def test_rest(x, y,c=0,ratio='auto'):
c=c
if(c==0):
print('Random under-sampling')
US = UnderSampler(indices_support=indices_support, verbose=verbose,ratio=ratio)
x, y, idx_tmp = US.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
elif(c==1):
print('Tomek links')
TL = TomekLinks(verbose=verbose,ratio=ratio)
x, y = TL.fit_transform(x, y)
elif(c==2):
print('Clustering centroids')
CC = ClusterCentroids(verbose=verbose,ratio=ratio)
x, y = CC.fit_transform(x, y)
elif(c==3):
print('NearMiss-1')
NM1 = NearMiss(version=1, indices_support=indices_support, verbose=verbose,ratio=ratio)
x, y, idx_tmp = NM1.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
elif(c==4):
print('NearMiss-2')
NM2 = NearMiss(version=2, indices_support=indices_support, verbose=verbose,ratio=ratio)
x, y, idx_tmp = NM2.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
elif(c==5):
print('NearMiss-3')
NM3 = NearMiss(version=3, indices_support=indices_support, verbose=verbose,ratio=ratio)
x, y, idx_tmp = NM3.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
elif(c==6):
print('Neighboorhood Cleaning Rule')
NCR = NeighbourhoodCleaningRule(indices_support=indices_support, verbose=verbose,ratio=ratio)
x, y, idx_tmp = NCR.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
elif(c==7):
print('Random over-sampling')
OS = OverSampler(verbose=verbose,ratio=ratio)
x, y = OS.fit_transform(x, y)
elif(c==8):
print('SMOTE Tomek links')
STK = SMOTETomek(verbose=verbose,ratio=ratio)
x, y = STK.fit_transform(x, y)
elif(c==9):
print('SMOTE ENN')
SENN = SMOTEENN(verbose=verbose,ratio=ratio)
x, y = SENN.fit_transform(x, y)
else:
print('EasyEnsemble')
EE = EasyEnsemble(verbose=verbose,ratio=ratio)
x, y = EE.fit_transform(x, y)
return x, y
def test_rest(x, y):
print('Random under-sampling')
US = UnderSampler(indices_support=indices_support, verbose=verbose)
usx, usy, idx_tmp = US.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
print('Tomek links')
TL = TomekLinks(verbose=verbose)
tlx, tly = TL.fit_transform(x, y)
print('Clustering centroids')
CC = ClusterCentroids(verbose=verbose)
ccx, ccy = CC.fit_transform(x, y)
print('NearMiss-1')
NM1 = NearMiss(version=1, indices_support=indices_support, verbose=verbose)
nm1x, nm1y, idx_tmp = NM1.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
print('NearMiss-2')
NM2 = NearMiss(version=2, indices_support=indices_support, verbose=verbose)
nm2x, nm2y, idx_tmp = NM2.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
print('NearMiss-3')
NM3 = NearMiss(version=3, indices_support=indices_support, verbose=verbose)
nm3x, nm3y, idx_tmp = NM3.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
print('Neighboorhood Cleaning Rule')
NCR = NeighbourhoodCleaningRule(indices_support=indices_support, verbose=verbose)
ncrx, ncry, idx_tmp = NCR.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
print('Random over-sampling')
OS = OverSampler(verbose=verbose)
ox, oy = OS.fit_transform(x, y)
print('SMOTE Tomek links')
STK = SMOTETomek(verbose=verbose)
stkx, stky = STK.fit_transform(x, y)
print('SMOTE ENN')
SENN = SMOTEENN(verbose=verbose)
sennx, senny = SENN.fit_transform(x, y)
print('EasyEnsemble')
EE = EasyEnsemble(verbose=verbose)
eex, eey = EE.fit_transform(x, y)
def test_ncr_fit_transform():
"""Test the fit transform routine"""
# Resample the data
ncr = NeighbourhoodCleaningRule(random_state=RND_SEED)
X_resampled, y_resampled = ncr.fit_transform(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'ncr_x.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'ncr_y.npy'))
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_ncr_fit_transform():
"""Test the fit transform routine"""
# Resample the data
ncr = NeighbourhoodCleaningRule(random_state=RND_SEED)
X_resampled, y_resampled = ncr.fit_transform(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'ncr_x.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'ncr_y.npy'))
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_ncr_fit():
"""Test the fitting method"""
# Create the object
ncr = NeighbourhoodCleaningRule(random_state=RND_SEED)
