test model and upload model pipeline

app.py

@@ -1,7 +1,29 @@
 import gradio as gr
+import joblib
+import numpy as np
+from sklearn.preprocessing import StandardScaler
 
-def greet(name):
-    return "Hello " + name + "!!"
+def make_prediction(MedInc,HouseAge,AveRooms,AveBedrms,Population,AveOccup,Latitude,Longitude):
+    scaler = joblib.load('scaler.pkl')
+    model = joblib.load("filename.pkl")
+    new_data = np.array([[MedInc,HouseAge,AveRooms,AveBedrms,Population,AveOccup,Latitude,Longitude]])
+    scaler_new = scaler.transform(new_data)
+    preds = model.predict(scaler_new)
+    pred = preds[0, 0]
+    return f"{pred:.2f}"
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+#Create the input component for Gradio since we are expecting 4 inputs
+MedInc   = gr.Number(label = "Enter MedInc")
+HouseAge = gr.Number(label = "Enter HouseAge")
+AveRooms = gr.Number(label = "Enter AveRooms")
+AveBedrms = gr.Number(label = "Enter AveBedrms")
+Population = gr.Number(label = "Enter Population")
+AveOccup = gr.Number(label = "Enter AveOccup")
+Latitude = gr.Number(label = "Enter Latitude")
+Longitude  = gr.Number(label = "Enter Longitude")
+# We create the output
+output = gr.Textbox()
+
+
+app = gr.Interface(fn = make_prediction, inputs=[MedInc,HouseAge,AveRooms,AveBedrms,Population,AveOccup,Latitude,Longitude], outputs=output)
+app.launch()