app.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import streamlit as st
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix, classification_report
from io import BytesIO
from PIL import Image

# Function for loading and processing the dataset
def load_and_process_data(file):
    df = pd.read_csv(file)  # Streamlit handles file reading directly
    
    # Display basic information
    buffer = []
    buffer.append(df.info())
    buffer.append(df.describe().to_string())
    
    # Correlation matrix
    plt.figure(figsize=(12, 10))
    corr_matrix = df.corr()
    sns.heatmap(corr_matrix, annot=True, fmt='.2f', cmap='coolwarm')
    plt.title('Correlation Matrix')
    st.pyplot(plt)  # Display the correlation matrix directly in Streamlit
    
    # Check for missing values
    missing_values = df.isnull().sum()
    
    return df, buffer, missing_values.to_string()

# Function for training and evaluating models
def train_and_evaluate_model(file, model_choice):
    df, buffer, missing_values = load_and_process_data(file)

    X = df.drop('target', axis=1)
    y = df['target']
    
    # Train-test split
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
    
    # Standardize the features
    scaler = StandardScaler()
    X_train_scaled = scaler.fit_transform(X_train)
    X_test_scaled = scaler.transform(X_test)

    # Define models
    models = {
        'Logistic Regression': LogisticRegression(random_state=42),
        'Decision Tree': DecisionTreeClassifier(random_state=42),
        'Random Forest': RandomForestClassifier(random_state=42)
    }
    
    model = models[model_choice]
    model.fit(X_train_scaled, y_train)
    y_pred = model.predict(X_test_scaled)

    # Classification report
    report = classification_report(y_test, y_pred)
    
    # Confusion matrix plot
    cm = confusion_matrix(y_test, y_pred)
    plt.figure(figsize=(8, 6))
    sns.heatmap(cm, annot=True, fmt='d', cmap='Blues')
    plt.title(f'Confusion Matrix - {model_choice}')
    plt.xlabel('Predicted')
    plt.ylabel('Actual')
    st.pyplot(plt)  # Display confusion matrix plot in Streamlit
    
    return report, buffer, missing_values

# Streamlit app
st.title("Heart Disease Model Training")

# File upload
file = st.file_uploader("Upload CSV File", type=["csv"])

if file is not None:
    # Model selection
    model_choice = st.selectbox("Choose a Model", ['Logistic Regression', 'Decision Tree', 'Random Forest'])
    
    if st.button("Run Model"):
        # Train and evaluate the model
        report, buffer, missing_values = train_and_evaluate_model(file, model_choice)
        
        # Display the results
        st.subheader("Model Results and Data Info")
        st.text(f"Model: {model_choice}\n\nClassification Report:\n{report}\n\nMissing Values:\n{missing_values}")