{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "c45c0b4e-50d1-4d26-8251-94783a7b2012",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package punkt to\n",
      "[nltk_data]     C:\\Users\\HP\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package punkt is already up-to-date!\n",
      "[nltk_data] Downloading package stopwords to\n",
      "[nltk_data]     C:\\Users\\HP\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package stopwords is already up-to-date!\n",
      "[nltk_data] Downloading package wordnet to\n",
      "[nltk_data]     C:\\Users\\HP\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package wordnet is already up-to-date!\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split, GridSearchCV\n",
    "from sklearn.preprocessing import StandardScaler, LabelEncoder\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score, classification_report\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import classification_report\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "import re\n",
    "import nltk\n",
    "import spacy\n",
    "\n",
    "from nltk.corpus import stopwords\n",
    "from nltk.tokenize import word_tokenize\n",
    "from nltk.stem import PorterStemmer\n",
    "from nltk.stem import WordNetLemmatizer\n",
    "\n",
    "\n",
    "\n",
    "nltk.download('punkt')\n",
    "nltk.download('stopwords')\n",
    "nltk.download('wordnet')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "13171d92-0a56-47df-9ace-375241e5c1dd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "text         0\n",
      "sentiment    0\n",
      "dtype: int64\n"
     ]
    },
    {
     "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>text</th>\n",
       "      <th>sentiment</th>\n",
       "      <th>clean_text</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Java Concurrency in Practice is probably the b...</td>\n",
       "      <td>positive</td>\n",
       "      <td>java concurrency in practice is probably the b...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>haha aww hun i bet you are more creative tha...</td>\n",
       "      <td>positive</td>\n",
       "      <td>haha aww hun i bet you are more creative tha...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>_pickle lol, thank you very much Hope you`re h...</td>\n",
       "      <td>positive</td>\n",
       "      <td>pickle lol thank you very much hope youre havi...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Out for an evening on the town with jeremy. Sa...</td>\n",
       "      <td>negative</td>\n",
       "      <td>out for an evening on the town with jeremy sad...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>- just took over the #1 Most Endorsed spot on...</td>\n",
       "      <td>positive</td>\n",
       "      <td>just took over the 1 most endorsed spot on t...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                text sentiment  \\\n",
       "0  Java Concurrency in Practice is probably the b...  positive   \n",
       "1    haha aww hun i bet you are more creative tha...  positive   \n",
       "2  _pickle lol, thank you very much Hope you`re h...  positive   \n",
       "3  Out for an evening on the town with jeremy. Sa...  negative   \n",
       "4   - just took over the #1 Most Endorsed spot on...  positive   \n",
       "\n",
       "                                          clean_text  \n",
       "0  java concurrency in practice is probably the b...  \n",
       "1    haha aww hun i bet you are more creative tha...  \n",
       "2  pickle lol thank you very much hope youre havi...  \n",
       "3  out for an evening on the town with jeremy sad...  \n",
       "4    just took over the 1 most endorsed spot on t...  "
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "# Check for null values\n",
    "print(df.isnull().sum())\n",
    "\n",
    "# Simple preprocessing: lowercase, remove punctuation\n",
    "import re\n",
    "def preprocess_text(text):\n",
    "    text = text.lower()\n",
    "    text = re.sub(r'[^a-zA-Z0-9\\s]', '', text)\n",
    "    return text\n",
    "\n",
    "df['clean_text'] = df['text'].apply(preprocess_text)\n",
    "df.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "43b2ada6-e41d-4a39-89aa-7c01052ddccf",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "X = df['clean_text']\n",
    "y = df['sentiment']\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "2ecc3fd5-5612-49d3-b431-45703ad6a5a9",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "vectorizer = TfidfVectorizer(max_features=5000)\n",
    "X_train_vec = vectorizer.fit_transform(X_train)\n",
