def test_allknn_fit_sample():
"""Test the fit sample routine"""
# Resample the data
allknn = AllKNN(random_state=RND_SEED)
X_resampled, y_resampled = allknn.fit_sample(X, Y)
X_gt = np.array([[-0.53171468, -0.53735182], [-0.88864036, -0.33782387],
[-0.46226554, -0.50481004], [-0.34474418, 0.21969797],
[1.02956816, 0.36061601], [1.12202806, 0.33811558],
[-1.10146139, 0.91782682], [0.73489726, 0.43915195],
[0.50307437, 0.498805], [0.84929742, 0.41042894],
[0.62649535, 0.46600596], [0.98382284, 0.37184502],
[0.69804044, 0.44810796], [0.04296502, -0.37981873],
[0.28294738, -1.00125525], [0.34218094, -0.58781961],
[0.2096964, -0.61814058], [1.59068979, -0.96622933],
[0.73418199, -0.02222847], [0.79270821, -0.41386668],
[1.16606871, -0.25641059], [1.0304995, -0.16955962],
[0.48921682, -1.38504507], [-0.03918551, -0.68540745],
[0.24991051, -1.00864997], [0.80541964, -0.34465185],
[0.1732627, -1.61323172]])
y_gt = np.array([
0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2
])
assert_allclose(X_resampled, X_gt, rtol=R_TOL)
assert_allclose(y_resampled, y_gt, rtol=R_TOL)
def test_allknn_fit_resample_with_nn_object():
nn = NearestNeighbors(n_neighbors=4)
allknn = AllKNN(n_neighbors=nn, kind_sel='mode')
X_resampled, y_resampled = allknn.fit_resample(X, Y)
X_gt = np.array([[-0.53171468, -0.53735182], [-0.88864036, -0.33782387],
[-0.46226554, -0.50481004], [-0.34474418, 0.21969797],
[-0.12840393, 0.66446571], [1.02956816, 0.36061601],
[1.12202806, 0.33811558], [-0.35946678, 0.72510189],
[-1.10146139, 0.91782682], [0.73489726, 0.43915195],
[-0.28479268, 0.70459548], [0.50307437, 0.498805],
[0.84929742, 0.41042894], [0.62649535, 0.46600596],
[0.98382284, 0.37184502], [0.69804044, 0.44810796],
[1.32319756, -0.13181616], [0.04296502, -0.37981873],
[0.28294738, -1.00125525], [0.34218094, -0.58781961],
[0.2096964, -0.61814058], [1.59068979, -0.96622933],
[0.73418199, -0.02222847], [0.79270821, -0.41386668],
[1.16606871, -0.25641059], [1.0304995, -0.16955962],
[0.48921682, -1.38504507], [-0.03918551, -0.68540745],
[0.24991051, -1.00864997], [0.80541964, -0.34465185],
[0.1732627, -1.61323172]])
y_gt = np.array([
0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2
])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def fit(self, c_data, x_data, y_data):
# this is to track evolution of the size of the training samples
self.samplesize = []
self.samplesize.append(len(x_data))
if self.reject_by_calendar:
mask = self.mask_cal(c_data, y_data)
# filter rows rejected by this calendar criteria
# not filtering them might improve second classifier training
#x_data = normalize(x_data[mask])
#y_data = y_data[mask]
self.samplesize.append(len(x_data))
if self.use_resampling:
# undersample
resampler = AllKNN()
x_data, y_data = resampler.fit_sample(x_data, y_data)
self.samplesize.append(len(x_data))
# oversample
resampler = SMOTEENN()
x_data, y_data = resampler.fit_sample(x_data, y_data)
self.samplesize.append(len(x_data))
# train clf only with filtered and resampled data
if self.use_weights:
try:
self.clf.fit(x_data, y_data, self.get_weights(y_data))
except TypeError:
print "The classifier selected does not admit weights for training samples"
print "Switching to no weights"
self.use_weights = False
self.clf.fit(x_data, y_data)
else:
self.clf.fit(x_data, y_data)
def test_allknn_fit_resample_with_nn_object():
nn = NearestNeighbors(n_neighbors=4)
allknn = AllKNN(n_neighbors=nn, kind_sel='mode')
X_resampled, y_resampled = allknn.fit_resample(X, Y)
X_gt = np.array([[-0.53171468, -0.53735182], [-0.88864036, -0.33782387], [
