Update app.py

app.py

@@ -1,12 +1,20 @@
 import pandas as pd
 import numpy as np
-import json
 import gradio as gr
 import matplotlib.pyplot as plt
 import seaborn as sns
 from datetime import datetime
 from sklearn.metrics import confusion_matrix, precision_score, recall_score
+from PIL import Image
+import requests
+from io import BytesIO
 
+# Load SabPaisa logo
+logo_url = "https://www.google.com/url?sa=i&url=https%3A%2F%2Fwww.facebook.com%2Fsabpaisa%2F&psig=AOvVaw1tJqk9DKF8WgvbGj1H004X&ust=1742646042537000&source=images&cd=vfe&opi=89978449&ved=0CBEQjRxqFwoTCPjmiLiUm4wDFQAAAAAdAAAAABAE"
+response = requests.get(logo_url)
+logo = Image.open(BytesIO(response.content))
+
+# Sample data preparation
 data = {
     'transaction_amount': [2500, 799, 9338, 11749, 8999, 1500, 3000, 4000, 300, 5000, 24990],
     'transaction_date': ['01-11-2024 16:08', '01-11-2024 16:15', '02-11-2024 14:43', '03-11-2024 11:14', 
@@ -25,50 +33,13 @@ data = {
 }
 
 df = pd.DataFrame(data)
+
 df['transaction_date'] = pd.to_datetime(df['transaction_date'], format='%d-%m-%Y %H:%M')
 
 np.random.seed(42)
 df['is_fraud_predicted'] = np.random.choice([0, 1], size=len(df), p=[0.3, 0.7])
 df['is_fraud_reported'] = np.random.choice([0, 1], size=len(df), p=[0.4, 0.6])
 
-df_fraud = pd.DataFrame(data)
-df_fraud['fraud_reason'] = 'Suspicious Activity'
-df_fraud['fraud_score'] = np.random.uniform(0.6, 0.95, size=len(df_fraud))
-
-fraud_dict = {
-    row['transaction_id_anonymous']: {
-        'is_fraud': True,
-        'fraud_reason': row['fraud_reason'],
-        'fraud_score': float(row['fraud_score'])
-    }
-    for _, row in df_fraud.iterrows()
-}
-
-def generate_non_fraud_transactions(n, start_id=1000):
-    non_fraud_dict = {}
-    
-    for i in range(n):
-        tx_id = f'ANON_{start_id + i}'
-        if tx_id in fraud_dict:
-            continue
-            
-        non_fraud_dict[tx_id] = {
-            'is_fraud': False,
-            'fraud_reason': 'Not Fraud',
-            'fraud_score': float(np.random.uniform(0.01, 0.4))
-        }
-    
-    return non_fraud_dict
-
-total_records = 172927
-fraud_records = len(fraud_dict)
-non_fraud_needed = total_records - fraud_records
-
-sample_non_fraud = generate_non_fraud_transactions(5, start_id=200000)
-
-with open('transactions_train.csv', 'w') as f:
-    json.dump(fraud_dict, f, indent=2)
-
 def filter_data(start_date, end_date, payer_id, payee_id, transaction_id):
     filtered_df = df.copy()
     
@@ -194,6 +165,8 @@ def update_interface(start_date, end_date, payer_id, payee_id, transaction_id, d
 with gr.Blocks() as demo:
     gr.Markdown("# Fraud Transaction Analysis Dashboard")
     
+    gr.Image(logo, show_label=False, width=200)
+    
     with gr.Row():
         with gr.Column():
             start_date = gr.Textbox(label="Start Date (YYYY-MM-DD)", value="2024-11-01")