update

app.py

@@ -6,12 +6,27 @@ from huggingface_hub import hf_hub_download
 import joblib
 import json
 
-REPO_ID = "rajistics/churn-model1"
-FILENAME = "churn.pkl"
-JSON_FILE = "config.json"
+REPO_ID = "AlbieCofie/predict-customer-churn"
+FILENAME = "sklearn_model.joblib"
+
+num_imputer = joblib.load(
+    hf_hub_download(repo_id=REPO_ID, filename="numerical_imputer.joblib")
+)
+
+cat_imputer = joblib.load(
+    hf_hub_download(repo_id=REPO_ID, filename="categorical_imputer.joblib")
+)
+
+encoder = joblib.load(
+    hf_hub_download(repo_id=REPO_ID, filename="encoder.joblib")
+)
+
+scaler = joblib.load(
+    hf_hub_download(repo_id=REPO_ID, filename="scaler.joblib")
+)
 
 model = joblib.load(
-    hf_hub_download(repo_id=REPO_ID, filename=FILENAME)
+    hf_hub_download(repo_id=REPO_ID, filename="Final_model.joblib")
 )
 
 if 'clicked' not in st.session_state:
@@ -22,83 +37,57 @@ def click_button():
 
 
 st.title("CUSTOMER CHURN PREDICTION APP")
+input_data = {}
 
 with st.form(key="customer-information"):
     st.markdown("This app predicts whether a customer will leave your company or not. Enter the details of the customer below to see the result")
-    gender = st.radio('Select your gender', ('male', 'female'))
-    SeniorCitizen = st.radio("Are you a Seniorcitizen; No=0 and Yes=1", ('0', '1'))
-    Partner = st.radio('Do you have Partner', ('Yes', 'No'))
-    Dependents = st.selectbox('Do you have any Dependents?', ('No', 'Yes'))
-    tenure = st.number_input('Lenght of tenure (no. of months with Telco)', min_value=0, max_value=90, value=1, step=1)
-    PhoneService = st.radio('Do you have PhoneService? ', ('No', 'Yes'))
-    MultipleLines = st.radio('Do you have MultipleLines', ('No', 'Yes'))
-    InternetService = st.radio('Do you have InternetService', ('DSL', 'Fiber optic', 'No'))
-    OnlineSecurity = st.radio('Do you have OnlineSecurity?', ('No', 'Yes'))
-    OnlineBackup = st.radio('Do you have OnlineBackup?', ('No', 'Yes'))
-    DeviceProtection = st.radio('Do you have DeviceProtection?', ('No', 'Yes'))
-    TechSupport = st.radio('Do you have TechSupport?', ('No', 'Yes'))
-    StreamingTV = st.radio('Do you have StreamingTV?', ('No', 'Yes'))
-    StreamingMovies = st.radio('Do you have StreamingMovies?', ('No', 'Yes'))
-    Contract = st.selectbox('which Contract do you use?', ('Month-to-month', 'One year', 'Two year'))
-    PaperlessBilling = st.radio('Do you prefer PaperlessBilling?', ('Yes', 'No'))
-    PaymentMethod = st.selectbox('Which PaymentMethod do you prefer?', ('Electronic check', 'Mailed check', 'Bank transfer (automatic)',
+    input_data["gender"] = st.radio('Select your gender', ('male', 'female'))
+    input_data["SeniorCitizen"] = st.radio("Are you a Seniorcitizen; No=0 and Yes=1", ('0', '1'))
+    input_data["Partner"] = st.radio('Do you have Partner', ('Yes', 'No'))
+    input_data["Dependents"] = st.selectbox('Do you have any Dependents?', ('No', 'Yes'))
+    input_data["tenure"] = st.number_input('Lenght of tenure (no. of months with Telco)', min_value=0, max_value=90, value=1, step=1)
+    input_data["PhoneService"] = st.radio('Do you have PhoneService? ', ('No', 'Yes'))
+    input_data["MultipleLines"] = st.radio('Do you have MultipleLines', ('No', 'Yes'))
+    input_data["InternetService"] = st.radio('Do you have InternetService', ('DSL', 'Fiber optic', 'No'))
+    input_data["OnlineSecurity"] = st.radio('Do you have OnlineSecurity?', ('No', 'Yes'))
+    input_data["OnlineBackup"] = st.radio('Do you have OnlineBackup?', ('No', 'Yes'))
+    input_data["DeviceProtection"] = st.radio('Do you have DeviceProtection?', ('No', 'Yes'))
+    input_data["TechSupport"] = st.radio('Do you have TechSupport?', ('No', 'Yes'))
+    input_data["StreamingTV"] = st.radio('Do you have StreamingTV?', ('No', 'Yes'))
+    input_data["StreamingMovies"] = st.radio('Do you have StreamingMovies?', ('No', 'Yes'))
+    input_data["Contract"] = st.selectbox('which Contract do you use?', ('Month-to-month', 'One year', 'Two year'))
+    input_data["PaperlessBilling"] = st.radio('Do you prefer PaperlessBilling?', ('Yes', 'No'))
+    input_data["PaymentMethod"] = st.selectbox('Which PaymentMethod do you prefer?', ('Electronic check', 'Mailed check', 'Bank transfer (automatic)',
                                         'Credit card (automatic)'))
-    MonthlyCharges = st.number_input("Enter monthly charges (the range should between 0-120)")
-    TotalCharges = st.number_input("Enter total charges (the range should between 0-10.000)")           
+    input_data["MonthlyCharges"] = st.number_input("Enter monthly charges (the range should between 0-120)")
+    input_data["TotalCharges"] = st.number_input("Enter total charges (the range should between 0-10.000)")           
     st.form_submit_button('Predict', on_click=click_button)
 