    "X_test_vec = vectorizer.transform(X_test)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "26869d29-f91f-46e9-bb8c-0779cfe38e8e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Naive Bayes Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "    negative       1.00      0.01      0.02       120\n",
      "    positive       0.77      1.00      0.87       400\n",
      "\n",
      "    accuracy                           0.77       520\n",
      "   macro avg       0.89      0.50      0.44       520\n",
      "weighted avg       0.82      0.77      0.67       520\n",
      "\n",
      "Logistic Regression Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "    negative       0.90      0.22      0.35       120\n",
      "    positive       0.81      0.99      0.89       400\n",
      "\n",
      "    accuracy                           0.81       520\n",
      "   macro avg       0.85      0.60      0.62       520\n",
      "weighted avg       0.83      0.81      0.77       520\n",
      "\n"
     ]
    }
   ],
   "source": [
    "\n",
    "# Naive Bayes\n",
    "nb_model = MultinomialNB()\n",
    "nb_model.fit(X_train_vec, y_train)\n",
    "nb_preds = nb_model.predict(X_test_vec)\n",
    "print(\"Naive Bayes Classification Report:\")\n",
    "print(classification_report(y_test, nb_preds))\n",
    "\n",
    "# Logistic Regression\n",
    "lr_model = LogisticRegression(max_iter=1000)\n",
    "lr_model.fit(X_train_vec, y_train)\n",
    "lr_preds = lr_model.predict(X_test_vec)\n",
    "print(\"Logistic Regression Classification Report:\")\n",
    "print(classification_report(y_test, lr_preds))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "602790b1-df66-4d2b-9bcc-e846cf7343b7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "# Check label distribution\n",
    "sns.countplot(x=y)\n",
    "plt.title('Class Distribution')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "237cfe68-b16b-47ae-a960-2874303f8da2",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n",
    "\n",
    "def evaluate_model(model, X_test, y_test, model_name=\"Model\"):\n",
    "    y_pred = model.predict(X_test)\n",
    "    print(f\"{model_name} Accuracy: {accuracy_score(y_test, y_pred):.4f}\")\n",
    "    print(f\"{model_name} Classification Report:\")\n",
    "    print(classification_report(y_test, y_pred))\n",
    "    cm = confusion_matrix(y_test, y_pred, labels=model.classes_)\n",
    "    disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=model.classes_)\n",
    "    disp.plot(cmap=plt.cm.Blues)\n",
    "    plt.title(f'{model_name} Confusion Matrix')\n",
    "    plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "1653204a-5cd3-4ac6-9633-36c12211c0bc",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Random Forest Accuracy: 0.8359\n",
      "Random Forest Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "    negative       0.85      0.35      0.50       180\n",
      "    positive       0.83      0.98      0.90       600\n",
      "\n",
      "    accuracy                           0.84       780\n",
      "   macro avg       0.84      0.67      0.70       780\n",
      "weighted avg       0.84      0.84      0.81       780\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "rf_model = RandomForestClassifier(n_estimators=100, random_state=42)\n",
    "rf_model.fit(X_train_vec, y_train)\n",
    "evaluate_model(rf_model, X_test_vec, y_test, \"Random Forest\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "a7537e12-2412-4310-af94-206a6c87dfc1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Logistic Regression Accuracy: 0.8064\n",
      "Logistic Regression Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "    negative       0.85      0.19      0.32       180\n",
      "    positive       0.80      0.99      0.89       600\n",
      "\n",
      "    accuracy                           0.81       780\n",
      "   macro avg       0.83      0.59      0.60       780\n",
      "weighted avg       0.82      0.81      0.76       780\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Logistic Regression\n",
    "lr_model = LogisticRegression(max_iter=1000)\n",
    "lr_model.fit(X_train_vec, y_train)\n",
    "evaluate_model(lr_model, X_test_vec, y_test, \"Logistic Regression\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "eca55479-cb0c-4431-af30-30f7848c811e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Support Vector Machine Accuracy: 0.8462\n",
      "Support Vector Machine Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "    negative       0.74      0.51      0.61       180\n",
      "    positive       0.87      0.95      0.90       600\n",
      "\n",
