Delete app.py

app.py

@@ -1,595 +0,0 @@
-"""
-NON-INVASIVE ANEMIA SCREENING WEBAPP
-=====================================
-Estimates hemoglobin from palpebral conjunctiva image + standardized form inputs.
-
-Deploy on Hugging Face Spaces (free).
-Collects anonymized data for model improvement.
-
-Author: JIPMER Anemia Screening Study
-"""
-
-import gradio as gr
-import numpy as np
-import pandas as pd
-import pickle
-import cv2
-import uuid
-from datetime import datetime
-from pathlib import Path
-
-# ============================================================
-# CONFIGURATION
-# ============================================================
-MODEL_PATH = "model.pkl"
-YOLO_PATH = "best.pt"
-DATA_LOG_PATH = "collected_data.csv"  # Local fallback; use Google Sheets in production
-
-# ============================================================
-# LOAD MODELS (done once at startup)
-# ============================================================
-def load_models():
-    """Load ML model and YOLO segmentation model."""
-    global ml_model, feature_names, yolo_model
-    
-    # Load ML model
-    with open(MODEL_PATH, 'rb') as f:
-        model_data = pickle.load(f)
-    ml_model = model_data['model']
-    feature_names = model_data['features']
-    print(f"✅ Loaded ML model: {model_data.get('name', 'Unknown')}")
-    print(f"   Features: {len(feature_names)}")
-    
-    # Load YOLO
-    from ultralytics import YOLO
-    yolo_model = YOLO(YOLO_PATH)
-    print(f"✅ Loaded YOLO model")
-    
-    return True
-
-# ============================================================
-# IMAGE PROCESSING
-# ============================================================
-def calibrate_image(img):
-    """White balance calibration using grey card."""
-    try:
-        if img is None:
-            return None
-        
-        # Convert to RGB if needed
-        if len(img.shape) == 2:
-            img_rgb = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)
-        elif img.shape[2] == 4:
-            img_rgb = cv2.cvtColor(img, cv2.COLOR_RGBA2RGB)
-        else:
-            img_rgb = img.copy()
-        
-        gray = cv2.cvtColor(img_rgb, cv2.COLOR_RGB2GRAY)
-        _, thresh = cv2.threshold(gray, 180, 255, cv2.THRESH_BINARY)
-        contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
-        
-        if not contours:
-            _, thresh = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY)
-            contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
-        
-        if not contours:
-            return img_rgb
-        
-        c = max(contours, key=cv2.contourArea)
-        x, y, w, h = cv2.boundingRect(c)
-        
-        if w * h < 1000:
-            return img_rgb
-        
-        patch = img_rgb[y+h//4:y+3*h//4, x+w//4:x+3*w//4]
-        if patch.size == 0:
-            return img_rgb
-        
-        avg = np.mean(patch, axis=(0, 1))
-        if any(v < 10 for v in avg):
-            return img_rgb
-        
-        scale = np.array([128, 128, 128]) / avg
-        return np.clip(img_rgb * scale, 0, 255).astype(np.uint8)
-    except Exception as e:
-        print(f"Calibration error: {e}")
-        return img
-
-
-def extract_image_features(img):
-    """Run YOLO segmentation and extract color features."""
