NLP-4 full project.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "762558fd",
   "metadata": {
    "heading_collapsed": true
   },
   "source": [
    "#### Importing Required Libraries and Loading Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 188,
   "id": "4f8df4da",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd # importing required libraries\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 189,
   "id": "79638925",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "df=pd.read_csv(\"WELFake_Dataset.csv\") # loading dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f01cc236",
   "metadata": {
    "heading_collapsed": true
   },
   "source": [
    "#### Data Inspection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 190,
   "id": "0a2742ad",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>title</th>\n",
       "      <th>text</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>LAW ENFORCEMENT ON HIGH ALERT Following Threat...</td>\n",
       "      <td>No comment is expected from Barack Obama Membe...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Did they post their votes for Hillary already?</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>UNBELIEVABLE! OBAMA’S ATTORNEY GENERAL SAYS MO...</td>\n",
       "      <td>Now, most of the demonstrators gathered last ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>Bobby Jindal, raised Hindu, uses story of Chri...</td>\n",
       "      <td>A dozen politically active pastors came here f...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>SATAN 2: Russia unvelis an image of its terrif...</td>\n",
       "      <td>The RS-28 Sarmat missile, dubbed Satan 2, will...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0                                              title  \\\n",
       "0           0  LAW ENFORCEMENT ON HIGH ALERT Following Threat...   \n",
       "1           1                                                NaN   \n",
       "2           2  UNBELIEVABLE! OBAMA’S ATTORNEY GENERAL SAYS MO...   \n",
       "3           3  Bobby Jindal, raised Hindu, uses story of Chri...   \n",
       "4           4  SATAN 2: Russia unvelis an image of its terrif...   \n",
       "\n",
       "                                                text  label  \n",
       "0  No comment is expected from Barack Obama Membe...      1  \n",
       "1     Did they post their votes for Hillary already?      1  \n",
       "2   Now, most of the demonstrators gathered last ...      1  \n",
       "3  A dozen politically active pastors came here f...      0  \n",
       "4  The RS-28 Sarmat missile, dubbed Satan 2, will...      1  "
      ]
     },
     "execution_count": 190,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 191,
   "id": "ab180075",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(72134, 4)"
      ]
     },
     "execution_count": 191,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 192,
   "id": "ab6bba7e",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "288536"
      ]
     },
     "execution_count": 192,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 193,
   "id": "d3d7d113",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "df=df.drop('Unnamed: 0',axis=1) # droping a column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 194,
   "id": "3d610919",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['title', 'text', 'label'], dtype='object')"
      ]
     },
     "execution_count": 194,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 195,
   "id": "a7c3b5c3",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "597"
      ]
     },
     "execution_count": 195,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum().sum() # checking null values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 197,
   "id": "3bfac656",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "title    558\n",
       "text      39\n",
       "label      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 197,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()  # checking null values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 200,
   "id": "32c13805",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "df=df.dropna() # droping null values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 201,
   "id": "55c64c4a",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(71537, 3)"
      ]
     },
     "execution_count": 201,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 202,
   "id": "9b803262",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "title    0\n",
       "text     0\n",
       "label    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 202,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3097e98b",
   "metadata": {
    "heading_collapsed": true
   },
   "source": [
    "#### Splitting of Data Into X and y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 203,
   "id": "a2dc1d6a",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "X=df.drop('label',axis=1) # independent feature"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 204,
   "id": "35c0d332",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "y=df['label'] # dependent feature"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 205,
   "id": "5ea74784",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(71537, 2)"
      ]
     },
     "execution_count": 205,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 206,
   "id": "0c314021",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(71537, 3)"
      ]
     },
     "execution_count": 206,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 207,
