Case Study - Balancing Class.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "review_data = pd.read_csv('C:/Users/awant/Documents/Reviews.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "review_data = review_data.sample(5000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "review_data = review_data[['Text','Score']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "review_data = review_data[review_data.Score != 3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "review_data['Sentiment'] = review_data.Score.map(lambda x: 0 if x < 3 else 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "from sklearn.naive_bayes import MultinomialNB"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "cv = CountVectorizer(stop_words='english')\n",
    "mnb = MultinomialNB()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    3895\n",
       "0     692\n",
       "Name: Sentiment, dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "review_data.Sentiment.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "from imblearn.over_sampling import SMOTE"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_selection import SelectKBest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "from imblearn.pipeline import make_pipeline as make_pipeline_imb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "word_selector = SelectKBest(k=2000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "pipeline = make_pipeline_imb(cv, word_selector, SMOTE(random_state=0), mnb)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "trainX,testX, trainY,testY = train_test_split(review_data.Text, review_data.Sentiment)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\awant\\Anaconda3\\lib\\site-packages\\imblearn\\pipeline.py:190: DeprecationWarning: The 'cachedir' attribute has been deprecated in version 0.12 and will be removed in version 0.14.\n",
      "Use os.path.join(memory.location, 'joblib') attribute instead.\n",
      "  if memory.cachedir is None:\n",
      "C:\\Users\\awant\\Anaconda3\\lib\\site-packages\\imblearn\\pipeline.py:190: DeprecationWarning: The 'cachedir' attribute has been deprecated in version 0.12 and will be removed in version 0.14.\n",
      "Use os.path.join(memory.location, 'joblib') attribute instead.\n",
      "  if memory.cachedir is None:\n",
      "C:\\Users\\awant\\Anaconda3\\lib\\site-packages\\imblearn\\pipeline.py:190: DeprecationWarning: The 'cachedir' attribute has been deprecated in version 0.12 and will be removed in version 0.14.\n",
      "Use os.path.join(memory.location, 'joblib') attribute instead.\n",
      "  if memory.cachedir is None:\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Pipeline(memory=None,\n",
       "     steps=[('countvectorizer', CountVectorizer(analyzer='word', binary=False, decode_error='strict',\n",
       "        dtype=<class 'numpy.int64'>, encoding='utf-8', input='content',\n",
       "        lowercase=True, max_df=1.0, max_features=None, min_df=1,\n",
       "        ngram_range=(1, 1), preprocessor=None, stop_words='english...svm_estimator=None)), ('multinomialnb', MultinomialNB(alpha=1.0, class_prior=None, fit_prior=True))])"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipeline.fit(trainX,trainY)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import confusion_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[107,  59],\n",
       "       [ 71, 910]], dtype=int64)"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred = pipeline.predict(testX)\n",
    "confusion_matrix(y_pred=pred, y_true=testY)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.pipeline import make_pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "review_pipeline = make_pipeline(cv, word_selector, mnb)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Pipeline(memory=None,\n",
       "     steps=[('countvectorizer', CountVectorizer(analyzer='word', binary=False, decode_error='strict',\n",
       "        dtype=<class 'numpy.int64'>, encoding='utf-8', input='content',\n",
       "        lowercase=True, max_df=1.0, max_features=None, min_df=1,\n",
       "        ngram_range=(1, 1), preprocessor=None, stop_words='english...x000002A4FB520840>)), ('multinomialnb', MultinomialNB(alpha=1.0, class_prior=None, fit_prior=True))])"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "review_pipeline.fit(trainX,trainY)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 49, 117],\n",
       "       [ 25, 956]], dtype=int64)"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred = review_pipeline.predict(testX)\n",
    "confusion_matrix(y_pred=pred, y_true=testY)"
   ]
  },
  {
   "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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}