Upload app.py with huggingface_hub

app.py

@@ -1,16 +1,18 @@
-import pathlib, shutil, zipfile, tempfile
+import pathlib, shutil, zipfile
 import pandas
 import gradio
 import huggingface_hub
-import autogluon.multimodal
-import PIL.Image
+import autogluon.tabular
 
-MODEL_REPO_ID = "george2cool36/hw2_image_automl_autogluon"
-ZIP_FILENAME  = "ag_image_predictor_dir.zip"
+MODEL_REPO_ID = "jennifee/classical_automl_model"
+ZIP_FILENAME  = "autogluon_predictor_dir.zip"
 CACHE_DIR = pathlib.Path("hf_assets")
 EXTRACT_DIR = CACHE_DIR / "predictor_native"
 
-CLASS_LABELS = {0: "🛑 Has Stop Sign", 1: "✅ No Stop Sign"}
+FEATURE_COLS_MODEL = ['phone_hours', 'computer_hours', 'device_count', 'sleep_quality', 'sleep_time', 'sleep_hours']
+TARGET_COL = "use_before_bed"
+SLEEP_QUALITY_LABELS = ['good', 'medium', 'bad']
+USE_BEFORE_BED_LABELS = {0: 'No', 1: 'Yes'}
 
 def _prepare_predictor_dir() -> str:
     CACHE_DIR.mkdir(parents=True, exist_ok=True)
@@ -31,66 +33,86 @@ def _prepare_predictor_dir() -> str:
     return str(predictor_root)
 
 PREDICTOR_DIR = _prepare_predictor_dir()
-PREDICTOR = autogluon.multimodal.MultiModalPredictor.load(PREDICTOR_DIR)
+PREDICTOR = autogluon.tabular.TabularPredictor.load(PREDICTOR_DIR, require_py_version_match=False)
 
 def _human_label(c):
     try:
         ci = int(c)
-        return CLASS_LABELS.get(ci, str(c))
+        if ci in USE_BEFORE_BED_LABELS:
+            return USE_BEFORE_BED_LABELS[ci]
     except Exception:
-        return CLASS_LABELS.get(c, str(c))
-
-def do_predict(pil_img: PIL.Image.Image):
-    if pil_img is None:
-        return {}, "No image provided."
-
-    tmpdir = pathlib.Path(tempfile.mkdtemp())
-    img_path = tmpdir / "input.png"
-    pil_img.save(img_path)
-
-    df = pandas.DataFrame({"image": [str(img_path)]})
-
-    proba_df = PREDICTOR.predict_proba(df)
-    proba_df = proba_df.rename(columns={0: "🛑 Has Stop Sign (0)", 1: "✅ No Stop Sign (1)"})
-    row = proba_df.iloc[0]
-
-    pretty_dict = {
-        "🛑 Has Stop Sign": float(row.get("🛑 Has Stop Sign (0)", 0.0)),
-        "✅ No Stop Sign": float(row.get("✅ No Stop Sign (1)", 0.0)),
+        pass
+    return str(c)
+
+def do_predict(phone_hours, computer_hours, device_count, sleep_quality_label, sleep_time, sleep_hours):
+    row = {
+        "phone_hours": float(phone_hours),
+        "computer_hours": float(computer_hours),
+        "device_count": int(device_count),
+        "sleep_quality": sleep_quality_label,
+        "sleep_time": int(sleep_time),
+        "sleep_hours": float(sleep_hours),
     }
+    X = pandas.DataFrame([row], columns=FEATURE_COLS_MODEL)
 
-    predicted_class = PREDICTOR.predict(df).iloc[0]
-    pred_label = _human_label(predicted_class)
-
-    md = f"**Prediction:** {pred_label}"
-    if pretty_dict:
-        md += f"  \n**Confidence:** {round(pretty_dict.get(pred_label, 0.0) * 100, 2)}%"
+    pred_series = PREDICTOR.predict(X)
+    raw_pred = pred_series.iloc[0]
+    pred_label = _human_label(raw_pred)
 
