app.py

import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix, classification_report
import gradio as gr

def process_and_evaluate(file):
    # Load the dataset
    df = pd.read_csv(file)

    # Encode categorical features
    categorical_columns = df.select_dtypes(include=['object']).columns
    label_encoders = {}
    for col in categorical_columns:
        le = LabelEncoder()
        df[col] = le.fit_transform(df[col])
        label_encoders[col] = le

    # Define the target and features
    target = 'target'  # Assuming the target column is named 'target'
    X = df.drop(columns=[target])
    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)

    # Train a RandomForestClassifier
    clf = RandomForestClassifier(random_state=42)
    clf.fit(X_train, y_train)

    # Predict on the test set
    y_pred = clf.predict(X_test)

    # Compute the confusion matrix
    conf_matrix = confusion_matrix(y_test, y_pred)

    # Print the classification report
    classification_rep = classification_report(y_test, y_pred)

    return classification_rep

# Create the Gradio interface
inputs = gr.File(label="Upload CSV File")
outputs = gr.Textbox(label="Classification Report")

gr.Interface(fn=process_and_evaluate, inputs=inputs, outputs=outputs, title="Heart Disease Prediction",
             description="Upload a CSV file containing heart disease data to get the classification report.").launch()