Sentiment Analysis Instagram Comment.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Import Package"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from sklearn.model_selection import train_test_split, GridSearchCV\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.metrics import classification_report\n",
    "\n",
    "from nltk.tokenize import word_tokenize\n",
    "from nltk.corpus import stopwords\n",
    "from string import punctuation\n",
    "\n",
    "sw_indo = stopwords.words(\"indonesian\") + list(punctuation)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Import Data"
   ]
  },
  {
   "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>Sentiment</th>\n",
       "      <th>Instagram Comment Text</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Id</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>negative</td>\n",
       "      <td>&lt;USERNAME&gt; TOLOL!! Gak ada hubungan nya kegug...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>negative</td>\n",
       "      <td>Geblek lo tata...cowo bgt dibela2in balikan......</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>negative</td>\n",
       "      <td>Kmrn termewek2 skr lengket lg duhhh kok labil ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>negative</td>\n",
       "      <td>Intinya kalau kesel dengan ATT nya, gausah ke ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>negative</td>\n",
       "      <td>hadewwwww permpuan itu lg!!!!sakit jiwa,knp ha...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Sentiment                             Instagram Comment Text\n",
       "Id                                                             \n",
       "1   negative   <USERNAME> TOLOL!! Gak ada hubungan nya kegug...\n",
       "2   negative  Geblek lo tata...cowo bgt dibela2in balikan......\n",
       "3   negative  Kmrn termewek2 skr lengket lg duhhh kok labil ...\n",
       "4   negative  Intinya kalau kesel dengan ATT nya, gausah ke ...\n",
       "5   negative  hadewwwww permpuan itu lg!!!!sakit jiwa,knp ha..."
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"Dataset/dataset_komentar_instagram_cyberbullying.csv\", index_col=\"Id\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Preparation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Mengubah kalimat menjadi huruf kecil semua\n",
    "\n",
    "def lower(text):\n",
    "    result = text.lower()\n",
    "    return result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"Instagram Comment Text\"] = df[\"Instagram Comment Text\"].apply(lower)"
   ]
  },
  {
   "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>Sentiment</th>\n",
       "      <th>Instagram Comment Text</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Id</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>negative</td>\n",
       "      <td>&lt;username&gt; tolol!! gak ada hubungan nya kegug...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>negative</td>\n",
       "      <td>geblek lo tata...cowo bgt dibela2in balikan......</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>negative</td>\n",
       "      <td>kmrn termewek2 skr lengket lg duhhh kok labil ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>negative</td>\n",
       "      <td>intinya kalau kesel dengan att nya, gausah ke ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>negative</td>\n",
       "      <td>hadewwwww permpuan itu lg!!!!sakit jiwa,knp ha...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Sentiment                             Instagram Comment Text\n",
       "Id                                                             \n",
       "1   negative   <username> tolol!! gak ada hubungan nya kegug...\n",
       "2   negative  geblek lo tata...cowo bgt dibela2in balikan......\n",
       "3   negative  kmrn termewek2 skr lengket lg duhhh kok labil ...\n",
       "4   negative  intinya kalau kesel dengan att nya, gausah ke ...\n",
       "5   negative  hadewwwww permpuan itu lg!!!!sakit jiwa,knp ha..."
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Sentiment                 400\n",
       "Instagram Comment Text    400\n",
       "dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Mengubah nilai sentiment menjadi angka 0 dan 1\n",
    "\n",
    "df[\"Sentiment\"] = df[\"Sentiment\"].replace(\"negative\",0)\n",
    "df[\"Sentiment\"] = df[\"Sentiment\"].replace(\"positive\",1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>Sentiment</th>\n",
       "      <th>Instagram Comment Text</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Id</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>&lt;username&gt; tolol!! gak ada hubungan nya kegug...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>geblek lo tata...cowo bgt dibela2in balikan......</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>kmrn termewek2 skr lengket lg duhhh kok labil ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>intinya kalau kesel dengan att nya, gausah ke ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>hadewwwww permpuan itu lg!!!!sakit jiwa,knp ha...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Sentiment                             Instagram Comment Text\n",
       "Id                                                              \n",
       "1           0   <username> tolol!! gak ada hubungan nya kegug...\n",
       "2           0  geblek lo tata...cowo bgt dibela2in balikan......\n",
       "3           0  kmrn termewek2 skr lengket lg duhhh kok labil ...\n",
       "4           0  intinya kalau kesel dengan att nya, gausah ke ...\n",
       "5           0  hadewwwww permpuan itu lg!!!!sakit jiwa,knp ha..."
