def train(self, read_article_ids=None, unread_article_ids=None):
"""
Trains the DecisionTree Classifier.
read_article_ids should be an iterable over read article ids
unread_article_ids should be an iterable over unread article ids
If one is None it will be loaded from database.
"""
#Load user feedback if needed
if read_article_ids is None:
read_article_ids = set(r.article.id
for r in ReadArticleFeedback.objects(user_id=self.user.id).only("article"))
else:
read_article_ids = set(read_article_ids)
#Get all articles the user did not read.
if unread_article_ids is None:
ranked_article_ids = (a.article.id
for a in RankedArticle.objects(user_id=self.user.id).only("article"))
all_article_ids = set(a.id
for a in Article.objects(id__in=ranked_article_ids).only("id"))
unread_article_ids = all_article_ids - read_article_ids
#convert all article features
all_articles, marks = self._get_samples(read_article_ids,
unread_article_ids,
p_synthetic_samples=self.p_synthetic_samples,
p_majority_samples=self.p_majority_samples)
logger.debug("Learn on %d samples." % len(marks))
self.clf = tree.DecisionTreeClassifier()
self.clf.fit(all_articles, marks)
def get_article_samples(config_):
#Connect to mongo database
logger.info("Connect to database...")
connect(config_['database']['db-name'],
username= config_['database']['user'],
password= config_['database']['passwd'],
port = config_['database']['port'])
#get user
user = User.objects(email=u"*****@*****.**").first()
ranked_article_ids = (a.article.id
for a
in RankedArticle.objects(user_id = user.id).only("article"))
all_article_ids = Set(a.id
for a
in Article.objects(id__in = ranked_article_ids).only("id"))
read_article_ids = Set(a.article.id
for a
in ReadArticleFeedback.objects(user_id = user.id).only("article"))
unread_article_ids = all_article_ids - read_article_ids
#sample test articles
X, y = get_samples(extractor, read_article_ids, unread_article_ids)
return X, y
def train(self, read_article_ids=None, unread_article_ids=None):
"""
Trains the Bayes Classifier.
read_article_ids should be an iterable over read article ids
unread_article_ids should be an iterable over unread article ids
If one is None it will be loaded from database.
"""
#Load user feedback if needed
if read_article_ids is None:
read_article_ids = set(r.article.id for r
in ReadArticleFeedback.objects(user_id=self.user.id).only("article"))
else:
read_article_ids = set(read_article_ids)
logger.info("Use %d read articles for learning." % len(read_article_ids))
read_articles = Article.objects(id__in=read_article_ids)
#Get all articles the user did not read.
if unread_article_ids is None:
ranked_article_ids = (a.article.id for a in RankedArticle.objects(user_id=self.user.id).only("article"))
all_article_ids = set(a.id for a in Article.objects(id__in=ranked_article_ids).only("id"))
unread_article_ids = all_article_ids - read_article_ids
#undersample unreads
logger.info("Use %d unread articles for learning." % (len(unread_article_ids)))
unread_articles = Article.objects(id__in=unread_article_ids)
#convert all article features
all_articles = UserModelBayes.AllArticles(read_articles, unread_articles, self.get_features)
self.clf.fit(np.array(list(all_articles)), np.array(list(all_articles.get_marks())))
def get_top_articles(self, date, min_rating):
'''
Returns iterator to articles from date and with a rating bigger than
min_rating.
'''
#get all articles from specific date
articles_from_date = Article.objects(date__gte = date.date(),
date__lt = date.date() + timedelta(days=1))
#get all ranked article form loaded articles
return [a.article for a in RankedArticle.objects(user_id = self.mongodb_user.id,
rating__gte = min_rating,
article__in = articles_from_date)]
def train(self, read_article_ids = None, unread_article_ids = None):
'''
Trains the several SVM and Naive Bayes Classifiers.
read_article_ids should be an iterable over read article ids
unread_article_ids should be an iterable over unread article ids
If one is None it will be loaded from database.
'''
#Load user feedback if needed
if read_article_ids is None:
read_article_ids = Set(r.article.id
for r
in ReadArticleFeedback.objects(user_id = self.user.id).only("article"))
else:
read_article_ids = Set(read_article_ids)
#Get all articles the user did not read.
