import numpy as np
import pandas as pd
from sklearn.neural_network import MLPClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score,classification_report,confusion_matrix
import matplotlib.pyplot as plt

# Load the dataset (assuming it's stored in a file)
data = pd.read_csv('heart.csv')

# Separate features and labels
X = data.iloc[:, :-1].values  # Features
y = data.iloc[:, -1].values   # Labels

# Split the dataset 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)

# Normalize the feature data
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Create and train the MLP model
mlp = MLPClassifier(hidden_layer_sizes=(100, 100), max_iter=1000, random_state=42)
training_loss = mlp.fit(X_train, y_train).loss_curve_

# Make predictions on the testing set
y_pred = mlp.predict(X_test)

# Evaluate the model
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)

# Plot the error convergence
plt.plot(training_loss)
plt.title("MLP Training Loss Convergence")
plt.xlabel("Iteration")
plt.ylabel("Training Loss")
plt.show()

conf_matrix=confusion_matrix(y_test,y_pred)
classification_rep=classification_report(y_test,y_pred)
print("\nConfusion Matrix:")
print(conf_matrix)
print("\nClassification Report:")
print(classification_rep)