01 Machine Learning | Spam Detection 1

pip install pandas scikit-learn nltk numpy

import pandas as pd
import numpy as np

# Load the SMS Spam Collection dataset (CSV file)
data = pd.read_csv('spam.csv', encoding='latin-1')

# Display the first few rows of the dataset
print(data.head())

import re
import nltk
from nltk.corpus import stopwords
from nltk.stem import PorterStemmer

# Download the stopwords corpus
#nltk.download('stopwords')

# Initialize the stemmer
stemmer = PorterStemmer()

# Preprocessing function
def preprocess_text(text):
    # Convert text to lowercase
    text = text.lower()
    # Remove non-alphabetic characters (keep spaces)
    text = re.sub(r'[^a-zA-Z\s]', '', text)
    # Tokenize the text
    words = text.split()
    # Remove stopwords and stem the words
    words = [stemmer.stem(word) for word in words if word not in stopwords.words('english')]
    return ' '.join(words)

# Apply the preprocessing function to the messages
data['v2'] = data['v2'].apply(preprocess_text)

# Display the cleaned data
print(data.head())

from sklearn.feature_extraction.text import TfidfVectorizer

# Sample messages
messages = ["Congratulations! You've won a prize.", "Hi, how are you?"]
# Convert text to numerical features

vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(messages)
print(X.toarray())  # Transformed text features

from sklearn.feature_extraction.text import TfidfVectorizer

# Convert text to numerical features using TF-IDF
vectorizer = TfidfVectorizer(max_features=5000)  # Limit to top 5000 features
X = vectorizer.fit_transform(data['v2']).toarray()

# Labels: spam or ham
y = data['v1'].map({'ham': 0, 'spam': 1}).values

from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

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

# Train the Naive Bayes model
model = MultinomialNB()
model.fit(X_train, y_train)



from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score

# Predict the test set
y_pred = model.predict(X_test)

# Calculate evaluation metrics
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)

print("Model Evaluation Metrics:")
print(f"Accuracy: {accuracy:.2f}")
print(f"Precision: {precision:.2f}")
print(f"Recall: {recall:.2f}")
print(f"F1-Score: {f1:.2f}")



from sklearn.metrics import classification_report

#Generate classification report
report = classification_report(y_test, y_pred, target_names=["Ham", "Spam"])
print(report)

def predict_spam(message):
    # Preprocess the input message
    processed_message = preprocess_text(message)
    # Convert the message to the same format as training data
    message_vector = vectorizer.transform([processed_message]).toarray()
    # Predict using the trained model
    prediction = model.predict(message_vector)
    return 'Spam' if prediction == 1 else 'Ham'

# Test the model with a new message
new_message = "Congratulations! You've won a $1000 gift card! Claim your prize now by clicking this link: [link]. Hurry, offer expires soon!"
print(predict_spam(new_message))

import joblib

# Save the model
joblib.dump(model, 'spam_detector_model.pkl')

# Save the vectorizer
joblib.dump(vectorizer, 'vectorizer.pkl')

print("Model and vectorizer saved successfully!")

import pandas as pd
import numpy as np

# Load the SMS Spam Collection dataset (CSV file)
data = pd.read_csv('spam.csv', encoding='latin-1')

# Display the first few rows of the dataset
print(data.head())

import re
import nltk
from nltk.corpus import stopwords
from nltk.stem import PorterStemmer

# Download the stopwords corpus
nltk.download('stopwords')

# Initialize the stemmer
stemmer = PorterStemmer()

# Preprocessing function
def preprocess_text(text):
    # Convert text to lowercase
    text = text.lower()
    # Remove non-alphabetic characters (keep spaces)
    text = re.sub(r'[^a-zA-Z\s]', '', text)
    # Tokenize the text
    words = text.split()
    # Remove stopwords and stem the words
    words = [stemmer.stem(word) for word in words if word not in stopwords.words('english')]
    return ' '.join(words)

# Apply the preprocessing function to the messages
data['v2'] = data['v2'].apply(preprocess_text)

# Display the cleaned data
print(data.head())

from sklearn.feature_extraction.text import TfidfVectorizer

# Convert text to numerical features using TF-IDF
vectorizer = TfidfVectorizer(max_features=5000)  # Limit to top 5000 features
X = vectorizer.fit_transform(data['v2']).toarray()

# Labels: spam or ham
y = data['v1'].map({'ham': 0, 'spam': 1}).values

from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

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

# Train the Naive Bayes model
model = MultinomialNB()
model.fit(X_train, y_train)



from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score

# Predict the test set
y_pred = model.predict(X_test)

# Calculate evaluation metrics
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)

print("Model Evaluation Metrics:")
print(f"Accuracy: {accuracy:.2f}")
print(f"Precision: {precision:.2f}")
print(f"Recall: {recall:.2f}")
print(f"F1-Score: {f1:.2f}")



from sklearn.metrics import classification_report

#Generate classification report
report = classification_report(y_test, y_pred, target_names=["Ham", "Spam"])
print(report)


def predict_spam(message):
    # Preprocess the input message
    processed_message = preprocess_text(message)
    # Convert the message to the same format as training data
    message_vector = vectorizer.transform([processed_message]).toarray()
    # Predict using the trained model
    prediction = model.predict(message_vector)
    return 'Spam' if prediction == 1 else 'Ham'

# Test the model with a new message
new_message = "Congratulations! You've won a $1000 gift card! Claim your prize now by clicking this link: [link]. Hurry, offer expires soon!"
print(predict_spam(new_message))

import joblib

# Save the model
joblib.dump(model, 'spam_detector_model.pkl')

# Save the vectorizer
joblib.dump(vectorizer, 'vectorizer.pkl')

print("Model and vectorizer saved successfully!")