def test_xgboost_random_states():
X, y, weights = generate_classification_data(n_classes=2, distance=5)
for random_state in [
145, None,
check_random_state(None),
check_random_state(145)
]:
clf1 = XGBoostClassifier(n_estimators=5,
max_depth=1,
subsample=0.1,
random_state=random_state)
clf1.fit(X, y)
clf2 = XGBoostClassifier(n_estimators=5,
max_depth=1,
subsample=0.1,
random_state=random_state)
clf2.fit(X, y)
if isinstance(random_state, numpy.random.RandomState):
assert not numpy.allclose(
clf1.predict_proba(X),
clf2.predict_proba(X)), 'seed: {}'.format(random_state)
else:
assert numpy.allclose(
clf1.predict_proba(X),
clf2.predict_proba(X)), 'seed: {}'.format(random_state)
def test_xgboost_random_states():
X, y, weights = generate_classification_data(n_classes=2, distance=5)
for random_state in [145, None, check_random_state(None), check_random_state(145)]:
clf1 = XGBoostClassifier(n_estimators=5, max_depth=1, subsample=0.1, random_state=random_state)
clf1.fit(X, y)
clf2 = XGBoostClassifier(n_estimators=5, max_depth=1, subsample=0.1, random_state=random_state)
clf2.fit(X, y)
if isinstance(random_state, numpy.random.RandomState):
assert not numpy.allclose(clf1.predict_proba(X), clf2.predict_proba(X)), 'seed: {}'.format(random_state)
else:
assert numpy.allclose(clf1.predict_proba(X), clf2.predict_proba(X)), 'seed: {}'.format(random_state)
def test_xgboost_feature_importance():
X, y, weights = generate_classification_data(n_classes=2, distance=5)
clf = XGBoostClassifier(n_estimators=1, max_depth=1)
clf.fit(X, y)
importances = clf.get_feature_importances()
original_features = set(X.columns)
importances_features = set(importances.index)
print(original_features, importances_features)
assert original_features == importances_features, 'feature_importances_ return something wrong'
assert len(original_features) == len(clf.feature_importances_)
def test_xgboost_feature_importance():
X, y, weights = generate_classification_data(n_classes=2, distance=5)
clf = XGBoostClassifier(n_estimators=1, max_depth=1)
clf.fit(X, y)
importances = clf.get_feature_importances()
original_features = set(X.columns)
importances_features = set(importances.index)
print(original_features, importances_features)
assert original_features == importances_features, 'feature_importances_ return something wrong'
assert len(original_features) == len(clf.feature_importances_)
def test_feature_importances():
clf = XGBoostClassifier()
X, y, sample_weight = generate_classification_data()
clf.fit(X, y, sample_weight=sample_weight)
# checking feature importance (three ways)
res_default = clf.xgboost_classifier.get_fscore()
res2 = clf._get_fscore()
res3 = clf.feature_importances_
assert res_default == res2, res_default
for i, val in enumerate(res3):
if val > 0.0:
assert val == res_default['f' + str(i)]
def test_xgboost_works_with_different_dtypes():
dtypes = ['float32', 'float64', 'int32', 'int64', 'uint32']
for dtype in dtypes:
X, y, weights = generate_classification_data(n_classes=2, distance=5)
clf = XGBoostClassifier(n_estimators=10)
clf.fit(X.astype(dtype=dtype), y.astype(dtype=dtype), sample_weight=weights.astype(dtype))
probabilities = clf.predict_proba(X.astype(dtype))
# testing single pandas.DataFrame with different dtypes
X, y, weights = generate_classification_data(n_classes=2, distance=5)
import pandas
X = pandas.DataFrame()
for dtype in dtypes:
X[dtype] = numpy.random.normal(0, 10, size=len(y)).astype(dtype)
clf = XGBoostClassifier(n_estimators=10)
clf.fit(X, y, sample_weight=weights)
probabilities = clf.predict_proba(X)
def test_xgboost_works_with_different_dtypes():
dtypes = ['float32', 'float64', 'int32', 'int64', 'uint32']
for dtype in dtypes:
X, y, weights = generate_classification_data(n_classes=2, distance=5)
clf = XGBoostClassifier(n_estimators=10)
clf.fit(X.astype(dtype=dtype),
y.astype(dtype=dtype),
sample_weight=weights.astype(dtype))
probabilities = clf.predict_proba(X.astype(dtype))
# testing single pandas.DataFrame with different dtypes
X, y, weights = generate_classification_data(n_classes=2, distance=5)
import pandas
X = pandas.DataFrame()
for dtype in dtypes:
X[dtype] = numpy.random.normal(0, 10, size=len(y)).astype(dtype)
clf = XGBoostClassifier(n_estimators=10)
clf.fit(X, y, sample_weight=weights)
probabilities = clf.predict_proba(X)
if ii==1 :
train= trainFeaturesObvious
Var='Mass'
if ii==2 :
train= trainFeaturesHH
Var='HH'
xgb = XGBoostClassifier(train) #,
original = xgboriginal.XGBClassifier(train)
"""
n_estimators = 200,
eta = 0.1,
max_depth = 7,
subsample = 0.9,
colsample = 0.6)
"""
xgb.fit(traindatasetmix[train].astype(np.float64), traindatasetmix.target.astype(np.bool), sample_weight= (traindatasetmix[weights].astype(np.float64)))
prob = xgb.predict_proba(valdatasetmix[train].astype(np.float64) )
if ii==0 : reportAll = xgb.test_on(traindatasetmix[trainFeaturesplot].astype(np.float64), traindatasetmix.target.astype(np.bool))
if ii==1 : reportObvious = xgb.test_on(traindatasetmix[trainFeaturesObvious].astype(np.float64), traindatasetmix.target.astype(np.bool))
if ii==2 : reportHH = xgb.test_on(traindatasetmix[trainFeaturesHH].astype(np.float64), traindatasetmix.target.astype(np.bool))
# compatible with lustr/lxplus
#features = ['costhst_DiJets[0]_HH', 'costhst_Jets[0]_DiJets[0]', 'costhst_Jets[2]_DiJets[1]', 'CSV3', 'CSV4', 'Jets[0].eta()', 'Jets[1].eta()', 'Jets[2].eta()', 'Jets[3].eta()', 'HT_other_jets']
#dataout = traindatasetmix.rename(index=str, columns={'HHCost':'costhst_DiJets[0]_HH', 'H1Costbb':'costhst_Jets[0]_DiJets[0]', 'H2Costbb':'costhst_Jets[2]_DiJets[1]', 'CSV3':'CSV3', 'CSV4':'CSV4', 'jeteta1':'Jets[0].eta()', 'jeteta2':'Jets[1].eta()', 'jeteta3':'Jets[2].eta()', 'jeteta4':'Jets[3].eta()', 'jetHTrest':'HT_other_jets'})
#param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic' }
#num_round = 2
#original = xgboriginal.XGBClassifier(param, train, num_round).fit(traindatasetmix[train].astype(np.float64), traindatasetmix.target.astype(np.bool), sample_weight= (traindatasetmix[weights].astype(np.float64)))
#proboriginal = original.predict_proba(valdatasetmix[train].astype(np.float64))
#print proboriginal
#joblib.dump(original, outputCentral+"_"+Var+'.pkl')
joblib.dump(prob, outputCentral+"_"+Var+'.pkl')
#pickle.dump(prob, outputCentral+"_"+Var+'.pkl')
