Gradient Boosting

Data

from data_prep_credit import *

Model

from sklearn.ensemble import GradientBoostingClassifier

clf = GradientBoostingClassifier(n_estimators=100, 
                                learning_rate=1.0,
                                max_depth=1, 
                                random_state=0).fit(X_train, y_train)

                                
y_pred = clf.fit(X_train, y_train).predict(X_test)

clf.score(X_test, y_test)

0.9696666666666667

Confusion matrix

from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
import matplotlib.pyplot as plt

cm = confusion_matrix(y_test, y_pred)

disp = ConfusionMatrixDisplay(confusion_matrix=cm,
                              display_labels=clf.classes_)
disp.plot()
plt.show()

Classification report

from sklearn.metrics import classification_report

print(classification_report(y_test, y_pred, target_names=['No', 'Yes']))

              precision    recall  f1-score   support

          No       0.97      1.00      0.98      2909
         Yes       0.00      0.00      0.00        91

    accuracy                           0.97      3000
   macro avg       0.48      0.50      0.49      3000
weighted avg       0.94      0.97      0.95      3000

/Users/jankirenz/opt/anaconda3/lib/python3.7/site-packages/sklearn/metrics/_classification.py:1308: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/Users/jankirenz/opt/anaconda3/lib/python3.7/site-packages/sklearn/metrics/_classification.py:1308: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
/Users/jankirenz/opt/anaconda3/lib/python3.7/site-packages/sklearn/metrics/_classification.py:1308: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))