{ "cells": [ { "cell_type": "code", "execution_count": 3, "id": "f99c6d70-18cc-4b96-89e3-7956e389df3c", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import re\n", "import string\n", "\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.feature_extraction.text import TfidfVectorizer\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.svm import LinearSVC\n", "from sklearn.metrics import classification_report, accuracy_score, f1_score\n", "from sklearn.utils.class_weight import compute_class_weight\n" ] }, { "cell_type": "code", "execution_count": 4, "id": "fb09003c-e258-4add-baa0-24e49a6c46a4", "metadata": {}, "outputs": [ { "ename": "SyntaxError", "evalue": "(unicode error) 'unicodeescape' codec can't decode bytes in position 2-3: truncated \\UXXXXXXXX escape (1851046779.py, line 2)", "output_type": "error", "traceback": [ "\u001b[1;36m Cell \u001b[1;32mIn[4], line 2\u001b[1;36m\u001b[0m\n\u001b[1;33m df = pd.read_csv(\"C:\\Users\\khh26\\Downloads\\archive (11)\\unbalanceddataset.csv\")\u001b[0m\n\u001b[1;37m ^\u001b[0m\n\u001b[1;31mSyntaxError\u001b[0m\u001b[1;31m:\u001b[0m (unicode error) 'unicodeescape' codec can't decode bytes in position 2-3: truncated \\UXXXXXXXX escape\n" ] } ], "source": [ "# Load dataset\n", "df = pd.read_csv(\"C:\\Users\\khh26\\Downloads\\archive (11)\\unbalanceddataset.csv\")\n", "\n", "df.head()\n" ] }, { "cell_type": "code", "execution_count": 5, "id": "f086ba60-ce92-4ae2-999d-f33ff1d47c42", "metadata": {}, "outputs": [ { "ename": "SyntaxError", "evalue": "(unicode error) 'unicodeescape' codec can't decode bytes in position 2-3: truncated \\UXXXXXXXX escape (4024888092.py, line 2)", "output_type": "error", "traceback": [ "\u001b[1;36m Cell \u001b[1;32mIn[5], line 2\u001b[1;36m\u001b[0m\n\u001b[1;33m df = pd.read_csv(\"C:\\Users\\khh26\\Downloads\\unbalanceddataset.csv\")\u001b[0m\n\u001b[1;37m ^\u001b[0m\n\u001b[1;31mSyntaxError\u001b[0m\u001b[1;31m:\u001b[0m (unicode error) 'unicodeescape' codec can't decode bytes in position 2-3: truncated \\UXXXXXXXX escape\n" ] } ], "source": [ "# Load dataset\n", "df = pd.read_csv(\"C:\\Users\\khh26\\Downloads\\unbalanceddataset.csv\")\n", "\n", "df.head()" ] }, { "cell_type": "code", "execution_count": null, "id": "a6cf0794-6fa7-4bcf-bc0d-64c8ed1f3686", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 6, "id": "fd84757b-ab68-423c-9c98-248ac9afda19", "metadata": {}, "outputs": [], "source": [ "df = pd.read_csv(r\"C:\\Users\\khh26\\Downloads\\unbalanceddataset.csv\")\n" ] }, { "cell_type": "code", "execution_count": 7, "id": "6dacd800-d14b-45c9-9fba-d5e4b22cf5a1", "metadata": {}, "outputs": [], "source": [ "def preprocess_text(text):\n", " text = text.lower()\n", " text = re.sub(r\"http\\S+|www\\S+\", \" \", text) # remove URLs\n", " text = re.sub(r\"<.*?>\", \" \", text) # remove HTML\n", " text = text.translate(str.maketrans(\"\", \"\", string.punctuation))\n", " text = re.sub(r\"\\s+\", \" \", text).strip()\n", " return text\n", "\n", "df[\"clean_text\"] = df[\"text\"].astype(str).apply(preprocess_text)\n" ] }, { "cell_type": "code", "execution_count": 8, "id": "4b2c73f6-5f46-4258-98ab-9da6f3ed443c", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "sentiment\n", "positive 2000\n", "negative 600\n", "Name: count, dtype: int64" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[\"sentiment\"].value_counts()\n" ] }, { "cell_type": "code", "execution_count": 9, "id": "e34c4117-b93b-4a8b-afc8-e8e756b87adb", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "sentiment\n", "positive 2000\n", "negative 600\n", "Name: count, dtype: int64" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[\"sentiment\"].value_counts()\n" ] }, { "cell_type": "code", "execution_count": 12, "id": "28745935-a022-48b2-890f-5478902519fa", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Index(['text', 'sentiment', 'clean_text'], dtype='object')" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.columns\n" ] }, { "cell_type": "code", "execution_count": 13, "id": "2fa9b278-87d6-4fc5-9b05-68fb8a43f3d8", "metadata": {}, "outputs": [], "source": [ "label_map = {\"negative\": 0, \"positive\": 1}\n", "df[\"label\"] = df[\"sentiment\"].map(label_map)\n" ] }, { "cell_type": "code", "execution_count": 14, "id": "824bbf62-6894-49be-89dd-85c75ef23c07", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
sentimentlabel
0positive1
1positive1
2positive1
3negative0
4positive1
\n", "
