本文整理汇总了Python中sklearn.dummy.DummyClassifier方法的典型用法代码示例。如果您正苦于以下问题:Python dummy.DummyClassifier方法的具体用法?Python dummy.DummyClassifier怎么用?Python dummy.DummyClassifier使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类sklearn.dummy
的用法示例。
在下文中一共展示了dummy.DummyClassifier方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: measure_performance_dummy_classifier
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def measure_performance_dummy_classifier():
outfile = get_out_file("dummy_classifier")
write_result(outfile, "smell,auc,precision,recall,f1,average_precision\n")
for smell in smell_list:
data_path = os.path.join(os.path.join(TOKENIZER_OUT_PATH, smell), DIM)
input_data = get_all_data(data_path, smell)
# clf = DummyClassifier(strategy='stratified', random_state=0)
clf = DummyClassifier(strategy='most_frequent', random_state=0)
inverted_train_labels = inputs.invert_labels(input_data.train_labels)
# clf.fit(input_data.train_data, input_data.train_labels)
clf.fit(input_data.train_data, inverted_train_labels)
y_pred = clf.predict(input_data.eval_data)
auc, precision, recall, f1, average_precision, fpr, tpr = \
metrics_util.get_all_metrics_(input_data.eval_labels, y_pred)
write_result(outfile,
smell + "," + str(auc) + "," + str(precision) + "," + str(recall) + "," + str(f1) + "," + str(
average_precision) + "\n")
示例2: measure_performance_dummy_classifier
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def measure_performance_dummy_classifier():
outfile = get_out_file("dummy_classifier")
write_result(outfile, "smell,auc,precision,recall,f1,average_precision\n")
for smell in smell_list:
data_path = os.path.join(os.path.join(TOKENIZER_OUT_PATH, smell), DIM)
input_data = get_all_data(data_path, smell)
# clf = DummyClassifier(strategy='stratified', random_state=0)
clf = DummyClassifier(strategy='most_frequent', random_state=0)
inverted_train_labels = inputs.invert_labels(input_data.train_labels)
clf.fit(input_data.train_data, inverted_train_labels)
# clf.fit(input_data.train_data, input_data.train_labels)
y_pred = clf.predict(input_data.eval_data)
auc, precision, recall, f1, average_precision, fpr, tpr = \
metrics_util.get_all_metrics_(input_data.eval_labels, y_pred)
write_result(outfile, smell +"," + str(auc) +"," + str(precision) +"," + str(recall) +"," + str(f1) +"," + str(average_precision) + "\n")
示例3: measure_performance_dummy_classifier
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def measure_performance_dummy_classifier():
outfile = get_out_file("dummy_classifier")
write_result(outfile, "smell,auc,precision,recall,f1,average_precision\n")
for smell in smell_list:
data_path = os.path.join(os.path.join(TOKENIZER_OUT_PATH, smell), DIM)
input_data = get_all_data(data_path, smell)
# clf = DummyClassifier(strategy='stratified', random_state=0)
clf = DummyClassifier(strategy='most_frequent', random_state=0)
inverted_train_labels = inputs.invert_labels(input_data.train_labels)
clf.fit(input_data.train_data, inverted_train_labels)
y_pred = clf.predict(input_data.eval_data)
auc, precision, recall, f1, average_precision, fpr, tpr = \
metrics_util.get_all_metrics_(input_data.eval_labels, y_pred)
write_result(outfile,
smell + "," + str(auc) + "," + str(precision) + "," + str(recall) + "," + str(f1) + "," + str(
average_precision) + "\n")
示例4: test_multidimensional_X
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def test_multidimensional_X():
"""
Check that the AdaBoost estimators can work with n-dimensional
data matrix
"""
from sklearn.dummy import DummyClassifier, DummyRegressor
rng = np.random.RandomState(0)
X = rng.randn(50, 3, 3)
yc = rng.choice([0, 1], 50)
yr = rng.randn(50)
boost = AdaBoostClassifier(DummyClassifier(strategy='most_frequent'))
boost.fit(X, yc)
boost.predict(X)
boost.predict_proba(X)
boost = AdaBoostRegressor(DummyRegressor())
boost.fit(X, yr)
boost.predict(X)
示例5: test_most_frequent_and_prior_strategy