     if st.session_state.clicked:
-        with open(JSON_FILE) as f:
-            config = json.load(f)
-    # The message and nested widget will remain on the page
-        list_input =[gender,SeniorCitizen,Partner,Dependents, tenure, PhoneService,MultipleLines,
-                       InternetService,OnlineSecurity,OnlineBackup,DeviceProtection,TechSupport,StreamingTV,StreamingMovies,
-                       Contract,PaperlessBilling,PaymentMethod,MonthlyCharges,TotalCharges]
-        df = pd.DataFrame({
-            'gender': [gender],
-            'SeniorCitizen': [SeniorCitizen],
-            'Partner': [Partner],
-            'Dependents': [Dependents],
-            'tenure': [tenure],
-            'PhoneService': [PhoneService],
-            'MultipleLines': [MultipleLines],
-            'InternetService': [InternetService],
-            'OnlineSecurity': [OnlineSecurity],
-            'OnlineBackup': [OnlineBackup],
-            'DeviceProtection': [DeviceProtection],
-            'TechSupport': [TechSupport],
-            'StreamingTV': [StreamingTV],
-            'StreamingMovies': [StreamingMovies],
-            'Contract': [Contract],
-            'PaperlessBilling': [PaperlessBilling],
-            'PaymentMethod': [PaymentMethod],
-            'MonthlyCharges': [MonthlyCharges],
-            'TotalCharges': [TotalCharges]
-            })
-        st.dataframe(
-            df,
-            column_config={
-                'gender': "gender",
-                'SeniorCitizen': "SeniorCitizen",
-                'Partner': "Partner",
-                'Dependents': "Dependents",
-                'tenure': "tenure",
-                'PhoneService': "PhoneService",
-                'MultipleLines': "MultipleLines",
-                'InternetService': "InternetService",
-                'OnlineSecurity': "OnlineSecurity",
-                'OnlineBackup': "OnlineBackup",
-                'DeviceProtection': "DeviceProtection",
-                'TechSupport': "TechSupport",
-                'StreamingTV': "StreamingTV",
-                'StreamingMovies': "StreamingMovies",
-                'Contract': "Contract",
-                'PaperlessBilling': "PaperlessBilling",
-                'PaymentMethod': "PaymentMethod",
-                'MonthlyCharges': "MonthlyCharges",
-                'TotalCharges': "TotalCharges"
-            },
-            hide_index=True,
-        )
-
-        model.predict(df(config["sklearn"][list_input]))
+        input_df = pd.DataFrame([input_data])
+        
+        # Selecting categorical and numerical columns separately
+        cat_columns = [col for col in input_df.columns if input_df[col].dtype == 'object']
+        num_columns = [col for col in input_df.columns if input_df[col].dtype != 'object']
+        
+        # Apply the imputers
+        input_df_imputed_cat = cat_imputer.transform(input_df[cat_columns])
+        input_df_imputed_num = num_imputer.transform(input_df[num_columns])
+        
+        # Encode the categorical columns
+        input_encoded_df = pd.DataFrame(encoder.transform(input_df_imputed_cat).toarray(),
+                                   columns=encoder.get_feature_names(cat_columns))
+        
+        # Scale the numerical columns
+        input_df_scaled = scaler.transform(input_df_imputed_num)
+        input_scaled_df = pd.DataFrame(input_df_scaled , columns = num_columns)
+        
+        #joining the cat encoded and num scaled
+        final_df = pd.concat([input_encoded_df, input_scaled_df], axis=1)
+        
+        # Make a prediction
+        prediction = model.predict(final_df)[0]
+        
+        # Display the prediction
+        st.write(f"The predicted sales are: {prediction}.")
+        st.table(input_df)