Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,92 @@
+
+import pathlib, shutil, zipfile
+import pandas as pd
+import gradio as gr
+from huggingface_hub import hf_hub_download
+from autogluon.tabular import TabularPredictor
+
+# ====== Settings (edit if your repo/zip name changes) ======
+MODEL_REPO_ID = "Iris314/classical-automl-model"
+ZIP_FILENAME  = "lego_predictor_dir.zip"
+
+# UI → model feature name mapping
+COLUMN_ALIAS = {
+    "Length": "Max Length (cm)",
+    "Height": "Max Height (cm)",
+    "Width":  "Width (cm)",
+    "Studs":  "Studs",
+}
+FEATURE_COLS_UI = ["Length", "Height", "Width", "Studs"]
+
+# ====== Load predictor from the model repo ======
+CACHE_DIR = pathlib.Path("hf_cache"); EXTRACT_DIR = CACHE_DIR / "predictor"
+CACHE_DIR.mkdir(exist_ok=True, parents=True)
+
+def load_predictor():
+    local_zip = 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(EXTRACT_DIR)
+    kids = list(EXTRACT_DIR.iterdir())
+    path = kids[0] if len(kids) == 1 and kids[0].is_dir() else EXTRACT_DIR
+    return TabularPredictor.load(str(path), require_py_version_match=False)
+
+PREDICTOR = load_predictor()
+
+def _cast_and_rename(row_dict):
+    row = dict(row_dict)
+    row["Length"] = float(row["Length"])
+    row["Height"] = float(row["Height"])
+    row["Width"]  = float(row["Width"])
+    row["Studs"]  = int(round(float(row["Studs"])))
+    X_ui = pd.DataFrame([row], columns=FEATURE_COLS_UI)
+    X_model = X_ui.rename(columns=COLUMN_ALIAS)
+    return X_model
+
+def classify_brick(length, height, width, studs):
+    try:
+        X = _cast_and_rename({"Length": length, "Height": height, "Width": width, "Studs": studs})
+        pred = PREDICTOR.predict(X)
+        pred_val = pred.iloc[0] if hasattr(pred, "iloc") else pred
+        try:
+            proba = PREDICTOR.predict_proba(X)
+            s = proba.iloc[0] if hasattr(proba, "iloc") else proba
+            s = s.sort_values(ascending=False)
+            s.index = [str(k) for k in s.index]
+            return {k: float(v) for k, v in s.items()}
+        except Exception:
+            return {"prediction": str(pred_val)}
+    except Exception as e:
+        import traceback
+        return {"error": f"{type(e).__name__}: {e}", "traceback": traceback.format_exc()}
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 🧱 LEGO Brick Classifier")
+    gr.Markdown("Enter dimensions to predict **Standard / Flat / Sloped**. Uses a classmate's AutoGluon model trained on `aedupuga/lego-sizes`.")
+    with gr.Row():
+        length = gr.Slider(1, 10, step=0.1, value=4,  label="Length")
+        height = gr.Slider(0.2, 5, step=0.1, value=1.2, label="Height")
+    with gr.Row():
+        width  = gr.Slider(1, 10, step=0.1, value=2,  label="Width")
+        studs  = gr.Number(value=4, precision=0, label="Studs")
+    out = gr.Label(num_top_classes=3, label="Predicted Class / Probabilities")
+    gr.Button("Classify Brick", variant="primary").click(
+        fn=classify_brick, inputs=[length, height, width, studs], outputs=out
+    )
+    gr.Examples(
+        examples=[[4, 1.2, 2, 4],[2, 0.6, 2, 2],[3, 2.0, 2, 2]],
+        inputs=[length, height, width, studs],
+        label="Examples",
+        cache_examples=False
+    )
+
+if __name__ == "__main__":
+    demo.launch()