Updated support scripts for LightGBM 4 - #8 [skip ci]

Co-authored-by: Nuno Silva <[email protected]>

Author: ankane

test/support/classifier.py

@@ -33,7 +33,7 @@
 
 print()
 print('test_early_stopping')
-model.fit(X_train, ym_train, eval_set=[(X_test, ym_test)], early_stopping_rounds=5, verbose=True)
+model.fit(X_train, ym_train, eval_set=[(X_test, ym_test)], callbacks=[lgb.early_stopping(stopping_rounds=5), lgb.log_evaluation()])
 
 print()
 print('test_missing_numeric')

test/support/cv.py

@@ -16,42 +16,42 @@
 regression_params = {'objective': 'regression', 'verbosity': -1}
 regression_train = lgb.Dataset(X_train, label=y_train)
 eval_hist = lgb.cv(regression_params, regression_train, shuffle=False, stratified=False)
-print(eval_hist['l2-mean'][0])
-print(eval_hist['l2-mean'][-1])
-print(eval_hist['l2-stdv'][0])
-print(eval_hist['l2-stdv'][-1])
+print(eval_hist['valid l2-mean'][0])
+print(eval_hist['valid l2-mean'][-1])
+print(eval_hist['valid l2-stdv'][0])
+print(eval_hist['valid l2-stdv'][-1])
 
 print()
 print('test_binary')
 
 binary_params = {'objective': 'binary', 'verbosity': -1}
 binary_train = lgb.Dataset(X_train, label=y_train.replace(2, 1))
 eval_hist = lgb.cv(binary_params, binary_train, shuffle=False, stratified=False)
-print(eval_hist['binary_logloss-mean'][0])
-print(eval_hist['binary_logloss-mean'][-1])
-print(eval_hist['binary_logloss-stdv'][0])
-print(eval_hist['binary_logloss-stdv'][-1])
+print(eval_hist['valid binary_logloss-mean'][0])
+print(eval_hist['valid binary_logloss-mean'][-1])
+print(eval_hist['valid binary_logloss-stdv'][0])
+print(eval_hist['valid binary_logloss-stdv'][-1])
 
 print()
 print('test_multiclass')
 
 multiclass_params = {'objective': 'multiclass', 'num_class': 3, 'verbosity': -1}
 multiclass_train = lgb.Dataset(X_train, label=y_train)
 eval_hist = lgb.cv(multiclass_params, multiclass_train, shuffle=False, stratified=False)
-print(eval_hist['multi_logloss-mean'][0])
-print(eval_hist['multi_logloss-mean'][-1])
-print(eval_hist['multi_logloss-stdv'][0])
-print(eval_hist['multi_logloss-stdv'][-1])
+print(eval_hist['valid multi_logloss-mean'][0])
+print(eval_hist['valid multi_logloss-mean'][-1])
+print(eval_hist['valid multi_logloss-stdv'][0])
+print(eval_hist['valid multi_logloss-stdv'][-1])
 
 print('')
 print('test_early_stopping_early')
 
-eval_hist = lgb.cv(regression_params, regression_train, shuffle=False, stratified=False, verbose_eval=True, early_stopping_rounds=5)
-print(len(eval_hist['l2-mean']))
+eval_hist = lgb.cv(regression_params, regression_train, shuffle=False, stratified=False, callbacks=[lgb.log_evaluation(), lgb.early_stopping(stopping_rounds=5)])
+print(len(eval_hist['valid l2-mean']))
 
 print('')
 print('test_early_stopping_not_early')
 
-eval_hist = lgb.cv(regression_params, regression_train, shuffle=False, stratified=False, verbose_eval=True, early_stopping_rounds=500)
-print(len(eval_hist['l2-mean']))
+eval_hist = lgb.cv(regression_params, regression_train, shuffle=False, stratified=False, callbacks=[lgb.log_evaluation(), lgb.early_stopping(stopping_rounds=500)])
+print(len(eval_hist['valid l2-mean']))
 

test/support/regressor.py

@@ -19,4 +19,4 @@
 print('feature_importances', model.feature_importances_.tolist())
 
 print('early_stopping')
-model.fit(X_train, y_train, eval_set=[(X_test, y_test)], early_stopping_rounds=5, verbose=True)
+model.fit(X_train, y_train, eval_set=[(X_test, y_test)], callbacks=[lgb.early_stopping(stopping_rounds=5), lgb.log_evaluation()])

test/support/train.py

@@ -17,7 +17,7 @@
 regression_params = {'objective': 'regression', 'verbosity': -1}
 regression_train = lgb.Dataset(X_train, label=y_train)
 regression_test = lgb.Dataset(X_test, label=y_test)
-bst = lgb.train(regression_params, regression_train, valid_sets=[regression_train, regression_test], verbose_eval=False)
+bst = lgb.train(regression_params, regression_train, valid_sets=[regression_train, regression_test])
 y_pred = bst.predict(X_test)
 print(np.sqrt(np.mean((y_pred - y_test)**2)))
 
@@ -27,7 +27,7 @@
 binary_params = {'objective': 'binary', 'verbosity': -1}
 binary_train = lgb.Dataset(X_train, label=y_train.replace(2, 1))
 binary_test = lgb.Dataset(X_test, label=y_test.replace(2, 1))
-bst = lgb.train(binary_params, binary_train, valid_sets=[binary_train, binary_test], verbose_eval=False)
+bst = lgb.train(binary_params, binary_train, valid_sets=[binary_train, binary_test])
 y_pred = bst.predict(X_test)
 print(y_pred[0])
 
@@ -37,28 +37,28 @@
 multiclass_params = {'objective': 'multiclass', 'num_class': 3, 'verbosity': -1}
 multiclass_train = lgb.Dataset(X_train, label=y_train)
 multiclass_test = lgb.Dataset(X_test, label=y_test)
-bst = lgb.train(multiclass_params, multiclass_train, valid_sets=[multiclass_train, multiclass_test], verbose_eval=False)
+bst = lgb.train(multiclass_params, multiclass_train, valid_sets=[multiclass_train, multiclass_test])
 y_pred = bst.predict(X_test)
 print(y_pred[0].tolist())
 
 print('')
 print('test_early_stopping_early')
 
-bst = lgb.train(regression_params, regression_train, valid_sets=[regression_train, regression_test], early_stopping_rounds=5)
+bst = lgb.train(regression_params, regression_train, valid_sets=[regression_train, regression_test], callbacks=[lgb.early_stopping(stopping_rounds=5), lgb.log_evaluation()])
 print(bst.best_iteration)
 
 print('')
 print('test_early_stopping_not_early')
 
-bst = lgb.train(regression_params, regression_train, valid_sets=[regression_train, regression_test], early_stopping_rounds=500)
+bst = lgb.train(regression_params, regression_train, valid_sets=[regression_train, regression_test], callbacks=[lgb.early_stopping(stopping_rounds=500), lgb.log_evaluation()])
 # appears to be using training set for best iteration instead of validation set
 print(bst.best_iteration)
 
 print('')
 print('test_early_stopping_early_higher_better')
 
 params = {'objective': 'binary', 'metric': 'auc', 'verbosity': -1}
-bst = lgb.train(params, binary_train, valid_sets=[binary_train, binary_test], early_stopping_rounds=5, verbose_eval=False)
+bst = lgb.train(params, binary_train, valid_sets=[binary_train, binary_test], callbacks=[lgb.early_stopping(stopping_rounds=5)])
 print(bst.best_iteration)
 
 print('')