Upload app.py with huggingface_hub

app.py

@@ -1,18 +1,18 @@
 
-import os
-import shutil
-import zipfile
-import pathlib
-import pandas
-import gradio
-import huggingface_hub
-import autogluon.tabular
+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"
-ZIP_FILENAME  = "autogluon_predictor_dir.zip"
+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"
+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 = [
@@ -23,12 +23,13 @@ FEATURE_COLS = [
     "sleep_time",
     "sleep_hours",
 ]
-TARGET_COL = "use_before_bed"
+TARGET_COL = "use_before_bed" # Assuming this is the target based on previous context
 
-# Encoding for sleep quality
+# 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
+# Encoding for outcome (assuming binary classification for use_before_bed)
 OUTCOME_LABELS = {
     0: "Does not use device before bed",
     1: "Uses device before bed",
@@ -83,16 +84,19 @@ def do_predict(phone_hours, computer_hours, device_count, sleep_quality_label, s
     }
     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:
+    except Exception as e:
         proba = None
 
+
     pred_label = _human_label(raw_pred)
 
     proba_dict = None
@@ -104,6 +108,7 @@ def do_predict(phone_hours, computer_hours, device_count, sleep_quality_label, s
             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),
@@ -114,9 +119,11 @@ def do_predict(phone_hours, computer_hours, device_count, sleep_quality_label, s
         md += f"  
 **Confidence:** {round(proba_dict.get(pred_label, 0.0) * 100, 2)}%"
 
+
     return proba_dict
 
-# Representative examples
+# 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],