sentiment_analysis.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "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>Product Name</th>\n",
       "      <th>Brand Name</th>\n",
       "      <th>Price</th>\n",
       "      <th>Rating</th>\n",
       "      <th>Reviews</th>\n",
       "      <th>Review Votes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>5</td>\n",
       "      <td>I feel so LUCKY to have found this used (phone...</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>4</td>\n",
       "      <td>nice phone, nice up grade from my pantach revu...</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>5</td>\n",
       "      <td>Very pleased</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>4</td>\n",
       "      <td>It works good but it goes slow sometimes but i...</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>4</td>\n",
       "      <td>Great phone to replace my lost phone. The only...</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                        Product Name Brand Name   Price  \\\n",
       "0  \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "1  \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "2  \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "3  \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "4  \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "\n",
       "   Rating                                            Reviews  Review Votes  \n",
       "0       5  I feel so LUCKY to have found this used (phone...           1.0  \n",
       "1       4  nice phone, nice up grade from my pantach revu...           0.0  \n",
       "2       5                                       Very pleased           0.0  \n",
       "3       4  It works good but it goes slow sometimes but i...           0.0  \n",
       "4       4  Great phone to replace my lost phone. The only...           0.0  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('data/Amazon_Unlocked_Mobile.csv')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "413840"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "334335"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dropna(inplace=True)\n",
    "len(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "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>Product Name</th>\n",
       "      <th>Brand Name</th>\n",
       "      <th>Price</th>\n",
       "      <th>Rating</th>\n",
       "      <th>Reviews</th>\n",
       "      <th>Review Votes</th>\n",
       "      <th>Positively Rated</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>5</td>\n",
       "      <td>I feel so LUCKY to have found this used (phone...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>4</td>\n",
       "      <td>nice phone, nice up grade from my pantach revu...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>5</td>\n",
       "      <td>Very pleased</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>4</td>\n",
       "      <td>It works good but it goes slow sometimes but i...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>4</td>\n",
       "      <td>Great phone to replace my lost phone. The only...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>1</td>\n",
       "      <td>I already had a phone with problems... I know ...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>2</td>\n",
       "      <td>The charging port was loose. I got that solder...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>2</td>\n",
       "      <td>Phone looks good but wouldn't stay charged, ha...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>5</td>\n",
       "      <td>I originally was using the Samsung S2 Galaxy f...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>\"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...</td>\n",
       "      <td>Samsung</td>\n",
       "      <td>199.99</td>\n",
       "      <td>5</td>\n",
       "      <td>This is a great product it came after two days...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                         Product Name Brand Name   Price  \\\n",
       "0   \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "1   \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "2   \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "3   \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "4   \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "5   \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "6   \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "7   \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "8   \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "11  \"CLEAR CLEAN ESN\" Sprint EPIC 4G Galaxy SPH-D7...    Samsung  199.99   \n",
       "\n",
       "    Rating                                            Reviews  Review Votes  \\\n",
       "0        5  I feel so LUCKY to have found this used (phone...           1.0   \n",
       "1        4  nice phone, nice up grade from my pantach revu...           0.0   \n",
       "2        5                                       Very pleased           0.0   \n",
       "3        4  It works good but it goes slow sometimes but i...           0.0   \n",
       "4        4  Great phone to replace my lost phone. The only...           0.0   \n",
       "5        1  I already had a phone with problems... I know ...           1.0   \n",
       "6        2  The charging port was loose. I got that solder...           0.0   \n",
       "7        2  Phone looks good but wouldn't stay charged, ha...           0.0   \n",
       "8        5  I originally was using the Samsung S2 Galaxy f...           0.0   \n",
       "11       5  This is a great product it came after two days...           0.0   \n",
       "\n",
       "    Positively Rated  \n",
       "0                  1  \n",
       "1                  1  \n",
       "2                  1  \n",
       "3                  1  \n",
       "4                  1  \n",
       "5                  0  \n",
       "6                  0  \n",
       "7                  0  \n",
       "8                  1  \n",
       "11                 1  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df[df['Rating'] != 3]\n",
    "df['Positively Rated'] = np.where(df['Rating'] > 3, 1, 0)\n",
    "df.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7482686025879323"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Positively Rated'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split( df['Reviews'], df['Positively Rated'], random_state=0 )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X_train first entry: \n",
      "\n",
      " I feel so LUCKY to have found this used (phone to us & not used hard at all), phone on line from someone who upgraded and sold this one. My Son liked his old one that finally fell apart after 2.5+ years and didn't want an upgrade!! Thank you Seller, we really appreciate it & your honesty re: said used phone.I recommend this seller very highly & would but from them again!!\n",
