naive_bayes.py

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score, classification_report

# Load the dataset
df = pd.read_csv("new2_clean_noneutral.csv")

# Check the first few rows to ensure the data is correct
print(df.head())

# Assuming your dataset has columns 'cleaned_text' for the text and 'Sentiment' for labels
# Convert sentiment labels to numeric values (positive=1, negative=0)
df['Sentiment'] = df['Sentiment'].map({'positive': 1, 'negative': 0})

# Define features and target
X = df['cleaned_text']
y = df['Sentiment']

# Split data into training and testing sets (80% train, 20% test)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Initialize TF-IDF vectorizer
vectorizer = TfidfVectorizer(max_features=5000)

# Fit and transform the training data
X_train_tfidf = vectorizer.fit_transform(X_train)

# Transform the test data
X_test_tfidf = vectorizer.transform(X_test)

# Initialize and train Multinomial Naive Bayes model
model = MultinomialNB()

# Train the model
model.fit(X_train_tfidf, y_train)

# Make predictions on the test set
y_pred = model.predict(X_test_tfidf)

# Evaluate the model's performance
print(f"Accuracy: {accuracy_score(y_test, y_pred):.4f}")
print("Classification Report:")
print(classification_report(y_test, y_pred))