# Always suppress warnings for a cleaner output.
import warnings; warnings.filterwarnings("ignore")
import numpy as np
np.random.seed(42)

# Data setup: Load Heart Disease Dataset
import kagglehub, os, pandas as pd
path = kagglehub.dataset_download('johnsmith88/heart-disease-dataset')
files = os.listdir(path)
df = pd.read_csv(os.path.join(path, files[0]))
print(df.shape)
print(df.head(3))

# Check for missing values
df.isnull().sum()

# Basic data info
df.info()

# View summary statistics
df.describe()

# Plot target variable counts
import matplotlib.pyplot as plt
import seaborn as sns
sns.countplot(data=df, x='target')
plt.title('Count of patients with and without heart disease')
plt.xlabel('Diagnosis (1 = Disease, 0 = No Disease)')
plt.ylabel('Number of patients')
plt.show()

# Visualize a key numeric feature
sns.histplot(data=df, x='age', hue='target', kde=True, bins=20)
plt.title('Age Distribution by Diagnosis')
plt.xlabel('Age')
plt.ylabel('Number of patients')
plt.legend(['No Disease', 'Disease'], title='Diagnosis')
plt.show()

# Look for correlation between features
corr = df.corr()
plt.figure(figsize=(10, 8))
sns.heatmap(corr, annot=True, cmap='coolwarm', fmt='.2f')
plt.title('Feature Correlations')
plt.show()

# Split into features and target, and then train test sets
from sklearn.model_selection import train_test_split
X = df.drop('target', axis=1)
y = df['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
print('Train samples:', X_train.shape[0])
print('Test samples:', X_test.shape[0])

# Scale data to standard range
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Initialize and train classifier
from sklearn.linear_model import LogisticRegression
model = LogisticRegression(random_state=42)
model.fit(X_train_scaled, y_train)

# Predict on test data
y_pred = model.predict(X_test_scaled)

# Measure model accuracy
from sklearn.metrics import accuracy_score
acc = accuracy_score(y_test, y_pred)
print(f"Test accuracy: {acc:.2f}")

# Show confusion matrix
from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
cm = confusion_matrix(y_test, y_pred)
disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=['No Disease', 'Disease'])
disp.plot(cmap='Blues')
plt.title('Confusion Matrix')
plt.show()

# Print classification report
from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred, target_names=['No Disease', 'Disease']))

# Enter new patient data for prediction
sample_idx = int(input("Enter a test sample index from 0 to {}: ".format(X_test.shape[0] - 1)))
sample_features = X_test.iloc[sample_idx]
sample_scaled = scaler.transform([sample_features])[0]
pred = model.predict([sample_scaled])[0]
print("Prediction for this patient:", "Disease" if pred == 1 else "No Disease")
print("Actual diagnosis:", "Disease" if y_test.iloc[sample_idx] == 1 else "No Disease")