Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Move Python testing utilities into xgboost module. (#8379)

Browse Source 
- Add typehints.
- Fixes for pylint.

Co-authored-by: Hyunsu Philip Cho <chohyu01@cs.washington.edu>
This commit is contained in:
Jiaming Yuan
2022-10-26 16:56:11 +08:00
committed by GitHub
parent 7e53189e7c
commit cf70864fa3
66 changed files with 652 additions and 595 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
tests/python/test_basic_models.py
View File

@@ -1,13 +1,15 @@
import numpy as np
import xgboost as xgb
import os
import json
import testing as tm
import pytest
import locale
import os
import tempfile
dpath = os.path.join(tm.PROJECT_ROOT, 'demo/data/')
import numpy as np
import pytest
import xgboost as xgb
from xgboost import testing as tm
dpath = tm.data_dir(__file__)
rng = np.random.RandomState(1994)
@@ -36,8 +38,8 @@ class TestModels:
param = {'verbosity': 0, 'objective': 'binary:logistic',
'booster': 'gblinear', 'alpha': 0.0001, 'lambda': 1,
'nthread': 1}
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
dtrain = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.train"))
dtest = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.test"))
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 4
bst = xgb.train(param, dtrain, num_round, watchlist)
@@ -49,8 +51,8 @@ class TestModels:
assert err < 0.2
def test_dart(self):
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
dtrain = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.train"))
dtest = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.test"))
param = {'max_depth': 5, 'objective': 'binary:logistic',
'eval_metric': 'logloss', 'booster': 'dart', 'verbosity': 1}
# specify validations set to watch performance
@@ -116,7 +118,7 @@ class TestModels:
def test_boost_from_prediction(self):
# Re-construct dtrain here to avoid modification
margined = xgb.DMatrix(dpath + 'agaricus.txt.train')
margined = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.train"))
bst = xgb.train({'tree_method': 'hist'}, margined, 1)
predt_0 = bst.predict(margined, output_margin=True)
margined.set_base_margin(predt_0)
@@ -124,13 +126,13 @@ class TestModels:
predt_1 = bst.predict(margined)
assert np.any(np.abs(predt_1 - predt_0) > 1e-6)
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtrain = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.train"))
bst = xgb.train({'tree_method': 'hist'}, dtrain, 2)
predt_2 = bst.predict(dtrain)
assert np.all(np.abs(predt_2 - predt_1) < 1e-6)
def test_boost_from_existing_model(self):
X = xgb.DMatrix(dpath + 'agaricus.txt.train')
X = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.train"))
booster = xgb.train({'tree_method': 'hist'}, X, num_boost_round=4)
assert booster.num_boosted_rounds() == 4
booster = xgb.train({'tree_method': 'hist'}, X, num_boost_round=4,
@@ -150,8 +152,8 @@ class TestModels:
'objective': 'reg:logistic',
"tree_method": tree_method
}
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
dtrain = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.train"))
dtest = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.test"))
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 10
@@ -197,8 +199,8 @@ class TestModels:
self.run_custom_objective()
def test_multi_eval_metric(self):
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
dtrain = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.train"))
dtest = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.test"))
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
param = {'max_depth': 2, 'eta': 0.2, 'verbosity': 1,
'objective': 'binary:logistic'}
@@ -220,7 +222,7 @@ class TestModels:
param['scale_pos_weight'] = ratio
return (dtrain, dtest, param)
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtrain = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.train"))
xgb.cv(param, dtrain, num_round, nfold=5,
metrics={'auc'}, seed=0, fpreproc=fpreproc)
@@ -228,7 +230,7 @@ class TestModels:
param = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
num_round = 2
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtrain = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.train"))
xgb.cv(param, dtrain, num_round, nfold=5,
metrics={'error'}, seed=0, show_stdv=False)
@@ -346,7 +348,7 @@ class TestModels:
os.remove(model_path)
try:
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtrain = xgb.DMatrix(os.path.join(dpath, "agaricus.txt.train"))
xgb.train({'objective': 'foo'}, dtrain, num_boost_round=1)
except ValueError as e:
e_str = str(e)