Upload app.py

app.py

@@ -2,29 +2,39 @@ import pandas as pd
 import numpy as np
 import joblib
 import gradio as gr
+
+
 # Load the preprocessing steps and the model
-label_encoders = joblib.load('label_encoders.pkl')
-one_hot_encoder = joblib.load('one_hot_encoder.pkl')
-min_max_scaler = joblib.load('min_max_scaler.pkl')
-model = joblib.load('logistic_regression_model.pkl')
-le_target = joblib.load('label_encoder_target.pkl')
+label_encoders = joblib.load("label_encoders.pkl")
+one_hot_encoder = joblib.load("one_hot_encoder.pkl")
+min_max_scaler = joblib.load("min_max_scaler.pkl")
+model = joblib.load("logistic_regression_model.pkl")
+le_target = joblib.load("label_encoder_target.pkl")
 
-def preprocess_data(data):
-    """
-    Preprocess the input data for prediction.
 
-    Parameters:
-    data (dict): Dictionary containing input data.
+def preprocess_data(data):
 
-    Returns:
-    np.array: Processed data ready for prediction.
-    """
     df = pd.DataFrame([data])
 
-    label_encode_cols = ["Partner", "Dependents", "PhoneService", "PaperlessBilling", "gender"]
-    one_hot_encode_cols = ["MultipleLines", "InternetService", "OnlineSecurity", "OnlineBackup",
-                           "DeviceProtection", "TechSupport", "StreamingTV", "StreamingMovies",
-                           "Contract", "PaymentMethod"]
+    label_encode_cols = [
+        "Partner",
+        "Dependents",
+        "PhoneService",
+        "PaperlessBilling",
+        "gender",
+    ]
+    one_hot_encode_cols = [
+        "MultipleLines",
+        "InternetService",
+        "OnlineSecurity",
+        "OnlineBackup",
+        "DeviceProtection",
+        "TechSupport",
+        "StreamingTV",
+        "StreamingMovies",
+        "Contract",
+        "PaymentMethod",
+    ]
     min_max_scale_cols = ["tenure", "MonthlyCharges", "TotalCharges"]
 
     # Strip leading and trailing spaces from string inputs
@@ -32,8 +42,11 @@ def preprocess_data(data):
         df[col] = df[col].str.strip()
 
     # Convert non-numeric values to NaN and fill them with the mean of the column
-    df[min_max_scale_cols] = df[min_max_scale_cols].replace(' ', np.nan).astype(float)
-    df[min_max_scale_cols] = df[min_max_scale_cols].fillna(df[min_max_scale_cols].mean())
+    df[min_max_scale_cols] = df[min_max_scale_cols].replace(" ", np.nan).astype(float)
+
+    df[min_max_scale_cols] = df[min_max_scale_cols].fillna(
+        df[min_max_scale_cols].mean()
+    )
 
     # Label encode specified columns
     for col in label_encode_cols:
@@ -47,23 +60,35 @@ def preprocess_data(data):
     scaled_numerical = min_max_scaler.transform(df[min_max_scale_cols])
 
     # Combine processed columns into one DataFrame
-    X_processed = np.hstack((df[label_encode_cols].values, scaled_numerical, one_hot_encoded))
+    X_processed = np.hstack(
+        (df[label_encode_cols].values, scaled_numerical, one_hot_encoded)
+    )
 
     return X_processed
 
 
-def predict(gender, senior_citizen, partner, dependents, tenure, phone_service, multiple_lines, internet_service,
-            online_security, online_backup, device_protection, tech_support, streaming_tv, streaming_movies,
-            contract, paperless_billing, payment_method, monthly_charges, total_charges):
-    """
-    Predict the churn status of a customer.
-
-    Parameters:
-    Various input features as separate parameters.
+def predict(
+    gender,
+    senior_citizen,
+    partner,
+    dependents,
+    tenure,
+    phone_service,
+    multiple_lines,
+    internet_service,
+    online_security,
+    online_backup,
+    device_protection,
+    tech_support,
+    streaming_tv,
+    streaming_movies,
+    contract,
+    paperless_billing,
+    payment_method,
+    monthly_charges,
+    total_charges,
+):
 
-    Returns:
-    str: Prediction result ("Churn" or "No Churn").
-    """
     data = {
         "gender": gender,
         "SeniorCitizen": senior_citizen,
@@ -83,18 +108,19 @@ def predict(gender, senior_citizen, partner, dependents, tenure, phone_service,
         "PaperlessBilling": paperless_billing,
         "PaymentMethod": payment_method,
         "MonthlyCharges": monthly_charges,
-        "TotalCharges": total_charges
+        "TotalCharges": total_charges,
     }
 
     try:
         X_new = preprocess_data(data)
         prediction = model.predict(X_new)
         prediction = le_target.inverse_transform(prediction)
-        return "Churn" if prediction[0] == 'Yes' else "No Churn"
+        return "Churn" if prediction[0] == "Yes" else "No Churn"
     except Exception as e:
         print("Error during prediction:", e)
         return str(e)
 
+
 # Define the Gradio interface
 inputs = [
     gr.Radio(label="Gender", choices=["Female", "Male"]),
@@ -113,12 +139,22 @@ inputs = [
     gr.Radio(label="Streaming Movies", choices=["Yes", "No", "No internet service"]),
     gr.Radio(label="Contract", choices=["Month-to-month", "One year", "Two year"]),
     gr.Radio(label="Paperless Billing", choices=["Yes", "No"]),
-    gr.Radio(label="Payment Method", choices=["Electronic check", "Mailed check", "Bank transfer (automatic)", "Credit card (automatic)"]),
+    gr.Radio(
+        label="Payment Method",
+        choices=[
+            "Electronic check",
+            "Mailed check",
+            "Bank transfer (automatic)",
+            "Credit card (automatic)",
+        ],
+    ),
     gr.Number(label="Monthly Charges (float)"),
-    gr.Number(label="Total Charges (float)")
+    gr.Number(label="Total Charges (float)"),
 ]
 
 outputs = gr.Textbox(label="Prediction")
 
 # Create the Gradio interface
-gr.Interface(fn=predict, inputs=inputs, outputs=outputs, title="Churn Prediction Model").launch()
+gr.Interface(
+    fn=predict, inputs=inputs, outputs=outputs, title="Churn Prediction Model"
+).launch(share=True)