-0.46226554, -0.50481004
], [-0.34474418, 0.21969797], [-0.12840393, 0.66446571], [
1.02956816, 0.36061601
], [1.12202806, 0.33811558], [-0.35946678, 0.72510189], [
-1.10146139, 0.91782682
], [0.73489726, 0.43915195], [-0.28479268, 0.70459548], [
0.50307437, 0.498805
], [0.84929742, 0.41042894], [0.62649535, 0.46600596], [
0.98382284, 0.37184502
], [0.69804044, 0.44810796], [1.32319756, -0.13181616], [
0.04296502, -0.37981873
], [0.28294738, -1.00125525], [0.34218094, -0.58781961], [
0.2096964, -0.61814058
], [1.59068979, -0.96622933], [0.73418199, -0.02222847], [
0.79270821, -0.41386668
], [1.16606871, -0.25641059], [1.0304995, -0.16955962], [
0.48921682, -1.38504507
], [-0.03918551, -0.68540745], [0.24991051, -1.00864997],
[0.80541964, -0.34465185], [0.1732627, -1.61323172]])
y_gt = np.array([
0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2
])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_allknn_fit_sample():
"""Test the fit sample routine"""
# Resample the data
allknn = AllKNN(random_state=RND_SEED)
X_resampled, y_resampled = allknn.fit_sample(X, Y)
X_gt = np.array([[-0.53171468, -0.53735182], [-0.88864036, -0.33782387],
[-0.46226554, -0.50481004], [-0.34474418, 0.21969797],
[1.02956816, 0.36061601], [1.12202806, 0.33811558],
[-1.10146139, 0.91782682], [0.73489726, 0.43915195],
[0.50307437, 0.498805], [0.84929742, 0.41042894],
[0.62649535, 0.46600596], [0.98382284, 0.37184502],
[0.69804044, 0.44810796], [0.04296502, -0.37981873],
[0.28294738, -1.00125525], [0.34218094, -0.58781961],
[0.2096964, -0.61814058], [1.59068979, -0.96622933],
[0.73418199, -0.02222847], [0.79270821, -0.41386668],
[1.16606871, -0.25641059], [1.0304995, -0.16955962],
[0.48921682, -1.38504507], [-0.03918551, -0.68540745],
[0.24991051, -1.00864997], [0.80541964, -0.34465185],
[0.1732627, -1.61323172]])
y_gt = np.array([
0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2
])
assert_array_almost_equal(X_resampled, X_gt)
assert_array_almost_equal(y_resampled, y_gt)
def test_allknn_fit_resample_with_indices():
allknn = AllKNN(return_indices=True)
X_resampled, y_resampled, idx_under = allknn.fit_resample(X, Y)
X_gt = np.array([[-0.53171468, -0.53735182], [-0.88864036, -0.33782387], [
-0.46226554, -0.50481004
], [-0.34474418, 0.21969797], [1.02956816, 0.36061601], [
1.12202806, 0.33811558
], [-1.10146139, 0.91782682], [0.73489726, 0.43915195], [
0.50307437, 0.498805
], [0.84929742, 0.41042894], [0.62649535, 0.46600596], [
0.98382284, 0.37184502
], [0.69804044, 0.44810796], [0.04296502, -0.37981873], [
0.28294738, -1.00125525
], [0.34218094, -0.58781961], [0.2096964, -0.61814058], [
1.59068979, -0.96622933
], [0.73418199, -0.02222847], [0.79270821, -0.41386668], [
1.16606871, -0.25641059
], [1.0304995, -0.16955962], [0.48921682, -1.38504507],
[-0.03918551, -0.68540745], [0.24991051, -1.00864997],
[0.80541964, -0.34465185], [0.1732627, -1.61323172]])
y_gt = np.array([
0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2
])
idx_gt = np.array([
6, 13, 32, 39, 4, 5, 14, 16, 22, 23, 24, 30, 37, 2, 11, 12, 17, 20, 21,
25, 26, 28, 31, 33, 34, 35, 36
])
assert_allclose(X_resampled, X_gt, rtol=R_TOL)
assert_allclose(y_resampled, y_gt, rtol=R_TOL)
assert_allclose(idx_under, idx_gt, rtol=R_TOL)
def test_allknn_fit_resample_with_indices():
allknn = AllKNN(return_indices=True)
X_resampled, y_resampled, idx_under = allknn.fit_resample(X, Y)
X_gt = np.array([[-0.53171468, -0.53735182], [-0.88864036, -0.33782387],
[-0.46226554, -0.50481004], [-0.34474418, 0.21969797],
[1.02956816, 0.36061601], [1.12202806, 0.33811558],
