sms_filter.py

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report

# Load SMS Spam Collection dataset
data = pd.read_csv('spam.csv', encoding='latin-1')
data = data[['v1', 'v2']].rename(columns={'v1': 'label', 'v2': 'text'})

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(data['text'], data['label'], test_size=0.2, random_state=42)

# Convert text data into feature vectors using CountVectorizer
vectorizer = CountVectorizer()
X_train = vectorizer.fit_transform(X_train)
X_test = vectorizer.transform(X_test)

# Train Random Forest classifier
rf_classifier = RandomForestClassifier(n_estimators=100, random_state=42)
rf_classifier.fit(X_train, y_train)

# Predict on test data
y_pred = rf_classifier.predict(X_test)

# Evaluate model
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
print("\nClassification Report:")
print(classification_report(y_test, y_pred))