-    try:
-        # Calibrate
-        img_cal = calibrate_image(img)
-        if img_cal is None:
-            return None
-        
-        # YOLO segmentation
-        results = yolo_model(img_cal, verbose=False)
-        
-        if len(results) > 0 and results[0].masks is not None:
-            masks = results[0].masks.data.cpu().numpy()
-            confs = results[0].boxes.conf.cpu().numpy()
-            if len(confs) > 0:
-                m = masks[np.argmax(confs)]
-                m = cv2.resize(m, (img_cal.shape[1], img_cal.shape[0]))
-                roi_mask = (m > 0.5).astype(np.uint8) * 255
-            else:
-                # Fallback to center crop
-                h, w = img_cal.shape[:2]
-                roi_mask = np.zeros((h, w), dtype=np.uint8)
-                roi_mask[h//4:3*h//4, w//4:3*w//4] = 255
-        else:
-            h, w = img_cal.shape[:2]
-            roi_mask = np.zeros((h, w), dtype=np.uint8)
-            roi_mask[h//4:3*h//4, w//4:3*w//4] = 255
-        
-        # Extract color features from ROI
-        px = img_cal[roi_mask > 0]
-        if len(px) == 0:
-            return None
-        
-        R, G, B = [np.mean(px[:, i]) for i in range(3)]
-        
-        hsv = cv2.cvtColor(img_cal, cv2.COLOR_RGB2HSV)
-        hpx = hsv[roi_mask > 0]
-        H, S, V = [np.mean(hpx[:, i]) for i in range(3)]
-        
-        lab = cv2.cvtColor(img_cal, cv2.COLOR_RGB2LAB)
-        lpx = lab[roi_mask > 0]
-        L, A, Bc = [np.mean(lpx[:, i]) for i in range(3)]
-        
-        return {
-            'R': R, 'G': G, 'B': B,
-            'H': H, 'S': S, 'V': V,
-            'L_color': L, 'A_color': A, 'B_color': Bc
-        }
-    except Exception as e:
-        print(f"Image processing error: {e}")
-        return None
-
-
-# ============================================================
-# FORM INPUT → FEATURE VECTOR MAPPING
-# ============================================================
-def form_to_features(
-    age, income_range, family_size, diet,
-    food_grains, food_leafy, food_cereals, food_pulses,
-    food_fish, food_eggs, food_meat, food_jaggery, food_nuts,
-    fruit_freq, veg_freq, tea_coffee,
-    comorb_dm, comorb_htn, comorb_thyroid,
-    prev_anemia, family_anemia, hookworm, bleeding_disorder, deworming,
-    menstrual, pads_per_day,
-    gravida, para, live_births, abortions, stillbirths,
-    family_dm, family_htn
-):
-    """Convert standardized form inputs to feature vector."""
-    
-    # Income mapping
-    income_map = {
-        "Below ₹5,000": 2500,
-        "₹5,000 - ₹10,000": 7500,
-        "₹10,000 - ₹15,000": 12500,
-        "₹15,000 - ₹25,000": 20000,
-        "₹25,000 - ₹50,000": 37500,
-        "Above ₹50,000": 75000
-    }
-    income = income_map.get(income_range, 20000)
-    income_per_capita = income / max(family_size, 1)
-    
-    # Diet one-hot
-    diet_veg = 1 if diet == "Vegetarian" else 0
-    diet_nonveg = 1 if diet == "Non-vegetarian" else 0
-    diet_mixed = 1 if diet == "Mixed" else 0
-    
-    # Iron foods
-    food_iron_count = sum([food_grains, food_leafy, food_cereals, food_pulses,
-                          food_fish, food_eggs, food_meat, food_jaggery, food_nuts])
-    
-    # Frequency mapping
-    freq_map = {"Daily": 4, "Twice a week": 3, "Once a week": 2, "Rarely": 1, "Never": 0}
-    fruit_freq_val = freq_map.get(fruit_freq, 2)
-    veg_freq_val = freq_map.get(veg_freq, 2)
-    
-    # Binary mappings
-    tea_coffee_val = 1 if tea_coffee == "Yes" else 0
-    comorb_dm_val = 1 if comorb_dm else 0
-    comorb_htn_val = 1 if comorb_htn else 0
-    comorb_thyroid_val = 1 if comorb_thyroid else 0
-    comorb_none = 1 if not any([comorb_dm, comorb_htn, comorb_thyroid]) else 0
-    comorb_count = comorb_dm_val + comorb_htn_val + comorb_thyroid_val
-    
-    prev_anemia_val = 1 if prev_anemia == "Yes" else 0
-    family_anemia_val = 1 if family_anemia == "Yes" else 0
-    hookworm_val = 1 if hookworm == "Yes" else 0
-    bleeding_val = 1 if bleeding_disorder == "Yes" else 0
-    deworming_val = 1 if deworming == "Yes" else 0
-    
-    # Menstrual
-    menstrual_regular = 1 if menstrual == "Regular" else 0
-    menstrual_irregular = 1 if menstrual == "Irregular" else 0
-    
-    # Pads mapping
-    pads_map = {"1-2": 1.5, "2-3": 2.5, "3-4": 3.5, "4-5": 4.5, "More than 5": 6, "Not applicable": 2.5}
-    pads_val = pads_map.get(pads_per_day, 2.5)
-    
-    # Obstetric
-    has_obstetric = 1 if gravida > 0 else 0
-    pregnancy_loss = abortions + stillbirths
-    parity_ratio = para / gravida if gravida > 0 else 0
-    
-    family_dm_val = 1 if family_dm == "Yes" else 0
-    family_htn_val = 1 if family_htn == "Yes" else 0
-    
-    # Build feature dict (order must match training!)
