def test_sample_regular_half():
"""Test sample function with regular SMOTE and a ratio of 0.5."""
# Create the object
ratio = 0.8
smote = SMOTEENN(ratio=ratio, random_state=RND_SEED)
# Fit the data
smote.fit(X, Y)
X_resampled, y_resampled = smote.fit_sample(X, Y)
X_gt = np.array([[0.11622591, -0.0317206],
[1.25192108, -0.22367336],
[0.53366841, -0.30312976],
[1.52091956, -0.49283504],
[0.88407872, 0.35454207],
[1.31301027, -0.92648734],
[-0.41635887, -0.38299653],
[1.70580611, -0.11219234],
[0.36784496, -0.1953161],
[-0.28162401, -2.10400981],
[0.83680821, 1.72827342],
[0.08711622, 0.93259929]])
y_gt = np.array([0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1])
assert_array_almost_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_sample_regular():
"""Test sample function with regular SMOTE."""
# Create the object
smote = SMOTEENN(random_state=RND_SEED)
# Fit the data
smote.fit(X, Y)
X_resampled, y_resampled = smote.fit_sample(X, Y)
X_gt = np.array([[0.11622591, -0.0317206],
[1.25192108, -0.22367336],
[0.53366841, -0.30312976],
[1.52091956, -0.49283504],
[0.88407872, 0.35454207],
[1.31301027, -0.92648734],
[-0.41635887, -0.38299653],
[1.70580611, -0.11219234],
[0.29307743, -0.14670439],
[0.84976473, -0.15570176],
[0.61319159, -0.11571668],
[0.66052536, -0.28246517],
[-0.28162401, -2.10400981],
[0.83680821, 1.72827342],
[0.08711622, 0.93259929]])
y_gt = np.array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1])
assert_array_almost_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_sample_wrong_X():
"""Test either if an error is raised when X is different at fitting
and sampling"""
# Create the object
sm = SMOTEENN(random_state=RND_SEED)
sm.fit(X, Y)
assert_raises(RuntimeError, sm.sample, np.random.random((100, 40)),
np.array([0] * 50 + [1] * 50))
def test_sample_wrong_X():
"""Test either if an error is raised when X is different at fitting
and sampling"""
# Create the object
sm = SMOTEENN(random_state=RND_SEED)
sm.fit(X, Y)
assert_raises(RuntimeError, sm.sample, np.random.random((100, 40)),
np.array([0] * 50 + [1] * 50))
def test_smote_fit():
"""Test the fitting method"""
# Create the object
smote = SMOTEENN(random_state=RND_SEED)
# Fit the data
smote.fit(X, Y)
# Check if the data information have been computed
assert_equal(smote.min_c_, 0)
assert_equal(smote.maj_c_, 1)
assert_equal(smote.stats_c_[0], 8)
assert_equal(smote.stats_c_[1], 12)
def test_smote_fit():
"""Test the fitting method"""
# Create the object
smote = SMOTEENN(random_state=RND_SEED)
# Fit the data
smote.fit(X, Y)
# Check if the data information have been computed
assert_equal(smote.min_c_, 0)
assert_equal(smote.maj_c_, 1)
assert_equal(smote.stats_c_[0], 500)
assert_equal(smote.stats_c_[1], 4500)
def test_sample_regular():
"""Test sample function with regular SMOTE."""
# Create the object
smote = SMOTEENN(random_state=RND_SEED)
# Fit the data
smote.fit(X, Y)
X_resampled, y_resampled = smote.fit_sample(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'smote_enn_reg_x.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'smote_enn_reg_y.npy'))
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_sample_regular():
"""Test sample function with regular SMOTE."""
# Create the object
smote = SMOTEENN(random_state=RND_SEED)
# Fit the data
smote.fit(X, Y)
X_resampled, y_resampled = smote.fit_sample(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'smote_enn_reg_x.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'smote_enn_reg_y.npy'))
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
class OUSampler(SamplerMixin):
def __init__(self, seed=666, activate=True):
self.seed = seed
self.activate = activate
self.sampler = SMOTEENN(random_state=self.seed, n_jobs=-1)
def fit(self, X, y):
if self.activate:
self.sampler.fit(X, y)
# Return fit object
return self
def _sample(self, X, y):
if self.activate:
sampled_X, sampled_y = self.sampler.sample(X, y)
sampled_X = pd.DataFrame(sampled_X, columns=X.columns)
sampled_y = pd.Series(sampled_y, name=y.name)
return sampled_X, sampled_y
else:
return X, y
def sample(self, X, y):
return self._sample(X, y)