[-1.10146139, 0.91782682], [0.73489726, 0.43915195],
[0.50307437, 0.498805], [0.84929742, 0.41042894],
[0.62649535, 0.46600596], [0.98382284, 0.37184502],
[0.69804044, 0.44810796], [0.04296502, -0.37981873],
[0.28294738, -1.00125525], [0.34218094, -0.58781961],
[0.2096964, -0.61814058], [1.59068979, -0.96622933],
[0.73418199, -0.02222847], [0.79270821, -0.41386668],
[1.16606871, -0.25641059], [1.0304995, -0.16955962],
[0.48921682, -1.38504507], [-0.03918551, -0.68540745],
[0.24991051, -1.00864997], [0.80541964, -0.34465185],
[0.1732627, -1.61323172]])
y_gt = np.array([
0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2
])
idx_gt = np.array([
6, 13, 32, 39, 4, 5, 14, 16, 22, 23, 24, 30, 37, 2, 11, 12, 17, 20, 21,
25, 26, 28, 31, 33, 34, 35, 36
])
assert_allclose(X_resampled, X_gt, rtol=R_TOL)
assert_allclose(y_resampled, y_gt, rtol=R_TOL)
assert_allclose(idx_under, idx_gt, rtol=R_TOL)
def test_allknn_sample_wrong_X():
"""Test either if an error is raised when X is different at fitting
and sampling"""
# Create the object
allknn = AllKNN(random_state=RND_SEED)
allknn.fit(X, Y)
assert_raises(RuntimeError, allknn.sample,
np.random.random((100, 40)), np.array([0] * 50 + [1] * 50))
def test_allknn_sample_wrong_X():
"""Test either if an error is raised when X is different at fitting
and sampling"""
# Create the object
allknn = AllKNN(random_state=RND_SEED)
allknn.fit(X, Y)
assert_raises(RuntimeError, allknn.sample, np.random.random((100, 40)),
np.array([0] * 50 + [1] * 50))
def resample(self):
"""
Resampling data usinf AllKNN and SMOTE
"""
print("Sampling data...")
# Under Sampling
allknn = AllKNN(sampling_strategy={28: 565})
self.X, self.y = allknn.fit_resample(self.X, self.y)
#Over Sampling
smote = SMOTE(ratio="all")
self.X, self.y = smote.fit_resample(self.X, self.y)
def all_KNN(X, Y):
from imblearn.under_sampling import AllKNN
allknn = AllKNN()
allknn.fit_resample(X, Y)
indexes = allknn.sample_indices_
nobj = len(Y)
mask = np.zeros(nobj, dtype=int)
for i in range(nobj):
if i in indexes:
mask[i] = 1
return True, mask
def test_allknn_fit_sample():
"""Test the fit sample routine"""
# Resample the data
allknn = AllKNN(random_state=RND_SEED)
X_resampled, y_resampled = allknn.fit_sample(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'allknn_x.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'allknn_y.npy'))
assert_array_almost_equal(X_resampled, X_gt)
assert_array_almost_equal(y_resampled, y_gt)
def test_allknn_fit_sample():
"""Test the fit sample routine"""
# Resample the data
allknn = AllKNN(random_state=RND_SEED)
X_resampled, y_resampled = allknn.fit_sample(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'allknn_x.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'allknn_y.npy'))
assert_array_almost_equal(X_resampled, X_gt)
assert_array_almost_equal(y_resampled, y_gt)
def test_allknn_fit_sample_mode():
"""Test the fit sample routine using the mode as selection"""
# Resample the data
allknn = AllKNN(random_state=RND_SEED, kind_sel='mode')
X_resampled, y_resampled = allknn.fit_sample(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'allknn_x_mode.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'allknn_y_mode.npy'))
assert_array_equal(X_resampled, X_gt)
assert_array_almost_equal(y_resampled, y_gt)
def all_KNN(X, Y):
from imblearn.under_sampling import AllKNN
allknn = AllKNN()
allknn.fit_resample(X, Y)
indexes = allknn.sample_indices_
mask = []
for i in range(len(X)):
if i in indexes:
mask.append(1)
else:
mask.append(0)
return True, np.asarray(mask)
