Upload app.py with huggingface_hub

app.py

@@ -7,6 +7,7 @@ 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
+import sklearn # Import sklearn to check version
 
 # Settings
 MODEL_REPO_ID = "jennifee/classical_automl_model" # Updated to the correct model repo
@@ -71,55 +72,83 @@ def _human_label(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]
+    print("Received inputs:")
+    print(f"  phone_hours: {phone_hours}")
+    print(f"  computer_hours: {computer_hours}")
+    print(f"  device_count: {device_count}")
+    print(f"  sleep_quality_label: {sleep_quality_label}")
+    print(f"  sleep_time: {sleep_time}")
+    print(f"  sleep_hours: {sleep_hours}")
+    print(f"  sklearn version: {sklearn.__version__}") # Print sklearn version
 
 
     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)
+        # 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)
+
+        print("Input DataFrame (X):")
+        print(X)
+
+        pred_series = PREDICTOR.predict(X)
+        raw_pred = pred_series.iloc[0]
+
+        print("Raw prediction (pred_series):")
+        print(pred_series)
+
+        try:
+            proba = PREDICTOR.predict_proba(X)
+            if isinstance(proba, pandas.Series):
+                proba = proba.to_frame().T
+            print("Prediction probabilities (proba):")
+            print(proba)
+        except Exception as e:
+            proba = None
+            print(f"Error getting prediction probabilities: {e}")
+
+
+        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))
+        print("Probability dictionary (proba_dict):")
+        print(proba_dict)
+
+
+        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)}%"
+        print("Markdown output (md):")
+        print(md)
+
+        return proba_dict
 
-    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 proba_dict
+    except Exception as e:
+        print(f"An error occurred during prediction: {e}")
+        import traceback
+        traceback.print_exc()
+        return None # Return None or an empty dictionary in case of an error
 
 # 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
@@ -134,9 +163,9 @@ EXAMPLES = [
 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.
-    """)
+    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])