Duplicate from bright1/Customer-Churn-App

Co-authored-by: Bright Eshun <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Customer Churn App
+emoji: 💻
+colorFrom: indigo
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.29.0
+app_file: app.py
+pinned: false
+duplicated_from: bright1/Customer-Churn-App
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,139 @@
+import gradio as gr
+import pickle 
+# import time
+import pandas as pd
+import numpy as np
+from utils import create_new_columns, create_processed_dataframe
+import os 
+
+
+
+pipeline_pkl = "full_pipeline.pkl"
+log_reg = "logistic_reg_class_model.pkl"
+
+# hist_df = "history.csv"
+
+# def check_csv(csv_file, data):
+#     if os.path.isfile(csv_file):
+#         data.to_csv(csv_file, mode='a', header=False, index=False, encoding='utf-8')
+#     else:
+#         history = data.copy()
+#         history.to_csv(csv_file, index=False)
+
+
+
+
+
+
+
+def tenure_values():
+    cols = ['0-2', '3-5', '6-8', '9-11', '12-14', '15-17', '18-20', '21-23', '24-26', '27-29', '30-32', '33-35', '36-38', '39-41', '42-44', '45-47', '48-50', '51-53', '54-56', '57-59', '60-62', '63-65', '66-68', '69-71', '72-74']
+    return cols
+
+def predict_churn(gender, SeniorCitizen, Partner, Dependents, Tenure, PhoneService, MultipleLines, InternetService, 
+                  OnlineSecurity, OnlineBackup, DeviceProtection,TechSupport,StreamingTV, StreamingMovies, 
+                  Contract, PaperlessBilling, PaymentMethod, MonthlyCharges, TotalCharges):
+    
+    data = [gender, SeniorCitizen, Partner, Dependents, Tenure, PhoneService, MultipleLines, InternetService, 
+                   OnlineSecurity, OnlineBackup, DeviceProtection,TechSupport,StreamingTV, StreamingMovies, 
+                   Contract, PaperlessBilling, PaymentMethod, MonthlyCharges, TotalCharges]
+    
+    x = np.array([data])
+    dataframe = pd.DataFrame(x, columns=train_features)
+    dataframe = dataframe.astype({'MonthlyCharges': 'float', 'TotalCharges': 'float', 'tenure': 'float'})
+    dataframe_ = create_new_columns(dataframe)
+    try:
+        processed_data = pipeline.transform(dataframe_)
+    except Exception as e:
+        raise gr.gradio('Kindly make sure to check/select all')
+    else:
+        # check_csv(hist_df, dataframe)
+        # history = pd.read_csv(hist_df)
+
+        processed_dataframe = create_processed_dataframe(processed_data, dataframe)
+        predictions = model.predict_proba(processed_dataframe)
+    return round(predictions[0][0], 3), round(predictions[0][1], 3)
+
+
+
+theme = gr.themes.Default().set(body_background_fill="#0E1117",
+                                 background_fill_secondary="#FFFFFF",
+                                 background_fill_primary="#262730",
+                                 body_text_color="#FF4B4B",
+                                 checkbox_background_color='#FFFFFF', 
+                                 button_secondary_background_fill="#FF4B4B")
+
+
+def load_pickle(filename):
+    with open(filename, 'rb') as file:
+        data = pickle.load(file)
+        return data
+
+pipeline = load_pickle(pipeline_pkl)
+model = load_pickle(log_reg)
+
+train_features = ['gender', 'SeniorCitizen', 'Partner', 'Dependents','tenure', 'PhoneService', 'MultipleLines', 'InternetService', 
+                   'OnlineSecurity', 'OnlineBackup', 'DeviceProtection','TechSupport','StreamingTV', 'StreamingMovies', 
+                   'Contract', 'PaperlessBilling', 'PaymentMethod', 'MonthlyCharges', 'TotalCharges']
+
+
+# theme = gr.themes.Base()
+with  gr.Blocks(theme=theme) as demo:
