Update python scripts to use lightgbm api v4

Author: nunosilva800

.gitignore

@@ -8,3 +8,4 @@
 /tmp/
 *.lock
 /vendor/lib_lightgbm.*
+/.venv/

test/support/booster.py

@@ -1,22 +1,57 @@
+# Run this script to regenerate the test/support/model.txt and test/support/model_categorical.txt files
+
 import lightgbm as lgb
 import pandas as pd
 
-df = pd.read_csv('test/support/data.csv')
+params = {'verbosity': -1}
+
+def booster():
+    df = pd.read_csv('test/support/data.csv')
+
+    X = df.drop(columns=['y'])
+    y = df['y']
+
+    X_train = X[:300]
+    y_train = y[:300]
+    X_test = X[300:]
+    y_test = y[300:]
+
+    train_data = lgb.Dataset(X_train, label=y_train)
+    bst = lgb.train(params, train_data)
+    bst.save_model('test/support/model.txt')
+
+    bst = lgb.Booster(model_file='test/support/model.txt')
+    print('x', X_train[:2].to_numpy().tolist())
+    print('predict', bst.predict(X_train)[:2].tolist())
+    print('feature_importance', bst.feature_importance().tolist())
+    print('feature_name', bst.feature_name())
+
+def booster_categorical():
+    df = pd.read_csv('test/support/data.csv', dtype={'x3': 'category'})
+
+    X = df.drop(columns=['y'])
+    y = df['y']
+
+    X_train = X[:300]
+    y_train = y[:300]
+    X_test = X[300:]
+    y_test = y[300:]
+
+    train_data = lgb.Dataset(X_train, label=y_train, categorical_feature='auto')
+    bst = lgb.train(params, train_data)
+    bst.save_model('test/support/model_categorical.txt')
+
+    bst = lgb.Booster(model_file='test/support/model_categorical.txt')
+    print('x', X_train[:2].to_numpy().tolist())
+    print('predict', bst.predict(X_train)[:2].tolist())
+    print('feature_importance', bst.feature_importance().tolist())
+    print('feature_name', bst.feature_name())
 
-X = df.drop(columns=['y'])
-y = df['y']
 
-X_train = X[:300]
-y_train = y[:300]
-X_test = X[300:]
-y_test = y[300:]
+print('booster -> model.txt')
+booster()
 
-train_data = lgb.Dataset(X_train, label=y_train)
-bst = lgb.train({}, train_data)
-bst.save_model('test/support/model.txt')
+print('')
 
-bst = lgb.Booster(model_file='test/support/model.txt')
-print('x', X_train[:2].to_numpy().tolist())
-print('predict', bst.predict(X_train)[:2].tolist())
-print('feature_importance', bst.feature_importance().tolist())
-print('feature_name', bst.feature_name())
+print('categorical')
+booster_categorical()

test/support/classifier.py

@@ -25,15 +25,16 @@
 print()
 print('test_multiclass')
 
-model = lgb.LGBMClassifier()
+model = lgb.LGBMClassifier(verbosity=-1)
 model.fit(X_train, ym_train)
 print(model.predict(X_test)[0:100].tolist())
 print(model.predict_proba(X_test)[0].tolist())
 print(model.feature_importances_.tolist())
 
 print()
 print('test_early_stopping')
-model.fit(X_train, ym_train, eval_set=[(X_test, ym_test)], early_stopping_rounds=5, verbose=True)
+model = lgb.LGBMClassifier(early_stopping_round=5, verbosity=1)
+model.fit(X_train, ym_train, eval_set=[(X_test, ym_test)])
 
 print()
 print('test_missing_numeric')

test/support/cv.py

@@ -16,42 +16,45 @@
 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']))
+regression_params = {'objective': 'regression', 'verbosity': 1, 'early_stopping_round': 5}
+eval_hist = lgb.cv(regression_params, regression_train, shuffle=False, stratified=False)
+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']))
+regression_params = {'objective': 'regression', 'verbosity': 1, 'early_stopping_round': 500}
+eval_hist = lgb.cv(regression_params, regression_train, shuffle=False, stratified=False)
+print(len(eval_hist['valid l2-mean']))
+