Skip to content

Commit 721bc2a

Browse files
author
Guillaume Lemaitre
committed
Change the printing style in logging
1 parent 12ac7d8 commit 721bc2a

15 files changed

+43
-52
lines changed

‎imblearn/base.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -102,8 +102,8 @@ def fit(self, X, y):
102102
self.min_c_ = min(self.stats_c_, key=self.stats_c_.get)
103103
self.maj_c_ = max(self.stats_c_, key=self.stats_c_.get)
104104

105-
self.logger.info('{} classes detected: {}'.format(uniques.size,
106-
self.stats_c_))
105+
self.logger.info('%s classes detected: %s', uniques.size,
106+
self.stats_c_)
107107

108108
# Check if the ratio provided at initialisation make sense
109109
if isinstance(self.ratio, float):

‎imblearn/ensemble/balance_cascade.py‎

Lines changed: 4 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -238,8 +238,7 @@ def _sample(self, X, y):
238238
# Find the misclassified index to keep them for the next round
239239
idx_mis_class = idx_sel_from_maj[np.nonzero(pred_label !=
240240
N_y[idx_sel_from_maj])]
241-
self.logger.debug('Elements misclassified: {}'.format(
242-
idx_mis_class))
241+
self.logger.debug('Elements misclassified: %s', idx_mis_class)
243242

244243
# Count how many random element will be selected
245244
if self.ratio == 'auto':
@@ -248,7 +247,7 @@ def _sample(self, X, y):
248247
num_samples = int(self.stats_c_[self.min_c_] / self.ratio)
249248
num_samples -= idx_mis_class.size
250249

251-
self.logger.debug('Creation of the subset #{}'.format(n_subsets))
250+
self.logger.debug('Creation of the subset #%s', n_subsets)
252251

253252
# We found a new subset, increase the counter
254253
n_subsets += 1
@@ -275,8 +274,7 @@ def _sample(self, X, y):
275274
idx_sel_from_maj),
276275
axis=0))
277276

278-
self.logger.debug('Creation of the subset #{}'.format(
279-
n_subsets))
277+
self.logger.debug('Creation of the subset #%s', n_subsets)
280278

281279
# We found a new subset, increase the counter
282280
n_subsets += 1
@@ -304,8 +302,7 @@ def _sample(self, X, y):
304302
idx_under.append(np.concatenate((idx_min,
305303
idx_sel_from_maj),
306304
axis=0))
307-
self.logger.debug('Creation of the subset #{}'.format(
308-
n_subsets))
305+
self.logger.debug('Creation of the subset #%s', n_subsets)
309306

310307
# We found a new subset, increase the counter
311308
n_subsets += 1

‎imblearn/ensemble/easy_ensemble.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -104,7 +104,7 @@ def _sample(self, X, y):
104104
idx_under = []
105105

106106
for s in range(self.n_subsets):
107-
self.logger.debug('Creation of the set #{}'.format(s))
107+
self.logger.debug('Creation of the set #%s', s)
108108

109109
# Create the object for random under-sampling
110110
rus = RandomUnderSampler(ratio=self.ratio,

‎imblearn/over_sampling/adasyn.py‎

Lines changed: 3 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -120,8 +120,7 @@ def _sample(self, X, y):
120120
X_min = X[y == self.min_c_]
121121

122122
# Print if verbose is true
123-
self.logger.debug('Finding the {} nearest neighbours...'.format(
124-
self.k))
123+
self.logger.debug('Finding the %s nearest neighbours ...', self.k)
125124

126125
# Look for k-th nearest neighbours, excluding, of course, the
127126
# point itself.
@@ -151,7 +150,7 @@ def _sample(self, X, y):
151150
X_resampled = np.vstack((X_resampled, x_gen))
152151
y_resampled = np.hstack((y_resampled, self.min_c_))
153152

154-
self.logger.info('Over-sampling performed: {}'.format(Counter(
155-
y_resampled)))
153+
self.logger.info('Over-sampling performed: %s', Counter(
154+
y_resampled))
156155

157156
return X_resampled, y_resampled

‎imblearn/over_sampling/random_over_sampler.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -114,7 +114,7 @@ def _sample(self, X, y):
114114
y[y == key],
115115
y[y == key][indx]), axis=0)
116116

117-
self.logger.info('Over-sampling performed: {}'.format(Counter(
118-
y_resampled)))
117+
self.logger.info('Over-sampling performed: %s', Counter(
118+
y_resampled))
119119

120120
return X_resampled, y_resampled

‎imblearn/over_sampling/smote.py‎

Lines changed: 12 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -229,7 +229,7 @@ def _make_samples(self, X, y_type, nn_data, nn_num, n_samples,
229229
# minority label
230230
y_new = np.array([y_type] * len(X_new))
231231

232-
self.logger.info('Generated {} new samples ...'.format(len(X_new)))
232+
self.logger.info('Generated %s new samples ...', len(X_new))
233233

234234
return X_new, y_new
235235

@@ -276,8 +276,7 @@ def _sample(self, X, y):
276276
# If regular SMOTE is to be performed
277277
if self.kind == 'regular':
278278