-    features = {
-        'age': age,
-        'income': income,
-        'family_size': family_size,
-        'income_per_capita': income_per_capita,
-        'diet_veg': diet_veg,
-        'diet_nonveg': diet_nonveg,
-        'diet_mixed': diet_mixed,
-        'food_whole_grains': 1 if food_grains else 0,
-        'food_green_leafy_vegetables': 1 if food_leafy else 0,
-        'food_cereals': 1 if food_cereals else 0,
-        'food_pulses': 1 if food_pulses else 0,
-        'food_fish': 1 if food_fish else 0,
-        'food_eggs': 1 if food_eggs else 0,
-        'food_meat': 1 if food_meat else 0,
-        'food_jaggery': 1 if food_jaggery else 0,
-        'food_nuts': 1 if food_nuts else 0,
-        'food_iron_count': food_iron_count,
-        'fruit_freq': fruit_freq_val,
-        'veg_freq': veg_freq_val,
-        'tea_coffee_daily': tea_coffee_val,
-        'tea_coffee_daily_missing': 0,
-        'comorb_dm': comorb_dm_val,
-        'comorb_htn': comorb_htn_val,
-        'comorb_thyroid': comorb_thyroid_val,
-        'comorb_none': comorb_none,
-        'comorb_count': comorb_count,
-        'prev_anemia': prev_anemia_val,
-        'prev_anemia_missing': 0,
-        'family_anemia': family_anemia_val,
-        'family_anemia_missing': 0,
-        'hookworm_history': hookworm_val,
-        'hookworm_history_missing': 0,
-        'bleeding_disorder': bleeding_val,
-        'bleeding_disorder_missing': 0,
-        'deworming_done': deworming_val,
-        'deworming_done_missing': 0,
-        'menstrual_regular': menstrual_regular,
-        'menstrual_irregular': menstrual_irregular,
-        'pads_per_day': pads_val,
-        'pads_missing': 0,
-        'gravida': gravida,
-        'para': para,
-        'live_births': live_births,
-        'abortions': abortions,
-        'stillbirths': stillbirths,
-        'has_obstetric_history': has_obstetric,
-        'pregnancy_loss': pregnancy_loss,
-        'parity_ratio': parity_ratio,
-        'family_dm': family_dm_val,
-        'family_dm_missing': 0,
-        'family_htn': family_htn_val,
-        'family_htn_missing': 0,
-    }
-    
-    return features
-
-
-# ============================================================
-# DATA LOGGING
-# ============================================================
-def log_data(session_id, features, image_features, predicted_hb, actual_hb=None):
-    """Log anonymized data for model improvement."""
