APPDOTPY(Updated)

README.md

@@ -1,14 +1,13 @@
 ---
 title: SleepGuardAI
-emoji: 😴
-colorFrom: blue
-colorTo: purple
-sdk: streamlit
-sdk_version: 1.57.0
+emoji: 👁
+colorFrom: gray
+colorTo: yellow
+sdk: gradio
+sdk_version: 6.4.0
 app_file: app.py
 pinned: false
+short_description: 'AI-based sleep risk screening system '
 ---
 
-# SleepGuardAI
-
-AI-powered sleep risk screening system.
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,184 +1,106 @@
 import joblib
-import numpy as np
 import pandas as pd
-import streamlit as st
-
-# =========================
-# CONFIG / CONSTANTS
-# =========================
-
-# These thresholds decide the UI label.
-# You can change them anytime.
-TH_LOW = 0.20   # below this => Low Risk
-TH_HIGH = 0.40  # above this => High Risk
-# between TH_LOW and TH_HIGH => Moderate Risk
-
-MODEL_PATH = "best_model_v2_calibrated.joblib"
-
-FEATURE_ORDER = [
-    "Age",
-    "Gender",
-    "BMI",
-    "BP_SYS",
-    "BP_DIA",
-    "Phys_Activity_Days",
-    "DPQ_Score",
-    "Smoking_Indicator",
-    "Alcohol_Feature",
-    "Diabetes_Indicator",
-    "Cycle",
-]
-
-# =========================
-# HELPERS
-# =========================
-
-def label_from_probability(prob: float) -> str:
-    """3-level risk label based on thresholds."""
-    if prob < TH_LOW:
-        return "Low Risk"
-    elif prob < TH_HIGH:
-        return "Moderate Risk"
-    else:
-        return "High Risk"
+import gradio as gr
+
+# ---------------- Load model bundle ----------------
+bundle = joblib.load("best_model_v2_calibrated.joblib")
+model = bundle["model"]
+threshold = float(bundle["threshold"])
 
