Update app.py

app.py

@@ -1,107 +1,83 @@
 import gradio as gr
 import pandas as pd
-import joblib
 import matplotlib.pyplot as plt
 import seaborn as sns
-import io
+import os
+import uuid
+import joblib
 
-# Load trained model
+# Load the model
 model = joblib.load("anomaly_detector_rf_model.pkl")
 
-# Features used during training
-feature_cols = [
-    "amount", "hour", "day_of_week", "is_weekend", "merchant_avg_amount",
-    "amount_zscore", "log_amount", "type_atm_withdrawal", "type_credit",
-    "type_debit", "merchant_encoded"
-]
+# Define the features expected by the model
+expected_features = ["amount"]  # Update this list as per your trained model
 
-# Function to detect anomalies
 def detect_anomalies(df):
-    original_df = df.copy()
-
-    for col in ["transaction_id", "merchant", "location", "amount"]:
-        if col not in original_df.columns:
-            original_df[col] = "N/A" if col != "amount" else 0.0
-
-    model_input = df.reindex(columns=feature_cols, fill_value=0)
-    preds = model.predict(model_input)
-    original_df["is_anomalous"] = preds
-
-    anomalies = original_df[original_df["is_anomalous"] == 1]
-    return original_df, anomalies[["transaction_id", "merchant", "location", "amount", "is_anomalous"]]
-
-# Function to plot charts
-def plot_charts(df):
-    fig, axes = plt.subplots(2, 2, figsize=(12, 10))
-
-    if "amount" in df.columns:
-        sns.histplot(df["amount"], bins=30, kde=True, ax=axes[0, 0])
-        axes[0, 0].set_title("Amount Distribution")
-        sns.boxplot(x=df["amount"], ax=axes[0, 1])
-        axes[0, 1].set_title("Amount Box Plot")
-    else:
-        axes[0, 0].text(0.5, 0.5, "No 'amount' column", ha='center')
-        axes[0, 1].text(0.5, 0.5, "No 'amount' column", ha='center')
-
-    if "day_of_week" in df.columns:
-        sns.countplot(x=df["day_of_week"], ax=axes[1, 0])
-        axes[1, 0].set_title("Transactions by Day of Week")
-    else:
-        axes[1, 0].text(0.5, 0.5, "No 'day_of_week' column", ha='center')
-
-    if "merchant" in df.columns:
-        top_merchants = df.groupby("merchant")["amount"].sum().nlargest(5).reset_index()
-        sns.barplot(data=top_merchants, x="merchant", y="amount", ax=axes[1, 1])
-        axes[1, 1].set_title("Top 5 Merchants by Amount")
-    else:
-        axes[1, 1].text(0.5, 0.5, "No 'merchant' column", ha='center')
-
-    plt.tight_layout()
-    return fig
-
-# Function to generate summary + charts + file
-def app_interface(csv_file):
-    df = pd.read_csv(csv_file)
-    full_df, anomalies = detect_anomalies(df)
+    df = df.copy()
+    df['is_anomalous'] = model.predict(df[expected_features])
+    anomalies = df[df['is_anomalous'] == 1]
 
-    total = len(full_df)
-    anom_count = len(anomalies)
-    percent = (anom_count / total) * 100 if total > 0 else 0
+    # Save anomalies to temporary CSV file
+    csv_filename = f"/tmp/anomalies_{uuid.uuid4().hex}.csv"
+    anomalies.to_csv(csv_filename, index=False)
 
-    summary = (
-        f"🔢 **Total Transactions**: {total}\n"
-        f"⚠️ **Anomalies Detected**: {anom_count}\n"
-        f"📊 **Anomaly Percentage**: {percent:.2f}%"
+    return (
+        anomalies[["transaction_id", "merchant", "location", "amount", "is_anomalous"]],
+        csv_filename
     )
 
-    # Convert anomalies to CSV bytes for download
-    csv_bytes = anomalies.to_csv(index=False).encode()
-    download = io.BytesIO(csv_bytes)
+def generate_summary(df):
+    total_transactions = len(df)
+    total_anomalies = df['is_anomalous'].sum()
+    percent_anomalies = round((total_anomalies / total_transactions) * 100, 2)
+    return f"Total Transactions: {total_transactions}\nTotal Anomalies: {total_anomalies}\nAnomaly Rate: {percent_anomalies}%"
 
-    fig = plot_charts(full_df)
+def generate_charts(df):
+    fig, ax = plt.subplots(1, 2, figsize=(12, 5))
 
-    return summary, anomalies, fig, download
+    # Distribution of Amounts
+    sns.histplot(df['amount'], bins=30, ax=ax[0], kde=True)
+    ax[0].set_title('Transaction Amount Distribution')
 
-# Gradio App with UI
-with gr.Blocks(theme=gr.themes.Soft()) as interface:
-    gr.Markdown("# 🛡️ Financial Abuse & Anomaly Detection App")
-    gr.Markdown("Upload your **transaction CSV** to detect anomalies and view insights.")
+    # Anomalies by Merchant
+    anomaly_counts = df[df['is_anomalous'] == 1]['merchant'].value_counts().nlargest(10)
+    sns.barplot(x=anomaly_counts.values, y=anomaly_counts.index, ax=ax[1])
+    ax[1].set_title('Top 10 Merchants with Anomalies')
 
-    with gr.Row():
-        file_input = gr.File(label="📁 Upload CSV File", file_types=[".csv"])
-        detect_button = gr.Button("🚨 Run Detection", variant="primary")
+    plt.tight_layout()
+    chart_path = f"/tmp/chart_{uuid.uuid4().hex}.png"
+    plt.savefig(chart_path)
+    plt.close()
+    return chart_path
+
+def app_interface(file):
+    df = pd.read_csv(file.name)
+    anomalies, csv_path = detect_anomalies(df)
+    summary = generate_summary(df)
+    chart_path = generate_charts(df)
+    return anomalies, summary, chart_path, csv_path
+
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("""
+    # 🔍 Elder Financial Abuse Detection Tool
+    Upload a transaction dataset to identify potential financial abuse patterns in elderly individuals.
+    """)
 
     with gr.Row():
-        summary_box = gr.Markdown("")
+        file_input = gr.File(label="📂 Upload Transaction CSV")
+        analyze_btn = gr.Button("🚀 Analyze")
 
-    with gr.Tab("📋 Anomalies Detected"):
-        result_table = gr.Dataframe(label="🔴 Anomalies")
-        download_btn = gr.File(label="⬇️ Download Detected Anomalies")
+    with gr.Row():
+        anomalies_output = gr.Dataframe(label="⚠️ Detected Anomalies", wrap=True)
+        summary_output = gr.Textbox(label="📊 Summary")
 
-    with gr.Tab("📊 Transaction Charts"):
-        chart_output = gr.Plot()
+    chart_output = gr.Image(label="📈 Analysis Charts")
+    csv_download = gr.File(label="📁 Download Anomalies CSV")
 
-    detect_button.click(fn=app_interface, inputs=file_input,
-                        outputs=[summary_box, result_table, chart_output, download_btn])
+    analyze_btn.click(
+        fn=app_interface,
+        inputs=[file_input],
+        outputs=[anomalies_output, summary_output, chart_output, csv_download]
+    )
 
-interface.launch(share=True)
+demo.launch()