+    gr.HTML("""
+    <h1 style="color:white; text-align:center">Customer Churn Classification App</h1>
+    <h2 style="color:white;">Welcome Cherished User 👋 </h2>
+    <h4 style="color:white;">Start predicting customer churn.</h4>
+    
+    """)
+    with gr.Row():
+        gender = gr.Dropdown(label='Gender', choices=['Female', 'Male'])
+        Contract  = gr.Dropdown(label='Contract', choices=['Month-to-month', 'One year', 'Two year'])
+        InternetService = gr.Dropdown(label='Internet Service', choices=['DSL', 'Fiber optic', 'No'])
+
+    with gr.Accordion('Yes or no'):
+
+        with gr.Row():
+            OnlineSecurity = gr.Radio(label="Online Security", choices=["Yes", "No", "No internet service"])
+            OnlineBackup = gr.Radio(label="Online Backup", choices=["Yes", "No", "No internet service"])
+            DeviceProtection = gr.Radio(label="Device Protection", choices=["Yes", "No", "No internet service"])
+            TechSupport = gr.Radio(label="Tech Support", choices=["Yes", "No", "No internet service"])
+            StreamingTV = gr.Radio(label="TV Streaming", choices=["Yes", "No", "No internet service"])
+            StreamingMovies = gr.Radio(label="Movie Streaming", choices=["Yes", "No", "No internet service"]) 
+        with gr.Row():
+            SeniorCitizen = gr.Radio(label="Senior Citizen", choices=["Yes", "No"])
+            Partner = gr.Radio(label="Partner", choices=["Yes", "No"])
+            Dependents = gr.Radio(label="Dependents", choices=["Yes", "No"])
+            PaperlessBilling = gr.Radio(label="Paperless Billing", choices=["Yes", "No"])
+            PhoneService = gr.Radio(label="Phone Service", choices=["Yes", "No"])
+            MultipleLines = gr.Radio(label="Multiple Lines", choices=["No phone service", "Yes", "No"]) 
+    
+    with gr.Row():
+        MonthlyCharges = gr.Number(label="Monthly Charges")
+        TotalCharges = gr.Number(label="Total Charges")
+        Tenure = gr.Number(label='Months of Tenure')
+        PaymentMethod = gr.Dropdown(label="Payment Method", choices=["Electronic check", "Mailed check", "Bank transfer (automatic)", "Credit card (automatic)"])
+
+    submit_button = gr.Button('Prediction')
+    # print(type([[122, 456]]))
+    
+    with gr.Row():
+        with gr.Accordion('Churn Prediction'):
+            output1 = gr.Slider(maximum=1,
+                                minimum=0,
+                                value=0.0,
+                                label='Yes')
+            output2 = gr.Slider(maximum=1,
+                                minimum=0,
+                                value=0.0,
+                                label='No')
+        # with gr.Accordion('Input History'):
+        #     output3 = gr.Dataframe()
+
+    submit_button.click(fn=predict_churn, inputs=[gender, SeniorCitizen, Partner, Dependents, Tenure, PhoneService, MultipleLines,     
+                                                  InternetService, OnlineSecurity, OnlineBackup, DeviceProtection,TechSupport,StreamingTV, StreamingMovies, Contract, PaperlessBilling, PaymentMethod, MonthlyCharges, TotalCharges], outputs=[output1, output2])
+
+
+# demo = gr.Interface(fn=predict_churn, inputs=[gender, SeniorCitizen, Partner, Dependents, Tenure, PhoneService, MultipleLines,
+#                                                    InternetService, OnlineSecurity, OnlineBackup, DeviceProtection,TechSupport,StreamingTV, StreamingMovies, Contract, PaperlessBilling, PaymentMethod, MonthlyCharges, TotalCharges], outputs=['slider', 'slider'], theme=theme)
+
+demo.launch(debug=True)

