Create app.py

app.py

@@ -0,0 +1,167 @@
+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 = "ccm/2024-24679-tabular-autolguon-predictor"
+ZIP_FILENAME  = "autogluon_predictor_dir.zip"
+CACHE_DIR = pathlib.Path("hf_assets")
+EXTRACT_DIR = CACHE_DIR / "predictor_native"
+
+# Feature schema (must match training)
+FEATURE_COLS = [
+    "About how many hours per week do you spend listening to music?",
+    "Approximately how many songs are in your music library?",
+    "Approximately how many playlists have you created yourself?",
+    "How often do you share music with others?",
+    "Which decade of music do you listen to most?",
+    "How often do you attend live music events?",
+    "Do you prefer songs with lyrics or instrumental music?",
+]
+TARGET_COL = "Do you usually listen to music alone or with others?"
+
+# Encodings (aligned to survey UI)
+LIKERT5_LABELS = ["Never", "Rarely", "Sometimes", "Often", "Very Often"]
+LIKERT5_MAP = {label: idx for idx, label in enumerate(LIKERT5_LABELS)}
+
+DECADE_LABELS = ["1970s and before", "1980s", "1990s", "2000s", "2010s", "2020s"]
+DECADE_MAP = {label: idx for idx, label in enumerate(DECADE_LABELS)}
+
+LYRICS_LABELS = ["Lyrics", "Instrumental", "Both equally"]
+LYRICS_MAP = {label: idx for idx, label in enumerate(LYRICS_LABELS)}
+
+# Outcome label mapping
+OUTCOME_LABELS = {
+    0: "Mostly Alone",
+    1: "Mostly With Others",
+}
+
+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)
+
+# Class-to-label mapper
+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)
+
+# Inference
+def do_predict(hours_per_week, num_songs, num_playlists, share_label, decade_label, live_events_label, lyrics_label):
+    share_code = LIKERT5_MAP[share_label]
+    decade_code = DECADE_MAP[decade_label]
+    live_events_code = LIKERT5_MAP[live_events_label]
+    lyrics_code = LYRICS_MAP[lyrics_label]
+
+    row = {
+        FEATURE_COLS[0]: float(hours_per_week),
+        FEATURE_COLS[1]: int(num_songs),
+        FEATURE_COLS[2]: int(num_playlists),
+        FEATURE_COLS[3]: int(share_code),
+        FEATURE_COLS[4]: int(decade_code),
+        FEATURE_COLS[5]: int(live_events_code),
+        FEATURE_COLS[6]: int(lyrics_code),
+    }
+    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:
+        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"  \n**Confidence:** {round(proba_dict.get(pred_label, 0.0) * 100, 2)}%"
+
+    return md, proba_dict, df_out
+
+# Representative examples
+EXAMPLES = [
+    [5.0, 300, 3,  "Rarely",      "2010s", "Rarely",      "Lyrics"],
+    [18.0, 1500, 25, "Often",     "2000s", "Often",       "Both equally"],
+    [12.0, 8000, 40, "Sometimes", "1990s", "Sometimes",   "Instrumental"],
+    [4.0, 120, 1,   "Never",      "1970s and before", "Rarely", "Lyrics"],
+    [22.0, 500, 10, "Very Often", "2020s", "Very Often",  "Lyrics"],
+]
+
+# Gradio UI
+with gradio.Blocks() as demo:
+    with gradio.Row():
+        hours_per_week = gradio.Slider(0, 80, step=0.5, value=5.0, label=FEATURE_COLS[0])
+        num_songs = gradio.Number(value=200, precision=0, label=FEATURE_COLS[1])
+        num_playlists = gradio.Number(value=5, precision=0, label=FEATURE_COLS[2])
+
+    with gradio.Row():
+        share_label = gradio.Radio(choices=LIKERT5_LABELS, value="Sometimes", label="How often do you share music with others?")
+        live_events_label = gradio.Radio(choices=LIKERT5_LABELS, value="Rarely", label="How often do you attend live music events?")
+
+    with gradio.Row():
+        decade_label = gradio.Radio(choices=DECADE_LABELS, value="2010s", label="Which decade of music do you listen to most?")
+        lyrics_label = gradio.Radio(choices=LYRICS_LABELS, value="Lyrics", label="Do you prefer songs with lyrics or instrumental music?")
+
+    proba_pretty = gradio.Label(num_top_classes=5, label="Class probabilities")
+    pred_table = gradio.Dataframe(headers=["Predicted outcome", "Confidence (%)"], label="Prediction (compact)", interactive=False)
+
+    inputs = [hours_per_week, num_songs, num_playlists, share_label, decade_label, live_events_label, lyrics_label]
+    for comp in inputs:
+        comp.change(fn=do_predict, inputs=inputs, outputs=[proba_pretty, pred_table])
+
+    gradio.Examples(
+        examples=EXAMPLES,
+        inputs=inputs,
+        label="Representative examples",
+        examples_per_page=5,
+        cache_examples=False,
+    )
+
+if __name__ == "__main__":
+    demo.launch()