import pandas as pd
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score

# Load the data
df = pd.read_csv('spam-sms.tsv', sep="\t", names=["label", "text"])

# Load and explore the data
print(df.head())
print(df.describe())

# Data cleaning
df.dropna(inplace=True)

# Feature extraction
vectorizer = CountVectorizer()
X = vectorizer.fit_transform(df['text'])
y = df['label']

# Split the 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)

# Initialize classifiers
classifiers = {
    "Naive Bayes": MultinomialNB(),
    "Logistic Regression": LogisticRegression(random_state=42),
    "Random Forest": RandomForestClassifier(n_estimators=100, random_state=42)
}

# Function to evaluate model
def evaluate_model(y_true, y_pred):
    return {
        "Accuracy": accuracy_score(y_true, y_pred),
        "Precision": precision_score(y_true, y_pred, pos_label='spam'),
        "Recall": recall_score(y_true, y_pred, pos_label='spam'),
        "F1-score": f1_score(y_true, y_pred, pos_label='spam')
    }

# Train and evaluate each classifier
results = {}

for name, clf in classifiers.items():
    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_test)
    results[name] = evaluate_model(y_test, y_pred)

# Print results
for name, metrics in results.items():
    print(f"\nResults for {name}:")
    for metric, value in metrics.items():
        print(f"{metric}: {value:.4f}")

# Compare classifiers
print("\nComparison of classifiers:")
metrics = list(results[name].keys())
for metric in metrics:
    print(f"\n{metric}:")
    for name in classifiers.keys():
        print(f"{name}: {results[name][metric]:.4f}")

# Find the best classifier for each metric
best_classifiers = {}
for metric in metrics:
    best_classifier = max(results, key=lambda x: results[x][metric])
    best_classifiers[metric] = best_classifier

print("\nBest classifier for each metric:")
for metric, classifier in best_classifiers.items():
    print(f"{metric}: {classifier}")