full_pipeline.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8258008cf92ff5e5446c62b85547661f5139b8034dd3408cb61224b44fdf7c1b
+size 3517

history.csv

@@ -0,0 +1,11 @@
+gender,SeniorCitizen,Partner,Dependents,PhoneService,MultipleLines,InternetService,OnlineSecurity,OnlineBackup,DeviceProtection,TechSupport,StreamingTV,StreamingMovies,Contract,PaperlessBilling,PaymentMethod,MonthlyCharges,TotalCharges,Monthly Variations,tenure_group
+Female,Yes,Yes,Yes,No,Yes,Fiber optic,Yes,Yes,Yes,No internet service,Yes,Yes,Month-to-month,No,Bank transfer (automatic),123.0,1345.0,-131.0,12-14
+Female,Yes,Yes,Yes,No,Yes,Fiber optic,Yes,Yes,Yes,No internet service,Yes,Yes,Month-to-month,No,Bank transfer (automatic),123.0,1345.0,-131.0,12-14
+Female,Yes,Yes,No,No,Yes,Fiber optic,Yes,Yes,Yes,No internet service,Yes,Yes,Month-to-month,No,Bank transfer (automatic),123.0,5677.0,4201.0,12-14
+Male,Yes,Yes,Yes,Yes,No phone service,Fiber optic,No internet service,Yes,Yes,No,Yes,No internet service,Two year,Yes,Bank transfer (automatic),123.0,1200.0,-276.0,12-14
+Male,Yes,No,Yes,No,Yes,Fiber optic,No internet service,Yes,Yes,No,Yes,No internet service,Two year,No,Mailed check,123.0,1200.0,-276.0,12-14
+Female,No,Yes,Yes,Yes,No phone service,Fiber optic,Yes,Yes,Yes,Yes,No internet service,No internet service,One year,Yes,Credit card (automatic),128.0,1234.0,-1710.0,21-23
+Female,No,Yes,Yes,Yes,No phone service,Fiber optic,No internet service,No internet service,No internet service,No internet service,No internet service,No internet service,One year,Yes,Credit card (automatic),128.0,1234.0,-1710.0,21-23
+Female,No,Yes,Yes,Yes,Yes,Fiber optic,No internet service,Yes,Yes,Yes,Yes,Yes,One year,Yes,Credit card (automatic),128.0,1234.0,-1710.0,21-23
+Male,Yes,Yes,Yes,Yes,No phone service,Fiber optic,No,Yes,No internet service,Yes,Yes,Yes,One year,Yes,Mailed check,120.0,12003.0,10923.0,9-11
+Female,Yes,Yes,Yes,Yes,Yes,DSL,Yes,Yes,Yes,Yes,No internet service,No internet service,One year,No,Bank transfer (automatic),167.0,2000.0,497.0,9-11

logistic_reg_class_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:909c3db0e63bc22cacd72f7bd76e53e978f8667b32123fb543ff66831b0e9d1a
+size 1301

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+matplotlib==3.3.4
+numpy==1.20.1
+pandas==1.2.4
+seaborn==0.11.1
+scikit-learn==0.24.1

utils.py

@@ -0,0 +1,35 @@
+import pandas as pd
+import numpy as np
+import pickle
+import os 
+
+
+
+# DIRPATH = os.path.dirname(os.path.realpath(__file__))
+
+pipeline_pkl = "full_pipeline.pkl"
+
+def load_pickle(filename):
+    with open(filename, 'rb') as file:
+        data = pickle.load(file)
+        return data
+
+preprocessor = load_pickle(pipeline_pkl)
+
+
+def create_new_columns(train_data):
+    train_data['Monthly Variations'] = (train_data.loc[:, 'TotalCharges']) -((train_data.loc[:, 'tenure'] * train_data.loc[:, 'MonthlyCharges']))
+    labels =['{0}-{1}'.format(i, i+2) for i in range(0, 73, 3)]
+    train_data['tenure_group'] = pd.cut(train_data['tenure'], bins=(range(0, 78, 3)), right=False, labels=labels)
+    train_data.drop(columns=['tenure'], inplace=True)
+    return train_data
+
+
+
+
+def create_processed_dataframe(processed_data, train_data):
+    train_num_cols=train_data.select_dtypes(exclude=['object', 'category']).columns
+    cat_features = preprocessor.named_transformers_['categorical']['cat_encoder'].get_feature_names()
+    labels = np.concatenate([train_num_cols, cat_features])
+    processed_dataframe = pd.DataFrame(processed_data.toarray(), columns=labels)
+    return processed_dataframe