   "id": "8443e462",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(71537,)"
      ]
     },
     "execution_count": 207,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9957718c",
   "metadata": {
    "heading_collapsed": true
   },
   "source": [
    "#### Import Deep Learning Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 208,
   "id": "1b60f00b",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "import tensorflow"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 209,
   "id": "0fc5d07b",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2.10.0'"
      ]
     },
     "execution_count": 209,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tf.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 210,
   "id": "bbdd01bf",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "from tensorflow.keras.layers import Embedding\n",
    "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.preprocessing.text import one_hot\n",
    "from tensorflow.keras.layers import LSTM\n",
    "from tensorflow.keras.layers import Dense"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 211,
   "id": "1489c510",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "voc_size=10000 # vocabulary size"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bc7f8ac5",
   "metadata": {
    "heading_collapsed": true
   },
   "source": [
    "#### One Hot Encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 212,
   "id": "eb63afc6",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "messages=X.copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 214,
   "id": "c1e05b92",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "' GOP Senator Just Smacked Down The Most Punchable Alt-Right Nazi On The Internet'"
      ]
     },
     "execution_count": 214,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "messages['title'][10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 216,
   "id": "ae2b7026",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "messages.reset_index(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 217,
   "id": "962362c5",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "import nltk\n",
    "import re\n",
    "from nltk.corpus import stopwords"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 218,
   "id": "c8e14d0f",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package stopwords to\n",
      "[nltk_data]     C:\\Users\\USER\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package stopwords is already up-to-date!\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 218,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nltk.download('stopwords')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 219,
   "id": "0e979c12",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "# data preprocessing\n",
    "from nltk.stem.porter import PorterStemmer \n",
    "ps=PorterStemmer()\n",
    "corpus=[]\n",
    "for i in range(0,len(messages)):\n",
    "    review = re.sub('[^a-zA-Z]',' ',messages['title'][i])\n",
    "    review = review.lower()\n",
    "    review = review.split()\n",
    "    review = [ps.stem(word) for word in review if not word in stopwords.words('english')]\n",
    "    review = ' '.join(review)\n",
    "    corpus.append(review)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 221,
   "id": "6957af0d",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'donald trump hillari clinton win easili new york primari new york time'"
      ]
     },
     "execution_count": 221,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "corpus[70000]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 222,
   "id": "4f286fed",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[9202, 571, 3839, 1484, 6815, 1532, 277, 145, 277, 3424]"
      ]
     },
     "execution_count": 222,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "onehot_repr=[one_hot(words,voc_size) for words in corpus]\n",
    "onehot_repr[10]           "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 223,
   "id": "4d7f475f",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'may brexit offer would hurt cost eu citizen eu parliament'"
      ]
     },
     "execution_count": 223,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "corpus[10]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f52d39ba",
   "metadata": {
    "heading_collapsed": true
   },
   "source": [
    "#### Embedding Representation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 224,
   "id": "154dc204",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "sent_length=20\n",
    "embedded_docs=pad_sequences(onehot_repr,padding='pre',maxlen=sent_length)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 225,
   "id": "b69cb3a7",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([   0,    0,    0,    0,    0,    0, 6518, 9944, 6477, 2635, 7918,\n",
       "       5260, 8777, 9497, 7869, 9353, 2507, 2975, 2464, 4209])"
      ]
     },
     "execution_count": 225,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "embedded_docs[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 226,
   "id": "9dd9f8d1",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([   0,    0,    0,    0,    0,    0,    0,    0, 6895, 1780, 3970,\n",
       "       9584, 4308, 1083, 5276, 6301, 9887, 3198, 4974, 4209])"
      ]
     },
     "execution_count": 226,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "embedded_docs[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a2b44f17",
   "metadata": {
    "heading_collapsed": true
   },
   "source": [
