sms.py

import os
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.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.metrics import classification_report, accuracy_score

# Set working directory
os.chdir(r'D:\Desktop\vscode\projects\python\aspirenex\sms span model')

# Try reading the file with different encodings and inspect the columns
try:
    df = pd.read_csv("spam.csv", encoding='utf-8')
except UnicodeDecodeError:
    df = pd.read_csv('spam.csv', encoding='ISO-8859-1')

# Display the first few rows and the column names
print(df.head())
print(df.columns)

# Assuming the columns are ['v1', 'v2', ...] where 'v1' is label and 'v2' is the message
# Adjust the column selection based on the actual column names
df = df[['v1', 'v2']]
df.columns = ['label', 'message']

# Convert labels to binary
df['label'] = df['label'].map({'ham': 0, 'spam': 1})

# Split the data
X_train, X_test, y_train, y_test = train_test_split(df['message'], df['label'], test_size=0.2, random_state=42)

# Feature extraction using TF-IDF
vectorizer = TfidfVectorizer()
X_train_tfidf = vectorizer.fit_transform(X_train)
X_test_tfidf = vectorizer.transform(X_test)

# Train and evaluate different models
models = {
    "Naive Bayes": MultinomialNB(),
    "Logistic Regression": LogisticRegression(max_iter=1000),
    "Support Vector Machine": SVC(kernel='linear', probability=True)
}

for name, model in models.items():
    model.fit(X_train_tfidf, y_train)
    predictions = model.predict(X_test_tfidf)
    print(f"{name}:\n")
    print(f"Accuracy: {accuracy_score(y_test, predictions)}")
    print(classification_report(y_test, predictions))
    print("\n")