Update app.py

app.py

@@ -1,61 +1,92 @@
 import gradio as gr
 import pandas as pd
 import numpy as np
-import joblib
-import datetime
+import pickle
+import tempfile
 import os
+from datetime import datetime
 
-# Load trained model
-model = joblib.load("anomaly_detector_rf_model.pkl")
+# Load model
+with open("anomaly_detector_rf_model.pkl", "rb") as f:
+    model = pickle.load(f)
 
+# Expected features for prediction
+expected_features = [
+    "amount", "log_amount", "amount_zscore",
+    "day_of_week", "hour", "is_weekend",
+]
+
+# Anomaly Detection Logic
 def detect_anomalies(df):
-    # Feature Engineering (must match training phase)
-    df['datetime'] = pd.to_datetime(df['timestamp'])
-    df['hour'] = df['datetime'].dt.hour
-    df['day_of_week'] = df['datetime'].dt.dayofweek
-    df['is_weekend'] = df['day_of_week'].isin([5, 6]).astype(int)
+    # Feature Engineering
     df['log_amount'] = np.log1p(df['amount'])
     df['amount_zscore'] = (df['amount'] - df['amount'].mean()) / df['amount'].std()
 
-    expected_features = ['amount', 'log_amount', 'amount_zscore', 'hour', 'day_of_week', 'is_weekend']
+    if 'timestamp' in df.columns:
+        df['timestamp'] = pd.to_datetime(df['timestamp'])
+        df['day_of_week'] = df['timestamp'].dt.dayofweek
+        df['hour'] = df['timestamp'].dt.hour
+        df['is_weekend'] = df['day_of_week'].apply(lambda x: 1 if x >= 5 else 0)
+    else:
+        # If timestamp missing, fill with default values
+        df['day_of_week'] = 0
+        df['hour'] = 0
+        df['is_weekend'] = 0
+
+    # Ensure all expected features exist
+    for col in expected_features:
+        if col not in df.columns:
+            df[col] = 0
 
+    # Predict
     df['is_anomalous'] = model.predict(df[expected_features])
 
+    # Extract anomaly rows
     anomalies = df[df['is_anomalous'] == 1]
-    anomalies_display = anomalies[['transaction_id', 'merchant', 'location', 'amount']].reset_index(drop=True)
 
-    # Save CSV for download
-    csv_path = "/tmp/anomalies.csv"
-    anomalies_display.to_csv(csv_path, index=False)
+    # Columns to return
+    display_cols = ['amount', 'transaction_id', 'merchant', 'location']
+
+    # CSV path
+    temp_dir = tempfile.mkdtemp()
+    csv_path = os.path.join(temp_dir, "anomalies.csv")
+    anomalies.to_csv(csv_path, index=False)
 
-    return anomalies_display, csv_path, {
-        "Total Transactions": len(df),
-        "Anomalies Detected": len(anomalies),
-        "Anomaly %": f"{(len(anomalies)/len(df)*100):.2f}%"
-    }
+    return anomalies[display_cols], csv_path
 
+# Gradio interface function
 def app_interface(file):
     try:
         df = pd.read_csv(file.name)
-        anomalies, csv_path, summary = detect_anomalies(df)
-        return anomalies, csv_path, summary
+        anomalies_df, csv_path = detect_anomalies(df)
+
+        summary = {
+            "Total Transactions": len(df),
+            "Anomalies Detected": len(anomalies_df),
+            "Anomaly %": round(100 * len(anomalies_df) / len(df), 2)
+        }
+
+        return anomalies_df, csv_path, summary
     except Exception as e:
-        return pd.DataFrame(), None, {"Error": str(e)}
+        return pd.DataFrame(), None, {"error": str(e)}
 
 # Gradio UI
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🧠 Financial Anomaly Detector\nUpload transaction data to detect anomalies using ML.")
+    gr.Markdown("# 🧠 Financial Anomaly Detector")
+    gr.Markdown("Upload your transaction CSV file to detect possible financial abuse in the elderly.")
 
     with gr.Row():
-        file_input = gr.File(label="📤 Upload CSV", file_types=[".csv"])
-        download_button = gr.File(label="📥 Download Anomalies CSV")
+        file_input = gr.File(label="📤 Upload Transaction CSV", file_types=[".csv"])
+        download_button = gr.File(label="📥 Download Anomalies (CSV)")
 
     with gr.Row():
-        output_table = gr.Dataframe(label="🚨 Detected Anomalies", wrap=True, height=300)
+        output_table = gr.Dataframe(label="🚨 Detected Anomalies")
         summary_box = gr.JSON(label="📊 Summary")
 
-    file_input.change(fn=app_interface, inputs=file_input, outputs=[output_table, download_button, summary_box])
+    file_input.change(
+        fn=app_interface,
+        inputs=file_input,
+        outputs=[output_table, download_button, summary_box]
+    )
 
-# If running locally
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()