      "    accuracy                           0.85       780\n",
      "   macro avg       0.80      0.73      0.75       780\n",
      "weighted avg       0.84      0.85      0.84       780\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "from sklearn.svm import LinearSVC\n",
    "\n",
    "svm_model = LinearSVC()\n",
    "svm_model.fit(X_train_vec, y_train)\n",
    "evaluate_model(svm_model, X_test_vec, y_test, \"Support Vector Machine\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "1f1a8ea1-0476-43cf-be42-afb15d0021c3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "K-Nearest Neighbors Accuracy: 0.8308\n",
      "K-Nearest Neighbors Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "    negative       0.74      0.41      0.53       180\n",
      "    positive       0.84      0.96      0.90       600\n",
      "\n",
      "    accuracy                           0.83       780\n",
      "   macro avg       0.79      0.68      0.71       780\n",
      "weighted avg       0.82      0.83      0.81       780\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "\n",
    "knn_model = KNeighborsClassifier(n_neighbors=5)\n",
    "knn_model.fit(X_train_vec, y_train)\n",
    "evaluate_model(knn_model, X_test_vec, y_test, \"K-Nearest Neighbors\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "e3312692-aa39-447f-9cc9-99987b798104",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TF-IDF with n-gram shape: (1820, 10000)\n"
     ]
    }
   ],
   "source": [
    "\n",
    "# TF-IDF with unigram + bigram (1,2)\n",
    "vectorizer_ngram = TfidfVectorizer(ngram_range=(1, 2), max_features=10000)\n",
    "X_train_ngram = vectorizer_ngram.fit_transform(X_train)\n",
    "X_test_ngram = vectorizer_ngram.transform(X_test)\n",
    "\n",
    "print(f\"TF-IDF with n-gram shape: {X_train_ngram.shape}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "e0c4f1a5-f6e4-4442-b62d-5c1b51b9b10e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Naive Bayes (N-gram TF-IDF) Accuracy: 0.7718\n",
      "Naive Bayes (N-gram TF-IDF) Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "    negative       1.00      0.01      0.02       180\n",
      "    positive       0.77      1.00      0.87       600\n",
      "\n",
      "    accuracy                           0.77       780\n",
      "   macro avg       0.89      0.51      0.45       780\n",
      "weighted avg       0.82      0.77      0.67       780\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Logistic Regression (N-gram TF-IDF) Accuracy: 0.7923\n",
      "Logistic Regression (N-gram TF-IDF) Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "    negative       0.88      0.12      0.21       180\n",
      "    positive       0.79      0.99      0.88       600\n",
      "\n",
      "    accuracy                           0.79       780\n",
      "   macro avg       0.83      0.56      0.54       780\n",
      "weighted avg       0.81      0.79      0.72       780\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Random Forest (N-gram TF-IDF) Accuracy: 0.8295\n",
      "Random Forest (N-gram TF-IDF) Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "    negative       0.86      0.31      0.46       180\n",
      "    positive       0.83      0.98      0.90       600\n",
      "\n",
      "    accuracy                           0.83       780\n",
      "   macro avg       0.84      0.65      0.68       780\n",
      "weighted avg       0.83      0.83      0.80       780\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SVM (N-gram TF-IDF) Accuracy: 0.8423\n",
      "SVM (N-gram TF-IDF) Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "    negative       0.76      0.47      0.58       180\n",
      "    positive       0.86      0.95      0.90       600\n",
      "\n",
      "    accuracy                           0.84       780\n",
      "   macro avg       0.81      0.71      0.74       780\n",
      "weighted avg       0.83      0.84      0.83       780\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "KNN (N-gram TF-IDF) Accuracy: 0.7949\n",
      "KNN (N-gram TF-IDF) Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "    negative       0.69      0.21      0.32       180\n",
      "    positive       0.80      0.97      0.88       600\n",
      "\n",
      "    accuracy                           0.79       780\n",
      "   macro avg       0.74      0.59      0.60       780\n",
      "weighted avg       0.78      0.79      0.75       780\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "# Naive Bayes\n",
    "nb_model_ng = MultinomialNB()\n",
    "nb_model_ng.fit(X_train_ngram, y_train)\n",
