Update app.py

app.py

@@ -1,25 +1,36 @@
+import gradio as gr
+import joblib
+import pandas as pd
+
+# Load saved objects
+model = joblib.load('fall_detection_model.joblib')
+scaler = joblib.load('scaler.joblib')
+encoder = joblib.load('encoder.joblib')
+feature_names = joblib.load('feature_names.joblib')  # make sure this has hour_of_day and minute_of_day
+
 def predict_fall(movement_activity, location, day_of_week, hour_of_day, minute_of_day, time_since_last_event):
     try:
-        data = {f: 0 for f in feature_names}  # fallback, keep for all known features
+        # Initialize all features with zero
+        data = {f: 0 for f in feature_names}
 
-        # Set your categorical one-hot
+        # One-hot encode categoricals
         data[f'Movement Activity_{movement_activity}'] = 1
         data[f'Location_{location}'] = 1
         data[f'day_of_week_{day_of_week}'] = 1
 
-        # Set numeric features
+        # Set numerical features
         data['hour_of_day'] = hour_of_day
         data['minute_of_day'] = minute_of_day
         data['time_since_last_event'] = time_since_last_event
 
-        # Build DataFrame with **all keys of data** (guarantees no missing columns)
-        input_df = pd.DataFrame([data], columns=list(data.keys()))
-
-        scaler_feature_names = scaler.feature_names_in_
+        # Build DataFrame with columns ordered as feature_names
+        input_df = pd.DataFrame([data], columns=feature_names)
 
-        scaled_array = scaler.transform(input_df[scaler_feature_names])
-        input_df.loc[:, scaler_feature_names] = scaled_array
+        # Scale numeric features
+        scaled_array = scaler.transform(input_df)
+        input_df.loc[:, feature_names] = scaled_array
 
+        # Predict probability
         pred_proba = model.predict_proba(input_df)[0, 1]
         threshold = 0.4
         pred_label = "Fall Detected" if pred_proba >= threshold else "No Fall"
@@ -31,3 +42,27 @@ def predict_fall(movement_activity, location, day_of_week, hour_of_day, minute_o
         tb = traceback.format_exc()
         print("Error in prediction:\n", tb)
         return f"Error: {str(e)}\nCheck server logs for details."
+
+# Prepare dropdown choices from encoder categories
+movement_choices = encoder.categories_[0].tolist()
+location_choices = encoder.categories_[1].tolist()
+day_choices = [col.replace('day_of_week_', '') for col in feature_names if col.startswith('day_of_week_')]
+
+# Gradio Interface
+iface = gr.Interface(
+    fn=predict_fall,
+    inputs=[
+        gr.Dropdown(choices=movement_choices, label="Movement Activity"),
+        gr.Dropdown(choices=location_choices, label="Location"),
+        gr.Dropdown(choices=day_choices, label="Day of Week"),
+        gr.Slider(0, 23, step=1, label="Hour of Day"),
+        gr.Slider(0, 59, step=1, label="Minute of Day"),
+        gr.Number(label="Time Since Last Event (seconds)", value=60)
+    ],
+    outputs="text",
+    title="Fall Detection Model",
+    description="Predicts fall based on sensor data."
+)
+
+if __name__ == "__main__":
+    iface.launch()