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

Enable flake8

Browse Source
This commit is contained in:
sinhrks
2016-04-24 16:34:46 +09:00
parent b3c9e6a0db
commit 8fc2456c87
19 changed files with 282 additions and 199 deletions
Download Patch File Download Diff File Expand all files Collapse all files

75
tests/python/test_with_sklearn.py
View File

@@ -1,6 +1,5 @@
import xgboost as xgb
import numpy as np
from sklearn.cross_validation import KFold
from sklearn.metrics import mean_squared_error
from sklearn.grid_search import GridSearchCV
from sklearn.datasets import load_iris, load_digits, load_boston
@@ -8,33 +7,46 @@ from sklearn.cross_validation import KFold, StratifiedKFold, train_test_split
rng = np.random.RandomState(1994)
def test_binary_classification():
digits = load_digits(2)
y = digits['target']
X = digits['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBClassifier().fit(X[train_index],y[train_index])
xgb_model = xgb.XGBClassifier().fit(X[train_index], y[train_index])
preds = xgb_model.predict(X[test_index])
labels = y[test_index]
err = sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) / float(len(preds))
assert err < 0.1
err = sum(1 for i in range(len(preds))
if int(preds[i] > 0.5) != labels[i]) / float(len(preds))
assert err < 0.1
def test_multiclass_classification():
def check_pred(preds, labels):
err = sum(1 for i in range(len(preds))
if int(preds[i] > 0.5) != labels[i]) / float(len(preds))
assert err < 0.4
iris = load_iris()
y = iris['target']
X = iris['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBClassifier().fit(X[train_index],y[train_index])
xgb_model = xgb.XGBClassifier().fit(X[train_index], y[train_index])
preds = xgb_model.predict(X[test_index])
# test other params in XGBClassifier().fit
preds2 = xgb_model.predict(X[test_index], output_margin=True, ntree_limit=3)
preds3 = xgb_model.predict(X[test_index], output_margin=True, ntree_limit=0)
preds4 = xgb_model.predict(X[test_index], output_margin=False, ntree_limit=3)
labels = y[test_index]
err = sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) / float(len(preds))
assert err < 0.4
check_pred(preds, labels)
check_pred(preds2, labels)
check_pred(preds3, labels)
check_pred(preds4, labels)
def test_boston_housing_regression():
boston = load_boston()
@@ -42,27 +54,33 @@ def test_boston_housing_regression():
X = boston['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBRegressor().fit(X[train_index],y[train_index])
xgb_model = xgb.XGBRegressor().fit(X[train_index], y[train_index])
preds = xgb_model.predict(X[test_index])
# test other params in XGBRegressor().fit
preds2 = xgb_model.predict(X[test_index], output_margin=True, ntree_limit=3)
preds3 = xgb_model.predict(X[test_index], output_margin=True, ntree_limit=0)
preds4 = xgb_model.predict(X[test_index], output_margin=False, ntree_limit=3)
labels = y[test_index]
assert mean_squared_error(preds, labels) < 25
assert mean_squared_error(preds, labels) < 25
assert mean_squared_error(preds2, labels) < 350
assert mean_squared_error(preds3, labels) < 25
assert mean_squared_error(preds4, labels) < 350
def test_parameter_tuning():
boston = load_boston()
y = boston['target']
X = boston['data']
xgb_model = xgb.XGBRegressor()
clf = GridSearchCV(xgb_model,
{'max_depth': [2,4,6],
'n_estimators': [50,100,200]}, verbose=1)
clf.fit(X,y)
clf = GridSearchCV(xgb_model, {'max_depth': [2, 4, 6],
'n_estimators': [50, 100, 200]}, verbose=1)
clf.fit(X, y)
assert clf.best_score_ < 0.7
assert clf.best_params_ == {'n_estimators': 100, 'max_depth': 4}
def test_regression_with_custom_objective():
def objective_ls(y_true, y_pred):
grad = (y_pred - y_true)
@@ -86,20 +104,17 @@ def test_regression_with_custom_objective():
pass
def dummy_objective(y_true, y_pred):
raise XGBCustomObjectiveException()
raise XGBCustomObjectiveException()
xgb_model = xgb.XGBRegressor(objective=dummy_objective)
np.testing.assert_raises(
XGBCustomObjectiveException,
xgb_model.fit,
X, y
)
np.testing.assert_raises(XGBCustomObjectiveException, xgb_model.fit, X, y)
def test_classification_with_custom_objective():
def logregobj(y_true, y_pred):
y_pred = 1.0 / (1.0 + np.exp(-y_pred))
grad = y_pred - y_true
hess = y_pred * (1.0-y_pred)
hess = y_pred * (1.0 - y_pred)
return grad, hess
digits = load_digits(2)
@@ -107,22 +122,20 @@ def test_classification_with_custom_objective():
X = digits['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBClassifier(objective=logregobj).fit(
X[train_index],y[train_index]
)
xgb_model = xgb.XGBClassifier(objective=logregobj)
xgb_model.fit(X[train_index], y[train_index])
preds = xgb_model.predict(X[test_index])
labels = y[test_index]
err = sum(1 for i in range(len(preds))
if int(preds[i]>0.5)!=labels[i]) / float(len(preds))
assert err < 0.1
if int(preds[i] > 0.5) != labels[i]) / float(len(preds))
assert err < 0.1
# Test that the custom objective function is actually used
class XGBCustomObjectiveException(Exception):
pass
def dummy_objective(y_true, y_preds):
raise XGBCustomObjectiveException()
raise XGBCustomObjectiveException()
xgb_model = xgb.XGBClassifier(objective=dummy_objective)
np.testing.assert_raises(
@@ -131,6 +144,7 @@ def test_classification_with_custom_objective():
X, y
)
def test_sklearn_api():
iris = load_iris()
tr_d, te_d, tr_l, te_l = train_test_split(iris.data, iris.target, train_size=120)
@@ -143,6 +157,7 @@ def test_sklearn_api():
err = sum([1 for p, l in zip(preds, labels) if p != l]) / len(te_l)
assert err < 0.2
def test_sklearn_plotting():
iris = load_iris()
@@ -168,12 +183,13 @@ def test_sklearn_plotting():
ax = xgb.plot_tree(classifier, num_trees=0)
assert isinstance(ax, Axes)
def test_sklearn_nfolds_cv():
digits = load_digits(3)
X = digits['data']
y = digits['target']
dm = xgb.DMatrix(X, label=y)
params = {
'max_depth': 2,
'eta': 1,
@@ -187,9 +203,8 @@ def test_sklearn_nfolds_cv():
nfolds = 5
skf = StratifiedKFold(y, n_folds=nfolds, shuffle=True, random_state=seed)
import pandas as pd
cv1 = xgb.cv(params, dm, num_boost_round=10, nfold=nfolds, seed=seed)
cv2 = xgb.cv(params, dm, num_boost_round=10, folds=skf, seed=seed)
cv3 = xgb.cv(params, dm, num_boost_round=10, nfold=nfolds, stratified=True, seed=seed)
assert cv1.shape[0] == cv2.shape[0] and cv2.shape[0] == cv3.shape[0]
assert cv2.iloc[-1,0] == cv3.iloc[-1,0]
assert cv2.iloc[-1, 0] == cv3.iloc[-1, 0]