ML Exp 5

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score, confusion_matrix

url = "https://raw.githubusercontent.com/sakshi2k/Social_Network_Ads/refs/heads/master/Social_Network_Ads.csv"
df = pd.read_csv(url)

df['Gender'] = df['Gender'].map({'Female': 0, 'Male': 1})
df = df.drop(['User ID'], axis=1)
X = df[['Age', 'EstimatedSalary', 'Gender']]
y = df['Purchased']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)

scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

log_model = LogisticRegression()
log_model.fit(X_train_scaled, y_train)
log_pred = log_model.predict(X_test_scaled)
log_acc = accuracy_score(y_test, log_pred)
log_cm = confusion_matrix(y_test, log_pred)

knn_model = KNeighborsClassifier(n_neighbors=5)
knn_model.fit(X_train_scaled, y_train)
knn_pred = knn_model.predict(X_test_scaled)
knn_acc = accuracy_score(y_test, knn_pred)
knn_cm = confusion_matrix(y_test, knn_pred)

tree_model = DecisionTreeClassifier(random_state=42)
tree_model.fit(X_train, y_train)
tree_pred = tree_model.predict(X_test)
tree_acc = accuracy_score(y_test, tree_pred)
tree_cm = confusion_matrix(y_test, tree_pred)

print("📊 Model Accuracy Comparison:")
print(f"Logistic Regression Accuracy: {log_acc:.2f}")
print(f"KNN Accuracy: {knn_acc:.2f}")
print(f"Decision Tree Accuracy: {tree_acc:.2f}")

print("\n🧮 Confusion Matrices:")
print("Logistic Regression Confusion Matrix:")
print(log_cm)

print("\nKNN Confusion Matrix:")
print(knn_cm)

print("\nDecision Tree Confusion Matrix:")
print(tree_cm)