def test_allknn_fit_sample_mode():
"""Test the fit sample routine using the mode as selection"""
# Resample the data
allknn = AllKNN(random_state=RND_SEED, kind_sel='mode')
X_resampled, y_resampled = allknn.fit_sample(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'allknn_x_mode.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'allknn_y_mode.npy'))
assert_array_equal(X_resampled, X_gt)
assert_array_almost_equal(y_resampled, y_gt)
def test_allknn_fit():
"""Test the fitting method"""
# Create the object
allknn = AllKNN(random_state=RND_SEED)
# Fit the data
allknn.fit(X, Y)
# Check if the data information have been computed
assert_equal(allknn.min_c_, 0)
assert_equal(allknn.maj_c_, 1)
assert_equal(allknn.stats_c_[0], 500)
assert_equal(allknn.stats_c_[1], 4500)
def aiiknn(X,
y,
visualize=False,
pca2d=True,
pca3d=True,
tsne=True,
pie_evr=True):
allknn = AllKNN()
X_res, y_res = allknn.fit_resample(X, y)
if visualize == True:
hist_over_and_undersampling(y_res)
pca_general(X_res, y_res, d2=pca2d, d3=pca3d, pie_evr=pie_evr)
return X_res, y_res
def test_allknn_fit():
"""Test the fitting method"""
# Create the object
allknn = AllKNN(random_state=RND_SEED)
# Fit the data
allknn.fit(X, Y)
# Check if the data information have been computed
assert_equal(allknn.min_c_, 0)
assert_equal(allknn.maj_c_, 1)
assert_equal(allknn.stats_c_[0], 500)
assert_equal(allknn.stats_c_[1], 4500)
def test_allknn_fit_sample_with_indices():
"""Test the fit sample routine with indices support"""
# Resample the data
allknn = AllKNN(return_indices=True, random_state=RND_SEED)
X_resampled, y_resampled, idx_under = allknn.fit_sample(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'allknn_x.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'allknn_y.npy'))
idx_gt = np.load(os.path.join(currdir, 'data', 'allknn_idx.npy'))
assert_array_almost_equal(X_resampled, X_gt)
assert_array_almost_equal(y_resampled, y_gt)
assert_array_almost_equal(idx_under, idx_gt)
def test_allknn_fit_sample_with_indices():
"""Test the fit sample routine with indices support"""
# Resample the data
allknn = AllKNN(return_indices=True, random_state=RND_SEED)
X_resampled, y_resampled, idx_under = allknn.fit_sample(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'allknn_x.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'allknn_y.npy'))
idx_gt = np.load(os.path.join(currdir, 'data', 'allknn_idx.npy'))
assert_array_almost_equal(X_resampled, X_gt)
assert_array_almost_equal(y_resampled, y_gt)
assert_array_almost_equal(idx_under, idx_gt)
def fit(self, X, y):
# Preparação dos argumentos para os métodos da biblioteca ``scikit-learn``
#Xlinha = X[self.columns]
#ylinha = y
allknn = AllKNN()
#allknn = AllKNN()
X_resampled, y_resampled = allknn.fit_resample(X, y)
X_train, X_test, y_train, y_test = train_test_split(X_resampled,
y_resampled,
test_size=0.2,
random_state=1)
model = XGBClassifier()
return model
def test_multiclass_fit_sample():
"""Test fit sample method with multiclass target"""
# Make y to be multiclass
y = Y.copy()
y[0:1000] = 2
# Resample the data
ann = AllKNN(random_state=RND_SEED)
X_resampled, y_resampled = ann.fit_sample(X, y)
# Check the size of y
count_y_res = Counter(y_resampled)
assert_equal(count_y_res[0], 341)
assert_equal(count_y_res[1], 2485)
assert_equal(count_y_res[2], 212)
def getsampler(self, type):
if type == 'none':
sampler = NoSampler()
elif type == 'randomunder':
sampler = RandomUnderSampler()
elif type == 'nearmiss':
sampler = NearMiss()
elif type == 'allknn':
sampler = AllKNN()
elif type == 'condensednn':
sampler = CondensedNearestNeighbour()
