n",
    "               optimizer='adam', \n",
    "            metrics=['accuracy'])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "history = model_two.fit(X_train, y_train,\n",
    "                     epochs=100,\n",
    "                     verbose=False,\n",
    "                     validation_data=(X_test, y_test),\n",
    "                    batch_size=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "dense_2 (Dense)              (None, 100)               44500     \n",
      "_________________________________________________________________\n",
      "dense_3 (Dense)              (None, 75)                7575      \n",
      "_________________________________________________________________\n",
      "dense_4 (Dense)              (None, 50)                3800      \n",
      "=================================================================\n",
      "Total params: 55,875\n",
      "Trainable params: 55,875\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model_two.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3750/3750 [==============================] - 1s 176us/step\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[0.0007415856130576382, 0.9997333333333334]"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_two.evaluate(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1250/1250 [==============================] - 0s 100us/step\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[2.1614733142852782, 0.7016]"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_two.evaluate(X_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#As the validation accuracy is quite a bit greater than the training accuracy, this suggests that we the model has overfitted."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "#We will now try a simpler model, with the aim of brining down the validation loss to somewhere closer to the training data loss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_three = Sequential()\n",
    "model_three.add(layers.Dense(100,input_dim = input_dimension, activation = 'relu'))\n",
    "model_three.add(layers.Dense(75,activation = 'relu'))\n",
    "model_three.add(layers.Dense(50, activation='softmax'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_three.compile(loss='categorical_crossentropy', \n",
    "               optimizer='sgd', \n",
    "            metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "#The model also tests the accuracy on the validation data set per epoch\n",
    "\n",
    "history = model_three.fit(X_train, y_train,\n",
    "                     epochs=200,\n",
    "                     verbose=False,\n",
    "                     validation_data=(X_test, y_test),\n",
    "                    batch_size=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3750/3750 [==============================] - 1s 186us/step\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[0.0015797486290956538, 1.0]"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_three.evaluate(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1250/1250 [==============================] - 0s 368us/step\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[1.7865182443752885, 0.704]"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_three.evaluate(X_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3750, 444)"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.toarray().shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "'Sequential' object has no attribute 'evaulate'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-89-dcb73983f907>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mmodel_two\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mevaulate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX_test\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0my_test\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;31mAttributeError\u001b[0m: 'Sequential' object has no attribute 'evaulate'"
     ]
    }
   ],
   "source": [
    "model_two.evaulate(X_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Part 1: Obtain word embedding representation of the articles. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Using gensim's pre-trained Word2Vec model for obtaining word-embeddings for the text data:\n",
