import numpy as np import pandas as pd import streamlit as st import joblib from pathlib import Path # ----------------------------- # Page config # ----------------------------- st.set_page_config( page_title='Diabetes Risk Predictor (LightGBM)', page_icon='🩺', layout='centered' ) st.title('🩺 Diabetes Risk Predictor') st.write('Predicts the probability of being diagnosed with diabetes using a trained LightGBM model.') # ----------------------------- # Paths (HF-friendly) # ----------------------------- BASE_DIR = Path(__file__).resolve().parent MODEL_PATH = BASE_DIR / 'lgbm_model.pkl' FEATURE_COLS_PATH = BASE_DIR / 'feature_cols.pkl' # ----------------------------- # Load artifacts # ----------------------------- @st.cache_resource def load_artifacts(): if not MODEL_PATH.exists(): raise FileNotFoundError( f'Model not found: {MODEL_PATH.name}. Put it in the repo root (same folder as app.py).' ) if not FEATURE_COLS_PATH.exists(): raise FileNotFoundError( f'Feature list not found: {FEATURE_COLS_PATH.name}. Put it in the repo root (same folder as app.py).' ) model = joblib.load(MODEL_PATH) feature_cols = joblib.load(FEATURE_COLS_PATH) return model, feature_cols model, feature_cols = load_artifacts() # ----------------------------- # Feature engineering (must match your notebook logic) # ----------------------------- def add_features(df: pd.DataFrame) -> pd.DataFrame: df = df.copy() eps = 1e-6 # Body / Age df['bmi_age_ratio'] = df['bmi'] / (df['age'] + eps) df['is_obese'] = (df['bmi'] >= 30).astype(int) # Activity df['activity_per_age'] = df['physical_activity_minutes_per_week'] / (df['age'] + eps) df['low_activity'] = (df['physical_activity_minutes_per_week'] < 150).astype(int) # Sleep df['sleep_deficit'] = 7 - df['sleep_hours_per_day'] df['poor_sleep'] = (df['sleep_hours_per_day'] < 6).astype(int) # Cholesterol if {'ldl_cholesterol', 'hdl_cholesterol'}.issubset(df.columns): df['chol_ratio'] = df['ldl_cholesterol'] / (df['hdl_cholesterol'] + eps) df['high_ldl'] = (df['ldl_cholesterol'] >= 130).astype(int) df['low_hdl'] = (df['hdl_cholesterol'] < 40).astype(int) return df # ----------------------------- # UI Inputs # ----------------------------- with st.form('input_form'): st.subheader('Patient Information') col1, col2 = st.columns(2) with col1: age = st.number_input('Age', min_value=1, max_value=120, value=45, step=1) gender = st.selectbox('Gender', ['Female', 'Male', 'Other']) ethnicity = st.selectbox('Ethnicity', ['White', 'Hispanic', 'Black', 'Asian', 'Other']) education_level = st.selectbox('Education Level', ['Highschool', 'Graduate', 'Postgraduate', 'No formal']) employment_status = st.selectbox('Employment Status', ['Employed', 'Retired', 'Unemployed', 'Student']) with col2: income_level = st.selectbox('Income Level', ['Low', 'Lower-Middle', 'Middle', 'Upper-Middle', 'High']) smoking_status = st.selectbox('Smoking Status', ['Never', 'Former', 'Current']) family_history_diabetes = st.selectbox('Family History of Diabetes', [0, 1], index=0) hypertension_history = st.selectbox('Hypertension History', [0, 1], index=0) cardiovascular_history = st.selectbox('Cardiovascular History', [0, 1], index=0) st.subheader('Lifestyle & Health Metrics') col3, col4 = st.columns(2) with col3: alcohol_consumption_per_week = st.number_input('Alcohol Consumption per Week', min_value=0, max_value=50, value=2, step=1) physical_activity_minutes_per_week = st.number_input('Physical Activity (minutes/week)', min_value=0, max_value=2000, value=90, step=5) diet_score = st.number_input('Diet Score', min_value=0.0, max_value=10.0, value=6.0, step=0.1) sleep_hours_per_day = st.number_input('Sleep Hours per Day', min_value=0.0, max_value=24.0, value=7.0, step=0.1) screen_time_hours_per_day = st.number_input('Screen Time Hours per Day', min_value=0.0, max_value=24.0, value=6.0, step=0.1) with col4: bmi = st.number_input('BMI', min_value=10.0, max_value=60.0, value=26.0, step=0.1) waist_to_hip_ratio = st.number_input('Waist-to-Hip Ratio', min_value=0.50, max_value=1.50, value=0.86, step=0.01) systolic_bp = st.number_input('Systolic BP', min_value=50, max_value=250, value=116, step=1) diastolic_bp = st.number_input('Diastolic BP', min_value=30, max_value=160, value=75, step=1) heart_rate = st.number_input('Heart Rate', min_value=20, max_value=220, value=70, step=1) col5, col6 = st.columns(2) with col5: cholesterol_total = st.number_input('Total Cholesterol', min_value=50, max_value=400, value=187, step=1) hdl_cholesterol = st.number_input('HDL Cholesterol', min_value=5, max_value=150, value=54, step=1) with col6: ldl_cholesterol = st.number_input('LDL Cholesterol', min_value=5, max_value=300, value=103, step=1) triglycerides = st.number_input('Triglycerides', min_value=10, max_value=600, value=123, step=1) submitted = st.form_submit_button('Predict Risk') # ----------------------------- # Prediction # ----------------------------- if submitted: # Build one-row dataframe (must match your training columns BEFORE encoding) row = { 'age': int(age), 'alcohol_consumption_per_week': int(alcohol_consumption_per_week), 'physical_activity_minutes_per_week': int(physical_activity_minutes_per_week), 'diet_score': float(diet_score), 'sleep_hours_per_day': float(sleep_hours_per_day), 'screen_time_hours_per_day': float(screen_time_hours_per_day), 'bmi': float(bmi), 'waist_to_hip_ratio': float(waist_to_hip_ratio), 'systolic_bp': int(systolic_bp), 'diastolic_bp': int(diastolic_bp), 'heart_rate': int(heart_rate), 'cholesterol_total': int(cholesterol_total), 'hdl_cholesterol': int(hdl_cholesterol), 'ldl_cholesterol': int(ldl_cholesterol), 'triglycerides': int(triglycerides), 'gender': gender, 'ethnicity': ethnicity, 'education_level': education_level, 'income_level': income_level, 'smoking_status': smoking_status, 'employment_status': employment_status, 'family_history_diabetes': int(family_history_diabetes), 'hypertension_history': int(hypertension_history), 'cardiovascular_history': int(cardiovascular_history), } X_user = pd.DataFrame([row]) # Feature engineering X_user = add_features(X_user) # One-hot encode X_user_enc = pd.get_dummies(X_user, drop_first=True) # Align columns to training feature set X_user_enc = X_user_enc.reindex(columns=feature_cols, fill_value=0) # Predict probability proba = float(model.predict_proba(X_user_enc)[:, 1][0]) st.success(f'Predicted Diabetes Probability: {proba:.3f}') st.progress(min(max(proba, 0.0), 1.0)) st.caption('Note: This app outputs probability (0–1). It is not a medical diagnosis.')