    "evaluate_model(nb_model_ng, X_test_ngram, y_test, \"Naive Bayes (N-gram TF-IDF)\")\n",
    "\n",
    "# Logistic Regression\n",
    "lr_model_ng = LogisticRegression(max_iter=1000)\n",
    "lr_model_ng.fit(X_train_ngram, y_train)\n",
    "evaluate_model(lr_model_ng, X_test_ngram, y_test, \"Logistic Regression (N-gram TF-IDF)\")\n",
    "\n",
    "# Random Forest\n",
    "\n",
    "rf_model_ng = RandomForestClassifier(n_estimators=100, random_state=42)\n",
    "rf_model_ng.fit(X_train_ngram, y_train)\n",
    "evaluate_model(rf_model_ng, X_test_ngram, y_test, \"Random Forest (N-gram TF-IDF)\")\n",
    "\n",
    "# Support Vector Machine\n",
    "svm_model_ng = LinearSVC()\n",
    "svm_model_ng.fit(X_train_ngram, y_train)\n",
    "evaluate_model(svm_model_ng, X_test_ngram, y_test, \"SVM (N-gram TF-IDF)\")\n",
    "\n",
    "# K-Nearest Neighbors\n",
    "knn_model_ng = KNeighborsClassifier(n_neighbors=5)\n",
    "knn_model_ng.fit(X_train_ngram, y_train)\n",
    "evaluate_model(knn_model_ng, X_test_ngram, y_test, \"KNN (N-gram TF-IDF)\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b8698164-e229-4883-bde9-77206cc18136",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "46d91e0a-db29-4597-9cb0-ee5600ba5b07",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "d4177c96-140b-454d-8ddc-e4a3744015b6",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package punkt to\n",
      "[nltk_data]     C:\\Users\\HP\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package punkt is already up-to-date!\n"
     ]
    }
   ],
   "source": [
    "import nltk\n",
    "nltk.download('punkt')\n",
    "\n",
    "def evaluate_model(model_name, y_true, y_pred):\n",
    "    accuracy = accuracy_score(y_true, y_pred)\n",
    "    precision = precision_score(y_true, y_pred, average='weighted') \n",
    "    recall = recall_score(y_true, y_pred, average='weighted') \n",
    "    f1 = f1_score(y_true, y_pred, average='weighted') \n",
    "    cm = confusion_matrix(y_true, y_pred)\n",
    "\n",
    "    report = classification_report(y_true, y_pred)\n",
    "    metrics = {\n",
    "        'Model Name': model_name,\n",
    "        'Accuracy': accuracy, \n",
    "        'Precision': precision, \n",
    "        'Recall': recall, \n",
    "        'F1 Score': f1,\n",
    "        'Classification Report': report\n",
    "    } \n",
    "    return metrics\n",
    "        \n",
    "        \n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "fc8c3df2-75e8-4d27-9a0d-cc3283d73fb6",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "def train_random_forest_classifier_with_grid_search(X_train_vec, y_train, X_test_vec, y_test, evaluate_model_func):\n",
    "    rf_classifier = RandomForestClassifier(random_state=42)\n",
    "    param_grid = { \n",
    "        'n_estimators': [100, 200, 300], \n",
    "        'max_depth': [None, 10, 20, 30], \n",
    "    }\n",
    "    grid_search = GridSearchCV(estimator=rf_classifier, param_grid=param_grid, cv=5, scoring='accuracy', n_jobs=-1)\n",
    "    grid_search.fit(X_train_vec, y_train)\n",
    "    best_rf_classifier = grid_search.best_estimator_y_pred = best_rf_classifier.predict(X_test_vec)\n",
    "    evaluation_results = evaluate_model_func('RandomForestClassifier', y_test, y_pred)\n",
    "    for key, value in evaluation_results.items():\n",
    "        if key == 'Classification Report':\n",
    "            print(value)\n",
    "        else:\n",
    "            print(f\"{key}: {value:.4f}\" if isinstance(value, float) \n",
    "    else f\"{key}: \\n{value}\")\n",
    "\n",
    "        print(\"\\nBest hyperparameters found by GridSearchCV:\") \n",
    "        print(grid_search.best_params_)\n",
    "    \n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "77fdbd6a-62c9-4885-bcf0-4055d0a48343",
   "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>text</th>\n",
       "      <th>sentiment</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Java Concurrency in Practice is probably the b...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>haha aww hun i bet you are more creative tha...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>_pickle lol, thank you very much Hope you`re h...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Out for an evening on the town with jeremy. Sa...</td>\n",
       "      <td>negative</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>- just took over the #1 Most Endorsed spot on...</td>\n",
       "      <td>positive</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                text sentiment\n",
       "0  Java Concurrency in Practice is probably the b...  positive\n",
       "1    haha aww hun i bet you are more creative tha...  positive\n",
