def _get_samples(self,
read_article_ids,
unread_article_ids,
p_synthetic_samples = 300,
p_majority_samples = 500,
k = 5):
'''
read_article_ids : Set
unread_article_ids : Set
p_synthetic_samples : Percentage of snythetic samples, 300 for 300%
If None no are created
p_majority_samples : Size of majority sample = p_majority_samples/n_minority_sample,
500 for 500%
If None under sampling ist not done
k : neighbourhood for k nearest neighbour, standard 5
Returns
-------
array-like full vector samples, shape = [n_features, n_samples]
array-like marks, shape = [n_samples]
'''
#Under-sample unread ids
if p_majority_samples is not None:
unread_article_ids = Set(sample(unread_article_ids,
min(p_majority_samples/100 * len(read_article_ids),
len(unread_article_ids))
)
)
#Create unread article vectors
unread_marks = numpy.empty(len(unread_article_ids))
unread_marks.fill(UserModelSVM.UNREAD)
unread_articles = numpy.empty(shape=(len(unread_article_ids),
self.num_features_))
for i, article in enumerate(Article.objects(id__in = unread_article_ids)):
try:
article_features_as_full_vec = self.get_features(article)
unread_articles[i,:] = article_features_as_full_vec[:]
except AttributeError as e:
logger.error("Article %s does not have attribute: %s."
% (article.id, e))
#Create read article vectors
read_marks = numpy.empty(len(read_article_ids))
read_marks.fill(UserModelSVM.READ)
read_articles = numpy.empty(shape=(len(read_article_ids),
self.num_features_))
for i, article in enumerate(Article.objects(id__in = read_article_ids)):
try:
article_features_as_full_vec = self.get_features(article)
read_articles[i,:] = article_features_as_full_vec[:]
except AttributeError as e:
logger.error("Article %s does not have attribute: %s."
% (article.id, e))
#SMOTE sample minorities
#synthetic_read_articles = SMOTE(read_articles, p_synthetic_samples, k)
#borderlineSMOTE sample minorites if p_synthetic_samples not None
X = numpy.concatenate((read_articles, unread_articles))
self._calculate_mean_and_std_deviation(X)
X = self._normalize(X)
y = numpy.concatenate((read_marks, unread_marks))
if p_synthetic_samples is None:
return X, y
else:
new_read_articles, synthetic_read_articles, danger_read_articles = borderlineSMOTE(X = X,
y = y,
minority_target = UserModelSVM.READ,
N = p_synthetic_samples, k = k)
#Create synthetic read samples
synthetic_marks = numpy.zeros(len(synthetic_read_articles))
synthetic_marks.fill(UserModelSVM.READ)
read_marks = numpy.empty(len(new_read_articles))
read_marks.fill(UserModelSVM.READ)
danger_read_marks = numpy.empty(len(danger_read_articles))
danger_read_marks.fill(UserModelSVM.READ)
logger.info("Use %d read, %d unread, %d danger reads and %d synthetic samples." %
(len(read_marks), len(unread_marks),
len(danger_read_marks), len(synthetic_marks)))
return (numpy.concatenate((new_read_articles,
synthetic_read_articles,
danger_read_articles,
unread_articles)),
numpy.concatenate((read_marks,
synthetic_marks,
danger_read_marks,
unread_marks))
)
def get_samples(extractor,
read_article_ids,
unread_article_ids,
p_synthetic_samples = 300,
p_majority_samples = 500,
k = 5):
'''
read_article_ids : Set
unread_article_ids : Set
n_synthetic_samples : Percentage of snythetic samples, 300 for 300%
k : neighbourhood for k nearest neighbour, standard 5
Returns
-------
array-like full vector samples, shape = [n_features, n_samples]
array-like marks, shape = [n_samples]
'''
#Under-sample unread ids
unread_article_ids = Set(sample(unread_article_ids,
min(p_majority_samples/100 * len(read_article_ids),
len(unread_article_ids))
)
)
#Create unread article vectors
unread_marks = np.empty(len(unread_article_ids))
unread_marks.fill(UNREAD)
unread_articles = np.empty(shape=(len(unread_article_ids),
extractor.get_feature_number()))
for i, article in enumerate(Article.objects(id__in = unread_article_ids)):
try:
article_features_as_full_vec = get_features(article, extractor)
unread_articles[i,:] = article_features_as_full_vec[:]
except AttributeError as e:
logger.error("Article %s does not have attribute: %s."
% (article.id, e))
#Create read article vectors
read_marks = np.empty(len(read_article_ids))
read_marks.fill(READ)
read_articles = np.empty(shape=(len(read_article_ids),
extractor.get_feature_number()))
for i, article in enumerate(Article.objects(id__in = read_article_ids)):
try:
article_features_as_full_vec = get_features(article, extractor)
read_articles[i,:] = article_features_as_full_vec[:]
except AttributeError as e:
logger.error("Article %s does not have attribute: %s."
% (article.id, e))
#SMOTE sample minorities
#synthetic_read_articles = SMOTE(read_articles, p_synthetic_samples, k)
#borderlineSMOTE sample minorites
X = np.concatenate((read_articles, unread_articles))
y = np.concatenate((read_marks, unread_marks))
new_read_articles, synthetic_read_articles, danger_read_articles = borderlineSMOTE(X = X,
y = y,
minority_target = READ,
N = p_synthetic_samples, k = k)
#Create synthetic read samples
synthetic_marks = np.zeros(len(synthetic_read_articles))
synthetic_marks.fill(READ)
read_marks = np.empty(len(new_read_articles))
read_marks.fill(READ)
danger_read_marks = np.empty(len(danger_read_articles))
danger_read_marks.fill(READ)
logger.info("Use %d read, %d unread, %d danger reads and %d synthetic samples." %
(len(read_marks), len(unread_marks),
len(danger_read_marks), len(synthetic_marks)))
return (np.concatenate((new_read_articles,
synthetic_read_articles,
danger_read_articles,
unread_articles)),
np.concatenate((read_marks,
synthetic_marks,
danger_read_marks,
unread_marks))
)
