app.py

import gradio as gr
import pandas as pd
import numpy as np
import zipfile
import os
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix, roc_curve, auc

# Extract ZIP File
zip_path = "DIABETES_PREDICTION.zip"
extract_path = "diabetes_data"
with zipfile.ZipFile(zip_path, 'r') as zip_ref:
    zip_ref.extractall(extract_path)

# Load Dataset
csv_file_path = os.path.join(extract_path, "diabetes_prediction_dataset.csv")  
df = pd.read_csv(csv_file_path)

# Data Preprocessing
df['smoking_history'] = df['smoking_history'].map({'never':0, 'No Info':1, 'current':2, 'former':3, 'ever':4, 'not current':5})
df['gender'] = df['gender'].map({'Male': 0, 'Female': 1})

# Feature Selection
target = 'diabetes'
X = df.drop(columns=[target])
y = df[target]

# Normalize Features
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Train-Test Split
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)

# Train Model
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

# Define Prediction Function
def predict_diabetes(gender, age, hypertension, heart_disease, smoking_history, bmi, HbA1c, blood_glucose):
    # Convert categorical inputs to numeric
    gender_numeric = 1 if gender == "Male" else 0  # Encode 'Male' as 1, 'Female' as 0
    
    # Prepare the input as a NumPy array
    input_data = np.array([[gender_numeric, age, hypertension, heart_disease, smoking_history, bmi, HbA1c, blood_glucose]])

    # Scale the input data
    input_scaled = scaler.transform(input_data)  # Ensure all values are numeric

    # Make prediction
    prediction = model.predict(input_scaled)

    return "Diabetes Positive" if prediction[0] == 1 else "Diabetes Negative"

# Define UI with Gradio
iface = gr.Interface(
    fn=predict_diabetes,
    inputs=[
        gr.Radio(["Male", "Female"], label="Gender"),
        gr.Number(label="Age"),
        gr.Radio([0, 1], label="Hypertension (0: No, 1: Yes)"),
        gr.Radio([0, 1], label="Heart Disease (0: No, 1: Yes)"),
        gr.Dropdown([0, 1, 2, 3, 4, 5], label="Smoking History (Encoded)"),
        gr.Number(label="BMI"),
        gr.Number(label="HbA1c Level"),
        gr.Number(label="Blood Glucose Level")
    ],
    outputs=gr.Textbox(label="Diabetes Prediction"),
    title="Diabetes Risk Prediction",
    description="Enter the patient's details to predict diabetes risk."
)

# Launch App
if __name__ == "__main__":
    iface.launch()