       "2  _pickle lol, thank you very much Hope you`re h...  positive\n",
       "3  Out for an evening on the town with jeremy. Sa...  negative\n",
       "4   - just took over the #1 Most Endorsed spot on...  positive"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"unbalanceddataset.csv\")\n",
    "df.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "dc6b131c-f301-4757-b674-ff938f6c507c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "sentiment\n",
       "positive    2000\n",
       "negative     600\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['sentiment'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "2d453d60-a3df-44e6-acb6-92f17d778912",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       java concurrency practice probably best java b...\n",
       "1                               haha aww hun bet creative\n",
       "2                  pickle lol thank hope having great day\n",
       "3                   evening town jeremy sad carrie t come\n",
       "4       just took endorsed spot twindexx com thanks en...\n",
       "                              ...                        \n",
       "2595    s yall early night think ima bout shower chill...\n",
       "2596                                                agree\n",
       "2597                                          yeah thanks\n",
       "2598                                         good morning\n",
       "2599     em baby starts kindergarten crazy summer s going\n",
       "Name: clean_text, Length: 2600, dtype: object"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import re\n",
    "import string\n",
    "from sklearn.feature_extraction.text import ENGLISH_STOP_WORDS\n",
    "\n",
    "def simple_preprocess(text):\n",
    "    text = str(text).lower() \n",
    "    text = re.sub(r\"<.*?>\", \" \", text)  \n",
    "    text = re.sub(r\"[^a-zA-Z\\s]\", \" \", text) \n",
    "    text = text.translate(str.maketrans(\"\", \"\", string.punctuation))  \n",
    "    tokens = text.split()\n",
    "    tokens = [word for word in tokens if word not in ENGLISH_STOP_WORDS]\n",
    "    return \" \".join(tokens)\n",
    "\n",
    "df[\"clean_text\"] = df[\"text\"].apply(simple_preprocess)\n",
    "df = df.dropna()\n",
    "df['clean_text']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "aeb70a7f-fb88-4646-a529-a0332976c757",
   "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>text</th>\n",
       "      <th>sentiment</th>\n",
       "      <th>clean_text</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Java Concurrency in Practice is probably the b...</td>\n",
       "      <td>positive</td>\n",
       "      <td>java concurrency practice probably best java b...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>haha aww hun i bet you are more creative tha...</td>\n",
       "      <td>positive</td>\n",
       "      <td>haha aww hun bet creative</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>_pickle lol, thank you very much Hope you`re h...</td>\n",
       "      <td>positive</td>\n",
       "      <td>pickle lol thank hope having great day</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Out for an evening on the town with jeremy. Sa...</td>\n",
       "      <td>negative</td>\n",
       "      <td>evening town jeremy sad carrie t come</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>- just took over the #1 Most Endorsed spot on...</td>\n",
       "      <td>positive</td>\n",
       "      <td>just took endorsed spot twindexx com thanks en...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                text sentiment  \\\n",
       "0  Java Concurrency in Practice is probably the b...  positive   \n",
       "1    haha aww hun i bet you are more creative tha...  positive   \n",
       "2  _pickle lol, thank you very much Hope you`re h...  positive   \n",
       "3  Out for an evening on the town with jeremy. Sa...  negative   \n",
       "4   - just took over the #1 Most Endorsed spot on...  positive   \n",
       "\n",
       "                                          clean_text  \n",
       "0  java concurrency practice probably best java b...  \n",
       "1                          haha aww hun bet creative  \n",
       "2             pickle lol thank hope having great day  \n",
       "3              evening town jeremy sad carrie t come  \n",
       "4  just took endorsed spot twindexx com thanks en...  "
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "73d4c14f-56ba-4dd5-b7a4-1959d4a09bc9",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = df['clean_text']\n",
