Model Tuning.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import numpy as np\n",
    "import gc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gc.disable()\n",
    "gc.isenabled()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import Data\n",
    "\n",
    "train_data,test_data = [],[]\n",
    "with open('train_data.json',encoding='utf-8') as read_file:\n",
    "    for line in read_file:\n",
    "        train_data.append(json.loads(line))\n",
    "    read_file.close()\n",
    "    \n",
    "with open('test_data.json',encoding='utf-8') as read_file:\n",
    "    for line in read_file:\n",
    "        test_data.append(json.loads(line))\n",
    "    read_file.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_review = train_data[0]['Reviews']\n",
    "train_label = np.asarray(train_data[0]['Ratings']).astype('float16')\n",
    "\n",
    "test_review = test_data[0]['Reviews']\n",
    "test_label = np.asarray(test_data[0]['Ratings']).astype('float16')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "for i in range(train_label.shape[0]):\n",
    "    if train_label[i]>5:\n",
    "        train_label[i]=1\n",
    "        test_label[i]=1\n",
    "    else:\n",
    "        train_label[i]=0\n",
    "        test_label[i]=0\n",
    "        \n",
    "np.max(train_label)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "import Data_Preprocss as clean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "546\n"
     ]
    }
   ],
   "source": [
    "train = clean.get_preocessed_data(train_review,key='Lemmatization')\n",
    "test = clean.get_preocessed_data(test_review,key='Lemmatization')\n",
    "print(len(train[0]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import CountVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "cv = CountVectorizer(max_features=12000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_data = ((cv.fit_transform(train).toarray()).astype('float16'))\n",
    "test_data = ((cv.transform(test).toarray()).astype('float16'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(25000, 12000)\n"
     ]
    }
   ],
   "source": [
    "print(train_data.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.decomposition import TruncatedSVD\n",
    "SVD = TruncatedSVD(n_components=500)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_data = SVD.fit_transform(train_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "lr = LogisticRegression(penalty='l2',random_state=0,max_iter=50)\n",
    "lr.fit(train_data,train_label)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_data = SVD.transform(test_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Predict Data And calculate accuracy\n",
    "\n",
    "def get_accuracy(data,label):\n",
    "    ypred = lr.predict(data)\n",
    "    acc = sum(ypred==label)/len(ypred)\n",
    "\n",
    "    return acc,ypred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "acc_lr,ypred_lr = get_accuracy(test_data,test_label)\n",
    "print(acc_lr)"
   ]
  },
  {
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}