import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

# Load the heart disease data
df = pd.read_csv("heart_disease_uci.csv")

# Get an overview of the data
print(df.head())
print(df.describe())

# Visualize the distribution of the target variable
sns.countplot(x='target', data=df)
plt.show()

# Visualize the correlation between the features
sns.heatmap(df.corr(), annot=True)
plt.show()

# Split the data into features and target
X = df.drop("target", axis=1)
y = df["target"]

# 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)

# Define the pipeline
pipeline = Pipeline([
    ('scaler', StandardScaler()),
    ('classifier', LogisticRegression())
])

# Fit the pipeline to the training data
pipeline.fit(X_train, y_train)

# Predict the target using the pipeline
y_pred = pipeline.predict(X_test)

# Evaluate the performance of the pipeline
print("Accuracy:", accuracy_score(y_test, y_pred))
print("Confusion Matrix:", confusion_matrix(y_test, y_pred))
print("Classification Report:", classification_report(y_test, y_pred))

# Experiment with a different classifier (Random Forest)
rf_pipeline = Pipeline([
    ('scaler', StandardScaler()),
    ('classifier', RandomForestClassifier())
])

# Fit the Random Forest pipeline to the training data
rf_pipeline.fit(X_train, y_train)

# Predict the target using the Random Forest pipeline
y_pred_rf = rf_pipeline.predict(X_test)

# Evaluate the performance of the Random Forest pipeline
print("Accuracy:", accuracy_score(y_test, y_pred_rf))
print("Confusion Matrix:", confusion_matrix(y_test, y_pred_rf))
print("Classification Report:", classification_report(y_test, y_pred_rf))