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_sample_with_indices():
allknn = AllKNN(return_indices=True, random_state=RND_SEED)
X_resampled, y_resampled, idx_under = 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
])
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_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_sample_with_nn_object():
"""Test the fit sample routine using a NN object"""
# Resample the data
nn = NearestNeighbors(n_neighbors=4)
allknn = AllKNN(n_neighbors=nn, random_state=RND_SEED, kind_sel='mode')
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],
[-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_allclose(X_resampled, X_gt, rtol=R_TOL)
assert_allclose(y_resampled, y_gt, rtol=R_TOL)
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_sample(X, y)
allknn = AllKNN()
X_res_2, y_res_2 = allknn.fit_sample(X, y)
assert len(y_res_1) < len(y_res_2)
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 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 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 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 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_sampling(xTrain, yTrain, neighbors=200):
"""
It reduces the sample size for the majority class using the model specificed. Always it has
to be applied to the training set.
:param xTrain: X training set.
:param yTrain: Y training set.
:param neighbors: size of the neighbourhood to consider to compute the
average distance to the minority point samples
:return: xTrain and yTrain oversampled
"""
xTrainNames = xTrain.columns.values.tolist()
yTrainNames = yTrain.columns.values.tolist()
model = AllKNN(random_state=42, ratio='majority', n_neighbors=neighbors)
xTrain, yTrain = model.fit_sample(xTrain, yTrain)
xTrain = pd.DataFrame(xTrain, columns=[xTrainNames])
yTrain = pd.DataFrame(yTrain, columns=[yTrainNames])
return xTrain, yTrain
''' [(0, 64), (1, 262), (2, 4674)] [(0, 64), (1, 213), (2, 4568)] ''' ''' 在此基础上, 延伸出了RepeatedEditedNearestNeighbours算法, 重复基础的EditedNearestNeighbours算法多次 ''' from imblearn.under_sampling import RepeatedEditedNearestNeighbours renn = RepeatedEditedNearestNeighbours(random_state=0) X_resampled, y_resampled = renn.fit_sample(X, y) print(sorted(Counter(y_resampled).items())) #[(0, 64), (1, 208), (2, 4551)] #与RepeatedEditedNearestNeighbours算法不同的是, ALLKNN算法在进行每次迭代的时候, 最近邻的数量都在增加. from imblearn.under_sampling import AllKNN allknn = AllKNN(random_state=0) X_resampled, y_resampled = allknn.fit_sample(X, y) print(sorted(Counter(y_resampled).items())) #[(0, 64), (1, 220), (2, 4601)] #Condensed nearest neighbors and derived algorithms ''' CondensedNearestNeighbour使用1近邻的方法来进行迭代,来判断一个样本是应该保留还是剔除,具体的实现步骤如下: 集合C:所有的少数类样本; 选择一个多数类样本(需要下采样)加入集合C,其他的这类样本放入集合S; 使用集合S训练一个1-NN的分类器,对集合S中的样本进行分类; 将集合S中错分的样本加入集合C; 重复上述过程, 直到没有样本再加入到集合C. ''' from imblearn.under_sampling import CondensedNearestNeighbour cnn = CondensedNearestNeighbour(random_state=0) X_resampled, y_resampled = cnn.fit_sample(X, y) print(sorted(Counter(y_resampled).items()))
def sampling(algorithm, x_train, y_train):
if (algorithm == 'standard'):
print('\nUsing Standard Scaler.\n')
scaler = StandardScaler().fit(x_train)
X_resampled = scaler.transform(x_train)
y_resampled = y_train
elif(algorithm == 'undersampling'):
# 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_train)
print('\nUsing Random Under Sampling.\n')
rus = RandomUnderSampler(return_indices=True)
X_resampled, y_resampled, idx_resampled = rus.fit_sample(x_train, y_train)
X_res_vis = pca.transform(X_resampled)
