def get_all_methods():
estimators = all_estimators()
for name, estimator in estimators:
if name.startswith("_"):
# skip private classes
continue
methods = [el for el in dir(estimator) if not el.startswith("_")]
methods.append(None)
for method in sorted(methods, key=lambda x: str(x)):
yield estimator, method
def get_all_methods():
estimators = all_estimators()
for name, Estimator in estimators:
if name.startswith("_"):
# skip private classes
continue
methods = []
for name in dir(Estimator):
if name.startswith("_"):
continue
method_obj = getattr(Estimator, name)
if (hasattr(method_obj, '__call__')
or isinstance(method_obj, property)):
methods.append(name)
methods.append(None)
for method in sorted(methods, key=lambda x: str(x)):
yield Estimator, method
# TODO: Remove when minimum python version is 3.7
# unwrap to get module because Pep562 backport wraps the original
# module
if isinstance(mod, Pep562):
mod = mod._module
try:
source = inspect.getsource(mod)
except IOError: # user probably should have run "make clean"
continue
assert '\t' not in source, ('"%s" has tabs, please remove them ',
'or add it to the ignore list' % modname)
@pytest.mark.parametrize('name, Estimator', all_estimators())
def test_fit_docstring_attributes(name, Estimator):
pytest.importorskip('numpydoc')
from numpydoc import docscrape
doc = docscrape.ClassDoc(Estimator)
attributes = doc['Attributes']
IGNORED = {
'ClassifierChain', 'ColumnTransformer', 'CountVectorizer',
'DictVectorizer', 'FeatureUnion', 'GaussianRandomProjection',
'GridSearchCV', 'MultiOutputClassifier', 'MultiOutputRegressor',
'NoSampleWeightWrapper', 'OneVsOneClassifier', 'OneVsRestClassifier',
'OutputCodeClassifier', 'Pipeline', 'RFE', 'RFECV',
'RandomizedSearchCV', 'RegressorChain', 'SelectFromModel',
'SparseCoder', 'SparseRandomProjection', 'SpectralBiclustering',
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
warnings.filterwarnings('ignore') # warning 무시하겠다! , 버전 안맞거나 difalut가 안맞아서 등등
dataset = load_iris()
x = dataset.data
y = dataset.target
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.2,
random_state=44)
kfold = KFold(n_splits=5, shuffle=True)
allAlgorithms = all_estimators(type_filter='classifier') #분류모델
for (name, algorithm) in allAlgorithms: # allAlgorithms 에서 인자가 2개 나온다 .
try:
model = algorithm()
score = cross_val_score(model, x_train, y_train, cv=kfold) #cv=5
# model.fit(x_train, y_train)
# y_pred = model.predict(x_test)
print(name, '의 정답률 : \n', score)
except: #예외가 발생하면
print(name, '은 없는 놈!')
# import sklearn
# print(sklearn.__version__) 버전 확인
or 'feature_extraction._hashing_fast' in modname):
continue
# because we don't import
mod = importlib.import_module(modname)
# TODO: Remove when minimum python version is 3.7
# unwrap to get module because Pep562 backport wraps the original
# module
if isinstance(mod, Pep562):
mod = mod._module
try:
source = inspect.getsource(mod)
except IOError: # user probably should have run "make clean"
continue
assert '\t' not in source, ('"%s" has tabs, please remove them ',
'or add it to theignore list' % modname)
@pytest.mark.parametrize('name, Classifier',
all_estimators(type_filter='classifier'))
def test_classifier_docstring_attributes(name, Classifier):
docscrape = pytest.importorskip('numpydoc.docscrape')
from numpydoc import docscrape
doc = docscrape.ClassDoc(Classifier)
attributes = doc['Attributes']
assert attributes
assert 'classes_' in [att.name for att in attributes]
from sklearn.svm import LinearSVC, SVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
warnings.filterwarnings('ignore') # warning 무시하겠다!
dataset = load_diabetes()
x = dataset.data
y = dataset.target
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.2,
random_state=44)
allAlgorithms = all_estimators(type_filter='regressor')
for (name, algorithm) in allAlgorithms: # allAlgorithms 에서 인자가 2개 나온다 .
try:
model = algorithm()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(name, '의 정답률 : ', r2_score(y_test, y_pred))
except: #예외가 발생하면
print(name, '은 없는 놈!')
import sklearn
# print(sklearn.__version__)