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    200\n",
       "0    200\n",
       "Name: Sentiment, dtype: int64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.Sentiment.value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Dataset Splitting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "MODEL = []\n",
    "TEST = []\n",
    "\n",
    "def eval(model,test1):\n",
    "    MODEL.append(model)\n",
    "    TEST.append(round(test1,2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = df[\"Instagram Comment Text\"]\n",
    "y = df.Sentiment\n",
    "\n",
    "# Membagi dataset menjadi dengan proporsi 80% data train dan 20% data test\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Algorithm: Logistic Regresion"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 5 folds for each of 8 candidates, totalling 40 fits\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done  40 out of  40 | elapsed:   13.1s finished\n",
      "C:\\Users\\ASUS\\Miniconda3\\envs\\jcopml\\lib\\site-packages\\sklearn\\feature_extraction\\text.py:385: UserWarning: Your stop_words may be inconsistent with your preprocessing. Tokenizing the stop words generated tokens ['``'] not in stop_words.\n",
      "  'stop_words.' % sorted(inconsistent))\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(1.0, 0.871875, 0.9125)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Pipeline\n",
    "pipeline = Pipeline([\n",
    "    ('tfidf', TfidfVectorizer(tokenizer=word_tokenize, stop_words=sw_indo, ngram_range=(1,3))),\n",
    "    ('algo',LogisticRegression())\n",
    "])\n",
    "\n",
    "\n",
    "#Hyperparameter Tuning\n",
    "parameter = {\n",
    "    \"algo__fit_intercept\" : [True,False],\n",
    "    \"algo__C\" : range(1,5,1)\n",
    "}\n",
    "\n",
    "#Training\n",
    "model_logistic = GridSearchCV(estimator=pipeline, param_grid=parameter, cv=5, n_jobs=-1, verbose=1)\n",
    "model_logistic.fit(X_train,y_train)\n",
    "model_logistic.score(X_train,y_train), model_logistic.best_score_, model_logistic.score(X_test,y_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Evaluation: Logistic Regresion"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = model_logistic.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.95      0.89      0.92        44\n",
      "           1       0.87      0.94      0.91        36\n",
      "\n",
      "    accuracy                           0.91        80\n",
      "   macro avg       0.91      0.92      0.91        80\n",
      "weighted avg       0.92      0.91      0.91        80\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(y_test, y_pred))\n",
    "eval(\"Logistic Regression\",model_logistic.score(X_test,y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_predict = [\n",
    "    [\"kamu sangat jelek sampe - sampe mau muntah ngeliatnya!!!\"], #negative Comment\n",
    "    [\"Kamu hari ini terlihat cantik banget\"] #positive Comment\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0], dtype=int64)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_logistic.predict(X_predict[0]) # Predict Negative Comment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1], dtype=int64)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_logistic.predict(X_predict[1]) # Predict positive Comment"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Algorithm: KNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 3 folds for each of 200 candidates, totalling 600 fits\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done  42 tasks      | elapsed:    7.5s\n",
      "[Parallel(n_jobs=-1)]: Done 192 tasks      | elapsed:   34.4s\n",
      "[Parallel(n_jobs=-1)]: Done 442 tasks      | elapsed:  1.3min\n",
      "[Parallel(n_jobs=-1)]: Done 600 out of 600 | elapsed:  1.7min finished\n",
      "C:\\Users\\ASUS\\Miniconda3\\envs\\jcopml\\lib\\site-packages\\sklearn\\feature_extraction\\text.py:385: UserWarning: Your stop_words may be inconsistent with your preprocessing. Tokenizing the stop words generated tokens ['``'] not in stop_words.\n",
      "  'stop_words.' % sorted(inconsistent))\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(1.0, 0.8500264503614883, 0.9125)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Pipeline\n",
    "pipeline = Pipeline([\n",
    "    ('tfidf', TfidfVectorizer(tokenizer=word_tokenize, stop_words=sw_indo, ngram_range=(1,3))),\n",
    "    ('algo',KNeighborsClassifier())\n",
    "])\n",
    "\n",
    "#Hyperparameter Tunning\n",
    "parameter = {\n",
    "    \"algo__n_neighbors\" : range(1,51,1),\n",
