@lalithapulapa81

Step 1: Import libraries

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, confusion_matrix, classification_report

Step 2: Load dataset

Example: SMS Spam Collection dataset (you can download as spam.csv)

data = pd.read_csv("spam.csv", encoding="latin-1")[["v1", "v2"]]
data.columns = ["label", "message"]

Step 3: Encode labels (ham = 0, spam = 1)

data["label"] = data["label"].map({"ham": 0, "spam": 1})

Step 4: Split dataset

X_train, X_test, y_train, y_test = train_test_split(
data["message"], data["label"], test_size=0.2, random_state=42
)

Step 5: Convert text to numerical features using TF-IDF

vectorizer = TfidfVectorizer(stop_words="english")
X_train_tfidf = vectorizer.fit_transform(X_train)
X_test_tfidf = vectorizer.transform(X_test)

Step 6: Train model (Naive Bayes)

model = MultinomialNB()
model.fit(X_train_tfidf, y_train)

Step 7: Predict

y_pred = model.predict(X_test_tfidf)

Step 8: Evaluate

print("✅ Accuracy:", accuracy_score(y_test, y_pred))
print("\nConfusion Matrix:\n", confusion_matrix(y_test, y_pred))
print("\nClassification Report:\n", classification_report(y_test, y_pred))