    "from gensim.models import Word2Vec\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "sentences = ' '.join(X_train)\n",
    "more_sentences = ' '.join(X_test)\n",
    "sentences = sentences + more_sentences"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "142922"
      ]
     },
     "execution_count": 130,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = Word2Vec(sentences,min_count = 10,window = 3, size = 100) #Taking too long to train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "metadata": {},
   "outputs": [],
   "source": [
    "#model = gensim.models.KeyedVectors.load_word2vec_format(\"glove.6B.300d.txt\", binary=False)\n",
    "#Maybe use a pre-trained model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "sample_inp = vectorizer.transform(df['Text'].iloc[1].split(' ')).toarray()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 1, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 1, ..., 0, 0, 0],\n",
       "       ...,\n",
       "       [0, 0, 0, ..., 1, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 1, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 1]])"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "encoder.transform(encoder.classes_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['__call__',\n",
       " '__class__',\n",
       " '__delattr__',\n",
       " '__dict__',\n",
       " '__dir__',\n",
       " '__doc__',\n",
       " '__eq__',\n",
       " '__format__',\n",
       " '__ge__',\n",
       " '__getattribute__',\n",
       " '__gt__',\n",
       " '__hash__',\n",
       " '__init__',\n",
       " '__init_subclass__',\n",
       " '__le__',\n",
       " '__lt__',\n",
       " '__module__',\n",
       " '__ne__',\n",
       " '__new__',\n",
       " '__reduce__',\n",
       " '__reduce_ex__',\n",
       " '__repr__',\n",
       " '__setattr__',\n",
       " '__sizeof__',\n",
       " '__str__',\n",
       " '__subclasshook__',\n",
       " '__weakref__',\n",
       " '_activity_regularizer',\n",
       " '_add_inbound_node',\n",
       " '_add_unique_metric_name',\n",
       " '_add_variable_with_custom_getter',\n",
       " '_assert_input_compatibility',\n",
       " '_base_init',\n",
       " '_build_input_shape',\n",
       " '_cache_output_metric_attributes',\n",
       " '_call_and_compute_mask',\n",
       " '_call_convention',\n",
       " '_check_trainable_weights_consistency',\n",
       " '_checkpoint_dependencies',\n",
       " '_checkpointable_saver',\n",
       " '_collected_trainable_weights',\n",
       " '_compute_output_and_mask_jointly',\n",
       " '_compute_previous_mask',\n",
       " '_dataset_iterator_cache',\n",
       " '_deferred_dependencies',\n",
       " '_determine_call_convention',\n",
       " '_distribution_standardize_user_data',\n",
       " '_distribution_strategy',\n",
       " '_dtype',\n",
       " '_eager_set_inputs',\n",
       " '_expects_training_arg',\n",
       " '_extra_variables',\n",
       " '_feed_input_names',\n",
       " '_feed_input_shapes',\n",
       " '_feed_inputs',\n",
       " '_feed_loss_fns',\n",
       " '_feed_output_names',\n",
       " '_feed_output_shapes',\n",
       " '_feed_outputs',\n",
       " '_feed_sample_weight_modes',\n",
       " '_feed_sample_weights',\n",
       " '_feed_targets',\n",
       " '_function_kwargs',\n",
       " '_gather_saveables_for_checkpoint',\n",
       " '_get_callback_model',\n",
       " '_get_iterator_get_next_tensors',\n",
       " '_get_node_attribute_at_index',\n",
       " '_graph',\n",
       " '_grouped_model',\n",
       " '_handle_activity_regularization',\n",
       " '_handle_deferred_dependencies',\n",
       " '_handle_metrics',\n",
       " '_handle_per_output_metrics',\n",
       " '_handle_weight_regularization',\n",
       " '_inbound_nodes',\n",
       " '_init_graph_network',\n",
       " '_init_metric_attributes',\n",
       " '_init_set_name',\n",
       " '_init_subclassed_network',\n",
       " '_input_coordinates',\n",
       " '_input_layers',\n",
       " '_inputs_from_call_args',\n",
       " '_is_compiled',\n",
       " '_is_graph_network',\n",
       " '_iterator_get_next',\n",
       " '_layers',\n",
       " '_layers_by_depth',\n",
       " '_lookup_dependency',\n",
       " '_losses',\n",