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def test_most_frequent_and_prior_strategy():
X = [[0], [0], [0], [0]] # ignored
y = [1, 2, 1, 1]
for strategy in ("most_frequent", "prior"):
clf = DummyClassifier(strategy=strategy, random_state=0)
clf.fit(X, y)
assert_array_equal(clf.predict(X), np.ones(len(X)))
_check_predict_proba(clf, X, y)
if strategy == "prior":
assert_array_almost_equal(clf.predict_proba([X[0]]),
clf.class_prior_.reshape((1, -1)))
else:
assert_array_almost_equal(clf.predict_proba([X[0]]),
clf.class_prior_.reshape((1, -1)) > 0.5)
示例6: test_most_frequent_and_prior_strategy_multioutput
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def test_most_frequent_and_prior_strategy_multioutput():
X = [[0], [0], [0], [0]] # ignored
y = np.array([[1, 0],
[2, 0],
[1, 0],
[1, 3]])
n_samples = len(X)
for strategy in ("prior", "most_frequent"):
clf = DummyClassifier(strategy=strategy, random_state=0)
clf.fit(X, y)
assert_array_equal(clf.predict(X),
np.hstack([np.ones((n_samples, 1)),
np.zeros((n_samples, 1))]))
_check_predict_proba(clf, X, y)
_check_behavior_2d(clf)
示例7: test_uniform_strategy_multioutput
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def test_uniform_strategy_multioutput():
X = [[0]] * 4 # ignored
y = np.array([[2, 1],
[2, 2],
[1, 2],
[1, 1]])
clf = DummyClassifier(strategy="uniform", random_state=0)
clf.fit(X, y)
X = [[0]] * 500
y_pred = clf.predict(X)
for k in range(y.shape[1]):
p = np.bincount(y_pred[:, k]) / float(len(X))
assert_almost_equal(p[1], 0.5, decimal=1)
assert_almost_equal(p[2], 0.5, decimal=1)
_check_predict_proba(clf, X, y)
_check_behavior_2d(clf)
示例8: test_constant_strategy_multioutput
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def test_constant_strategy_multioutput():
X = [[0], [0], [0], [0]] # ignored
y = np.array([[2, 3],
[1, 3],
[2, 3],
[2, 0]])
n_samples = len(X)
clf = DummyClassifier(strategy="constant", random_state=0,
constant=[1, 0])
clf.fit(X, y)
assert_array_equal(clf.predict(X),
np.hstack([np.ones((n_samples, 1)),
np.zeros((n_samples, 1))]))
_check_predict_proba(clf, X, y)
示例9: test_constant_strategy_sparse_target
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def test_constant_strategy_sparse_target():
X = [[0]] * 5 # ignored
y = sp.csc_matrix(np.array([[0, 1],
[4, 0],
[1, 1],
[1, 4],
[1, 1]]))
n_samples = len(X)
clf = DummyClassifier(strategy="constant", random_state=0, constant=[1, 0])
clf.fit(X, y)
y_pred = clf.predict(X)
assert sp.issparse(y_pred)
assert_array_equal(y_pred.toarray(), np.hstack([np.ones((n_samples, 1)),
np.zeros((n_samples, 1))]))
示例10: test_stratified_strategy_sparse_target
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def test_stratified_strategy_sparse_target():
X = [[0]] * 5 # ignored
y = sp.csc_matrix(np.array([[4, 1],
[0, 0],
[1, 1],
[1, 4],
[1, 1]]))
clf = DummyClassifier(strategy="stratified", random_state=0)
clf.fit(X, y)
X = [[0]] * 500
y_pred = clf.predict(X)
assert sp.issparse(y_pred)
y_pred = y_pred.toarray()
for k in range(y.shape[1]):
p = np.bincount(y_pred[:, k]) / float(len(X))
assert_almost_equal(p[1], 3. / 5, decimal=1)
assert_almost_equal(p[0], 1. / 5, decimal=1)
assert_almost_equal(p[4], 1. / 5, decimal=1)
示例11: test_most_frequent_and_prior_strategy_sparse_target
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def test_most_frequent_and_prior_strategy_sparse_target():
X = [[0]] * 5 # ignored
y = sp.csc_matrix(np.array([[1, 0],
[1, 3],
[4, 0],
[0, 1],
[1, 0]]))
n_samples = len(X)
y_expected = np.hstack([np.ones((n_samples, 1)), np.zeros((n_samples, 1))])
for strategy in ("most_frequent", "prior"):
clf = DummyClassifier(strategy=strategy, random_state=0)
clf.fit(X, y)
y_pred = clf.predict(X)
assert sp.issparse(y_pred)
assert_array_equal(y_pred.toarray(), y_expected)
示例12: test_warning_recursion_non_constant_init
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def test_warning_recursion_non_constant_init():
