import pandas as pd import nltk import re from sklearn.model_selection import train_test_split from sklearn.feature_extraction.text import TfidfVectorizer from nltk.corpus import stopwords from sklearn.linear_model import LogisticRegression import matplotlib.pyplot as plt import seaborn as sns from wordcloud import WordCloud from sklearn.metrics import accuracy_score, precision_score, f1_score, confusion_matrix, classification_report

File_CSV ="F:/Per Semester/Semester 7/NLP_Materi/Tugas/Tugas 5_162112233066/GTA_Review Data Sets.csv" CSV = pd.read_csv(File_CSV)

print("Data Training : ", CSV.head())

nltk.download('stopwords') stop_words = set(stopwords.words('english'))

def preprocess_text(text): if isinstance(text, str):
text = re.sub(r"[^a-zA-Z\s]", "", text)
text = text.lower()
words = [word for word in text.split() if word not in stop_words]
return " ".join(words) return "No Value"

Preprocess_CSV = CSV['processed_text'] = CSV['Review'].apply(preprocess_text)

print("Train Result : \n" , Preprocess_CSV.head(100))

long_string = ','.join(list(CSV['processed_text'].values)) wordcloud = WordCloud(background_color="white", max_words=100, contour_width=3, contour_color='steelblue') wordcloud.generate(long_string) wordcloud.to_image()

tfidf = TfidfVectorizer(max_features=1000)

X = tfidf.fit_transform(CSV['processed_text']).toarray() y = CSV['Sentiment']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

from sklearn.linear_model import LogisticRegression from sklearn.metrics import accuracy_score, classification_report

model = LogisticRegression() model.fit(X_train, y_train)

y_pred = model.predict(X_test)

accuracy = accuracy_score(y_test, y_pred) accuracy = accuracy_score(y_test, y_pred) precision = precision_score(y_test, y_pred, average='weighted') f1 = f1_score(y_test, y_pred, average='weighted') conf_matrix = confusion_matrix(y_test, y_pred)

print("Accuracy:", accuracy) print("Precision:", precision) print("F1 Score :", f1)

print("Result :\n", classification_report(y_test, y_pred))

plt.figure(figsize=(10, 7)) sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues', xticklabels=['Irrelevant', 'Positive', 'Negative', 'Neutral'], yticklabels=['Irrelevant', 'Positive', 'Negative', 'Neutral']) plt.xlabel('Predicted') plt.ylabel('Actual') plt.title('Confusion Matrix') plt.show()