       " '_make_callback_model',\n",
       " '_make_predict_function',\n",
       " '_make_test_function',\n",
       " '_make_train_function',\n",
       " '_maybe_initialize_checkpointable',\n",
       " '_name',\n",
       " '_name_based_attribute_restore',\n",
       " '_name_based_restores',\n",
       " '_name_scope',\n",
       " '_network_nodes',\n",
       " '_no_dependency',\n",
       " '_nodes_by_depth',\n",
       " '_outbound_nodes',\n",
       " '_output_coordinates',\n",
       " '_output_layers',\n",
       " '_output_mask_cache',\n",
       " '_output_shape_cache',\n",
       " '_output_tensor_cache',\n",
       " '_per_output_metrics',\n",
       " '_per_output_weighted_metrics',\n",
       " '_preload_simple_restoration',\n",
       " '_restore_from_checkpoint_position',\n",
       " '_reuse',\n",
       " '_run_internal_graph',\n",
       " '_scope',\n",
       " '_set_connectivity_metadata_',\n",
       " '_set_inputs',\n",
       " '_set_learning_phase_metadata',\n",
       " '_set_mask_metadata',\n",
       " '_set_metric_attributes',\n",
       " '_set_per_output_metric_attributes',\n",
       " '_set_sample_weight_attributes',\n",
       " '_setattr_tracking',\n",
       " '_single_restoration_from_checkpoint_position',\n",
       " '_standardize_user_data',\n",
       " '_standardize_weights',\n",
       " '_symbolic_set_inputs',\n",
       " '_tf_api_names',\n",
       " '_tf_api_names_v1',\n",
       " '_track_checkpointable',\n",
       " '_track_layers',\n",
       " '_unconditional_checkpoint_dependencies',\n",
       " '_unconditional_deferred_dependencies',\n",
       " '_unconditional_dependency_names',\n",
       " '_unfiltered_losses',\n",
       " '_unfiltered_updates',\n",
       " '_update_uid',\n",
       " '_updated_config',\n",
       " '_updates',\n",
       " 'activity_regularizer',\n",
       " 'add',\n",
       " 'add_loss',\n",
       " 'add_update',\n",
       " 'add_variable',\n",
       " 'add_weight',\n",
       " 'apply',\n",
       " 'build',\n",
       " 'built',\n",
       " 'call',\n",
       " 'compile',\n",
       " 'compute_mask',\n",
       " 'compute_output_shape',\n",
       " 'count_params',\n",
       " 'dtype',\n",
       " 'evaluate',\n",
       " 'evaluate_generator',\n",
       " 'fit',\n",
       " 'fit_generator',\n",
       " 'from_config',\n",
       " 'get_config',\n",
       " 'get_input_at',\n",
       " 'get_input_mask_at',\n",
       " 'get_input_shape_at',\n",
       " 'get_layer',\n",
       " 'get_losses_for',\n",
       " 'get_output_at',\n",
       " 'get_output_mask_at',\n",
       " 'get_output_shape_at',\n",
       " 'get_updates_for',\n",
       " 'get_weights',\n",
       " 'history',\n",
       " 'inbound_nodes',\n",
       " 'input',\n",
       " 'input_mask',\n",
       " 'input_names',\n",
       " 'input_shape',\n",
       " 'input_spec',\n",
       " 'inputs',\n",
       " 'layers',\n",
       " 'load_weights',\n",
       " 'loss',\n",
       " 'loss_functions',\n",
       " 'loss_weights',\n",
       " 'loss_weights_list',\n",
       " 'losses',\n",
       " 'metrics',\n",
       " 'metrics_names',\n",
       " 'metrics_tensors',\n",
       " 'metrics_updates',\n",
       " 'name',\n",
       " 'non_trainable_variables',\n",
       " 'non_trainable_weights',\n",
       " 'optimizer',\n",
       " 'outbound_nodes',\n",
       " 'output',\n",
       " 'output_mask',\n",
       " 'output_names',\n",
       " 'output_shape',\n",
       " 'outputs',\n",
       " 'pop',\n",
       " 'predict',\n",
       " 'predict_classes',\n",
       " 'predict_function',\n",
       " 'predict_generator',\n",
       " 'predict_on_batch',\n",
       " 'predict_proba',\n",
       " 'reset_states',\n",
       " 'sample_weight_mode',\n",
       " 'sample_weight_modes',\n",
       " 'sample_weights',\n",
       " 'save',\n",
       " 'save_weights',\n",
       " 'set_weights',\n",
       " 'state_updates',\n",
       " 'stateful',\n",
       " 'stateful_metric_functions',\n",
       " 'stateful_metric_names',\n",
       " 'stop_training',\n",
       " 'summary',\n",
       " 'supports_masking',\n",
       " 'target_tensors',\n",
       " 'targets',\n",
       " 'test_function',\n",
       " 'test_on_batch',\n",
       " 'to_json',\n",