    "y = df['sentiment']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cd5d2c6c-e574-429a-a5a2-7e9f18bc88b5",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.30, random_state=42, stratify=y)\n",
    "\n",
    "vectorizer = TfidfVectorizer()\n",
    "X_train_vec = vectorizer.fit_transform(X_train)\n",
    "X_test_vec = vectorizer.transform(X_test)\n",
    "\n",
    "train_random_forest_classifier_with_grid_search(X_train_vec, y_train, X_test_vec, y_test, evaluate_model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0e5ee91c-5b59-441f-aef7-3d8d3f610a7d",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.30, random_state=42, stratify=y\n",
    ")\n",
    "\n",
    "# 2. تحويل النصوص إلى متجهات باستخدام TF-IDF\n",
    "vectorizer = TfidfVectorizer()\n",
    "X_train_vec = vectorizer.fit_transform(X_train)\n",
    "X_test_vec = vectorizer.transform(X_test)\n",
    "\n",
    "# 3. دالة لتقييم النموذج\n",
    "def evaluate_model(model_name, y_true, y_pred):\n",
    "    return {\n",
    "        \"Model\": model_name,\n",
    "        \"Accuracy\": accuracy_score(y_true, y_pred),\n",
    "        \"Precision\": precision_score(y_true, y_pred, average='weighted'),\n",
    "        \"Recall\": recall_score(y_true, y_pred, average='weighted'),\n",
    "        \"F1-Score\": f1_score(y_true, y_pred, average='weighted'),\n",
    "        \"Confusion Matrix\": confusion_matrix(y_true, y_pred)\n",
    "    }\n",
    "\n",
    "# 4. دالة تدريب RandomForest مع GridSearchCV\n",
    "def train_random_forest_classifier_with_grid_search(X_train_vec, y_train, X_test_vec, y_test, evaluate_model_func):\n",
    "    rf_classifier = RandomForestClassifier(random_state=42)\n",
    "\n",
    "    param_grid = {\n",
    "        'n_estimators': [100, 200],\n",
    "        'max_depth': [None, 10, 20],\n",
    "        'min_samples_split': [2, 5],\n",
    "        'min_samples_leaf': [1, 2]\n",
    "    }\n",
    "\n",
    "    grid_search = GridSearchCV(estimator=rf_classifier, param_grid=param_grid, cv=5, scoring='accuracy', n_jobs=-1)\n",
    "    grid_search.fit(X_train_vec, y_train)\n",
    "\n",
    "    best_rf_classifier = grid_search.best_estimator_\n",
    "    y_pred = best_rf_classifier.predict(X_test_vec)\n",
    "\n",
    "    evaluation_results = evaluate_model_func('RandomForestClassifier', y_test, y_pred)\n",
    "    for key, value in evaluation_results.items():\n",
    "        print(f\"{key}:\\n{value}\\n\")\n",
    "\n",
    "# 5. تشغيل التدريب والتقييم\n",
    "train_random_forest_classifier_with_grid_search(X_train_vec, y_train, X_test_vec, y_test, evaluate_model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e1ae6ed2-6c2a-4772-849f-a298b3ccdfce",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=42, stratify=y)\n",
    "vectorizer = TfidfVectorizer()\n",
    "X_train_vec = vectorizer.fit_transform(X_train)\n",
    "X_test_vec = vectorizer.transform(X_test)\n",
    "\n",
    "from imblearn.over_sampling import RandomOverSampler\n",
    "from collections import Counter\n",
    "ros = RandomOverSampler(random_state=42)\n",
    "X_ros, y_ros = ros.fit_resample(X_train_vec, y_train)\n",
    "print(\"After RandomOversampling:\", Counter(y_ros))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0dc157b8-8431-44e5-84db-f25161b99b1a",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_random_forest_classifier_with_grid_search(X_ros, y_ros, X_test_vec, y_test, evaluate_model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d070721a-4500-4c95-98c2-330310683d83",
   "metadata": {},
   "outputs": [],
   "source": [
    "from imblearn.over_sampling import SMOTE\n",
    "smote = SMOTE(random_state=42)\n",
    "X_smote, y_smote = smote.fit_resample(X_train_vec, y_train)\n",
    "\n",
    "print(\"After SMOTE:\", Counter(y_smote))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "1034dfbc-1139-4669-ab32-695e412a4a17",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model:\n",
      "RandomForestClassifier\n",
      "\n",
      "Accuracy:\n",
      "0.8487179487179487\n",
      "\n",
      "Precision:\n",
      "0.8435643828668294\n",
      "\n",
      "Recall:\n",
      "0.8487179487179487\n",
      "\n",
      "F1-Score:\n",
      "0.8324125513217512\n",
      "\n",
      "Confusion Matrix:\n",
      "[[ 82  98]\n",
      " [ 20 580]]\n",
      "\n"
     ]
    }
   ],
   "source": [
    "train_random_forest_classifier_with_grid_search(X_smote, y_smote, X_test_vec, y_test, evaluate_model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b86ead8e-8834-4ac1-b40e-ecad07860b30",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.12.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}