-    try:
-        record = {
-            'session_id': session_id,
-            'timestamp': datetime.now().isoformat(),
-            'predicted_hb': predicted_hb,
-            'actual_hb': actual_hb,
-            **features,
-            **image_features
-        }
-        
-        df = pd.DataFrame([record])
-        
-        # Append to CSV (or send to Google Sheets in production)
-        if Path(DATA_LOG_PATH).exists():
-            df.to_csv(DATA_LOG_PATH, mode='a', header=False, index=False)
-        else:
-            df.to_csv(DATA_LOG_PATH, index=False)
-        
-        return True
-    except Exception as e:
-        print(f"Logging error: {e}")
-        return False
-
-
-# ============================================================
-# MAIN PREDICTION FUNCTION
-# ============================================================
-def predict_hb(
-    image,
-    age, income_range, family_size, diet,
-    food_grains, food_leafy, food_cereals, food_pulses,
-    food_fish, food_eggs, food_meat, food_jaggery, food_nuts,
-    fruit_freq, veg_freq, tea_coffee,
-    comorb_dm, comorb_htn, comorb_thyroid,
-    prev_anemia, family_anemia, hookworm, bleeding_disorder, deworming,
-    menstrual, pads_per_day,
-    gravida, para, live_births, abortions, stillbirths,
-    family_dm, family_htn,
-    actual_hb_input
-):
-    """Main prediction function."""
-    
-    # Generate session ID
-    session_id = str(uuid.uuid4())[:8]
-    
-    # Validate image
-    if image is None:
-        return "❌ Please upload an image of the palpebral conjunctiva with color card.", "", ""
-    
-    # Extract image features
-    image_features = extract_image_features(image)
-    if image_features is None:
-        return "❌ Could not process image. Please ensure the palpebral conjunctiva is clearly visible.", "", ""
-    
-    # Convert form to features
-    tabular_features = form_to_features(
-        age, income_range, family_size, diet,
-        food_grains, food_leafy, food_cereals, food_pulses,
-        food_fish, food_eggs, food_meat, food_jaggery, food_nuts,
-        fruit_freq, veg_freq, tea_coffee,
-        comorb_dm, comorb_htn, comorb_thyroid,
-        prev_anemia, family_anemia, hookworm, bleeding_disorder, deworming,
-        menstrual, pads_per_day,
-        gravida, para, live_births, abortions, stillbirths,
-        family_dm, family_htn
-    )
-    
-    # Combine features
-    all_features = {**tabular_features, **image_features}
-    
-    # Create feature vector in correct order
-    X = pd.DataFrame([all_features])[feature_names]
-    
-    # Predict
-    hb_pred = ml_model.predict(X)[0]
-    hb_pred = round(float(hb_pred), 1)
-    
-    # Classify severity
-    if hb_pred >= 12:
-        severity = "Normal"
-        color = "🟢"
-        recommendation = "No signs of anemia detected. Maintain a balanced diet."
-    elif hb_pred >= 11:
-        severity = "Mild Anemia"
-        color = "🟡"
-        recommendation = "Mild anemia indicated. Consider iron-rich foods and consult a healthcare provider."
-    elif hb_pred >= 8:
-        severity = "Moderate Anemia"
-        color = "🟠"
-        recommendation = "Moderate anemia detected. Please consult a healthcare provider for a confirmatory blood test."
-    else:
-        severity = "Severe Anemia"
-        color = "🔴"
-        recommendation = "Severe anemia indicated. Please seek immediate medical attention."
-    
-    # Log data
-    actual_hb = float(actual_hb_input) if actual_hb_input and actual_hb_input > 0 else None
-    log_data(session_id, tabular_features, image_features, hb_pred, actual_hb)
-    
-    # Format result
-    result = f"""
-    ## {color} Estimated Hemoglobin: {hb_pred} g/dL
-    
-    ### Status: {severity}
-    
-    {recommendation}
-    
-    ---
-    *Session ID: {session_id}*  
-    *Save this ID if you want to provide actual Hb value later.*
-    """
-    
-    return result, session_id, f"{hb_pred} g/dL"
-
-
-# ============================================================
-# GRADIO INTERFACE
-# ============================================================
-def create_interface():
-    """Build the Gradio UI."""
-    
-    with gr.Blocks(title="Anemia Screening Tool", theme=gr.themes.Soft()) as app:
-        
-        gr.Markdown("""
-        # 🩺 Non-Invasive Anemia Screening Tool
-        
-        Estimate hemoglobin levels from a photo of the palpebral conjunctiva (inner eyelid).