       " 'to_yaml',\n",
       " 'total_loss',\n",
       " 'train_function',\n",
       " 'train_on_batch',\n",
       " 'trainable',\n",
       " 'trainable_variables',\n",
       " 'trainable_weights',\n",
       " 'updates',\n",
       " 'uses_learning_phase',\n",
       " 'variables',\n",
       " 'weighted_metrics',\n",
       " 'weights']"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dir(model_two)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.21312012, 0.05426535, 0.00128296, ..., 0.10208776, 0.01495079,\n",
       "        0.00639352],\n",
       "       [0.18153667, 0.02038331, 0.00097499, ..., 0.07116063, 0.1217784 ,\n",
       "        0.00437038],\n",
       "       [0.21312012, 0.05426535, 0.00128296, ..., 0.10208776, 0.01495079,\n",
       "        0.00639352],\n",
       "       ...,\n",
       "       [0.21312012, 0.05426535, 0.00128296, ..., 0.10208776, 0.01495079,\n",
       "        0.00639352],\n",
       "       [0.21312012, 0.05426535, 0.00128296, ..., 0.10208776, 0.01495079,\n",
       "        0.00639352],\n",
       "       [0.21312012, 0.05426535, 0.00128296, ..., 0.10208776, 0.01495079,\n",
       "        0.00639352]], dtype=float32)"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_two.predict(sample_inp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(237, 444)"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sample_inp.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1749"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(df['Text'].iloc[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3750, 444)"
      ]
     },
     "execution_count": 81,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.toarray().shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 0,  0,  0,  1,  0,  0,  0,  0,  0,  0,  0,  0,  0,  2,  1,  0,  0,\n",
       "        0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  2,  1,  1,  1,  0,  0,  0,\n",
       "        2,  0,  0,  0,  0,  0,  0,  0,  0,  1,  0,  0,  0,  0,  1,  0,  0,\n",
       "        0,  0,  0,  0,  1,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  2,  0,\n",
       "        1,  0,  0,  0,  0,  0,  0,  3,  0,  0,  1,  1,  0,  0,  2,  0,  0,\n",
       "        0,  0,  1,  0,  0,  0,  0,  0,  0,  0,  1,  1,  2,  2,  0,  0,  1,\n",
       "        0,  0,  0,  0,  1,  0,  0,  0,  0,  0,  1,  0,  0,  0,  1,  3,  0,\n",
       "        0,  0,  0,  0,  0,  0,  0,  0,  1,  5,  0,  0,  0,  0,  1,  0,  0,\n",
       "        0,  0,  0,  0,  1,  0,  0,  0,  2,  2,  0,  1,  0,  0,  0,  0,  0,\n",
       "        2,  0,  1,  0,  0,  0,  0,  0,  0,  2,  0,  0,  0,  0,  0,  0,  0,\n",
       "        0,  0,  0,  0,  0,  1,  0,  0,  1,  1,  1,  0,  0,  0,  0,  0,  0,\n",
       "        0,  0,  1,  1,  0,  0,  0,  0,  1,  0,  0,  0,  0,  0,  0,  0,  0,\n",
       "        1,  3,  0,  2,  0,  0,  0,  0,  0,  0,  1,  0,  1,  0,  0,  0,  0,\n",
       "        1,  0,  0,  0,  0,  0,  0,  1,  0,  0,  1,  0,  0,  0,  1,  0,  0,\n",
       "        0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  1,  0,  0,  0,\n",
       "        1,  0,  0,  0,  0,  0,  0,  0,  1,  0,  0,  0,  0,  2,  0,  0,  0,\n",
       "        0,  0,  3,  0,  1,  1,  1,  0,  0,  0,  0,  0,  0,  1,  7,  1,  0,\n",
       "        1,  0,  1,  0,  1,  0,  0,  0,  0,  0,  1,  0,  0,  0,  0,  0,  0,\n",
       "        0,  0,  0,  0,  0,  2,  1,  2,  0,  0,  0,  0,  0,  0,  1,  0,  0,\n",
       "        2,  0,  0,  1,  0,  0,  1,  0,  0,  0,  0,  0,  0,  2,  0,  0,  0,\n",
       "        0,  0,  0,  0,  1,  0,  1,  0,  0,  0,  0,  9,  1,  0,  0,  0,  0,\n",
       "        0,  0,  0,  0,  2,  5,  0,  0,  1,  0,  2,  0,  0,  0,  0,  0,  0,\n",
       "        0,  0,  0,  0,  0,  1,  0,  1,  0,  0,  0,  0,  0,  0,  0,  0,  0,\n",
       "        1,  0,  0,  0, 12,  0,  0,  1,  1,  0,  0,  0,  0,  0,  2,  0,  0,\n",
       "        0,  1,  0,  0,  1,  0,  0,  0,  0,  0,  0,  0,  0,  0,  1,  0,  0,\n",
       "        0,  0,  1,  0,  0,  0,  0,  0,  1,  1,  0,  0,  0,  0,  0,  1,  1,\n",