elif type == 'editednn':
sampler = EditedNearestNeighbours()
elif type == 'repeatededitednn':
sampler = RepeatedEditedNearestNeighbours()
elif type == 'tomeklinks':
sampler = TomekLinks()
elif type == 'randomover':
sampler = RandomOverSampler()
elif type == 'smote':
sampler = SMOTE()
elif type == 'adasyn':
sampler = ADASYN()
elif type == 'smotenc':
sampler = SMOTENC()
elif type == 'quality': # and self.quality_model_selection_type == 'extended':
sampler = QualitySampler(self.n_init)
else:
print("Unsupported sampler %s" % type)
exit(1)
if type != 'none' and type != 'quality' and 'random_state' in sampler.get_params(
).keys():
sampler.set_params(random_state=self.random_state)
return sampler
def test_multiclass_fit_sample():
"""Test fit sample method with multiclass target"""
# Make y to be multiclass
y = Y.copy()
y[0:1000] = 2
# Resample the data
ann = AllKNN(random_state=RND_SEED)
X_resampled, y_resampled = ann.fit_sample(X, y)
# Check the size of y
count_y_res = Counter(y_resampled)
assert_equal(count_y_res[0], 341)
assert_equal(count_y_res[1], 2485)
assert_equal(count_y_res[2], 212)
def under_sample(X, y, sampler="RandomUnderSampler"):
# list of all samplers, in case you want to iterate all of them
samplers_list = ['RandomUnderSampler', 'ClusterCentroids', 'NearMiss', 'InstanceHardnessThreshold',
'CondensedNearestNeighbour', 'EditedNearestNeighbours', 'RepeatedEditedNearestNeighbours',
'AllKNN', 'NeighbourhoodCleaningRule', 'OneSidedSelection']
print(samplers_list)
# currently there is no parameters sampler
# this dict is used to choose a resampler by user. default is random
samplers = {
"RandomUnderSampler": RandomUnderSampler(),
"ClusterCentroids": ClusterCentroids(),
"NearMiss": NearMiss(),
"InstanceHardnessThreshold": InstanceHardnessThreshold(),
"CondensedNearestNeighbour": CondensedNearestNeighbour(),
"EditedNearestNeighbours": EditedNearestNeighbours(),
"RepeatedEditedNearestNeighbours": RepeatedEditedNearestNeighbours(),
"AllKNN": AllKNN(),
"NeighbourhoodCleaningRule": NeighbourhoodCleaningRule(),
"OneSidedSelection": OneSidedSelection(),
}
sampler = samplers[sampler]
# plot y class count before and after resample
print("before", sorted(Counter(y).items()))
# to resample simply call fit_resample method of sampler
X_resampled, y_resampled = sampler.fit_resample(X, y)
print("after", sorted(Counter(y_resampled).items()))
print('===' * 4, 'under_sample finished')
return X_resampled, y_resampled
class ResamplingAlgorithms(Enum):
RO = ("Random Over-sampling", RandomOverSampler(random_state=1))
SMOTE = ("Smote", SMOTE(random_state=1))
ADASYN = ("ADASYN", ADASYN(random_state=1))
SMOTE_TL = ('SMOTE+TL', SMOTETomek(random_state=1))
SMOTE_ENN = ('SMOTE+ENN', SMOTEENN(random_state=1))
SMOTE_BOOST = ("SMOTEBoost", smote_boost.SMOTEBoost())
RU = ("Random Under-sampling", RandomUnderSampler(random_state=1))
CLUSTERCENTROIDS = ("ClusterCentroids", ClusterCentroids(random_state=1))
TOMEK_LINKS = ("TomekLinks", TomekLinks())
NM1 = ("NM1", NearMiss(version=1))
NM2 = ("NM2", NearMiss(version=2))
NM3 = ("NM3", NearMiss(version=3))
CNN = ("CNN", CondensedNearestNeighbour(random_state=1))
OSS = ("OneSidedSelection", OneSidedSelection(random_state=1))
ENN = ('ENN', EditedNearestNeighbours())
NCL = ('NCL', NeighbourhoodCleaningRule())
IHT = ('IHT', (InstanceHardnessThreshold(random_state=1)))
RENN = ('RENN', RepeatedEditedNearestNeighbours())
AllKNN = ('AllKNN', AllKNN())
@classmethod
def get_algorithm_by_name(cls, name):
filtered_algos = filter(lambda ra: ra.value[0] == name,
ResamplingAlgorithms)
