NLP_Machine_learning_model_selection.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import nltk\n",
    "import pandas as pd\n",
    "import re\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "import string\n",
    "\n",
    "stopwords = nltk.corpus.stopwords.words('english')\n",
    "ps = nltk.PorterStemmer()\n",
    "\n",
    "data = pd.read_csv('SMSSpamCollection.tsv', sep='\\t')\n",
    "data.columns = ['label', 'body_text']\n",
    "\n",
    "def count_punct(text):\n",
    "    count = sum((1 for char in text if char in string.punctuation))\n",
    "    return round(count/(len(text) - text.count(' ')), 3)*100\n",
    "\n",
    "data['body_len'] = data['body_text'].apply(lambda x: len(x) - x.count(\" \"))\n",
    "data['punct%'] = data['body_text'].apply(lambda x: count_punct(x))\n",
    "\n",
    "def clean_text(text):\n",
    "    text = ''.join([word.lower() for word in text if word not in string.punctuation])\n",
    "    tokens = re.split('\\W+', text)\n",
    "    text = [ps.stem(word) for word in tokens if word not in stopwords]\n",
    "    return text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(data[['body_text', 'body_len', 'punct%']], data['label'], test_size = 0.2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>body_len</th>\n",
       "      <th>punct%</th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>...</th>\n",
       "      <th>7077</th>\n",
       "      <th>7078</th>\n",
       "      <th>7079</th>\n",
       "      <th>7080</th>\n",
       "      <th>7081</th>\n",
       "      <th>7082</th>\n",
       "      <th>7083</th>\n",
       "      <th>7084</th>\n",
       "      <th>7085</th>\n",
       "      <th>7086</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>32</td>\n",
       "      <td>15.6</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>111</td>\n",
       "      <td>2.7</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>73</td>\n",
       "      <td>13.7</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>39</td>\n",
       "      <td>5.1</td>\n",
       "      <td>0.297981</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>137</td>\n",
       "      <td>4.4</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 7089 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   body_len  punct%         0    1    2    3    4    5    6    7  ...   7077  \\\n",
       "0        32    15.6  0.000000  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...    0.0   \n",
       "1       111     2.7  0.000000  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...    0.0   \n",
       "2        73    13.7  0.000000  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...    0.0   \n",
       "3        39     5.1  0.297981  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...    0.0   \n",
       "4       137     4.4  0.000000  0.0  0.0  0.0  0.0  0.0  0.0  0.0  ...    0.0   \n",
       "\n",
       "   7078  7079  7080  7081  7082  7083  7084  7085  7086  \n",
       "0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "1   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "2   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "3   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "4   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0   0.0  \n",
       "\n",
       "[5 rows x 7089 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tfidf_vect = TfidfVectorizer(analyzer=clean_text)\n",
    "tfidf_vect_fit = tfidf_vect.fit(X_train['body_text'])\n",
    "\n",
    "tfidf_train = tfidf_vect_fit.transform(X_train['body_text'])\n",
    "tfidf_test = tfidf_vect_fit.transform(X_test['body_text'])\n",
    "\n",
    "X_train_vect = pd.concat([X_train[['body_len', 'punct%']].reset_index(drop=True),\n",
    "           pd.DataFrame(tfidf_train.toarray())], axis = 1)\n",
    "X_test_vect = pd.concat([X_test[['body_len', 'punct%']].reset_index(drop=True),\n",
    "           pd.DataFrame(tfidf_test.toarray())], axis = 1)\n",
    "\n",
    "X_train_vect.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier\n",
    "from sklearn.metrics import precision_recall_fscore_support as score\n",
    "import time"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fit time: 260.481 / Predict time:0.191 ----- Precision: 0.927 / Recall: 0.87 / Accuracy: 0.971\n"
     ]
    }
   ],
   "source": [
    "gb = GradientBoostingClassifier(n_estimators=150, max_depth=11)\n",
    "\n",
    "start = time.time()\n",
    "gb_model = gb.fit(X_train_vect, y_train)\n",
    "end = time.time()\n",
    "fit_time = (end - start)\n",
    "\n",
    "start = time.time()\n",
    "y_pred = gb_model.predict(X_test_vect)\n",
    "end = time.time()\n",
    "pred_time = (end - start)\n",
    "\n",
    "precision, recall, fscore, train_support = score(y_test, y_pred, pos_label='spam', average= 'binary')\n",
    "print('Fit time: {} / Predict time:{} ----- Precision: {} / Recall: {} / Accuracy: {}'.format(\n",
    "round(fit_time, 3), round(pred_time, 3), round(precision, 3), round(recall, 3), round((y_pred==y_test).sum()/len(y_pred), 3)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fit time: 6.3 / Predict time:0.237 ----- Precision: 1.0 / Recall: 0.839 / Accuracy: 0.977\n"
     ]
    }
   ],
   "source": [
    "rf = RandomForestClassifier(n_estimators=150, max_depth=None, n_jobs=-1)\n",
    "\n",
    "start = time.time()\n",
    "rf_model = rf.fit(X_train_vect, y_train)\n",
    "end = time.time()\n",
    "fit_time = (end - start)\n",
    "\n",
    "start = time.time()\n",
    "y_pred = rf_model.predict(X_test_vect)\n",
    "end = time.time()\n",
    "pred_time = (end - start)\n",
    "\n",
    "precision, recall, fscore, train_support = score(y_test, y_pred, pos_label='spam', average= 'binary')\n",
    "print('Fit time: {} / Predict time:{} ----- Precision: {} / Recall: {} / Accuracy: {}'.format(\n",
    "round(fit_time, 3), round(pred_time, 3), round(precision, 3), round(recall, 3), round((y_pred==y_test).sum()/len(y_pred), 3)))"
   ]
  },
  {
   "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}