       "        0,  0], dtype=int64)"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.toarray()[0,:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1250, 444)"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.toarray().shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Check accuracy on a subset of the test set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0, 0, 0, ..., 1, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 1, ..., 1, 0, 0],\n",
       "       ...,\n",
       "       [2, 0, 0, ..., 0, 0, 1],\n",
       "       [0, 0, 0, ..., 3, 1, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0]], dtype=int64)"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test.toarray().shape\n",
    "arr = X_test.toarray()\n",
    "inps =[arr[i,:] for i in range(10)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Error when checking input: expected dense_5_input to have shape (444,) but got array with shape (1,)",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-106-14810246bc8b>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mmodel_two\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0minps\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\tensorflow\\python\\keras\\engine\\training.py\u001b[0m in \u001b[0;36mpredict\u001b[1;34m(self, x, batch_size, verbose, steps, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[0;32m   1862\u001b[0m     \u001b[1;31m# means that we end up calculating it twice which we should avoid.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1863\u001b[0m     x, _, _ = self._standardize_user_data(\n\u001b[1;32m-> 1864\u001b[1;33m         x, check_steps=True, steps_name='steps', steps=steps)\n\u001b[0m\u001b[0;32m   1865\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1866\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mcontext\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexecuting_eagerly\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\tensorflow\\python\\keras\\engine\\training.py\u001b[0m in \u001b[0;36m_standardize_user_data\u001b[1;34m(self, x, y, sample_weight, class_weight, batch_size, check_steps, steps_name, steps, validation_split)\u001b[0m\n\u001b[0;32m    990\u001b[0m         \u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msample_weight\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnext_element\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    991\u001b[0m     x, y, sample_weights = self._standardize_weights(x, y, sample_weight,\n\u001b[1;32m--> 992\u001b[1;33m                                                      class_weight, batch_size)\n\u001b[0m\u001b[0;32m    993\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msample_weights\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    994\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\tensorflow\\python\\keras\\engine\\training.py\u001b[0m in \u001b[0;36m_standardize_weights\u001b[1;34m(self, x, y, sample_weight, class_weight, batch_size)\u001b[0m\n\u001b[0;32m   1115\u001b[0m         \u001b[0mfeed_input_shapes\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1116\u001b[0m         \u001b[0mcheck_batch_axis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m  \u001b[1;31m# Don't enforce the batch size.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1117\u001b[1;33m         exception_prefix='input')\n\u001b[0m\u001b[0;32m   1118\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1119\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0my\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\tensorflow\\python\\keras\\engine\\training_utils.py\u001b[0m in \u001b[0;36mstandardize_input_data\u001b[1;34m(data, names, shapes, check_batch_axis, exception_prefix)\u001b[0m\n\u001b[0;32m    330\u001b[0m                 \u001b[1;34m'Error when checking '\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mexception_prefix\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;34m': expected '\u001b[0m \u001b[1;33m+\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    331\u001b[0m                 \u001b[0mnames\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;34m' to have shape '\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mstr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m+\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 332\u001b[1;33m                 ' but got array with shape ' + str(data_shape))\n\u001b[0m\u001b[0;32m    333\u001b[0m   \u001b[1;32mreturn\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    334\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mValueError\u001b[0m: Error when checking input: expected dense_5_input to have shape (444,) but got array with shape (1,)"