" ], "text/plain": [ " sentiment label\n", "0 positive 1\n", "1 positive 1\n", "2 positive 1\n", "3 negative 0\n", "4 positive 1" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[[\"sentiment\", \"label\"]].head()\n" ] }, { "cell_type": "code", "execution_count": 15, "id": "1ee50fc6-409d-4a53-8969-3da8b7fca756", "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import train_test_split\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(\n", " df[\"clean_text\"],\n", " df[\"label\"],\n", " test_size=0.2,\n", " random_state=42,\n", " stratify=df[\"label\"]\n", ")\n" ] }, { "cell_type": "code", "execution_count": 16, "id": "9bf94c91-b5e8-4e1b-994b-b15a260f4342", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "label\n", "1 0.769231\n", "0 0.230769\n", "Name: proportion, dtype: float64" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y_train.value_counts(normalize=True)\n" ] }, { "cell_type": "code", "execution_count": 19, "id": "38fab310-91af-4729-85c7-acbbe7735255", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{0: np.float64(2.1666666666666665), 1: np.float64(0.65)}" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import numpy as np\n", "from sklearn.utils.class_weight import compute_class_weight\n", "\n", "class_weights = compute_class_weight(\n", " class_weight=\"balanced\",\n", " classes=np.unique(y_train),\n", " y=y_train\n", ")\n", "\n", "class_weight_dict = {\n", " 0: class_weights[0],\n", " 1: class_weights[1]\n", "}\n", "\n", "class_weight_dict\n" ] }, { "cell_type": "code", "execution_count": 20, "id": "93e58b7d-4793-41ae-a60d-297c701bc520", "metadata": {}, "outputs": [ { "ename": "NameError", "evalue": "name 'X_train_tfidf' is not defined", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)", "Cell \u001b[1;32mIn[20], line 4\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01msklearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01msvm\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m LinearSVC\n\u001b[0;32m 3\u001b[0m svm \u001b[38;5;241m=\u001b[39m LinearSVC(class_weight\u001b[38;5;241m=\u001b[39mclass_weight_dict)\n\u001b[1;32m----> 4\u001b[0m svm\u001b[38;5;241m.\u001b[39mfit(X_train_tfidf, y_train)\n\u001b[0;32m 6\u001b[0m y_pred_svm \u001b[38;5;241m=\u001b[39m svm\u001b[38;5;241m.\u001b[39mpredict(X_test_tfidf)\n", "\u001b[1;31mNameError\u001b[0m: name 'X_train_tfidf' is not defined" ] } ], "source": [ "from sklearn.svm import LinearSVC\n", "\n", "svm = LinearSVC(class_weight=class_weight_dict)\n", "svm.fit(X_train_tfidf, y_train)\n", "\n", "y_pred_svm = svm.predict(X_test_tfidf)\n" ] }, { "cell_type": "code", "execution_count": 21, "id": "121fe4a5-d77e-4cfb-a86a-c43a46db48bc", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "((2080, 15756), (520, 15756))" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.feature_extraction.text import TfidfVectorizer\n", "\n", "vectorizer = TfidfVectorizer(\n", " ngram_range=(1, 2),\n", " max_features=50000,\n", " stop_words=\"english\",\n", " sublinear_tf=True\n", ")\n", "\n", "X_train_tfidf = vectorizer.fit_transform(X_train)\n", "X_test_tfidf = vectorizer.transform(X_test)\n", "\n", "X_train_tfidf.shape, X_test_tfidf.shape\n" ] }, { "cell_type": "code", "execution_count": 22, "id": "848e0ff3-3077-42af-a81a-b1440f55b710", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{0: np.float64(2.1666666666666665), 1: np.float64(0.65)}" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import numpy as np\n", "from sklearn.utils.class_weight import compute_class_weight\n", "\n", "class_weights = compute_class_weight(\n", " class_weight=\"balanced\",\n", " classes=np.unique(y_train),\n", " y=y_train\n", ")\n", "\n", "class_weight_dict = {0: class_weights[0], 1: class_weights[1]}\n", "class_weight_dict\n" ] }, { "cell_type": "code", "execution_count": 23, "id": "ccabdcf0-2b84-4a61-a69d-61849c175251", "metadata": {}, "outputs": [], "source": [ "from sklearn.svm import LinearSVC\n", "\n", "svm = LinearSVC(class_weight=class_weight_dict)\n", "svm.fit(X_train_tfidf, y_train)\n", "\n", "y_pred_svm = svm.predict(X_test_tfidf)\n" ] }, { "cell_type": "code", "execution_count": 24, "id": "818a0609-a3d4-4a44-9d6b-31eb7e9ab0e8", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.8634615384615385\n", "Macro F1: 0.7858853686402097\n", " precision recall f1-score support\n", "\n", " 0 0.78 0.57 0.66 120\n", " 1 0.88 0.95 0.91 400\n", "\n", " accuracy 0.86 520\n", " macro avg 0.83 0.76 0.79 520\n", "weighted avg 0.86 0.86 0.86 520\n", "\n" ] } ], "source": [ "from sklearn.metrics import accuracy_score, f1_score, classification_report\n", "\n", "print(\"Accuracy:\", accuracy_score(y_test, y_pred_svm))\n", "print(\"Macro F1:\", f1_score(y_test, y_pred_svm, average=\"macro\"))\n", "print(classification_report(y_test, y_pred_svm))\n" ] }, { "cell_type": "code", "execution_count": null, "id": "4f7a38ab-cfcd-47dc-9a3a-89bfa2565b16", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python (base)", "language": "python", "name": "base" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.13.5" } }, "nbformat": 4, "nbformat_minor": 5 }