def test_CNN(x, y):
print('Condensed Nearest Neighbour')
CNN = CondensedNearestNeighbour(verbose=verbose)
cnnx, cnny = CNN.fit_transform(x, y)
print('One-Sided Selection')
OSS = OneSidedSelection(verbose=verbose)
ossx, ossy = OSS.fit_transform(x, y)
print('BalanceCascade')
BS = BalanceCascade(verbose=verbose)
bsx, bsy = BS.fit_transform(x, y)
def test_CNN(x, y):
print('Condensed Nearest Neighbour')
CNN = CondensedNearestNeighbour(verbose=verbose)
cnnx, cnny = CNN.fit_transform(x, y)
print('One-Sided Selection')
OSS = OneSidedSelection(verbose=verbose)
ossx, ossy = OSS.fit_transform(x, y)
print('BalanceCascade')
BS = BalanceCascade(verbose=verbose)
bsx, bsy = BS.fit_transform(x, y)
def test_cnn_fit_transform():
"""Test the fit transform routine"""
# Resample the data
cnn = CondensedNearestNeighbour(random_state=RND_SEED)
X_resampled, y_resampled = cnn.fit_transform(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'cnn_x.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'cnn_y.npy'))
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_cnn_fit():
"""Test the fitting method"""
# Create the object
cnn = CondensedNearestNeighbour(random_state=RND_SEED)
# Fit the data
cnn.fit(X, Y)
# Check if the data information have been computed
assert_equal(cnn.min_c_, 0)
assert_equal(cnn.maj_c_, 1)
assert_equal(cnn.stats_c_[0], 500)
assert_equal(cnn.stats_c_[1], 4500)
def test_cnn_fit_transform_with_indices():
"""Test the fit transform routine with indices support"""
# Resample the data
cnn = CondensedNearestNeighbour(return_indices=True, random_state=RND_SEED)
X_resampled, y_resampled, idx_under = cnn.fit_transform(X, Y)
currdir = os.path.dirname(os.path.abspath(__file__))
X_gt = np.load(os.path.join(currdir, 'data', 'cnn_x.npy'))
y_gt = np.load(os.path.join(currdir, 'data', 'cnn_y.npy'))
idx_gt = np.load(os.path.join(currdir, 'data', 'cnn_idx.npy'))
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
assert_array_equal(idx_under, idx_gt)
def balance_data_ensemblesampling_condensed_nearest_neighbour(self):
'''
Balance data using condensed nearest neighbour.
'''
x = self.X
y = self.y
y.shape = (len(self.y))
verbose = True
CNN = CondensedNearestNeighbour(verbose=verbose)
cnnx, cnny = CNN.fit_transform(x, y)
self.X = cnnx
self.y = cnny
self.y.shape = (len(self.y), 1)
def test_CNN(x, y):
print('Condensed Nearest Neighbour')
CNN = CondensedNearestNeighbour(indices_support=indices_support, verbose=verbose)
cnnx, cnny, idx_tmp = CNN.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
print('One-Sided Selection')
OSS = OneSidedSelection(indices_support=indices_support, verbose=verbose)
ossx, ossy, idx_tmp = OSS.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
print('BalanceCascade')
BS = BalanceCascade(verbose=verbose)
bsx, bsy = BS.fit_transform(x, y)
def test_cnn_transform_wt_fit():
"""Test either if an error is raised when transform is called before
fitting"""
# Create the object
cnn = CondensedNearestNeighbour(random_state=RND_SEED)
assert_raises(RuntimeError, cnn.transform, X, Y)
def test_CNN(x, y,c=0,ratio='auto'):
if(c==0):
print('Condensed Nearest Neighbour')
CNN = CondensedNearestNeighbour(indices_support=indices_support, verbose=verbose)
x,y, idx_tmp = CNN.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
elif(c==1):
print('One-Sided Selection')
OSS = OneSidedSelection(indices_support=indices_support, verbose=verbose)
x,y, idx_tmp = OSS.fit_transform(x, y)
print ('Indices selected')
print(idx_tmp)
elif(c==2):
print('BalanceCascade')
BS = BalanceCascade(ratio='auto',verbose=verbose)
x,y = BS.fit_transform(x, y)
return x,y
def test_cnn_fit_single_class():
"""Test either if an error when there is a single class"""
# Create the object
cnn = CondensedNearestNeighbour(random_state=RND_SEED)
# Resample the data
# Create a wrong y
y_single_class = np.zeros((X.shape[0], ))
assert_raises(RuntimeError, cnn.fit, X, y_single_class)
def test_cnn_init():
"""Test the initialisation of the object"""
# Define a ratio
verbose = True
cnn = CondensedNearestNeighbour(random_state=RND_SEED, verbose=verbose)
assert_equal(cnn.size_ngh, 1)
assert_equal(cnn.n_seeds_S, 1)
assert_equal(cnn.n_jobs, -1)
assert_equal(cnn.rs_, RND_SEED)
assert_equal(cnn.verbose, verbose)
assert_equal(cnn.min_c_, None)
assert_equal(cnn.maj_c_, None)
assert_equal(cnn.stats_c_, {})
from unbalanced_dataset.under_sampling import CondensedNearestNeighbour
# Generate the dataset
X, y = make_classification(n_classes=2, class_sep=2, 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
cnn = CondensedNearestNeighbour()
X_resampled, y_resampled = cnn.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], label="Class #1", alpha=0.5,
edgecolor=almost_black, facecolor=palette[2], linewidth=0.15)
ax1.set_title('Original set')
ax2.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)