    "    \"algo__weights\" : [\"distance\",\"uniform\"],\n",
    "    \"algo__p\" : [1,2]\n",
    "}\n",
    "\n",
    "#Training\n",
    "model_knn = GridSearchCV(estimator=pipeline, param_grid=parameter, cv=3, n_jobs=-1, verbose=1)\n",
    "model_knn.fit(X_train,y_train)\n",
    "model_knn.score(X_train,y_train), model_knn.best_score_, model_knn.score(X_test,y_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Evaluation: KNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = model_knn.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.95      0.89      0.92        44\n",
      "           1       0.87      0.94      0.91        36\n",
      "\n",
      "    accuracy                           0.91        80\n",
      "   macro avg       0.91      0.92      0.91        80\n",
      "weighted avg       0.92      0.91      0.91        80\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(y_test, y_pred))\n",
    "eval(\" K-Nearest Neighbour (KNN)\",model_knn.score(X_test,y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_predict = [\n",
    "    [\"kamu sangat jelek sampe - sampe mau muntah ngeliatnya!!!\"], #negative Comment\n",
    "    [\"Kamu hari ini terlihat cantik banget\"] #positive comment\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0], dtype=int64)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_knn.predict(X_predict[0]) # Predict Negative Comment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1], dtype=int64)"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_knn.predict(X_predict[1]) # Predict positive Comment"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Algorithm: SVM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 3 folds for each of 125 candidates, totalling 375 fits\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 4 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done  42 tasks      | elapsed:    7.4s\n",
      "[Parallel(n_jobs=-1)]: Done 192 tasks      | elapsed:   29.7s\n"
     ]
    }
   ],
   "source": [
    "#Pipeline\n",
    "pipeline = Pipeline([\n",
    "    ('tfidf', TfidfVectorizer(tokenizer=word_tokenize, stop_words=sw_indo, ngram_range=(1,3))),\n",
    "    ('algo',SVC(max_iter=500))\n",
    "])\n",
    "\n",
    "#Hyperparameter Tunning\n",
    "parameter = {\n",
    "    \"algo__kernel\" : ['linear', 'poly', 'rbf', 'sigmoid', 'precomputed'],\n",
    "    \"algo__C\" : [0.001, 0.01, 0.1, 1, 10],\n",
    "    \"algo__gamma\" : ['scale',10, 5, 1, 0.1]\n",
    "}\n",
    "\n",
    "#Training\n",
    "model_svm = GridSearchCV(estimator=pipeline, param_grid=parameter, cv=3, n_jobs=-1, verbose=1)\n",
    "model_svm.fit(X_train,y_train)\n",
    "model_svm.score(X_train,y_train), model_svm.best_score_, model_svm.score(X_test,y_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Evaluation: SVM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = model_svm.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(classification_report(y_test, y_pred))\n",
    "eval(\"Support Vector Machine (SVM)\",model_svm.score(X_test,y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_predict = [\n",
    "    [\"kamu sangat jelek sampe - sampe mau muntah ngeliatnya!!!\"], #negative Comment\n",
    "    [\"Kamu hari ini terlihat cantik banget\"] #positive Comment\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_svm.predict(X_predict[0]) # Predict Negative Comment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_svm.predict(X_predict[1]) # Predict positive Comment"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Kesimpulan "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"\\t\\t\\tTest Accuracy\")\n",
    "results2 = pd.DataFrame({ 'Model': MODEL,\n",
    "                         'Test Accuracy': TEST})\n",
    "\n",
    "results2.sort_values(by='Test Accuracy',ascending=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Akurasi yang dihasilkan dengan menggunakan Algoritma Logistic Regresion, KNN, SVM tidak jauh berbeda, namun akurasi yang terbesar adalah SVM dengan score 92%, selain akurasi nilai recal menggunakan algoritma SVM juga yang terbesar yaitu berada di angka 0: 91% dan 1: 94%. itu artinya keberhasilan model memprediksi data yang berlabel 0 (Negative) sebesar 91% dan data yang berlabel 1 (Positive) sebesar 94%, jadi bisa di katakan model yang terbaik untuk kasus ini adalah `Support Vector Machine (SVM)`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:jcopml]",
   "language": "python",
   "name": "conda-env-jcopml-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.0"
  },
  "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": 4
}