-        
-        **Instructions:**
-        1. Upload a clear photo of the lower inner eyelid WITH the color calibration card visible
-        2. Fill in the health information form
-        3. Click "Estimate Hemoglobin"
-        
-        ⚠️ *This is a screening tool, not a diagnosis. Please consult a healthcare provider for confirmation.*
-        
-        ---
-        """)
-        
-        with gr.Row():
-            # Left column - Image upload
-            with gr.Column(scale=1):
-                gr.Markdown("### 📷 Image Upload")
-                image_input = gr.Image(
-                    label="Palpebral Conjunctiva Image (with color card)",
-                    type="numpy"
-                )
-                gr.Markdown("*Ensure the grey/white color card is visible in the image for accurate calibration.*")
-            
-            # Right column - Form
-            with gr.Column(scale=2):
-                gr.Markdown("### 📋 Health Information")
-                
-                with gr.Accordion("Demographics", open=True):
-                    with gr.Row():
-                        age = gr.Slider(minimum=10, maximum=80, value=25, step=1, label="Age (years)")
-                        family_size = gr.Slider(minimum=1, maximum=15, value=4, step=1, label="Family Size")
-                    income_range = gr.Dropdown(
-                        choices=["Below ₹5,000", "₹5,000 - ₹10,000", "₹10,000 - ₹15,000", 
-                                "₹15,000 - ₹25,000", "₹25,000 - ₹50,000", "Above ₹50,000"],
-                        value="₹10,000 - ₹15,000",
-                        label="Monthly Family Income"
-                    )
-                
-                with gr.Accordion("Diet & Nutrition", open=True):
-                    diet = gr.Radio(
-                        choices=["Vegetarian", "Non-vegetarian", "Mixed"],
-                        value="Mixed",
-                        label="Dietary Habit"
-                    )
-                    gr.Markdown("**Iron-rich foods consumed regularly:**")
-                    with gr.Row():
-                        food_grains = gr.Checkbox(label="Whole Grains", value=True)
-                        food_leafy = gr.Checkbox(label="Leafy Vegetables", value=True)
-                        food_cereals = gr.Checkbox(label="Cereals", value=True)
-                    with gr.Row():
-                        food_pulses = gr.Checkbox(label="Pulses/Lentils", value=True)
-                        food_fish = gr.Checkbox(label="Fish", value=False)
-                        food_eggs = gr.Checkbox(label="Eggs", value=False)
-                    with gr.Row():
-                        food_meat = gr.Checkbox(label="Meat", value=False)
-                        food_jaggery = gr.Checkbox(label="Jaggery", value=False)
-                        food_nuts = gr.Checkbox(label="Nuts", value=False)
-                    with gr.Row():
-                        fruit_freq = gr.Dropdown(
-                            choices=["Daily", "Twice a week", "Once a week", "Rarely", "Never"],
-                            value="Twice a week",
-                            label="Fruit Consumption"
-                        )
-                        veg_freq = gr.Dropdown(
-                            choices=["Daily", "Twice a week", "Once a week", "Rarely", "Never"],
-                            value="Daily",
-                            label="Vegetable Consumption"
-                        )
-                    tea_coffee = gr.Radio(
-                        choices=["Yes", "No"],
-                        value="Yes",
-                        label="Daily Tea/Coffee Consumption"
-                    )
-                
-                with gr.Accordion("Medical History", open=False):
-                    gr.Markdown("**Current Conditions:**")
-                    with gr.Row():
-                        comorb_dm = gr.Checkbox(label="Diabetes", value=False)
-                        comorb_htn = gr.Checkbox(label="Hypertension", value=False)
-                        comorb_thyroid = gr.Checkbox(label="Thyroid Disorder", value=False)
-                    with gr.Row():
-                        prev_anemia = gr.Radio(choices=["Yes", "No"], value="No", label="Anemia in past 12 months")
-                        family_anemia = gr.Radio(choices=["Yes", "No"], value="No", label="Family history of anemia")
-                    with gr.Row():
-                        hookworm = gr.Radio(choices=["Yes", "No"], value="No", label="History of hookworm")