     ]
    }
   ],
   "source": [
    "model_two.predict(inps[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 array(s), but instead got the following list of 10 arrays: [array([[ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n    ...",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-108-80fbe29f12a2>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mmodel_two\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0minps\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\tensorflow\\python\\keras\\engine\\training.py\u001b[0m in \u001b[0;36mpredict\u001b[1;34m(self, x, batch_size, verbose, steps, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[0;32m   1862\u001b[0m     \u001b[1;31m# means that we end up calculating it twice which we should avoid.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1863\u001b[0m     x, _, _ = self._standardize_user_data(\n\u001b[1;32m-> 1864\u001b[1;33m         x, check_steps=True, steps_name='steps', steps=steps)\n\u001b[0m\u001b[0;32m   1865\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1866\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mcontext\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexecuting_eagerly\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\tensorflow\\python\\keras\\engine\\training.py\u001b[0m in \u001b[0;36m_standardize_user_data\u001b[1;34m(self, x, y, sample_weight, class_weight, batch_size, check_steps, steps_name, steps, validation_split)\u001b[0m\n\u001b[0;32m    990\u001b[0m         \u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msample_weight\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnext_element\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    991\u001b[0m     x, y, sample_weights = self._standardize_weights(x, y, sample_weight,\n\u001b[1;32m--> 992\u001b[1;33m                                                      class_weight, batch_size)\n\u001b[0m\u001b[0;32m    993\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msample_weights\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    994\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\tensorflow\\python\\keras\\engine\\training.py\u001b[0m in \u001b[0;36m_standardize_weights\u001b[1;34m(self, x, y, sample_weight, class_weight, batch_size)\u001b[0m\n\u001b[0;32m   1115\u001b[0m         \u001b[0mfeed_input_shapes\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1116\u001b[0m         \u001b[0mcheck_batch_axis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m  \u001b[1;31m# Don't enforce the batch size.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1117\u001b[1;33m         exception_prefix='input')\n\u001b[0m\u001b[0;32m   1118\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1119\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0my\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\tensorflow\\python\\keras\\engine\\training_utils.py\u001b[0m in \u001b[0;36mstandardize_input_data\u001b[1;34m(data, names, shapes, check_batch_axis, exception_prefix)\u001b[0m\n\u001b[0;32m    291\u001b[0m                        \u001b[1;34m'Expected to see '\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mstr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnames\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;34m' array(s), '\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    292\u001b[0m                        \u001b[1;34m'but instead got the following list of '\u001b[0m \u001b[1;33m+\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 293\u001b[1;33m                        str(len(data)) + ' arrays: ' + str(data)[:200] + '...')\n\u001b[0m\u001b[0;32m    294\u001b[0m     \u001b[1;32melif\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnames\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    295\u001b[0m       raise ValueError(\n",
      "\u001b[1;31mValueError\u001b[0m: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 array(s), but instead got the following list of 10 arrays: [array([[ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n       [ 0],\n    ..."