return next(filtered_algos, ResamplingAlgorithms.RO)
def under_sampling(X, y, method):
if method == 'ClusterCentroids':
model = ClusterCentroids()
X_resampled, y_resampled = model.fit_resample(X, y)
elif method == 'RandomUnderSampler':
model = RandomUnderSampler()
X_resampled, y_resampled = model.fit_resample(X, y)
elif method == 'NearMiss':
model = NearMiss()
X_resampled, y_resampled = model.fit_resample(X, y)
elif method == 'EditedNearestNeighbours':
model = EditedNearestNeighbours()
X_resampled, y_resampled = model.fit_resample(X, y)
elif method == 'RepeatedEditedNearestNeighbours':
model = RepeatedEditedNearestNeighbours()
X_resampled, y_resampled = model.fit_resample(X, y)
elif method == 'AllKNN':
model = AllKNN()
X_resampled, y_resampled = model.fit_resample(X, y)
elif method == 'NeighbourhoodCleaningRule':
model = NeighbourhoodCleaningRule()
X_resampled, y_resampled = model.fit_resample(X, y)
elif method == 'OneSidedSelection':
model = OneSidedSelection()
X_resampled, y_resampled = model.fit_resample(X, y)
return X_resampled, y_resampled
def sampler(name, ratio, random_state=0, return_indices=True, **kwargs):
if name == "rus":
sampler = RandomUnderSampler(
ratio=ratio,
return_indices=return_indices,
random_state=random_state,
**kwargs,
)
elif name == "nm":
sampler = NearMiss(
ratio=ratio,
return_indices=return_indices,
random_state=random_state,
**kwargs,
)
elif name == "enn":
sampler = EditedNearestNeighbours(return_indices=return_indices,
random_state=random_state,
**kwargs)
elif name == "renn":
sampler = RepeatedEditedNearestNeighbours(
return_indices=return_indices, random_state=random_state, **kwargs)
elif name == "allknn":
sampler = AllKNN(return_indices=return_indices,
random_state=random_state,
**kwargs)
elif name == "tl":
sampler = TomekLinks(return_indices=return_indices,
random_state=random_state,
**kwargs)
else:
raise ValueError
return sampler
def test_allknn_sample_wt_fit():
"""Test either if an error is raised when sample is called before
fitting"""
# Create the object
allknn = AllKNN(random_state=RND_SEED)
assert_raises(RuntimeError, allknn.sample, X, Y)
def test_allknn_init():
# Define a ratio
allknn = AllKNN(random_state=RND_SEED)
assert_equal(allknn.n_neighbors, 3)
assert_equal(allknn.kind_sel, 'all')
assert_equal(allknn.n_jobs, -1)
assert_equal(allknn.random_state, RND_SEED)
def test_continuous_error():
"""Test either if an error is raised when the target are continuous
type"""
# continuous case
y = np.linspace(0, 1, 40)
ann = AllKNN(random_state=RND_SEED)
assert_warns(UserWarning, ann.fit, X, y)
def Resampling(train_x, train_y, resampling_method):
train_y.data = LabelEncoder().fit_transform(train_y.data)
# summarize distribution
# scommentare la riga di seguito se si vuole visualizzare il grafico a torta della distribuzione delle classi prima di resampling
#plotGraphics.piePlot(train_y, "Before Resampling")
# ---- UNDER-SAMPLING ------ #
if resampling_method == "ClusterCentroids":
resample = ClusterCentroids(voting='hard', random_state=42)
if resampling_method == "CondensedNearestNeighbour":
resample = CondensedNearestNeighbour(n_neighbors=7, random_state=42)
if resampling_method == "EditedNearestNeighbours":
resample = EditedNearestNeighbours(n_neighbors=7,
kind_sel='mode',
n_jobs=-1)
if resampling_method == "RepeatedEditedNearestNeighbours":
resample = RepeatedEditedNearestNeighbours(n_neighbors=7,
kind_sel='mode',
n_jobs=-1)
if resampling_method == "AllKNN":
resample = AllKNN(n_neighbors=7,
kind_sel='mode',
allow_minority=True,
n_jobs=-1)