-                        bleeding_disorder = gr.Radio(choices=["Yes", "No"], value="No", label="Bleeding disorder")
-                    with gr.Row():
-                        deworming = gr.Radio(choices=["Yes", "No"], value="Yes", label="Deworming done")
-                    with gr.Row():
-                        family_dm = gr.Radio(choices=["Yes", "No"], value="No", label="Family history: Diabetes")
-                        family_htn = gr.Radio(choices=["Yes", "No"], value="No", label="Family history: Hypertension")
-                
-                with gr.Accordion("Menstrual & Obstetric History", open=False):
-                    with gr.Row():
-                        menstrual = gr.Radio(
-                            choices=["Regular", "Irregular", "Not applicable"],
-                            value="Regular",
-                            label="Menstrual Cycle"
-                        )
-                        pads_per_day = gr.Dropdown(
-                            choices=["1-2", "2-3", "3-4", "4-5", "More than 5", "Not applicable"],
-                            value="2-3",
-                            label="Pads per day (first 2-3 days)"
-                        )
-                    gr.Markdown("**Obstetric History (enter 0 if not applicable):**")
-                    with gr.Row():
-                        gravida = gr.Slider(minimum=0, maximum=10, value=0, step=1, label="Gravida (pregnancies)")
-                        para = gr.Slider(minimum=0, maximum=10, value=0, step=1, label="Para (deliveries)")
-                        live_births = gr.Slider(minimum=0, maximum=10, value=0, step=1, label="Live Births")
-                    with gr.Row():
-                        abortions = gr.Slider(minimum=0, maximum=5, value=0, step=1, label="Abortions")
-                        stillbirths = gr.Slider(minimum=0, maximum=5, value=0, step=1, label="Stillbirths")
-        
-        gr.Markdown("---")
-        
-        with gr.Row():
-            with gr.Column():
-                actual_hb_input = gr.Number(
-                    label="Already have a blood test result? Enter actual Hb (g/dL) — Optional",
-                    value=0,
-                    minimum=0,
-                    maximum=25
-                )
-            with gr.Column():
-                submit_btn = gr.Button("🔬 Estimate Hemoglobin", variant="primary", size="lg")
-        
-        gr.Markdown("---")
-        
-        # Results
-        with gr.Row():
-            result_output = gr.Markdown(label="Result")
-        with gr.Row():
-            session_output = gr.Textbox(label="Session ID", interactive=False)
-            hb_output = gr.Textbox(label="Estimated Hb", interactive=False)
-        
-        # Privacy notice
-        gr.Markdown("""
-        ---
-        ### 🔒 Privacy Notice
-        
-        Your data is collected **anonymously** to improve this screening tool. We do NOT collect:
-        - Name, address, phone number, or email
-        - Raw images (only extracted color features are stored)
-        - Any personally identifiable information
-        
-        By using this tool, you consent to anonymous data collection for research purposes.
-        
-        ---
-        *Developed by for an Anemia Screening Study | For research use only | Contact gangadharananirudh@gmail.com for more info*
-        """)
-        
-        # Connect button
-        submit_btn.click(
-            fn=predict_hb,
-            inputs=[
-                image_input,
-                age, income_range, family_size, diet,
-                food_grains, food_leafy, food_cereals, food_pulses,
-                food_fish, food_eggs, food_meat, food_jaggery, food_nuts,
-                fruit_freq, veg_freq, tea_coffee,
-                comorb_dm, comorb_htn, comorb_thyroid,
-                prev_anemia, family_anemia, hookworm, bleeding_disorder, deworming,
-                menstrual, pads_per_day,
-                gravida, para, live_births, abortions, stillbirths,
-                family_dm, family_htn,
-                actual_hb_input
-            ],
-            outputs=[result_output, session_output, hb_output]
-        )
-    
-    return app
-
-
-# ============================================================
-# MAIN
-# ============================================================
-if __name__ == "__main__":
-    print("Loading models...")
-    load_models()
-    
-    print("Starting app...")
-    app = create_interface()
-    app.launch()