import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

df = pd.read_csv('heart_failure_clinical_records_dataset.csv')

df.info()

df.describe()

df.isnull().sum()

sns.pairplot(df, hue='DEATH_EVENT', palette="inferno", corner=True)
plt.show()

# Correlation matrix
plt.figure(figsize = (12,10))
sns.heatmap(df.corr(), annot=True)
plt.show()

X = df.drop(['DEATH_EVENT'], axis=1)
y = df['DEATH_EVENT']

# 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)

log_reg = LogisticRegression()
log_reg.fit(X_train, y_train)
y_pred = log_reg.predict(X_test)
print('Logistic Regression Accuracy: {:.2f}%'.format(accuracy_score(y_test, y_pred) * 100))
print('Confusion Matrix:\n', confusion_matrix(y_test, y_pred))
print('Classification Report:\n', classification_report(y_test, y_pred))

knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(X_train, y_train)
y_pred = knn.predict(X_test)
print('KNN Accuracy: {:.2f}%'.format(accuracy_score(y_test, y_pred) * 100))
print('Confusion Matrix:\n', confusion_matrix(y_test, y_pred))
print('Classification Report:\n', classification_report(y_test, y_pred))

dtc = DecisionTreeClassifier(max_depth=3)
dtc.fit(X_train, y_train)
y_pred = dtc.predict(X_test)
print('Decision Tree Accuracy: {:.2f}%'.format(accuracy_score(y_test, y_pred) * 100))
print('Confusion Matrix:\n', confusion_matrix(y_test, y_pred))
print('Classification Report:\n', classification_report(y_test, y_pred))