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
idx_samples_removed = np.setdiff1d(np.arange(X_vis.shape[0]),
idx_resampled)
idx_class_0 = y_resampled == 0
plt.scatter(X_res_vis[idx_class_0, 0], X_res_vis[idx_class_0, 1],
alpha=.8, label='Class #0')
plt.scatter(X_res_vis[~idx_class_0, 0], X_res_vis[~idx_class_0, 1],
alpha=.8, label='Class #1')
plt.scatter(X_vis[idx_samples_removed, 0], X_vis[idx_samples_removed, 1],
alpha=.8, label='Removed samples')
# make nice plotting
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.get_xaxis().tick_bottom()
ax.get_yaxis().tick_left()
ax.spines['left'].set_position(('outward', 10))
ax.spines['bottom'].set_position(('outward', 10))
ax.set_xlim([-6, 6])
ax.set_ylim([-6, 6])
plt.title('Under-sampling using random under-sampling')
plt.legend()
plt.tight_layout()
plt.show()
elif(algorithm == 'smote'):
print('\nUsing SMOTE.\n')
# 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_train)
kinds = ['regular', 'borderline1', 'borderline2', 'svm']
kind = [kinds[int(sys.argv[2] if len(sys.argv) >= 3 else 'regular')]]
print(kind)
sm = [SMOTE(kind=k) for k in kind]
X_resampled = []
y_resampled = []
X_res_vis = []
for method in sm:
X_res, y_res = method.fit_sample(x_train, y_train)
X_resampled.append(X_res)
y_resampled.append(y_res)
X_res_vis.append(pca.transform(X_res))
f, ((ax1, ax2), (ax3, ax4), (ax5, ax6)) = plt.subplots(3, 2)
ax2.axis('off')
ax_res = [ax3, ax4, ax5, ax6]
c0, c1 = plot_resampling(ax1, X_vis, y_train, 'Original set')
for i in range(len(kind)):
plot_resampling(ax_res[i], X_res_vis[i], y_resampled[i],
'SMOTE {}'.format(kind[i]))
ax2.legend((c0, c1), ('Class #0', 'Class #1'), loc='center',
ncol=1, labelspacing=0.)
plt.tight_layout()
plt.show()
elif(algorithm=='neighbourhood'):
print('\nUsing Neighbourhood Cleaning Rule.\n')
pca = PCA(n_components=2)
X_vis = pca.fit_transform(x_train)
ncl = NeighbourhoodCleaningRule(return_indices=True)
X_resampled, y_resampled, idx_resampled = ncl.fit_sample(x_train, y_train)
X_res_vis = pca.transform(X_resampled)
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
idx_samples_removed = np.setdiff1d(np.arange(X_vis.shape[0]),
idx_resampled)
idx_class_0 = y_resampled == 0
plt.scatter(X_res_vis[idx_class_0, 0], X_res_vis[idx_class_0, 1],
alpha=.8, label='Class #0')
plt.scatter(X_res_vis[~idx_class_0, 0], X_res_vis[~idx_class_0, 1],
alpha=.8, label='Class #1')
plt.scatter(X_vis[idx_samples_removed, 0], X_vis[idx_samples_removed, 1],
alpha=.8, label='Removed samples')
# make nice plotting
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.get_xaxis().tick_bottom()
ax.get_yaxis().tick_left()
ax.spines['left'].set_position(('outward', 10))
ax.spines['bottom'].set_position(('outward', 10))
ax.set_xlim([-6, 6])
ax.set_ylim([-6, 6])
plt.title('Under-sampling using neighbourhood cleaning rule')
plt.legend()
plt.tight_layout()
plt.show()
elif(algorithm == 'ENN'):
print('\nUsing ENN.\n')
enn = EditedNearestNeighbours(return_indices=True)
X_resampled, y_resampled, idx_resampled = enn.fit_sample(x_train, y_train)
reduction_str = ('Reduced {:.2f}%'.format(100 * (1 - float(len(X_resampled)) /
len(x_train))))
print(reduction_str)
elif(algorithm == 'RENN'):
print('\nUsing RENN.\n')
renn = RepeatedEditedNearestNeighbours(return_indices=True)
X_resampled, y_resampled, idx_resampled = renn.fit_sample(x_train, y_train)
reduction_str = ('Reduced {:.2f}%'.format(100 * (1 - float(len(X_resampled)) /
len(x_train))))
print(reduction_str)
elif(algorithm == 'AllKNN'):
print('\nUsing AllKNN.\n')
