14fba01b5a
* Add UpdatePredictionCache() option to updaters Some updaters (e.g. fast_hist) has enough information to quickly compute prediction cache for the training data. Each updater may override UpdaterPredictionCache() method to update the prediction cache. Note: this trick does not apply to validation data. * Respond to code review * Disable some debug messages by default * Document UpdatePredictionCache() interface * Remove base_margin logic from UpdatePredictionCache() implementation * Do not take pointer to cfg, as reference may get stale * Improve multi-threaded performance * Use columnwise accessor to accelerate ApplySplit() step, with support for a compressed representation * Parallel sort for evaluation step * Inline BuildHist() function * Cache gradient pairs when building histograms in BuildHist() * Add missing #if macro * Respond to code review * Use wrapper to enable parallel sort on Linux * Fix C++ compatibility issues * MSVC doesn't support unsigned in OpenMP loops * gcc 4.6 doesn't support using keyword * Fix lint issues * Respond to code review * Fix bug in ApplySplitSparseData() * Attempting to read beyond the end of a sparse column * Mishandling the case where an entire range of rows have missing values * Fix training continuation bug Disable UpdatePredictionCache() in the first iteration. This way, we can accomodate the scenario where we build off of an existing (nonempty) ensemble. * Add regression test for fast_hist * Respond to code review * Add back old version of ApplySplitSparseData
137 lines
5.1 KiB
Python
137 lines
5.1 KiB
Python
import xgboost as xgb
|
|
import testing as tm
|
|
import numpy as np
|
|
import unittest
|
|
|
|
rng = np.random.RandomState(1994)
|
|
|
|
|
|
class TestFastHist(unittest.TestCase):
|
|
def test_fast_hist(self):
|
|
tm._skip_if_no_sklearn()
|
|
from sklearn.datasets import load_digits
|
|
try:
|
|
from sklearn.model_selection import train_test_split
|
|
except:
|
|
from sklearn.cross_validation import train_test_split
|
|
|
|
# regression test --- hist must be same as exact on all-categorial data
|
|
dpath = 'demo/data/'
|
|
ag_dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
|
|
ag_dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
|
|
ag_param = {'max_depth': 2,
|
|
'tree_method': 'exact',
|
|
'eta': 1,
|
|
'silent': 1,
|
|
'objective': 'binary:logistic',
|
|
'eval_metric': 'auc'}
|
|
ag_param2 = {'max_depth': 2,
|
|
'tree_method': 'hist',
|
|
'eta': 1,
|
|
'silent': 1,
|
|
'objective': 'binary:logistic',
|
|
'eval_metric': 'auc'}
|
|
ag_res = {}
|
|
ag_res2 = {}
|
|
|
|
xgb.train(ag_param, ag_dtrain, 10, [(ag_dtrain, 'train'), (ag_dtest, 'test')],
|
|
evals_result=ag_res)
|
|
xgb.train(ag_param2, ag_dtrain, 10, [(ag_dtrain, 'train'), (ag_dtest, 'test')],
|
|
evals_result=ag_res2)
|
|
assert ag_res['train']['auc'] == ag_res2['train']['auc']
|
|
assert ag_res['test']['auc'] == ag_res2['test']['auc']
|
|
|
|
digits = load_digits(2)
|
|
X = digits['data']
|
|
y = digits['target']
|
|
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
|
|
dtrain = xgb.DMatrix(X_train, y_train)
|
|
dtest = xgb.DMatrix(X_test, y_test)
|
|
|
|
param = {'objective': 'binary:logistic',
|
|
'tree_method': 'hist',
|
|
'grow_policy': 'depthwise',
|
|
'max_depth': 3,
|
|
'eval_metric': 'auc'}
|
|
res = {}
|
|
xgb.train(param, dtrain, 10, [(dtrain, 'train'), (dtest, 'test')],
|
|
evals_result=res)
|
|
assert self.non_decreasing(res['train']['auc'])
|
|
assert self.non_decreasing(res['test']['auc'])
|
|
|
|
param2 = {'objective': 'binary:logistic',
|
|
'tree_method': 'hist',
|
|
'grow_policy': 'lossguide',
|
|
'max_depth': 0,
|
|
'max_leaves': 8,
|
|
'eval_metric': 'auc'}
|
|
res = {}
|
|
xgb.train(param2, dtrain, 10, [(dtrain, 'train'), (dtest, 'test')],
|
|
evals_result=res)
|
|
assert self.non_decreasing(res['train']['auc'])
|
|
assert self.non_decreasing(res['test']['auc'])
|
|
|
|
param3 = {'objective': 'binary:logistic',
|
|
'tree_method': 'hist',
|
|
'grow_policy': 'lossguide',
|
|
'max_depth': 0,
|
|
'max_leaves': 8,
|
|
'max_bin': 16,
|
|
'eval_metric': 'auc'}
|
|
res = {}
|
|
xgb.train(param3, dtrain, 10, [(dtrain, 'train'), (dtest, 'test')],
|
|
evals_result=res)
|
|
assert self.non_decreasing(res['train']['auc'])
|
|
|
|
# fail-safe test for dense data
|
|
from sklearn.datasets import load_svmlight_file
|
|
dpath = 'demo/data/'
|
|
X2, y2 = load_svmlight_file(dpath + 'agaricus.txt.train')
|
|
X2 = X2.toarray()
|
|
dtrain2 = xgb.DMatrix(X2, label=y2)
|
|
|
|
param = {'objective': 'binary:logistic',
|
|
'tree_method': 'hist',
|
|
'grow_policy': 'depthwise',
|
|
'max_depth': 2,
|
|
'eval_metric': 'auc'}
|
|
res = {}
|
|
xgb.train(param, dtrain2, 10, [(dtrain2, 'train')], evals_result=res)
|
|
assert self.non_decreasing(res['train']['auc'])
|
|
assert res['train']['auc'][0] >= 0.85
|
|
|
|
for j in range(X2.shape[1]):
|
|
for i in np.random.choice(X2.shape[0], size=10, replace=False):
|
|
X2[i, j] = 2
|
|
|
|
dtrain3 = xgb.DMatrix(X2, label=y2)
|
|
res = {}
|
|
xgb.train(param, dtrain3, 10, [(dtrain3, 'train')], evals_result=res)
|
|
assert self.non_decreasing(res['train']['auc'])
|
|
assert res['train']['auc'][0] >= 0.85
|
|
|
|
for j in range(X2.shape[1]):
|
|
for i in np.random.choice(X2.shape[0], size=10, replace=False):
|
|
X2[i, j] = 3
|
|
|
|
dtrain4 = xgb.DMatrix(X2, label=y2)
|
|
res = {}
|
|
xgb.train(param, dtrain4, 10, [(dtrain4, 'train')], evals_result=res)
|
|
assert self.non_decreasing(res['train']['auc'])
|
|
assert res['train']['auc'][0] >= 0.85
|
|
|
|
# fail-safe test for max_bin=2
|
|
param = {'objective': 'binary:logistic',
|
|
'tree_method': 'hist',
|
|
'grow_policy': 'depthwise',
|
|
'max_depth': 2,
|
|
'eval_metric': 'auc',
|
|
'max_bin': 2}
|
|
res = {}
|
|
xgb.train(param, dtrain2, 10, [(dtrain2, 'train')], evals_result=res)
|
|
assert self.non_decreasing(res['train']['auc'])
|
|
assert res['train']['auc'][0] >= 0.85
|
|
|
|
def non_decreasing(self, L):
|
|
return all(x <= y for x, y in zip(L, L[1:]))
|