     ]
    }
   ],
   "source": [
    "model_two.predict(inps)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'int'> 0\n",
      "<class 'pandas.core.series.Series'> Author                                        AaronPressman\n",
      "Text      U.S. Senators on Tuesday sharply criticized a ...\n",
      "Name: 0, dtype: object\n"
     ]
    }
   ],
   "source": [
    "for x in range(1):\n",
    "    row = next(df.iterrows()) #df.iterrows creates a generator which churns out two item tuples, the first item is index, and\n",
    "    #the second is a Data Series\n",
    "    for item in row:\n",
    "        print(type(item),item)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['__class__',\n",
       " '__delattr__',\n",
       " '__dict__',\n",
       " '__dir__',\n",
       " '__doc__',\n",
       " '__eq__',\n",
       " '__format__',\n",
       " '__ge__',\n",
       " '__getattribute__',\n",
       " '__getstate__',\n",
       " '__gt__',\n",
       " '__hash__',\n",
       " '__init__',\n",
       " '__init_subclass__',\n",
       " '__le__',\n",
       " '__lt__',\n",
       " '__module__',\n",
       " '__ne__',\n",
       " '__new__',\n",
       " '__reduce__',\n",
       " '__reduce_ex__',\n",
       " '__repr__',\n",
       " '__setattr__',\n",
       " '__setstate__',\n",
       " '__sizeof__',\n",
       " '__str__',\n",
       " '__subclasshook__',\n",
       " '__weakref__',\n",
       " '_char_ngrams',\n",
       " '_char_wb_ngrams',\n",
       " '_check_stop_words_consistency',\n",
       " '_check_vocabulary',\n",
       " '_count_vocab',\n",
       " '_get_param_names',\n",
       " '_limit_features',\n",
       " '_sort_features',\n",
       " '_stop_words_id',\n",
       " '_validate_params',\n",
       " '_validate_vocabulary',\n",
       " '_white_spaces',\n",
       " '_word_ngrams',\n",
       " 'analyzer',\n",
       " 'binary',\n",
       " 'build_analyzer',\n",
       " 'build_preprocessor',\n",
       " 'build_tokenizer',\n",
       " 'decode',\n",
       " 'decode_error',\n",
       " 'dtype',\n",
       " 'encoding',\n",
       " 'fit',\n",
       " 'fit_transform',\n",
       " 'fixed_vocabulary_',\n",
       " 'get_feature_names',\n",
       " 'get_params',\n",
       " 'get_stop_words',\n",
       " 'input',\n",
       " 'inverse_transform',\n",
       " 'lowercase',\n",
       " 'max_df',\n",
       " 'max_features',\n",
       " 'min_df',\n",
       " 'ngram_range',\n",
       " 'preprocessor',\n",
       " 'set_params',\n",
       " 'stop_words',\n",
       " 'stop_words_',\n",
       " 'strip_accents',\n",
       " 'token_pattern',\n",
       " 'tokenizer',\n",
       " 'transform',\n",
       " 'vocabulary',\n",
       " 'vocabulary_']"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dir(vectorizer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "'Series' object has no attribute 'indices'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-35-f01378ee35b5>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mvectorizer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_sort_features\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'Text'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mvectorizer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvocabulary_\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\sklearn\\feature_extraction\\text.py\u001b[0m in \u001b[0;36m_sort_features\u001b[1;34m(self, X, vocabulary)\u001b[0m\n\u001b[0;32m    874\u001b[0m         \"\"\"\n\u001b[0;32m    875\u001b[0m         \u001b[0msorted_features\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0msorted\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msix\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0miteritems\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvocabulary\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 876\u001b[1;33m         \u001b[0mmap_index\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mempty\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msorted_features\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mindices\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    877\u001b[0m         \u001b[1;32mfor\u001b[0m \u001b[0mnew_val\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mterm\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mold_val\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msorted_features\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    878\u001b[0m             \u001b[0mvocabulary\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mterm\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnew_val\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36m__getattr__\u001b[1;34m(self, name)\u001b[0m\n\u001b[0;32m   5065\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_info_axis\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_can_hold_identifiers_and_holds_name\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   5066\u001b[0m                 \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 5067\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   5068\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   5069\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__setattr__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mAttributeError\u001b[0m: 'Series' object has no attribute 'indices'"