if resampling_method == "NearMiss":
resample = NearMiss(n_neighbors=7, n_jobs=-1)
if resampling_method == "NeighbourhoodCleaningRule":
resample = NeighbourhoodCleaningRule(n_neighbors=7, kind_sel='all')
if resampling_method == "RandomUnderSampler":
resample = RandomUnderSampler(random_state=42)
if resampling_method == "TomekLinks":
resample = TomekLinks(n_jobs=-1)
# ---- OVER-SAMPLING ------ #
if resampling_method == "BorderlineSMOTE":
resample = BorderlineSMOTE(random_state=42, n_jobs=-1)
if resampling_method == "KMeansSMOTE":
resample = KMeansSMOTE(random_state=42)
if resampling_method == "RandomUnderSampler":
resample = RandomOverSampler(random_state=42)
if resampling_method == "SMOTE":
resample = SMOTE(random_state=42, n_jobs=-1)
# transform the dataset
train_x.data, train_y.data = resample.fit_resample(train_x.data,
train_y.data)
def test_allknn_fit_single_class():
"""Test either if an error when there is a single class"""
# Create the object
allknn = AllKNN(random_state=RND_SEED)
# Resample the data
# Create a wrong y
y_single_class = np.zeros((X.shape[0], ))
assert_warns(UserWarning, allknn.fit, X, y_single_class)
def test_all_knn_allow_minority():
X, y = make_classification(
n_samples=10000,
n_features=2,
n_informative=2,
n_redundant=0,
n_repeated=0,
n_classes=3,
n_clusters_per_class=1,
weights=[0.2, 0.3, 0.5],
class_sep=0.4,
random_state=0)
allknn = AllKNN(allow_minority=True)
X_res_1, y_res_1 = allknn.fit_resample(X, y)
allknn = AllKNN()
X_res_2, y_res_2 = allknn.fit_resample(X, y)
assert len(y_res_1) < len(y_res_2)
def test_allknn_init():
"""Test the initialisation of the object"""
# Define a ratio
allknn = AllKNN(random_state=RND_SEED)
assert_equal(allknn.n_neighbors, 3)
assert_equal(allknn.kind_sel, 'all')
assert_equal(allknn.n_jobs, -1)
assert_equal(allknn.random_state, RND_SEED)
def resample(self, X, y, by, random_state=None, visualize=False):
'''
by: String
The method used to perform re-sampling
currently support: ['RUS', 'CNN', 'ENN', 'NCR', 'Tomek', 'ALLKNN', 'OSS',
'NM', 'CC', 'SMOTE', 'ADASYN', 'BorderSMOTE', 'SMOTEENN', 'SMOTETomek',
'ORG']
'''
if by == 'RUS':
sampler = RandomUnderSampler(random_state=random_state)
elif by == 'CNN':
sampler = CondensedNearestNeighbour(random_state=random_state)
elif by == 'ENN':
sampler = EditedNearestNeighbours(random_state=random_state)
elif by == 'NCR':
sampler = NeighbourhoodCleaningRule(random_state=random_state)
elif by == 'Tomek':
sampler = TomekLinks(random_state=random_state)
elif by == 'ALLKNN':
sampler = AllKNN(random_state=random_state)
elif by == 'OSS':
sampler = OneSidedSelection(random_state=random_state)
elif by == 'NM':
sampler = NearMiss(random_state=random_state)
elif by == 'CC':
sampler = ClusterCentroids(random_state=random_state)
elif by == 'SMOTE':
sampler = SMOTE(random_state=random_state)
elif by == 'ADASYN':
sampler = ADASYN(random_state=random_state)
elif by == 'BorderSMOTE':
sampler = BorderlineSMOTE(random_state=random_state)
elif by == 'SMOTEENN':
sampler = SMOTEENN(random_state=random_state)
elif by == 'SMOTETomek':
sampler = SMOTETomek(random_state=random_state)
elif by == 'ORG':
sampler = None
else:
raise Error('Unexpected \'by\' type {}'.format(by))
if by != 'ORG':
X_train, y_train = sampler.fit_resample(X, y)
else:
X_train, y_train = X, y
if visualize:
df = pd.DataFrame(X_train)
df['label'] = y_train
df.plot.scatter(x=0,
y=1,
c='label',
s=3,
colormap='coolwarm',
title='{} training set'.format(by))
return X_train, y_train
def __init__(self, name):
self.strategie = None
self.name = name
if name == "enn":