+    proba = None
+    try:
+        proba = PREDICTOR.predict_proba(X)
+        if isinstance(proba, pandas.Series):
+            proba = proba.to_frame().T
+    except Exception as e:
+        print(f"Error calculating probabilities: {e}")
+        proba = None
+
+    proba_dict = None
+    if proba is not None:
+        row0 = proba.iloc[0]
+        tmp = {}
+        for cls in [0, 1]:
+            val = None
+            if cls in row0.index:
+                val = row0[cls]
+            elif str(cls) in row0.index:
+                val = row0[str(cls)]
+            if val is not None:
+                key = _human_label(cls)
+                tmp[key] = float(tmp.get(key, 0.0)) + float(val)
+        if tmp:
+            proba_dict = dict(sorted(tmp.items(), key=lambda kv: kv[1], reverse=True))
 
-    return pretty_dict, md
+    md = f"**Prediction:** {pred_label}"
+    if proba_dict:
+        md += f"  \n**Confidence:** {round(proba_dict.get(pred_label, 0.0) * 100, 2)}%"
 
-EXAMPLES = [
-    ["https://www.kingsrivercasting.com/images/stories/virtuemart/product/STOP%20SIGN%20(5).jpg"],
-    ["https://www.trafficsafetywarehouse.com/Resources/images/traffic-sign-shapes.jpeg"],
-    ["https://di-uploads-pod16.dealerinspire.com/toyotaofnorthcharlotte/uploads/2020/08/yield-road-sign.jpg"]
-]
+    return proba_dict, md
 
+EXAMPLES = [[3.5, 5.0, 3, 'good', 23, 7.0], [4.2, 6.5, 3, 'medium', 0, 6.5], [5.0, 4.0, 4, 'bad', 1, 6.0], [2.0, 7.5, 3, 'good', 22, 7.5], [3.8, 6.0, 3, 'medium', 0, 6.0]]
 
 with gradio.Blocks() as demo:
-    gradio.Markdown("# Has Stop Sign or Not?")
+    gradio.Markdown("# Predict Phone Use Before Bed")
     gradio.Markdown(
-        "This is a simple app that demonstrates how to use an autogluon multimodal"
-        "predictor in a gradio space to predict whether an image contains a stop sign. To use,"
-        "just upload a photo. The result should be generated automatically."
+        "This app predicts whether a student uses their phone before bed based on their sleeping habits."
+        "\nEnter the student's sleeping habits below to get a prediction."
     )
 
-    image_in = gradio.Image(type="pil", label="Input image", sources=["upload", "webcam"])
+    with gradio.Row():
+        phone_hours = gradio.Number(value=3.5, precision=1, label=FEATURE_COLS_MODEL[0])
+        computer_hours = gradio.Number(value=5.0, precision=1, label=FEATURE_COLS_MODEL[1])
+        device_count = gradio.Number(value=3, precision=0, label=FEATURE_COLS_MODEL[2])
 
-    proba_pretty = gradio.Label(num_top_classes=2, label="Class probabilities")
-    prediction_output = gradio.Markdown()
+    with gradio.Row():
+        sleep_quality_label = gradio.Radio(choices=SLEEP_QUALITY_LABELS, value="good", label=FEATURE_COLS_MODEL[3])
+        sleep_time = gradio.Number(value=23, precision=0, label=FEATURE_COLS_MODEL[4])
+        sleep_hours = gradio.Number(value=7.0, precision=1, label=FEATURE_COLS_MODEL[5])
 
+    proba_pretty = gradio.Label(num_top_classes=2, label="Probability of Using Phone Before Bed")
+    prediction_output = gradio.Markdown()
 
-    inputs = [image_in]
+    inputs = [phone_hours, computer_hours, device_count, sleep_quality_label, sleep_time, sleep_hours]
     outputs = [proba_pretty, prediction_output]
     for comp in inputs:
         comp.change(fn=do_predict, inputs=inputs, outputs=outputs)
@@ -99,7 +121,7 @@ with gradio.Blocks() as demo:
         examples=EXAMPLES,
         inputs=inputs,
         label="Representative examples",
-        examples_per_page=8,
+        examples_per_page=5,
         cache_examples=False,
     )