-def get_texts(lang: str):
-    """Simple bilingual text dictionary."""
+# ---------------- Output formatting ----------------
+def format_output(lang, label, proba):
     if lang == "বাংলা":
-        return {
-            "title": "SleepGuardAI – Sleep Risk Screening (NHANES-based)",
-            "subtitle": "ফর্ম পূরণ করুন → ঝুঁকির স্কোর দেখুন। (এটি মেডিকেল ডায়াগনসিস নয়)",
-            "predict_btn": "Predict / ফলাফল দেখুন",
-            "result": "ফলাফল",
-            "prob": "ঝুঁকি সম্ভাবনা",
-            "thresholds": "থ্রেশহোল্ড",
-            "warning": "⚠️ এটি একটি স্ক্রিনিং টুল, মেডিকেল ডায়াগনসিস নয়। লক্ষণ থাকলে ডাক্তার দেখান।",
-            "low": "কম ঝুঁকি",
-            "mod": "মাঝারি ঝুঁকি",
-            "high": "উচ্চ ঝুঁকি",
-        }
+        risk_text = "উচ্চ ঝুঁকি" if label == "High Risk" else "কম ঝুঁকি"
+        return (
+            f"### ফলাফল: **{risk_text}**\n"
+            f"- ঝুঁকির সম্ভাবনা (Probability): **{proba:.3f}**\n"
+            f"- Threshold: **{threshold:.2f}**\n\n"
+            "⚠️ এটি একটি **স্ক্রিনিং টুল**, চিকিৎসা নির্ণয় নয়। সমস্যা থাকলে ডাক্তারের পরামর্শ নিন।"
+        )
     else:
-        return {
-            "title": "SleepGuardAI – Sleep Risk Screening (NHANES-based)",
-            "subtitle": "Fill the form → get a risk score. (This is NOT a medical diagnosis)",
-            "predict_btn": "Predict / ফলাফল দেখুন",
-            "result": "Result",
-            "prob": "Risk probability",
-            "thresholds": "Thresholds",
-            "warning": "⚠️ This is a screening tool, not a medical diagnosis. If you have symptoms, consult a clinician.",
-            "low": "Low Risk",
-            "mod": "Moderate Risk",
-            "high": "High Risk",
-        }
-
-@st.cache_resource
-def load_model():
-    return joblib.load(MODEL_PATH)
-
-def build_feature_row(
-    age, gender, bmi, bp_sys, bp_dia, phys_days, dpq, smoking, alcohol, diabetes, cycle
-) -> pd.DataFrame:
-    """Build one-row DataFrame in the exact feature order used by training."""
-    row = {
+        return (
+            f"### Result: **{label}**\n"
+            f"- Risk probability: **{proba:.3f}**\n"
+            f"- Threshold: **{threshold:.2f}**\n\n"
+            "⚠️ This is a **screening tool**, not a medical diagnosis. If you have symptoms, consult a clinician."
+        )
+
+def web_speak_html(text, lang):
+    voice_lang = "bn-BD" if lang == "বাংলা" else "en-US"
+    safe = text.replace("`", "").replace("\\", "\\\\").replace("'", "\\'")
+    return f"""
+    <div style="display:flex;gap:10px;align-items:center;">
+      <button onclick="(function(){{
+        const msg = new SpeechSynthesisUtterance('{safe}');
+        msg.lang = '{voice_lang}';
+        window.speechSynthesis.cancel();
+        window.speechSynthesis.speak(msg);
+      }})()" style="padding:10px 14px;border-radius:10px;border:1px solid #ccc;cursor:pointer;">
+        🔊 Speak / শোনান
+      </button>
+      <span style="opacity:0.7;">(Voice depends on browser installed voices)</span>
+    </div>
+    """
+
+# ---------------- Prediction ----------------
+def predict(lang, age, gender, bmi, bp_sys, bp_dia, phys_days, dpq, smoking, alcohol, diabetes, cycle):
+    sample = pd.DataFrame([{
         "Age": float(age),
-        "Gender": str(gender),  # keep as string (your pipeline encodes it)
+        "Gender": gender,
         "BMI": float(bmi),
         "BP_SYS": float(bp_sys),
         "BP_DIA": float(bp_dia),
         "Phys_Activity_Days": float(phys_days),
         "DPQ_Score": float(dpq),
-        "Smoking_Indicator": int(smoking),
+        "Smoking_Indicator": float(smoking),
         "Alcohol_Feature": float(alcohol),
-        "Diabetes_Indicator": int(diabetes),
-        "Cycle": str(cycle),
-    }
-    df = pd.DataFrame([row])[FEATURE_ORDER]
-    return df
-
-# =========================
-# UI
-# =========================
-
-st.set_page_config(page_title="SleepGuardAI", layout="wide")
-
-lang = st.radio("Language / ভাষা", ["English", "বাংলা"], horizontal=True)
-T = get_texts(lang)
-
-st.title(T["title"])
-st.caption(T["subtitle"])
-
-# Load model
-try:
-    bundle = load_model()
-except FileNotFoundError:
-    st.error(
-        f"Model file not found: '{MODEL_PATH}'. Put it in the same folder as app.py."
-    )
-    st.stop()
-
-# We support two possible save formats:
-# 1) bundle is a dict with {"model":..., "calibrator":..., ...}
-# 2) bundle is directly a sklearn Pipeline/Calibrated model with predict_proba
-model = bundle.get("model") if isinstance(bundle, dict) and "model" in bundle else bundle
-calibrator = bundle.get("calibrator") if isinstance(bundle, dict) and "calibrator" in bundle else None
-
-colA, colB = st.columns(2)
-
-with colA:
-    age = st.slider("Age / বয়স", 10, 90, 30)
-    gender = st.selectbox("Gender", ["Male", "Female"])
-
-    bmi = st.slider("BMI", 10.0, 50.0, 25.0, 0.1)
-    bp_sys = st.slider("Systolic BP", 80, 220, 120)
-    bp_dia = st.slider("Diastolic BP", 40, 140, 80)
-
-    phys_days = st.slider("Physical Activity Days/Week", 0, 7, 3)
-
-with colB:
-    st.markdown("### Optional (improves accuracy if known)")
-    dpq = st.slider("DPQ Depression Score (0–27)", 0, 27, 5)
-    smoking = st.selectbox("Smoking (1=Yes, 2=No)", [2, 1], index=0)
-    diabetes = st.selectbox("Diabetes (1=Yes, 2=No)", [2, 1], index=0)
-    alcohol = st.slider("Alcohol feature (proxy)", 0.0, 30.0, 2.0, 0.5)
-    cycle = st.selectbox("NHANES Cycle", ["G", "H", "I", "J"])
-
-st.divider()
-
-if st.button(T["predict_btn"], use_container_width=True):
-    X = build_feature_row(age, gender, bmi, bp_sys, bp_dia, phys_days, dpq, smoking, alcohol, diabetes, cycle)
-
-    # Get probability
-    # If you saved a separate calibrator, run model -> probs -> calibrator
-    # Otherwise assume model already outputs calibrated proba.
-    try:
-        raw_proba = model.predict_proba(X)[:, 1]
-    except Exception as e:
-        st.error(f"Model could not compute predict_proba. Error: {e}")
-        st.stop()
-
-    if calibrator is not None:
-        # calibrator usually expects 2D array
-        prob = float(calibrator.predict(raw_proba.reshape(-1, 1))[0])
-    else:
-        prob = float(raw_proba[0])
+        "Diabetes_Indicator": float(diabetes),
+        "Cycle": cycle
+    }])
 