self.strategie = EditedNearestNeighbours(sampling_strategy='auto',
n_neighbors=3,
kind_sel='all',
n_jobs=-1)
elif name == "allknn":
self.strategie = AllKNN(sampling_strategy='auto',
n_neighbors=3,
kind_sel='all',
allow_minority=False,
n_jobs=-1)
elif name == "renn":
self.strategie = RepeatedEditedNearestNeighbours(
sampling_strategy='auto',
n_neighbors=3,
max_iter=100,
kind_sel='all',
n_jobs=-1)
elif name == "tomek":
self.strategie = TomekLinks(sampling_strategy='auto', n_jobs=-1)
elif name == "smote":
self.strategie = SMOTE(sampling_strategy='auto',
k_neighbors=5,
n_jobs=-1,
random_state=42)
elif name == "bdsmote":
self.strategie = BorderlineSMOTE(random_state=42, n_jobs=-1)
elif name == "adasyn":
self.strategie = ADASYN(sampling_strategy='auto',
n_neighbors=5,
n_jobs=-1,
random_state=42)
elif name == "smoteenn":
self.strategie = SMOTEENN(sampling_strategy='auto',
smote=None,
enn=None,
n_jobs=-1,
random_state=42)
elif name == "smotetomek":
self.strategie = SMOTETomek(sampling_strategy='auto',
smote=None,
tomek=None,
n_jobs=-1,
random_state=42)
def Allknn_us(X_train,
Y_train,
seed,
sampling_strategy,
n_neighbors=3,
kind_sel='all'):
knn = AllKNN(random_state=seed,
n_jobs=-1,
n_neighbors=n_neighbors,
kind_sel=kind_sel,
sampling_strategy=sampling_strategy)
print('Before Allknn undersampling : ', sorted(Counter(Y_train).items()))
X_train_resampled, Y_train_resampled = knn.fit_resample(X_train, Y_train)
print('After Allknn undersampling : ',
sorted(Counter(Y_train_resampled).items()))
X_train_resampled, Y_train_resampled = shuffle_dataset(
X_train_resampled, Y_train_resampled, seed)
return X_train_resampled, Y_train_resampled
def undersampling(type):
if type == 'random':
und = RandomUnderSampler(ratio='majority', random_state=42)
elif type == 'knn':
und = AllKNN(ratio='majority', random_state=42, n_jobs=4)
elif type == 'centroids':
und = ClusterCentroids(ratio='majority', n_jobs=-1)
x, y = und.fit_sample(train, label)
x = pd.DataFrame(x, columns=train.columns.values)
y = pd.DataFrame(y, columns=['is_attributed'])
return x, y
def test_alknn_not_good_object():
nn = 'rnd'
allknn = AllKNN(n_neighbors=nn, kind_sel='mode')
with raises(ValueError):
allknn.fit_resample(X, Y)
def test_deprecation_random_state():
allknn = AllKNN(random_state=0)
with warns(
DeprecationWarning, match="'random_state' is deprecated from 0.4"):
allknn.fit_resample(X, Y)
print('RENN')
renn = RepeatedEditedNearestNeighbours()
X_resampled, y_resampled = renn.fit_sample(X, y)
X_res_vis = pca.transform(X_resampled)
print('Reduced {:.2f}\%'.format(100 * (1 - float(len(X_resampled))/ len(X))))
ax3.scatter(X_res_vis[y_resampled == 0, 0], X_res_vis[y_resampled == 0, 1],
label="Class #0", alpha=.5, edgecolor=almost_black,
facecolor=palette[0], linewidth=0.15)
ax3.scatter(X_res_vis[y_resampled == 1, 0], X_res_vis[y_resampled == 1, 1],
label="Class #1", alpha=.5, edgecolor=almost_black,
facecolor=palette[2], linewidth=0.15)
ax3.set_title('Repeated Edited nearest neighbours')
# Apply the AllKNN
print('AllKNN')
allknn = AllKNN()
X_resampled, y_resampled = allknn.fit_sample(X, y)
X_res_vis = pca.transform(X_resampled)
print('Reduced {:.2f}\%'.format(100 * (1 - float(len(X_resampled))/ len(X))))
ax4.scatter(X_res_vis[y_resampled == 0, 0], X_res_vis[y_resampled == 0, 1],
label="Class #0", alpha=.5, edgecolor=almost_black,
facecolor=palette[0], linewidth=0.15)
ax4.scatter(X_res_vis[y_resampled == 1, 0], X_res_vis[y_resampled == 1, 1],
label="Class #1", alpha=.5, edgecolor=almost_black,
facecolor=palette[2], linewidth=0.15)
ax4.set_title('AllKNN')
plt.show()