Update slapp.py

slapp.py

@@ -1,60 +1,40 @@
-import streamlit as st
-import requests
+import threading
+import uvicorn
+import pandas as pd
+import pickle
+from fastapi import FastAPI
 
-# Streamlit app interface
-st.title("Fraud Detection API")
-st.markdown("Welcome to the Fraud Detection API! Please enter the transaction details below:")
+# Initialize FastAPI app
+app = FastAPI()
 
-# Tabs for input sections
-tab1, tab2, tab3 = st.tabs(["Basic Info", "Features (V1 - V14)", "Features (V15 - V28)"])
+# Load the saved model
+def load_model():
+    try:
+        with open('model.pkl', 'rb') as file:
+            model = pickle.load(file)
+        return model
+    except Exception as e:
+        raise RuntimeError(f"Error loading model: {e}")
 
-# Horizontal layout for Basic Info
-with tab1:
-    st.header("Basic Information")
-    col1, col2 = st.columns(2)
-    with col1:
-        time = st.number_input("Time", min_value=0.0, step=0.1)
-    with col2:
-        amount = st.number_input("Amount", min_value=0.0, step=0.1)
+model = load_model()
 
-# Horizontal layout for Features V1 - V14
-with tab2:
-    st.header("Features (V1 - V14)")
-    cols = st.columns(7)
-    v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, v13, v14 = [
-        st.number_input(f"V{i+1}", step=0.01) for i in range(14)
-    ]
+# Define the FastAPI endpoint
+@app.post("/predict")
+async def predict_transaction(data: dict):
+    try:
+        # Convert the input data to a DataFrame
+        transaction_data = pd.DataFrame([data])
+        prediction = model.predict(transaction_data)
 
-# Horizontal layout for Features V15 - V28
-with tab3:
-    st.header("Features (V15 - V28)")
-    cols = st.columns(7)
-    v15, v16, v17, v18, v19, v20, v21, v22, v23, v24, v25, v26, v27, v28 = [
-        st.number_input(f"V{i+15}", step=0.01) for i in range(14)
-    ]
+        result = "Fraudulent transaction" if prediction[0] == 1 else "Acceptable transaction"
+        return {"prediction": result}
+    except Exception as e:
+        return {"error": str(e)}
 
-# Button to make predictions
-if st.button("Predict"):
-    # Create a dictionary from the input data
-    transaction_data = {
-        'Time': time,
-        'V1': v1, 'V2': v2, 'V3': v3, 'V4': v4, 'V5': v5, 'V6': v6,
-        'V7': v7, 'V8': v8, 'V9': v9, 'V10': v10, 'V11': v11, 'V12': v12,
-        'V13': v13, 'V14': v14, 'V15': v15, 'V16': v16, 'V17': v17, 'V18': v18,
-        'V19': v19, 'V20': v20, 'V21': v21, 'V22': v22, 'V23': v23, 'V24': v24,
-        'V25': v25, 'V26': v26, 'V27': v27, 'V28': v28, 'Amount': amount
-    }
+# Function to run the FastAPI server
+def run_fastapi():
+    uvicorn.run(app, host="0.0.0.0", port=8000)
 
-    # Send a POST request to the FastAPI server
-    try:
-        response = requests.post("http://localhost:8000/predict", json=transaction_data)
-        if response.status_code == 200:
-            result = response.json().get("prediction")
-            if result == "Acceptable transaction":
-                st.success("✅ " + result)
-            else:
-                st.error("🚨 " + result)
-        else:
-            st.error("Error: " + response.text)
-    except Exception as e:
-        st.error(f"Error connecting to API: {e}")
+# Start the FastAPI server in a separate thread
+thread = threading.Thread(target=run_fastapi, daemon=True)
+thread.start()