Update app.py

app.py

@@ -1,57 +1,107 @@
-# app.py
 import gradio as gr
 import pandas as pd
-import numpy as np
-import pickle
-from datetime import datetime
+import joblib
+import matplotlib.pyplot as plt
+import seaborn as sns
+import io
 
-# Load model
-with open("anomaly_detector_rf_model.pkl", "rb") as f:
-    model = pickle.load(f)
+# Load trained 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"
+]
+
+# Function to detect anomalies
 def detect_anomalies(df):
-    df["log_amount"] = np.log1p(df["amount"])
-    df["amount_zscore"] = (df["amount"] - df["amount"].mean()) / df["amount"].std()
-    df["transaction_date"] = pd.to_datetime(df["transaction_date"])
-    df["day_of_week"] = df["transaction_date"].dt.dayofweek
-    df["hour"] = df["transaction_date"].dt.hour
-    df["is_weekend"] = df["day_of_week"].isin([5, 6]).astype(int)
+    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')
 
-    features = ["amount", "log_amount", "amount_zscore", "day_of_week", "hour", "is_weekend"]
-    df["is_anomalous"] = model.predict(df[features])
+    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')
 
-    anomalies = df[df["is_anomalous"] == 1][["transaction_id", "amount", "merchant", "location", "transaction_date"]]
+    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')
 
-    # Save anomalies to CSV
-    csv_path = "/tmp/anomalies.csv"
-    anomalies.to_csv(csv_path, index=False)
+    plt.tight_layout()
+    return fig
 
-    return anomalies, csv_path
+# Function to generate summary + charts + file
+def app_interface(csv_file):
+    df = pd.read_csv(csv_file)
+    full_df, anomalies = detect_anomalies(df)
 
-# Summary function
-def generate_summary(df):
-    total = len(df)
-    anomalous = df["is_anomalous"].sum()
-    return f"Total Transactions: {total} | 🚨 Anomalies: {anomalous} | ⚠️ Rate: {anomalous/total:.2%}"
+    total = len(full_df)
+    anom_count = len(anomalies)
+    percent = (anom_count / total) * 100 if total > 0 else 0
 
-# Gradio UI
-with gr.Blocks() as app:
-    gr.Markdown("## 💸 Financial Transaction Anomaly Detector")
-    gr.Markdown("Upload your CSV with columns: `transaction_id`, `amount`, `merchant`, `location`, `transaction_date`")
+    summary = (
+        f"🔢 **Total Transactions**: {total}\n"
+        f"⚠️ **Anomalies Detected**: {anom_count}\n"
+        f"📊 **Anomaly Percentage**: {percent:.2f}%"
+    )
+
+    # Convert anomalies to CSV bytes for download
+    csv_bytes = anomalies.to_csv(index=False).encode()
+    download = io.BytesIO(csv_bytes)
+
+    fig = plot_charts(full_df)
+
+    return summary, anomalies, fig, download
+
+# 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.")
+
+    with gr.Row():
+        file_input = gr.File(label="📁 Upload CSV File", file_types=[".csv"])
+        detect_button = gr.Button("🚨 Run Detection", variant="primary")
 
     with gr.Row():
-        file_input = gr.File(file_types=[".csv"], label="📁 Upload Transaction File")
-        download_button = gr.File(label="⬇️ Download Anomalies CSV")
+        summary_box = gr.Markdown("")
 
-    summary_text = gr.Textbox(label="📊 Summary", interactive=False)
-    output_table = gr.Dataframe(label="🚨 Detected Anomalies")
+    with gr.Tab("��� Anomalies Detected"):
+        result_table = gr.Dataframe(label="🔴 Anomalies")
+        download_btn = gr.File(label="⬇️ Download Detected Anomalies")
 
-    def app_interface(file):
-        df = pd.read_csv(file.name)
-        anomalies, csv_path = detect_anomalies(df)
-        summary = generate_summary(df)
-        return summary, anomalies, csv_path
+    with gr.Tab("📊 Transaction Charts"):
+        chart_output = gr.Plot()
 
-    file_input.change(fn=app_interface, inputs=[file_input], outputs=[summary_text, output_table, download_button])
+    detect_button.click(fn=app_interface, inputs=file_input,
+                        outputs=[summary_box, result_table, chart_output, download_btn])
 
-app.launch()
+interface.launch(share=True)