# make sure that passing a non-constant init parameter to a GBDT and using
# recursion method yields a warning.
gbc = GradientBoostingClassifier(init=DummyClassifier(), random_state=0)
gbc.fit(X, y)
with pytest.warns(
UserWarning,
match='Using recursion method with a non-constant init predictor'):
partial_dependence(gbc, X, [0], method='recursion')
with pytest.warns(
UserWarning,
match='Using recursion method with a non-constant init predictor'):
partial_dependence(gbc, X, [0], method='recursion')
示例13: get_methods_multitask
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def get_methods_multitask(tasks_number, header, random_restarts=-1):
FEATURES_BOW, FEATURES_BROWN, index_task, _=extract_feature_indices(header)
GPCONSTRUCTOR=lambda kernel_constructor, name, random_restarts: MCGP(kernel_constructor=kernel_constructor,
labels=LABELS, name=name, random_restarts=random_restarts)
methodsmultitask=[
lambda: SklearnBaseline(lambda: DummyClassifier("most_frequent"), "MostFrequentPooled", [0]),
lambda: GPCONSTRUCTOR(kernel_constructor=lambda: single_task_kernel(FEATURES_BOW, False, "FEATURES_BOW"),
name="BOWGPjoinedfeaturesPooledLIN",
random_restarts=random_restarts),
lambda: GPCONSTRUCTOR(kernel_constructor=lambda: single_task_kernel(FEATURES_BROWN, False, "FEATURES_BROWN"),
name="BROWNGPjoinedfeaturesPooledLIN",
random_restarts=random_restarts),
lambda: GPCONSTRUCTOR(kernel_constructor=lambda: multi_task_kernel(tasks_number, index_task,
single_task_kernel(FEATURES_BROWN, False, "FEATURES_BROWN")),
name="BROWNGPjoinedfeaturesICMLIN", random_restarts=random_restarts),
lambda: GPCONSTRUCTOR(kernel_constructor=lambda: multi_task_kernel(tasks_number, index_task,
single_task_kernel(FEATURES_BOW, False, "FEATURES_BOW")),
name="BOWGPjoinedfeaturesICMLIN", random_restarts=random_restarts),
]
return methodsmultitask, map(lambda x: x().name, methodsmultitask)
示例14: __init__
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def __init__(self, df,
strategy='most_frequent',
weight=False,
min_ct=0):
self.logger = logging.getLogger(__name__)
super(DummyClf, self).__init__() # call base constructor
#self.set_min_count(min_ct)
self.is_weighted_sample = False
# process data
#df = self._filter_rows(df) # filter out low count rows
df = df.fillna(df.mean())
self.x, self.y = futils.randomize(df)
# setup classifier
self.clf = DummyClassifier(strategy=strategy)
示例15: _call_oracle
# 需要导入模块: from sklearn import dummy [as 别名]
# 或者: from sklearn.dummy import DummyClassifier [as 别名]
def _call_oracle(self, lambda_vec):
signed_weights = self.obj.signed_weights() + self.constraints.signed_weights(lambda_vec)
redY = 1 * (signed_weights > 0)
redW = signed_weights.abs()
redW = self.n * redW / redW.sum()
redY_unique = np.unique(redY)
classifier = None
if len(redY_unique) == 1:
logger.debug("redY had single value. Using DummyClassifier")
classifier = DummyClassifier(strategy='constant',
constant=redY_unique[0])
self.n_oracle_calls_dummy_returned += 1
else:
classifier = pickle.loads(self.pickled_estimator)
oracle_call_start_time = time()
classifier.fit(self.X, redY, sample_weight=redW)
self.oracle_execution_times.append(time() - oracle_call_start_time)
self.n_oracle_calls += 1
return classifier