machphy
diff --git a/‎Random_Forest_project/src/__pycache__/datapreproc.cpython-312.pyc
Copy file name to clipboard
1.46 KB b/‎Random_Forest_project/src/__pycache__/datapreproc.cpython-312.pyc
Copy file name to clipboard
1.46 KB
diff --git a/‎Random_Forest_project/src/__pycache__/model_training.cpython-312.pyc
Copy file name to clipboard
192 Bytes b/‎Random_Forest_project/src/__pycache__/model_training.cpython-312.pyc
Copy file name to clipboard
192 Bytes
diff --git a/‎Random_Forest_project/src/datapreproc.py
Copy file name to clipboard
+27Lines changed: 27 additions & 0 deletions b/‎Random_Forest_project/src/datapreproc.py
Copy file name to clipboard
+27Lines changed: 27 additions & 0 deletions
diff --git a/‎Random_Forest_project/src/kuchbhi.py
Copy file name to clipboard
+13Lines changed: 13 additions & 0 deletions b/‎Random_Forest_project/src/kuchbhi.py
Copy file name to clipboard
+13Lines changed: 13 additions & 0 deletions
diff --git a/‎Random_Forest_project/src/model_training.py
Copy file name to clipboardExpand all lines: Random_Forest_project/src/model_training.py b/‎Random_Forest_project/src/model_training.py
Copy file name to clipboardExpand all lines: Random_Forest_project/src/model_training.py
diff --git a/‎Random_Forest_project/src/modelevelution.py
Copy file name to clipboardExpand all lines: Random_Forest_project/src/modelevelution.py b/‎Random_Forest_project/src/modelevelution.py
Copy file name to clipboardExpand all lines: Random_Forest_project/src/modelevelution.py
@@ -0,0 +1,27 @@
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder, StandardScaler
+
+def preprocess_data(data):
+    
+    data.fillna(method='ffill', inplace=True)
+
+
+    data['Age_Tenure_Product'] = data['Age'] * data['Tenure'] * data['NumOfProducts']
+    data['Balance'] = np.log1p(data['Balance']) 
+
+    le = LabelEncoder()
+    data['Geography'] = le.fit_transform(data['Geography'])
+    data['Gender'] = le.fit_transform(data['Gender'])
+
+    
+    scaler = StandardScaler()
+    data[['CreditScore', 'Age', 'Tenure', 'Balance', 'NumOfProducts', 'EstimatedSalary']] = scaler.fit_transform(data[['CreditScore', 'Age', 'Tenure', 'Balance', 'NumOfProducts', 'EstimatedSalary']])
+
+    
+    X = data.drop('Exited', axis=1)
+    y = data['Exited']
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+    return X_train, X_test, y_train, y_test
@@ -0,0 +1,13 @@
+import pandas as pd
+from datapreproc import preprocess_data
+from model_training import train_model
+from modelevelution import evaluate_model
+
+
+data = pd.read_csv('Churn_Modelling.csv')
+
+X_train, X_test, y_train, y_test = preprocess_data(data)
+
+model = train_model(X_train, y_train)
+
+evaluate_model(model, X_test, y_test)