-    label = label_from_probability(prob)
+    proba = float(model.predict_proba(sample)[:, 1][0])
+    pred = int(proba >= threshold)
+    label = "High Risk" if pred == 1 else "Low Risk"
 
-    # Display with bilingual mapping
-    if label == "Low Risk":
-        pretty_label = T["low"]
-        st.success(f"{T['result']}: {pretty_label}")
-    elif label == "Moderate Risk":
-        pretty_label = T["mod"]
-        st.warning(f"{T['result']}: {pretty_label}")
-    else:
-        pretty_label = T["high"]
-        st.error(f"{T['result']}: {pretty_label}")
+    md = format_output(lang, label, proba)
+    speak = web_speak_html(md, lang)
+    return md, speak
+
+# ---------------- UI ----------------
+with gr.Blocks(title="SleepGuardAI – Sleep Risk Screening") as demo:
+    gr.Markdown("# SleepGuardAI – Sleep Risk Screening (NHANES-based)")
+    gr.Markdown("Fill the form → get risk score. Bilingual output + Speak button included.")
+
+    lang = gr.Radio(["English", "বাংলা"], value="English", label="Language / ভাষা")
 
-    st.write(f"**{T['prob']}:** {prob:.3f}")
-    st.write(f"**{T['thresholds']}:** Low<{TH_LOW:.2f} | Moderate {TH_LOW:.2f}–{TH_HIGH:.2f} | High≥{TH_HIGH:.2f}")
-    st.caption(T["warning"])
+    with gr.Row():
+        age = gr.Slider(10, 90, value=30, label="Age / বয়স")
+        gender = gr.Dropdown(["Male", "Female"], value="Male", label="Gender")
+
+    with gr.Row():
+        bmi = gr.Slider(10, 50, value=25, label="BMI")
+        bp_sys = gr.Slider(80, 220, value=120, label="Systolic BP")
+        bp_dia = gr.Slider(40, 140, value=80, label="Diastolic BP")
+
+    phys = gr.Slider(0, 7, value=3, step=1, label="Physical Activity Days/Week")
+
+    gr.Markdown("### Optional (improves accuracy if known)")
+    with gr.Row():
+        dpq = gr.Slider(0, 27, value=0, step=1, label="DPQ Depression Score (0–27)")
+        smoking = gr.Dropdown([1, 2], value=2, label="Smoking (1=Yes, 2=No)")
+        diabetes = gr.Dropdown([1, 2], value=2, label="Diabetes (1=Yes, 2=No)")
+        alcohol = gr.Slider(0, 30, value=0, step=1, label="Alcohol feature (proxy)")
+
+    cycle = gr.Dropdown(["G", "H", "I", "J"], value="J", label="NHANES Cycle")
+
+    btn = gr.Button("Predict / ফলাফল দেখুন")
+    out_md = gr.Markdown()
+    out_speak = gr.HTML()
+
+    btn.click(
+        predict,
+        inputs=[lang, age, gender, bmi, bp_sys, bp_dia, phys, dpq, smoking, alcohol, diabetes, cycle],
+        outputs=[out_md, out_speak]
+    )
 
