def _check_X_y(X, y):
"""Overwrite the checking to let pass some string for categorical
features.
"""
y, binarize_y = check_target_type(y, indicate_one_vs_all=True)
X, y = check_X_y(X, y, accept_sparse=['csr', 'csc'], dtype=None)
return X, y, binarize_y
def fit(self, X, y):
"""Find the classes statistics before to perform sampling.
Parameters
----------
X : {array-like, sparse matrix}, shape (n_samples, n_features)
Matrix containing the data which have to be sampled.
y : array-like, shape (n_samples,)
Corresponding label for each sample in X.
Returns
-------
self : object,
Return self.
"""
X, y = check_X_y(X, y, accept_sparse=['csr', 'csc'])
y = check_target_type(y)
self.X_hash_, self.y_hash_ = hash_X_y(X, y)
self.ratio_ = check_ratio(self.ratio, y, self._sampling_type)
# Cluster input space
self.clustering_labels_ = self.clusterer[0][1].fit_predict(X, y)
# Identify majority and minority
majority_label = [label for label, n_samples in self.ratio_.items() if n_samples == 0][0]
minority_labels = [label for label in self.ratio_.keys() if label != majority_label]
# Clusters imbalance ratios
weights = pd.DataFrame()
return self
def fit(self, X, y):
X, y = check_X_y(X, y, accept_sparse=['csr', 'csc'])
y = check_target_type(y)
self.X_hash_, self.y_hash_ = hash_X_y(X, y)
self._fit(X, y)
return self
def _check_X_y(self, X, y):
"""Overwrite the checking to let pass some string for categorical
features.
"""
y, binarize_y = check_target_type(y, indicate_one_vs_all=True)
X, y = self._validate_data(
X, y, reset=True, dtype=None, accept_sparse=["csr", "csc"]
)
return X, y, binarize_y
def fit(self, X, y):
"""
Find the classes statistics to perform sampling.
Parameters
----------
X : 2d ndarray or scipy sparse matrix, shape [n_samples, n_features]
Matrix containing the data which have to be sampled.
y : 1d ndarray, shape [n_samples]
Corresponding label for each sample in X.
Returns
-------
self
"""
X, y = check_X_y(X, y, accept_sparse=['csr', 'csc'])
y = check_target_type(y)
self.X_hash_, self.y_hash_ = hash_X_y(X, y)
self.ratio_ = check_ratio(self.ratio, y)
return self
def fit(self, X, y):
"""Find the classes statistics before to perform sampling.
Parameters
----------
X : {array-like, sparse matrix}, shape (n_samples, n_features)
Matrix containing the data which have to be sampled.
y : array-like, shape (n_samples,)
Corresponding label for each sample in X.
Returns
-------
self : object,
Return self.
"""
X, y = check_X_y(X, y, accept_sparse=['csr', 'csc'], dtype=None)
y = check_target_type(y)
self.ratio_ = self.ratio
self.X_hash_, self.y_hash_ = hash_X_y(X, y)
labels = np.unique(y)
counts = np.bincount(y)
under_dict = {}
over_dict = {}
for lbl in labels:
count = counts[lbl]
if count < self.min_freq:
under_dict[lbl] = count
over_dict[lbl] = self.min_freq
elif count > self.max_freq:
under_dict[lbl] = self.max_freq
over_dict[lbl] = self.max_freq
else:
under_dict[lbl] = count
over_dict[lbl] = count
self.under_sampler = RandomUnderSampler(ratio=under_dict,
random_state=self.random_state)
self.over_sampler = RandomOverSampler(ratio=over_dict,
random_state=self.random_state)
return self
def test_check_target_type_ova(target, output_target, is_ova):
converted_target, binarize_target = check_target_type(
target.astype(int), indicate_one_vs_all=True)
assert_array_equal(converted_target, output_target.astype(int))
assert binarize_target == is_ova
def test_check_target_type(target, output_target):
converted_target = check_target_type(target.astype(int))
assert_array_equal(converted_target, output_target.astype(int))
def fit(self, X, y):
X, y = check_X_y(X, y, accept_sparse=True)
y, _ = check_target_type(y, indicate_one_vs_all=True)
self.sampling_strategy_ = 'sampling_strategy_'
return self
def fit(self, X, y):
y, _ = check_target_type(y, indicate_one_vs_all=True)
X, y = check_X_y(X, y, accept_sparse=True)
return self
def _check_X_y(X, y):
y, binarize_y = check_target_type(y, indicate_one_vs_all=True)
X, y = check_X_y(X, y, accept_sparse=['csr', 'csc'], dtype=None)
return X, y, binarize_y
def test_check_target_type_ova(target, output_target, is_ova):
converted_target, binarize_target = check_target_type(
target.astype(int), indicate_one_vs_all=True)
assert_array_equal(converted_target, output_target.astype(int))
assert binarize_target == is_ova
def fit(self, X, y):
y, _ = check_target_type(y, indicate_one_vs_all=True)
X, y = check_X_y(X, y, accept_sparse=False)
self.sampling_strategy_ = 'sampling_strategy_'
return self
def test_check_target_warning():
target = np.arange(4).reshape((2, 2))
with pytest.warns(UserWarning, match='should be of types'):
check_target_type(target)
def _check_X_y(X, y):
y, binarize_y = check_target_type(y, indicate_one_vs_all=True)
X, y = check_X_y(X, y, accept_sparse=['csr', 'csc'], dtype=None)
return X, y, binarize_y
def test_check_target_warning():
target = np.arange(4).reshape((2, 2))
with pytest.warns(UserWarning, match='should be of types'):
check_target_type(target)
def test_check_target_type(target, output_target):
converted_target = check_target_type(target.astype(int))
assert_array_equal(converted_target, output_target.astype(int))
def fit(self, X, y):
y, _ = check_target_type(y, indicate_one_vs_all=True)
X, y = check_X_y(X, y, accept_sparse=True)
return self