# Fit the data
ncr.fit(X, Y)
# Check if the data information have been computed
assert_equal(ncr.min_c_, 0)
assert_equal(ncr.maj_c_, 1)
assert_equal(ncr.stats_c_[0], 500)
assert_equal(ncr.stats_c_[1], 4500)
def test_ncr_fit():
"""Test the fitting method"""
# Create the object
ncr = NeighbourhoodCleaningRule(random_state=RND_SEED)
# Fit the data
ncr.fit(X, Y)
# Check if the data information have been computed
assert_equal(ncr.min_c_, 0)
assert_equal(ncr.maj_c_, 1)
assert_equal(ncr.stats_c_[0], 500)
assert_equal(ncr.stats_c_[1], 4500)
def test_ncr_fit_transform_with_indices():
"""Test the fit transform routine with indices support"""
# Resample the data
ncr = NeighbourhoodCleaningRule(return_indices=True, random_state=RND_SEED)
X_resampled, y_resampled, idx_under = ncr.fit_transform(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'ncr_x.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'ncr_y.npy'))
idx_gt = np.load(os.path.join(currdir, 'data', 'ncr_idx.npy'))
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
assert_array_equal(idx_under, idx_gt)
def test_ncr_fit_transform_with_indices():
"""Test the fit transform routine with indices support"""
# Resample the data
ncr = NeighbourhoodCleaningRule(return_indices=True, random_state=RND_SEED)
X_resampled, y_resampled, idx_under = ncr.fit_transform(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'ncr_x.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'ncr_y.npy'))
idx_gt = np.load(os.path.join(currdir, 'data', 'ncr_idx.npy'))
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
assert_array_equal(idx_under, idx_gt)
def ncl_undersampling(X, y):
"""
Perform the Neighbourhood Cleaning Rule undersampling
Keyword arguments:
X -- The feature vectors
y -- The target vector
"""
if verbose:
print '\nUndersampling with the Neighbourhood Cleaning Rule ...'
undersampler = NeighbourhoodCleaningRule(verbose=verbose)
X_undersampled, y_undersampled = undersampler.fit_transform(X, y)
return X_undersampled, y_undersampled
def ncl_undersampling(X,y): """ Perform the Neighbourhood Cleaning Rule undersampling Keyword arguments: X -- The feature vectors y -- The target vector """ if verbose: print '\nUndersampling with the Neighbourhood Cleaning Rule ...' undersampler=NeighbourhoodCleaningRule(verbose=verbose) X_undersampled,y_undersampled = undersampler.fit_transform(X,y) return X_undersampled,y_undersampled
def test_ncr_transform_wt_fit():
"""Test either if an error is raised when transform is called before
fitting"""
# Create the object
ncr = NeighbourhoodCleaningRule(random_state=RND_SEED)
assert_raises(RuntimeError, ncr.transform, X, Y)
def test_ncr_fit_single_class():
"""Test either if an error when there is a single class"""
# Create the object
ncr = NeighbourhoodCleaningRule(random_state=RND_SEED)
# Resample the data
# Create a wrong y
y_single_class = np.zeros((X.shape[0], ))
assert_raises(RuntimeError, ncr.fit, X, y_single_class)
def test_ncr_init():
"""Test the initialisation of the object"""
# Define a ratio
verbose = True
ncr = NeighbourhoodCleaningRule(random_state=RND_SEED, verbose=verbose)
assert_equal(ncr.size_ngh, 3)
assert_equal(ncr.n_jobs, -1)
assert_equal(ncr.rs_, RND_SEED)
assert_equal(ncr.verbose, verbose)
assert_equal(ncr.min_c_, None)
assert_equal(ncr.maj_c_, None)
assert_equal(ncr.stats_c_, {})
weights=[0.1, 0.9],
n_informative=3,
n_redundant=1,
flip_y=0,
n_features=20,
n_clusters_per_class=1,
n_samples=5000,
random_state=10)
# Instanciate a PCA object for the sake of easy visualisation
pca = PCA(n_components=2)
# Fit and transform x to visualise inside a 2D feature space
X_vis = pca.fit_transform(X)
# Apply the random under-sampling
ncl = NeighbourhoodCleaningRule()
X_resampled, y_resampled = ncl.fit_transform(X, y)
X_res_vis = pca.transform(X_resampled)
# Two subplots, unpack the axes array immediately
f, (ax1, ax2) = plt.subplots(1, 2)
ax1.scatter(X_vis[y == 0, 0],
X_vis[y == 0, 1],
label="Class #0",
alpha=0.5,
edgecolor=almost_black,
facecolor=palette[0],
linewidth=0.15)
ax1.scatter(X_vis[y == 1, 0],
X_vis[y == 1, 1],