XGBoost - n_estimators = 1 equal to single-tree classifier?
import subprocess
import numpy as np
from xgboost import XGBClassifier, plot_tree
from sklearn.tree import DecisionTreeClassifier, export_graphviz
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn import metrics
import matplotlib.pyplot as plt
RANDOM_STATE = 100
params = {
'max_depth': 5,
'min_samples_leaf': 5,
'random_state': RANDOM_STATE
}
X, y = make_classification(
n_samples=1000000,
n_features=5,
random_state=RANDOM_STATE
)
Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, random_state=RANDOM_STATE)
# __init__(self, max_depth=3, learning_rate=0.1,
# n_estimators=100, silent=True,
# objective='binary:logistic', booster='gbtree',
# n_jobs=1, nthread=None, gamma=0,
# min_child_weight=1, max_delta_step=0,
# subsample=1, colsample_bytree=1, colsample_bylevel=1,
# reg_alpha=0, reg_lambda=1, scale_pos_weight=1,
# base_score=0.5, random_state=0, seed=None, missing=None, **kwargs)
xgb_model = XGBClassifier(
n_estimators=1,
max_depth=3,
min_samples_leaf=5,
random_state=RANDOM_STATE
)
# __init__(self, criterion='gini',
# splitter='best', max_depth=None,
# min_samples_split=2, min_samples_leaf=1,
# min_weight_fraction_leaf=0.0, max_features=None,
# random_state=None, max_leaf_nodes=None,
# min_impurity_decrease=0.0, min_impurity_split=None,
# class_weight=None, presort=False)
sk_model = DecisionTreeClassifier(
max_depth=3,
min_samples_leaf=5,
random_state=RANDOM_STATE
)
xgb_model.fit(Xtrain, ytrain)
xgb_pred = xgb_model.predict(Xtest)
sk_model.fit(Xtrain, ytrain)
sk_pred = sk_model.predict(Xtest)
print(metrics.classification_report(ytest, xgb_pred))
print(metrics.classification_report(ytest, sk_pred))
plot_tree(xgb_model, rankdir='LR'); plt.show()
export_graphviz(sk_model, 'sk_model.dot'); subprocess.call('dot -Tpng sk_model.dot -o sk_model.png'.split())
Some performance metrics (I know, I didn't calibrate the classifiers totally)...
>>> print(metrics.classification_report(ytest, xgb_pred))
precision recall f1-score support
0 0.86 0.82 0.84 125036
1 0.83 0.87 0.85 124964
micro avg 0.85 0.85 0.85 250000
macro avg 0.85 0.85 0.85 250000
weighted avg 0.85 0.85 0.85 250000
>>> print(metrics.classification_report(ytest, sk_pred))
precision recall f1-score support
0 0.86 0.82 0.84 125036
1 0.83 0.87 0.85 124964
micro avg 0.85 0.85 0.85 250000
macro avg 0.85 0.85 0.85 250000
weighted avg 0.85 0.85 0.85 250000
And some pictures:
So, barring any investigate mistakes/overgeneralizations, an XGBClassifier
(and, I would assume, Regressor) with one estimator seems identical to a scikit-learn DecisionTreeClassifier
with the same shared parameters.