      "\n",
      "\n",
      "X_train shape:  (231207,)\n"
     ]
    }
   ],
   "source": [
    "print('X_train first entry: \\n\\n', X_train[0])\n",
    "print('\\n\\nX_train shape: ', X_train.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "vect = CountVectorizer().fit(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['00',\n",
       " '4less',\n",
       " 'adr6275',\n",
       " 'assignment',\n",
       " 'blazingly',\n",
       " 'cassettes',\n",
       " 'condishion',\n",
       " 'debi',\n",
       " 'dollarsshipping',\n",
       " 'esteem',\n",
       " 'flashy',\n",
       " 'gorila',\n",
       " 'human',\n",
       " 'irullu',\n",
       " 'like',\n",
       " 'microsaudered',\n",
       " 'nightmarish',\n",
       " 'p770',\n",
       " 'poori',\n",
       " 'quirky',\n",
       " 'responseive',\n",
       " 'send',\n",
       " 'sos',\n",
       " 'synch',\n",
       " 'trace',\n",
       " 'utiles',\n",
       " 'withstanding']"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vect.get_feature_names()[::2000]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "53216"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(vect.get_feature_names())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<231207x53216 sparse matrix of type '<class 'numpy.int64'>'\n",
       "\twith 6117776 stored elements in Compressed Sparse Row format>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_train_vectorized = vect.transform(X_train)\n",
    "x_train_vectorized"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\damaro\\AppData\\Roaming\\Python\\Python38\\site-packages\\sklearn\\linear_model\\_logistic.py:937: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html.\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "                   intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
       "                   multi_class='auto', n_jobs=None, penalty='l2',\n",
       "                   random_state=None, solver='lbfgs', tol=0.0001, verbose=0,\n",
       "                   warm_start=False)"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "model = LogisticRegression()\n",
    "model.fit(x_train_vectorized, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "AUC:  0.9205592121965233\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import roc_auc_score\n",
    "\n",
    "predictions = model.predict(vect.transform(X_test))\n",
    "\n",
    "print('AUC: ', roc_auc_score(y_test, predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Smallest Coefs:\n",
      "['worst' 'garbage' 'junk' 'unusable' 'false' 'worthless' 'useless'\n",
      " 'crashing' 'disappointing' 'awful']\n",
      "\n",
      "Largest Coefs:\n",
      "['excelent' 'excelente' 'exelente' 'loving' 'loves' 'perfecto' 'excellent'\n",
      " 'complaints' 'awesome' 'buen']\n",
      "\n"
     ]
    }
   ],
   "source": [
    "feature_names = np.array(vect.get_feature_names())\n",
    "\n",
    "sorted_coef_index = model.coef_[0].argsort()\n",
    "\n",
    "print('Smallest Coefs:\\n{}\\n'.format(feature_names[sorted_coef_index[:10]]))\n",
    "print('Largest Coefs:\\n{}\\n'.format(feature_names[sorted_coef_index[:-11:-1]]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Tfidf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "17951"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "\n",
    "vect1 = TfidfVectorizer(min_df=5).fit(X_train)\n",
    "len(vect1.get_feature_names())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\damaro\\AppData\\Roaming\\Python\\Python38\\site-packages\\sklearn\\linear_model\\_logistic.py:937: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html.\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "AUC:  0.9265848398605042\n"
     ]
    }
   ],
   "source": [
    "x_train_vectorized1 = vect1.transform(X_train)\n",
    "\n",
    "model1 = LogisticRegression()\n",
    "model1.fit(x_train_vectorized1, y_train)\n",
    "\n",
    "predictions1 = model1.predict(vect1.transform(X_test))\n",
    "\n",
    "print('AUC: ', roc_auc_score(y_test, predictions1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Smallest Coefs:\n",
      "['commenter' 'pthalo' 'warmness' 'storageso' 'aggregration' '1300'\n",
      " '625nits' 'a10' 'submarket' 'brawns']\n",
      "\n",
      "Largest Coefs:\n",
      "['defective' 'batteries' 'gooood' 'epic' 'luis' 'goood' 'basico'\n",
      " 'aceptable' 'problems' 'excellant']\n",
      "\n"
     ]
    }
   ],
   "source": [
    "feature_names1 = np.array(vect1.get_feature_names())\n",
    "\n",
    "sorted_coef_index1 = x_train_vectorized1.max(0).toarray()[0].argsort()\n",
    "\n",
    "print('Smallest Coefs:\\n{}\\n'.format(feature_names1[sorted_coef_index1[:10]]))\n",
    "print('Largest Coefs:\\n{}\\n'.format(feature_names1[sorted_coef_index1[:-11:-1]]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 0]\n"
     ]
    }
   ],
   "source": [
    "print(model1.predict(vect1.transform(['not an issue, phone is working',\n",
    "                                      'an issue, phone is not working'])))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 0]\n"
     ]
    }
   ],
   "source": [
    "print(model.predict(vect.transform(['not an issue, phone is working',\n",
    "                                      'an issue, phone is not working'])))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## n-grams"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "198917"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vect2 = CountVectorizer(min_df=5,  ngram_range=(1, 2)).fit(X_train)\n",
    "\n",
    "x_train_vectorized2 = vect2.transform(X_train)\n",
    "\n",
    "len(vect2.get_feature_names())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\damaro\\AppData\\Roaming\\Python\\Python38\\site-packages\\sklearn\\linear_model\\_logistic.py:937: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html.\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "AUC:  0.9599601154447429\n"
     ]
    }
   ],
   "source": [
    "model2 = LogisticRegression()\n",
    "model2.fit(x_train_vectorized2, y_train)\n",
    "\n",
    "predictions2 = model2.predict(vect2.transform(X_test))\n",
    "\n",
    "print('AUC: ', roc_auc_score(y_test, predictions2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "feature_names2 = np.array(vect2.get_feature_names())\n",
    "\n",
    "sorted_coef_index2 = x_train_vectorized2.max(0).toarray()[0].argsort()\n",
    "\n",
    "print('Smallest Coefs:\\n{}\\n'.format(feature_names2[sorted_coef_index2[:10]]))\n",
    "print('Largest Coefs:\\n{}\\n'.format(feature_names2[sorted_coef_index2[:-11:-1]]))"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "b3ba2566441a7c06988d0923437866b63cedc61552a5af99d1f4fb67d367b25f"
  },
  "kernelspec": {
   "display_name": "Python 3.8.5 64-bit ('base': conda)",
   "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"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}