-    # Debug view if you want to show professor:
-    with st.expander("Show input feature row (for debugging/paper)"):
-        st.dataframe(X)
+demo.launch()

find_threshold_recall.py

@@ -1,79 +0,0 @@
-import joblib
-import numpy as np
-import pandas as pd
-from sklearn.model_selection import train_test_split
-from sklearn.metrics import recall_score, fbeta_score, roc_auc_score
-
-MODEL_PATH = "best_model_v2_calibrated.joblib"
-CSV_PATH = "nhanes_sleep_extended_v2.csv"
-
-TARGET = "Sleep_Risk"
-
-FEATURES = [
-    "Age",
-    "Gender",
-    "BMI",
-    "BP_SYS",
-    "BP_DIA",
-    "Phys_Activity_Days",
-    "DPQ_Score",
-    "Smoking_Indicator",
-    "Alcohol_Feature",
-    "Diabetes_Indicator",
-    "Cycle",
-]
-
-def main():
-    df = pd.read_csv(CSV_PATH)
-
-    # drop rows with missing values in required columns
-    df = df.dropna(subset=FEATURES + [TARGET]).copy()
-
-    X = df[FEATURES]
-    y = df[TARGET].astype(int)
-
-    # Train/test split (keep same logic as training if possible)
-    X_train, X_test, y_train, y_test = train_test_split(
-        X, y, test_size=0.20, random_state=42, stratify=y
-    )
-
-    bundle = joblib.load(MODEL_PATH)
-    model = bundle.get("model") if isinstance(bundle, dict) and "model" in bundle else bundle
-    calibrator = bundle.get("calibrator") if isinstance(bundle, dict) and "calibrator" in bundle else None
-
-    # Get probabilities
-    p_test_raw = model.predict_proba(X_test)[:, 1]
-    if calibrator is not None:
-        p_test = calibrator.predict(p_test_raw.reshape(-1, 1))
-    else:
-        p_test = p_test_raw
-
-    # AUC (threshold-free)
-    auc = roc_auc_score(y_test, p_test)
-    print(f"TEST AUC: {auc:.4f}")
-
-    # Sweep thresholds
-    thresholds = np.round(np.arange(0.05, 0.90, 0.01), 2)
-
-    best_f2 = (-1, None)
-    th_recall_085 = None
-
-    for th in thresholds:
-        pred = (p_test >= th).astype(int)
-        rec = recall_score(y_test, pred)
-        f2 = fbeta_score(y_test, pred, beta=2)
-
-        if f2 > best_f2[0]:
-            best_f2 = (f2, th)
-
-        if th_recall_085 is None and rec >= 0.85:
-            th_recall_085 = th
-
-    print(f"Best threshold by F2: {best_f2[1]} (F2={best_f2[0]:.4f})")
-    if th_recall_085 is not None:
-        print(f"Threshold achieving recall ≥ 0.85 : {th_recall_085}")
-    else:
-        print("No threshold achieved recall ≥ 0.85 in tested range.")
-
-if __name__ == "__main__":
-    main()

requirements.txt

@@ -1,7 +1,6 @@
-pandas
-numpy
-scikit-learn
-joblib
-xgboost
-matplotlib
-protobuf<4
+gradio
+pandas
+numpy
+scikit-learn
+joblib
+xgboost