279-
self.logger.debug('Finding the {} nearest neighbours...'.format(
280-
self.k))
279+
self.logger.debug('Finding the %s nearest neighbours ...', self.k)
281280

282281
# Look for k-th nearest neighbours, excluding, of course, the
283282
# point itself.
@@ -308,8 +307,7 @@ def _sample(self, X, y):
308307

309308
if self.kind == 'borderline1' or self.kind == 'borderline2':
310309

311-
self.logger.debug('Finding the {} nearest neighbours ...'.format(
312-
self.m))
310+
self.logger.debug('Finding the %s nearest neighbours ...', self.m)
313311

314312
# Find the NNs for all samples in the data set.
315313
self.nearest_neighbour.fit(X)
@@ -413,8 +411,7 @@ def _sample(self, X, y):
413411

414412
# First, find the nn of all the samples to identify samples
415413
# in danger and noisy ones
416-
self.logger.debug('Finding the {} nearest neighbours ...'.format(
417-
self.m))
414+
self.logger.debug('Finding the %s nearest neighbours ...', self.m)
418415

419416
# As usual, fit a nearest neighbour model to the data
420417
self.nearest_neighbour.fit(X)
@@ -428,17 +425,16 @@ def _sample(self, X, y):
428425
kind='danger')
429426
safety_bool = np.logical_not(danger_bool)
430427

431-
self.logger.debug('Out of {0} support vectors, {1} are noisy, '
432-
'{2} are in danger '
433-
'and {3} are safe.'.format(
434-
support_vector.shape[0],
435-
noise_bool.sum().astype(int),
436-
danger_bool.sum().astype(int),
437-
safety_bool.sum().astype(int)))
428+
self.logger.debug('Out of %s support vectors, %s are noisy, '
429+
'%s are in danger '
430+
'and %s are safe.',
431+
support_vector.shape[0],
432+
noise_bool.sum().astype(int),
433+
danger_bool.sum().astype(int),
434+
safety_bool.sum().astype(int))
438435

439436
# Proceed to find support vectors NNs among the minority class
440-
self.logger.debug('Finding the {} nearest neighbours ...'.format(
441-
self.k))
437+
self.logger.debug('Finding the %s nearest neighbours ...', self.k)
442438

443439
self.nearest_neighbour.set_params(**{'n_neighbors': self.k + 1})
444440
self.nearest_neighbour.fit(X_min)

‎imblearn/under_sampling/cluster_centroids.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -127,7 +127,7 @@ def _sample(self, X, y):
127127
num_samples)),
128128
axis=0)
129129

130-
self.logger.info('Under-sampling performed: {}'.format(Counter(
131-
y_resampled)))
130+
self.logger.info('Under-sampling performed: %s', Counter(
131+
y_resampled))
132132

133133
return X_resampled, y_resampled

‎imblearn/under_sampling/condensed_nearest_neighbour.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -196,8 +196,8 @@ def _sample(self, X, y):
196196
X_resampled = np.concatenate((X_resampled, sel_x), axis=0)
197197
y_resampled = np.concatenate((y_resampled, sel_y), axis=0)
198198

199-
self.logger.info('Under-sampling performed: {}'.format(Counter(
200-
y_resampled)))
199+
self.logger.info('Under-sampling performed: %s', Counter(
200+
y_resampled))
201201

202202
# Check if the indices of the samples selected should be returned too
203203
if self.return_indices:

‎imblearn/under_sampling/edited_nearest_neighbours.py‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -173,8 +173,8 @@ def _sample(self, X, y):
173173
X_resampled = np.concatenate((X_resampled, sel_x), axis=0)
174174
y_resampled = np.concatenate((y_resampled, sel_y), axis=0)
175175

176-
self.logger.info("Under-sampling performed: {}".format(Counter(
177-
y_resampled)))
176+
self.logger.info('Under-sampling performed: %s', Counter(
177+
y_resampled))
178178

179179
# Check if the indices of the samples selected should be returned too
180180
if self.return_indices:
@@ -326,7 +326,7 @@ def _sample(self, X, y):
326326

327327
for n_iter in range(self.max_iter):
328328

329-
self.logger.debug('Apply ENN iteration #{}'.format(n_iter + 1))
329+
self.logger.debug('Apply ENN iteration #%s', n_iter + 1)
330330

331331
prev_len = y_.shape[0]
332332
if self.return_indices:
@@ -338,7 +338,7 @@ def _sample(self, X, y):
338338
if prev_len == y_.shape[0]:
339339
break
340340

341-
self.logger.info("Under-sampling performed: {}".format(Counter(y_)))
341+
self.logger.info('Under-sampling performed: %s', Counter(y_))
342342

343343
X_resampled, y_resampled = X_, y_
344344

‎imblearn/under_sampling/instance_hardness_threshold.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -188,8 +188,8 @@ def _sample(self, X, y):
188188
X_resampled = X[mask]
189189
y_resampled = y[mask]
190190

191-
self.logger.info('Under-sampling performed: {}'.format(Counter(
192-
y_resampled)))
191+
self.logger.info('Under-sampling performed: %s', Counter(
192+
y_resampled))
193193

194194
# If we need to offer support for the indices
195195
if self.return_indices:

0 commit comments

Comments
 (0)