Create app.py

app.py

@@ -0,0 +1,109 @@
+import gradio as gr
+import numpy as np
+import pickle
+import pandas as pd
+
+
+def load_pickle(filename):
+    with open(filename, 'rb') as file:
+        data = pickle.load(file)
+        return data
+
+pkl_file=load_pickle('modelcomponent1.pkl') 
+numeric_imputer=pkl_file['numerical_imputer']
+categoric_imputer=pkl_file['categorical_imputer']
+scaler_=pkl_file['scaler']
+encoder_=pkl_file['encoder']
+best_model = pkl_file['model']
+top_pack=pkl_file['top_pack_values']
+
+def preprocess_data(Data_Volume, On_Net,Orange, Tigo, Regularity, Freq_Top_Pack,
+                                     Region, Tenure, Top_Pack):
+    
+    df=pd.DataFrame({
+        'Data_Volume':[Data_Volume],
+        'On_Net':[On_Net],
+        'Orange':[Orange],
+        'Tigo' :[Tigo],
+        'Regularity':[Regularity],
+        'Freq_Top_Pack':[Freq_Top_Pack],
+        'Region':[Region],
+        'Tenure' :[Tenure],
+        'Top_Pack':[Top_Pack]
+})
+    
+    # Preprocess the data
+    # Selecting categorical and numerical columns separately
+    cat_columns = df.select_dtypes(include=['object', 'category']).columns.tolist()
+    num_columns = df.select_dtypes(exclude=['object', 'category']).columns.tolist()
+    
+    
+
+    # Apply the imputers on the input data
+    
+    cat_imputer=categoric_imputer.transform(df[cat_columns])
+    num_imputer=numeric_imputer.transform(df[num_columns])
+    
+    
+    #Encode
+    cat_encode = encoder_.transform(cat_imputer)
+    cat_encoded_df = pd.DataFrame(cat_encode.toarray(), columns=encoder_.get_feature_names_out(cat_columns))
+    print(num_imputer)
+    # Scale the numerical columns
+    
+    num_scaler=scaler_.transform( num_imputer)
+    num_scaler_df=pd.DataFrame(num_scaler, columns=num_columns)
+    
+    #combined
+    df_final = pd.concat([num_scaler_df, cat_encoded_df], axis=1)
+    #print(df_final)
+    return df_final
+
+def predict_churn(Data_Volume, On_Net, Orange,Tigo, Regularity, Freq_Top_Pack, Region, Tenure,  Top_Pack):
+  
+    preprocessed_data = preprocess_data(Data_Volume, On_Net,Orange, Tigo, Regularity, Freq_Top_Pack, Region, Tenure,  Top_Pack) 
+    
+    # Make predictions
+    predictions = best_model.predict_proba(preprocessed_data)
+    #print(predictions)
+    return round(predictions[0][0],3), round(predictions[0][1],3)
+
+with gr.Blocks() as demo:
+        gr.Markdown(''' # Welcome cherished user, let's predict customer churn!''')
+        with gr.Row():
+            Region = gr.Dropdown(label='Region', choices=['DAKAR', 'DIOURBEL', 'FATICK',
+                                                  'KAFFRINE', 'KAOLACK', 'KEDOUGOU',
+                                                  'KOLDA', 'LOUGA', 'MATAM',
+                                                  'SAINT-LOUIS', 'SEDHIOU', 'TAMBACOUNDA', 'THIES', 'ZIGUINCHOR'])
+            Tenure = gr.Dropdown(label='Tenure', choices=['K > 24 month', 'I 18-21 month', 'H 15-18 month' , 'G 12-15 month',
+                                                  'J 21-24 month','F 9-12 month','E 6-9 month','D 3-6 month'])
+        Top_Pack =gr.Dropdown(label='Top_Pack', choices=top_pack)
+        with gr.Row():   
+            Data_Volume= gr.Number(label='Data_Volume')
+            On_Net=gr.Number(label='On_Net')
+            
+            Orange=gr.Number(label='Orange')
+            Tigo=gr.Number(label='Tigo')
+            Regularity=gr.Slider(label='Regularity', minimum=int(1), maximum=int(62), value=1, step=1)
+            Freq_Top_Pack=gr.Number(label='Freq_Top_Pack')
+            
+        submit_button=gr.Button('Predict')
+    
+        with gr.Row():
+            with gr.Accordion('Churn Prediction'):
+                output1=gr.Slider(maximum=1,
+                             minimum=0,
+                             value=1,
+                             label='Yes')
+                output2=gr.Slider(maximum=1,
+                             minimum=0,
+                             value=1,
+                             label='No')
+    
+    
+    
+        submit_button.click(fn=predict_churn,  inputs=[ Data_Volume, On_Net, Orange, Tigo, Regularity, Freq_Top_Pack, Region, Tenure,  Top_Pack ], outputs=[output1, output2])
+    
+demo.launch()  
+    
+