Create app.py

app.py

@@ -0,0 +1,28 @@
+import gradio as gr
+import pickle
+import numpy as np
+
+def make_prediction(placement, LargestTrait, MaxTraitCount, Itemcount, Fivecost, Fourcost, Threecost, Twocost, Onecost):
+    with open("modelforweb.pkl", "rb") as f:
+        clf  = pickle.load(f)
+        preds = clf.predict([[placement, LargestTrait, MaxTraitCount, Itemcount, Fivecost, Fourcost, Threecost, Twocost, Onecost]])
+        pred = np.round(preds)
+    return pred
+
+#Create the input component for Gradio since we are expecting 4 inputs
+
+placement_input = gr.Number(label = "Enter your placement")
+LargestTrait_input = gr.Number(label= "Enter your largest active trait number")
+MaxTraitCount_input = gr.Number(label = "Enter your all active trait sum")
+Itemcount_input = gr.Number(label = "Enter your items number")
+Fivecost_input = gr.Number(label = "Enter your five cost champs number")
+Fourcost_input = gr.Number(label= "Enter your four cost champs number")
+Threecost_input = gr.Number(label = "Enter your three cost champs number")
+Twocost_input = gr.Number(label = "Enter your two cost champs number")
+Onecost_input = gr.Number(label = "Enter your one cost champs number")
+# We create the output
+output = gr.Number(label = "Predicted level")
+
+
+app = gr.Interface(fn = make_prediction, inputs=[placement_input, LargestTrait_input, MaxTraitCount_input, Itemcount_input, Fivecost_input, Fourcost_input, Threecost_input, Twocost_input, Onecost_input], outputs=output)
+app.launch()