Updated the libraries

form_configs/churn_detection.json

@@ -0,0 +1,76 @@
+{
+    "Churn Detection Form": {
+      "Credit Score": {
+        "type": "number",
+        "min_value": 0,
+        "max_value": 1000,
+        "default_value": 0,
+        "step": 10,
+        "field_name": "cs"
+      },
+      "Geography": {
+        "type": "dropdown",
+        "options": ["France", "Germany","Spain"],
+        "default_value": "France",
+        "field_name": "geo"
+      },
+      "Gender": {
+        "type": "dropdown",
+        "options": ["Female", "Male"],
+        "default_value": "Female",
+        "field_name": "gen"
+      },
+      "Age": {
+        "type": "number",
+        "min_value": 0,
+        "max_value": 100,
+        "default_value": 0,
+        "step": 1,
+        "field_name": "age"
+      },
+      "Tenure": {
+        "type": "number",
+        "min_value": 0,
+        "max_value": 30,
+        "default_value": 0,
+        "step": 1,
+        "field_name": "tenure"
+      },
+      "Balance": {
+        "type": "float",
+        "min_value": 0.0,
+        "max_value": 1000000.0,
+        "default_value": 0.0,
+        "step": 100.5,
+        "field_name": "bal"
+      },
+      "Number Of Products": {
+        "type": "number",
+        "min_value": 0,
+        "max_value": 10,
+        "default_value": 0,
+        "step": 1,
+        "field_name": "nop"
+      },
+      "Has Credit Card": {
+        "type": "dropdown",
+        "field_name": "hcc",
+        "options": [0,1],
+        "default_value": 0
+      },
+      "Is Active Member": {
+        "type": "dropdown",
+        "field_name": "iam",
+        "options": [0,1],
+        "default_value": 0
+      },
+      "Estimated Salary": {
+        "type": "float",
+        "min_value": 0.0,
+        "max_value": 1000000.0,
+        "default_value": 0.0,
+        "step": 100.5,
+        "field_name": "es"
+      }
+    }
+}

models/Customer_Churn_Prediction/Model.py

@@ -0,0 +1,17 @@
+import joblib
+import numpy as np
+model = joblib.load('models/Customer_Churn_Prediction/saved_models/Gradient_Boosting_Classifier.joblib')
+scaler = joblib.load('models/Customer_Churn_Prediction/saved_models/scaler.joblib')
+def customer_churn_prediction(cs,geo,gen,age,tenure,bal,nop,hcc,iam,es):
+    features = {'CreditScore':cs,'Geography':geo,'Gender':gen,'Age':age,'Tenure':tenure,'Balance':bal,'NumOfProducts':nop,'HasCrCard':hcc,'IsActiveMember':iam,'EstimatedSalary':es}
+    geography_map = {'France': 0, 'Spain': 1, 'Germany': 2}
+    gender_map = {'Female': 0, 'Male': 1}
+    features['Geography'] = geography_map[features['Geography']]
+    features['Gender'] = gender_map[features['Gender']]
+    input_array = np.array(list(features.values())).reshape(1, -1)
+    scaled_input = scaler.transform(input_array)
+    preprocessed_input = scaled_input
+    prediction = model.predict(preprocessed_input)
+    probability = model.predict_proba(preprocessed_input)[0][1]
+    print(prediction)
+    return prediction[0], probability

models/Customer_Churn_Prediction/Predict.py

@@ -0,0 +1,9 @@
+from models.Customer_Churn_Prediction.Model import customer_churn_prediction
+def get_prediction(cs,geo,gen,age,tenure,bal,nop,hcc,iam,es):
+    prediction,probability=customer_churn_prediction(cs,geo,gen,age,tenure,bal,nop,hcc,iam,es)
+    output=""
+    if prediction == 1:
+        output=f"The customer is likely to churn with a probability of {probability:.2f}"
+    else:
+        output=f"The customer is likely to stay with a probability of {1-probability:.2f}"
+    return output