    "#### Adding Dropout"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 228,
   "id": "8f583d38",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "# creating model\n",
    "embedding_vector_features=40 # feature representation\n",
    "model=Sequential()\n",
    "model.add(Embedding(voc_size,embedding_vector_features,input_length=sent_length))\n",
    "model.add(LSTM(100))\n",
    "model.add(Dense(1,activation='sigmoid'))\n",
    "model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 229,
   "id": "9571c3e4",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential_5\"\n",
      "_________________________________________________________________\n",
      " Layer (type)                Output Shape              Param #   \n",
      "=================================================================\n",
      " embedding_4 (Embedding)     (None, 20, 40)            400000    \n",
      "                                                                 \n",
      " lstm_4 (LSTM)               (None, 100)               56400     \n",
      "                                                                 \n",
      " dense_3 (Dense)             (None, 1)                 101       \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 456,501\n",
      "Trainable params: 456,501\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 230,
   "id": "aea49cf0",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(71537, (71537,))"
      ]
     },
     "execution_count": 230,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(embedded_docs),y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 231,
   "id": "d4ed49d9",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "X_final=np.array(embedded_docs)\n",
    "y_final=np.array(y) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 232,
   "id": "ab9fbe1e",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((71537, 20), (71537,))"
      ]
     },
     "execution_count": 232,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_final.shape,y_final.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 233,
   "id": "3e828ad8",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train,X_test,y_train,y_test=train_test_split(X_final,y_final,test_size=0.33,random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "535ca054",
   "metadata": {
    "heading_collapsed": true
   },
   "source": [
    "#### Model Training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 241,
   "id": "69551a25",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/5\n",
      "10/10 [==============================] - 47s 5s/step - loss: 0.1252 - accuracy: 0.9543 - val_loss: 0.3259 - val_accuracy: 0.8807\n",
      "Epoch 2/5\n",
      "10/10 [==============================] - 55s 6s/step - loss: 0.1395 - accuracy: 0.9460 - val_loss: 0.3066 - val_accuracy: 0.8854\n",
      "Epoch 3/5\n",
      "10/10 [==============================] - 66s 7s/step - loss: 0.1254 - accuracy: 0.9548 - val_loss: 0.3194 - val_accuracy: 0.8891\n",
      "Epoch 4/5\n",
      "10/10 [==============================] - 68s 7s/step - loss: 0.1164 - accuracy: 0.9592 - val_loss: 0.3338 - val_accuracy: 0.8860\n",
      "Epoch 5/5\n",
      "10/10 [==============================] - 62s 6s/step - loss: 0.1182 - accuracy: 0.9568 - val_loss: 0.3168 - val_accuracy: 0.8885\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x1dae7f18d30>"
      ]
     },
     "execution_count": 241,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# final training\n",
    "model.fit(X_train,y_train,validation_data=(X_test,y_test),epochs=5, batch_size=5000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 247,
   "id": "05b18d9e",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "738/738 [==============================] - 21s 28ms/step\n"
     ]
    }
   ],
   "source": [
    "y_pred=model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 260,
   "id": "5d574b8b",
   "metadata": {
    "hidden": true
   },
   "outputs": [],
   "source": [
    "y_pred=np.where(y_pred>0.5,1,0)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "79ef0f63",
   "metadata": {
    "heading_collapsed": true
   },
   "source": [
    "#### Perfomence Metrics and Accuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 261,
   "id": "5c34ae4e",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[10224,  1469],\n",
       "       [ 1164, 10751]], dtype=int64)"
      ]
     },
     "execution_count": 261,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.metrics import accuracy_score\n",
    "confusion_matrix(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 262,
   "id": "d5231476",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "accuracy prercentage is : 88.85 %\n"
     ]
    }
   ],
   "source": [
    "print(\"accuracy prercentage is : {} %\".format(((accuracy_score(y_test,y_pred))*100).round(2)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 263,
   "id": "1d803452",
   "metadata": {
    "hidden": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.90      0.87      0.89     11693\n",
      "           1       0.88      0.90      0.89     11915\n",
      "\n",
      "    accuracy                           0.89     23608\n",
      "   macro avg       0.89      0.89      0.89     23608\n",
      "weighted avg       0.89      0.89      0.89     23608\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "print(classification_report(y_test,y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e1354645",
   "metadata": {
    "hidden": true
   },
   "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": "3.9.12"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}