Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,168 @@
+
+import os  # For filesystem operations
+import shutil  # For directory cleanup
+import zipfile  # For extracting model archives
+import pathlib  # For path manipulations
+import pandas  # For tabular data handling
+import gradio  # For interactive UI
+import huggingface_hub  # For downloading model assets
+import autogluon.tabular  # For loading and running AutoGluon predictors
+
+# Settings
+MODEL_REPO_ID = "jennifee/classical_automl_model" # Updated to the correct model repo
+ZIP_FILENAME  = "autogluon_predictor_dir.zip" # Assuming the zip filename is the same
+CACHE_DIR = pathlib.Path("hf_assets")
+EXTRACT_DIR = CACHE_DIR / "predictor_native_sleep" # Changed extract directory name
+
+# Feature column names and target column names based on the provided data structure
+FEATURE_COLS = [
+    "phone_hours",
+    "computer_hours",
+    "device_count",
+    "sleep_quality",
+    "sleep_time",
+    "sleep_hours",
+]
+TARGET_COL = "use_before_bed" # Assuming this is the target based on previous context
+
+# Encoding for sleep quality (assuming a categorical mapping is needed for the model)
+# This mapping is an example and may need adjustment based on the actual values in the dataset
+SLEEP_QUALITY_MAP = {"Poor": 0, "Fair": 1, "Good": 2, "Excellent": 3}
+
+# Encoding for outcome (assuming binary classification for use_before_bed)
+OUTCOME_LABELS = {
+    0: "Does not use device before bed",
+    1: "Uses device before bed",
+}
+
+# Download & load the native predictor
+def _prepare_predictor_dir() -> str:
+    CACHE_DIR.mkdir(parents=True, exist_ok=True)
+    local_zip = huggingface_hub.hf_hub_download(
+        repo_id=MODEL_REPO_ID,
+        filename=ZIP_FILENAME,
+        repo_type="model",
+        local_dir=str(CACHE_DIR),
+        local_dir_use_symlinks=False,
+    )
+    if EXTRACT_DIR.exists():
+        shutil.rmtree(EXTRACT_DIR)
+    EXTRACT_DIR.mkdir(parents=True, exist_ok=True)
+    with zipfile.ZipFile(local_zip, "r") as zf:
+        zf.extractall(str(EXTRACT_DIR))
+    contents = list(EXTRACT_DIR.iterdir())
+    predictor_root = contents[0] if (len(contents) == 1 and contents[0].is_dir()) else EXTRACT_DIR
+    return str(predictor_root)
+
+PREDICTOR_DIR = _prepare_predictor_dir()
+PREDICTOR = autogluon.tabular.TabularPredictor.load(PREDICTOR_DIR, require_py_version_match=False)
+
+# A mapping utility to make it easier to encode the variables
+def _human_label(c):
+    try:
+        ci = int(c)
+        if ci in OUTCOME_LABELS:
+            return OUTCOME_LABELS[ci]
+    except Exception:
+        pass
+    if c in OUTCOME_LABELS:
+        return OUTCOME_LABELS[c]
+    return str(c)
+
+# This functions takes all of our features, encodes this accordingly, and performs a predictions
+def do_predict(phone_hours, computer_hours, device_count, sleep_quality_label, sleep_time, sleep_hours):
+    # Encode categorical features
+    sleep_quality_code = SLEEP_QUALITY_MAP[sleep_quality_label]
+
+    row = {
+        FEATURE_COLS[0]: float(phone_hours),
+        FEATURE_COLS[1]: float(computer_hours),
+        FEATURE_COLS[2]: int(device_count),
+        FEATURE_COLS[3]: sleep_quality_code,
+        FEATURE_COLS[4]: int(sleep_time),
+        FEATURE_COLS[5]: float(sleep_hours),
+    }
+    X = pandas.DataFrame([row], columns=FEATURE_COLS)
+
+
+    pred_series = PREDICTOR.predict(X)
+    raw_pred = pred_series.iloc[0]
+
+
+    try:
+        proba = PREDICTOR.predict_proba(X)
+        if isinstance(proba, pandas.Series):
+            proba = proba.to_frame().T
+    except Exception as e:
+        proba = None
+
+
+    pred_label = _human_label(raw_pred)
+
+    proba_dict = None
+    if proba is not None:
+        row0 = proba.iloc[0]
+        tmp = {}
+        for cls, val in row0.items():
+            key = _human_label(cls)
+            tmp[key] = float(val) + float(tmp.get(key, 0.0))
+        proba_dict = dict(sorted(tmp.items(), key=lambda kv: kv[1], reverse=True))
+
+
+    df_out = pandas.DataFrame([{
+        "Predicted outcome": pred_label,
+        "Confidence (%)": round((proba_dict.get(pred_label, 1.0) if proba_dict else 1.0) * 100, 2),
+    }])
+
+    md = f"**Prediction:** {pred_label}"
+    if proba_dict:
+        md += f"  
+**Confidence:** {round(proba_dict.get(pred_label, 0.0) * 100, 2)}%"
+
+
+    return proba_dict
+
+# Representative examples (these will need to be updated based on the new model's features)
+# These examples are placeholders and should be replaced with actual examples from the dataset if available
+EXAMPLES = [
+    [2.0, 3.0, 3, "Good", 2200, 8.0],
+    [5.0, 6.0, 5, "Fair", 100, 6.0],
+    [1.0, 1.0, 1, "Excellent", 2300, 9.0],
+
+]
+
+# Gradio UI for the sleep habits model
+with gradio.Blocks() as demo:
+    # Provide an introduction
+    gradio.Markdown("# Device Use Before Sleep Predictor")
+    gradio.Markdown("""
+    This app predicts whether a student uses their device before sleep based on their device usage and sleeping habits.
+    """)
+
+    with gradio.Row():
+        phone_hours = gradio.Slider(0, 10, step=0.1, value=2.0, label=FEATURE_COLS[0])
+        computer_hours = gradio.Slider(0, 10, step=0.1, value=3.0, label=FEATURE_COLS[1])
+        device_count = gradio.Number(value=3, precision=0, label=FEATURE_COLS[2])
+
+    with gradio.Row():
+        sleep_quality_label = gradio.Radio(choices=list(SLEEP_QUALITY_MAP.keys()), value="Good", label=FEATURE_COLS[3])
+        sleep_time = gradio.Number(value=2200, precision=0, label=FEATURE_COLS[4])
+        sleep_hours = gradio.Slider(0, 12, step=0.1, value=8.0, label=FEATURE_COLS[5])
+
+
+    proba_pretty = gradio.Label(num_top_classes=2, label="Class probabilities") # Assuming binary classification
+
+    inputs = [phone_hours, computer_hours, device_count, sleep_quality_label, sleep_time, sleep_hours]
+    for comp in inputs:
+        comp.change(fn=do_predict, inputs=inputs, outputs=[proba_pretty])
+
+    gradio.Examples(
+        examples=EXAMPLES,
+        inputs=inputs,
+        label="Representative examples",
+        examples_per_page=3,
+        cache_examples=False,
+    )
+
+if __name__ == "__main__":
+    demo.launch()