allknn = AllKNN(return_indices=True)
X_resampled, y_resampled, idx_resampled = allknn.fit_sample(x_train, y_train)
reduction_str = ('Reduced {:.2f}%'.format(100 * (1 - float(len(X_resampled)) /
len(x_train))))
print(reduction_str)
elif(algorithm == 'centroids'):
print('\nUsing Cluster Centroids.\n')
# Apply Cluster Centroids
cc = ClusterCentroids()
X_resampled, y_resampled = cc.fit_sample(x_train, y_train)
elif(algorithm == 'centroidshard'):
print('\nUsing Cluster Centroids with Hard Voting.\n')
pca = PCA(n_components=2)
X_vis = pca.fit_transform(x_train)
# Apply Cluster Centroids
cc = ClusterCentroids()
X_resampled, y_resampled = cc.fit_sample(x_train, y_train)
X_res_vis_soft = pca.transform(X_resampled)
# Use hard voting instead of soft voting
cc = ClusterCentroids(voting='hard')
X_resampled, y_resampled = cc.fit_sample(x_train, y_train)
X_res_vis_hard = pca.transform(X_resampled)
# Two subplots, unpack the axes array immediately
f, (ax1, ax2, ax3) = plt.subplots(1, 3, figsize=(15, 5))
c0 = ax1.scatter(X_vis[y_train == 0, 0], X_vis[y_train == 0, 1], label="Class #0",
alpha=0.5)
c1 = ax1.scatter(X_vis[y_train == 1, 0], X_vis[y_train == 1, 1], label="Class #1",
alpha=0.5)
ax1.set_title('Original set')
ax2.scatter(X_res_vis_soft[y_resampled == 0, 0],
X_res_vis_soft[y_resampled == 0, 1],
label="Class #0", alpha=.5)
ax2.scatter(X_res_vis_soft[y_resampled == 1, 0],
X_res_vis_soft[y_resampled == 1, 1],
label="Class #1", alpha=.5)
ax2.scatter(X_vis[y_train == 1, 0],
X_vis[y_train == 1, 1], label="Original #1",
alpha=0.2)
ax2.set_title('Cluster centroids with soft voting')
ax3.scatter(X_res_vis_hard[y_resampled == 0, 0],
X_res_vis_hard[y_resampled == 0, 1],
label="Class #0", alpha=.5)
ax3.scatter(X_res_vis_hard[y_resampled == 1, 0],
X_res_vis_hard[y_resampled == 1, 1],
label="Class #1", alpha=.5)
ax3.scatter(X_vis[y_train == 1, 0],
X_vis[y_train == 1, 1],
alpha=0.2)
ax3.set_title('Cluster centroids with hard voting')
# make nice plotting
for ax in (ax1, ax2, ax3):
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.get_xaxis().tick_bottom()
ax.get_yaxis().tick_left()
ax.spines['left'].set_position(('outward', 10))
ax.spines['bottom'].set_position(('outward', 10))
ax.set_xlim([-6, 8])
ax.set_ylim([-6, 6])
plt.figlegend((c0, c1), ('Class #0', 'Class #1', 'Original Class #1'),
loc='lower center',
ncol=3, labelspacing=0.)
plt.tight_layout(pad=3)
plt.show()
else:
# 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_train)
return x_train, y_train
return X_resampled, y_resampled
try:
X_resampled, Y_resampled = enn.fit_sample(X, Y)
except Exception, e:
print str(e)
X_resampled, Y_resampled = X, Y
elif index == 6:
renn = RepeatedEditedNearestNeighbours(random_state=0)
try:
X_resampled, Y_resampled = renn.fit_sample(X, Y)
except Exception, e:
print str(e)
X_resampled, Y_resampled = X, Y
elif index == 7:
allknn = AllKNN(random_state=0)
try:
X_resampled, Y_resampled = allknn.fit_sample(X, Y)
except Exception, e:
print str(e)
X_resampled, Y_resampled = X, Y
return X_resampled, Y_resampled
algo_list = ['dt', 'GaNB', 'linear_svc', 'logistic', 'nn', 'rf', 'svc']
X_list = []
Y_list = []
for algo in algo_list:
username_val, X, Y = read_file(algo)
X_list.append(X)
def test_alknn_not_good_object():
nn = 'rnd'
allknn = AllKNN(n_neighbors=nn, kind_sel='mode')
with raises(ValueError):
allknn.fit_sample(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()
def fit_sample(self, X, y):
allknn = AllKNN()
return allknn.fit_sample(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_sample(X, Y)