if unread_article_ids is None:
ranked_article_ids = (a.article.id
for a
in RankedArticle.objects(user_id = self.user.id).only("article"))
all_article_ids = Set(a.id
for a
in Article.objects(id__in = ranked_article_ids).only("id"))
unread_article_ids = all_article_ids - read_article_ids
classifiers = [lambda: svm.SVC(kernel='rbf'),
lambda: svm.SVC(kernel='rbf'),
lambda: svm.SVC(kernel='rbf'),
lambda: svm.SVC(kernel='rbf'),
lambda: svm.SVC(kernel='rbf'),
GaussianNB,
GaussianNB,
GaussianNB,
GaussianNB]
parameters = [#SVM
{'read_article_ids': read_article_ids,
'unread_article_ids': unread_article_ids,
'p_synthetic_samples': 100,
'p_majority_samples': 200,
'k': 10},
{'read_article_ids': read_article_ids,
'unread_article_ids': unread_article_ids,
'p_synthetic_samples': 200,
'p_majority_samples': 300,
'k': 10},
{'read_article_ids': read_article_ids,
'unread_article_ids': unread_article_ids,
'p_synthetic_samples': 300,
'p_majority_samples': 400,
'k': 10},
{'read_article_ids': read_article_ids,
'unread_article_ids': unread_article_ids,
'p_synthetic_samples': 400,
'p_majority_samples': 500,
'k': 10},
{'read_article_ids': read_article_ids,
'unread_article_ids': unread_article_ids,
'p_synthetic_samples': 500,
'p_majority_samples': 600,
'k': 10},
#Naive Bayes
{'read_article_ids': read_article_ids,
'unread_article_ids': unread_article_ids,
'p_synthetic_samples': 100,
'p_majority_samples': 100,
'k': 10},
{'read_article_ids': read_article_ids,
'unread_article_ids': unread_article_ids,
'p_synthetic_samples': 100,
'p_majority_samples': 200,
'k': 10},
{'read_article_ids': read_article_ids,
'unread_article_ids': unread_article_ids,
'p_synthetic_samples': 300,
'p_majority_samples': 500,
'k': 10},
{'read_article_ids': read_article_ids,
'unread_article_ids': unread_article_ids,
'p_synthetic_samples': 600,
'p_majority_samples': 600,
'k': 10}]
self._call_classifiers(classifiers, parameters)
username=config_["database"]["user"],
password=config_["database"]["passwd"],
port=config_["database"]["port"],
)
# Load feature extractor
# feature_extractor = EsaFeatureExtractor(prefix = config_['prefix'])
# feature_extractor = TfidfFeatureExtractor(prefix = config_['prefix'])
# feature_extractor = LdaFeatureExtractor(prefix = config_['prefix'])
# feature_extractor = LdaBowFeatureExtractor(prefix = config_['prefix'])
feature_extractor = cEsaFeatureExtractor(prefix=config_["prefix"])
# get user
user = User.objects(email=u"*****@*****.**").first()
ranked_article_ids = (a.article.id for a in RankedArticle.objects(user_id=user.id).only("article"))
all_article_ids = set(a.id for a in Article.objects(id__in=ranked_article_ids).only("id"))
read_article_ids = set(a.article.id for a in ReadArticleFeedback.objects(user_id=user.id).only("article"))
unread_article_ids = all_article_ids - read_article_ids
for p_synthetic in xrange(100, 700, 100):
for p_majority in xrange(100, 700, 100):
logger.info("Synthetic over-sampling %d and majority undersampling %d" % (p_synthetic, p_majority))
# run test N_ITERATIONS
precisions_read = np.zeros((N_ITERATIONS))
recalls_read = np.zeros((N_ITERATIONS))
f1_scores_read = np.zeros((N_ITERATIONS))
password= config_['database']['passwd'],
port = config_['database']['port'])
#Load feature extractor
#feature_extractor = EsaFeatureExtractor(prefix = config_['prefix'])
#feature_extractor = TfidfFeatureExtractor(prefix = config_['prefix'])
#feature_extractor = LdaFeatureExtractor(prefix = config_['prefix'])
#feature_extractor = LdaBowFeatureExtractor(prefix = config_['prefix'])
feature_extractor = cEsaFeatureExtractor(prefix = config_['prefix'])
#get user
user = User.objects(email=u"*****@*****.**").first()
ranked_article_ids = (a.article.id
for a
in RankedArticle.objects(user_id = user.id).only("article"))
all_article_ids = Set(a.id
for a
in Article.objects(id__in = ranked_article_ids).only("id"))
read_article_ids = Set(a.article.id
for a
in ReadArticleFeedback.objects(user_id = user.id).only("article"))
unread_article_ids = all_article_ids - read_article_ids
for p_synthetic in xrange(100, 700, 100):
for p_majority in xrange(100, 700, 100):
logger.info("Synthetic over-sampling %d and majority undersampling %d" %
(p_synthetic, p_majority))
def test_constructor_with_file_wikicorpus(self):
#load tf-idf model
tfidf_model = tfidfmodel.TfidfModel.load("/media/sdc1/test_dump/result/test_tfidf.model")
extractor = TfidfFeatureExtractor("/media/sdc1/test_dump/result/test")
#load tf-idf corpus
tfidf_corpus = MmCorpus('/media/sdc1/test_dump/result/test_tfidf_corpus.mm')
#load lda corpus
#lda_corpus = MmCorpus('/media/sdc1/test_dump/result/test_lda_corpus.mm')
#load dictionary
id2token = Dictionary.load("/media/sdc1/test_dump/result/test_wordids.dict")
#load article titles
document_titles = DocumentTitles.load("/media/sdc1/test_dump/result/test_articles.txt")
#Connect to mongo database
connect(self.config_['database']['db-name'],
username= self.config_['database']['user'],
password= self.config_['database']['passwd'],
port = self.config_['database']['port'])
#Load articles as test corpus
user = User.objects(email=u"*****@*****.**").first()
ranked_article_ids = (a.article.id
for a
in RankedArticle.objects(user_id = user.id).only("article"))
all_article_ids = Set(a.id
for a
in Article.objects(id__in = ranked_article_ids).only("id"))
read_article_ids = Set(a.article.id
for a
in ReadArticleFeedback.objects(user_id = user.id).only("article"))
unread_article_ids = all_article_ids - read_article_ids
#sample test articles
X, y = get_samples(extractor, read_article_ids, unread_article_ids)
s,f = X.shape
logger.debug("Traning with %d samples, %d features, %d marks" %
(s,f, len(y)))
#train esa model
esa_model = CosineEsaModel(tfidf_corpus,
document_titles = document_titles,
test_corpus = X,
test_corpus_targets = y,
num_test_corpus = len(y),
num_best_features = 15,
num_features = len(id2token))
print esa_model
esa_model.save('/media/sdc1/test_dump/result/test_cesa.model')
tmp_esa = CosineEsaModel.load('/media/sdc1/test_dump/result/test_cesa.model')
print tmp_esa