     ]
    }
   ],
   "source": [
    "vectorizer._sort_features(df['Text'],vectorizer.vocabulary_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LabelBinarizer(neg_label=0, pos_label=1, sparse_output=False)"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import LabelBinarizer\n",
    "encoder2 = LabelBinarizer()\n",
    "encoder2.fit(df['Author'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['__class__',\n",
       " '__delattr__',\n",
       " '__dict__',\n",
       " '__dir__',\n",
       " '__doc__',\n",
       " '__eq__',\n",
       " '__format__',\n",
       " '__ge__',\n",
       " '__getattribute__',\n",
       " '__getstate__',\n",
       " '__gt__',\n",
       " '__hash__',\n",
       " '__init__',\n",
       " '__init_subclass__',\n",
       " '__le__',\n",
       " '__lt__',\n",
       " '__module__',\n",
       " '__ne__',\n",
       " '__new__',\n",
       " '__reduce__',\n",
       " '__reduce_ex__',\n",
       " '__repr__',\n",
       " '__setattr__',\n",
       " '__setstate__',\n",
       " '__sizeof__',\n",
       " '__str__',\n",
       " '__subclasshook__',\n",
       " '__weakref__',\n",
       " '_get_param_names',\n",
       " 'classes_',\n",
       " 'fit',\n",
       " 'fit_transform',\n",
       " 'get_params',\n",
       " 'inverse_transform',\n",
       " 'neg_label',\n",
       " 'pos_label',\n",
       " 'set_params',\n",
       " 'sparse_input_',\n",
       " 'sparse_output',\n",
       " 'transform',\n",
       " 'y_type_']"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dir(encoder2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "'str' object has no attribute 'argmax'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-71-745ab70acff2>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mencoder2\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0minverse_transform\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0my_train\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\sklearn\\preprocessing\\label.py\u001b[0m in \u001b[0;36minverse_transform\u001b[1;34m(self, Y, threshold)\u001b[0m\n\u001b[0;32m    504\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    505\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0my_type_\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;34m\"multiclass\"\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 506\u001b[1;33m             \u001b[0my_inv\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_inverse_binarize_multiclass\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mY\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclasses_\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    507\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    508\u001b[0m             y_inv = _inverse_binarize_thresholding(Y, self.y_type_,\n",
      "\u001b[1;32m~\\Anaconda3\\envs\\tensorflow_gpuenv\\lib\\site-packages\\sklearn\\preprocessing\\label.py\u001b[0m in \u001b[0;36m_inverse_binarize_multiclass\u001b[1;34m(y, classes)\u001b[0m\n\u001b[0;32m    715\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0mclasses\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0my_i_argmax\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    716\u001b[0m     \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 717\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mclasses\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtake\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0my\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0margmax\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"clip\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    718\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    719\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mAttributeError\u001b[0m: 'str' object has no attribute 'argmax'"
     ]
    }
   ],
   "source": [
    "encoder2.inverse_transform(y_train[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "'LabelBinarizer' object has no attribute 'fit_tranform'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-76-473a6f8ae454>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mencoder2\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit_tranform\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0my_train\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;31mAttributeError\u001b[0m: 'LabelBinarizer' object has no attribute 'fit_tranform'"
     ]
    }
   ],
   "source": [
    "encoder2.fit_tranform(y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0],\n",
       "       [0, 0, 0, 0, 0, 0, 0, 0, 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, 0, 0, 0, 0, 0, 0, 0, 1,\n",
       "        0, 0, 0, 0, 0, 0],\n",
       "       [0, 0, 0, 0, 0, 0, 0, 0, 1, 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, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0],\n",
       "       [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0],\n",
       "       [0, 0, 0, 1, 0, 0, 0, 0, 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, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0]])"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_train[:5,:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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": "3.6.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}