def init_hierarchical_model(class_ids):
score = [artm.PerplexityScore(name='perplexity_words', class_ids=['body']),
artm.PerplexityScore(name='perplexity_bigrams', class_ids=['bigrams'])]
top_tokens = [artm.TopTokensScore(name='top_words', num_tokens=15, class_id='body'),
artm.TopTokensScore(name='top_bigrams', num_tokens=10, class_id='bigrams')]
sparsity = [artm.SparsityThetaScore(name='sparsity_theta', eps=1e-6),
artm.SparsityPhiScore(name='sparsity_phi_words', class_id='words', eps=1e-6),
artm.SparsityPhiScore(name='sparsity_phi_bigrams', class_id='bigrams', eps=1e-6)]
regularizers = [artm.DecorrelatorPhiRegularizer(tau=0, class_ids=['body'], name='decorr_words'),
artm.DecorrelatorPhiRegularizer(tau=0, class_ids=['bigram'], name='decorr_bigrams'),
artm.DecorrelatorPhiRegularizer(tau=0, class_ids=['categories'], name='decorr_categories'),
artm.SmoothSparseThetaRegularizer(tau=0, name='sparsity_theta'),
artm.SmoothSparsePhiRegularizer(tau=0, class_ids=['body'], name='sparsity_words'),
artm.SmoothSparsePhiRegularizer(tau=0, class_ids=['bigram'], name='sparsity_bigrams')]
hmodel = artm.hARTM(class_ids=class_ids,
cache_theta=True,
reuse_theta=True,
scores=score + top_tokens + sparsity,
regularizers=regularizers,
theta_columns_naming='title')
return hmodel
def add_complex_scores_to_model(artm_model,
n_top_tokens,
p_mass_threshold,
common_topics,
subject_topics,
class_name,
_debug_print=False):
if _debug_print:
print '[{}] adding scores'.format(datetime.now())
# subject
artm_model.scores.add(
artm.PerplexityScore(name='perplexity_score_subject',
dictionary=dictionary,
topic_names=subject_topics))
artm_model.scores.add(
artm.SparsityPhiScore(name='ss_phi_score_subject',
class_id=class_name,
topic_names=subject_topics))
artm_model.scores.add(
artm.SparsityThetaScore(name='ss_theta_score_subject',
topic_names=subject_topics))
artm_model.scores.add(
artm.TopicKernelScore(name='topic_kernel_score_subject',
class_id=class_name,
topic_names=subject_topics,
probability_mass_threshold=p_mass_threshold))
artm_model.scores.add(
artm.TopTokensScore(name='top_tokens_score_subject',
class_id=class_name,
topic_names=subject_topics,
num_tokens=n_top_tokens))
# common
artm_model.scores.add(
artm.PerplexityScore(name='perplexity_score_common',
dictionary=dictionary,
topic_names=common_topics))
artm_model.scores.add(
artm.SparsityPhiScore(name='ss_phi_score_common',
class_id=class_name,
topic_names=common_topics))
artm_model.scores.add(
artm.SparsityThetaScore(name='ss_theta_score_common',
topic_names=common_topics))
artm_model.scores.add(
artm.TopicKernelScore(name='topic_kernel_score_common',
class_id=class_name,
topic_names=common_topics,
probability_mass_threshold=p_mass_threshold))
artm_model.scores.add(
artm.TopTokensScore(name='top_tokens_score_common',
class_id=class_name,
topic_names=common_topics,
num_tokens=n_top_tokens))
def experiment(filename, tau_phi, tau_theta):
batch_vectorizer = artm.BatchVectorizer(data_path=filename, data_format='vowpal_wabbit',
target_folder='batches')
dictionary = batch_vectorizer.dictionary
topic_num = 30
tokens_num = 100
print("ARTM training")
topic_names = ['topic_{}'.format(i) for i in range(topic_num)]
model_artm = artm.ARTM(topic_names=topic_names, dictionary=dictionary, cache_theta=True)
model_plsa = artm.ARTM(topic_names=topic_names, cache_theta=True,
scores=[artm.PerplexityScore(name='PerplexityScore', dictionary=dictionary)])
model_lda = artm.LDA(num_topics=topic_num)
model_artm.scores.add(artm.PerplexityScore(name='perplexity_score', dictionary=dictionary))
model_artm.scores.add(artm.SparsityPhiScore(name='sparsity_phi_score'))
model_artm.scores.add(artm.SparsityThetaScore(name='sparsity_theta_score'))
model_artm.scores.add(artm.TopTokensScore(name='top_tokens_score', num_tokens=tokens_num))
model_artm.scores.add(artm.TopicKernelScore(name='topic_kernel_score', probability_mass_threshold=0.3))
model_artm.scores.add(artm.BackgroundTokensRatioScore(name='background_tokens_ratio_score'))
model_artm.scores.add(artm.ClassPrecisionScore(name='class_precision_score'))
model_artm.scores.add(artm.TopicMassPhiScore(name='topic_mass_phi_score'))
model_plsa.scores.add(artm.PerplexityScore(name='perplexity_score', dictionary=dictionary))
model_plsa.scores.add(artm.SparsityPhiScore(name='sparsity_phi_score'))
model_plsa.scores.add(artm.SparsityThetaScore(name='sparsity_theta_score'))
model_plsa.scores.add(artm.TopTokensScore(name='top_tokens_score'))
model_plsa.scores.add(artm.TopicKernelScore(name='topic_kernel_score', probability_mass_threshold=0.3))
model_plsa.scores.add(artm.BackgroundTokensRatioScore(name='background_tokens_ratio_score'))
model_plsa.scores.add(artm.ClassPrecisionScore(name='class_precision_score'))
model_plsa.scores.add(artm.TopicMassPhiScore(name='topic_mass_phi_score'))
model_artm.regularizers.add(artm.SmoothSparsePhiRegularizer(name='sparse_phi_regularizer'))
model_artm.regularizers.add(artm.SmoothSparseThetaRegularizer(name='sparse_theta_regularizer'))
model_artm.regularizers.add(artm.DecorrelatorPhiRegularizer(name='decorrelator_phi_regularizer'))
model_artm.regularizers['sparse_phi_regularizer'].tau = tau_phi
model_artm.regularizers['sparse_theta_regularizer'].tau = tau_theta
model_artm.regularizers['decorrelator_phi_regularizer'].tau = 1e+3
model_plsa.initialize(dictionary=dictionary)
model_artm.initialize(dictionary=dictionary)
model_lda.initialize(dictionary=dictionary)
passes = 100
model_plsa.fit_offline(batch_vectorizer=batch_vectorizer, num_collection_passes=passes)
model_artm.fit_offline(batch_vectorizer=batch_vectorizer, num_collection_passes=passes)
model_lda.fit_offline(batch_vectorizer=batch_vectorizer, num_collection_passes=passes)
print_measures(model_plsa, model_artm, model_lda)
def set_scores(self):
self.model.scores.add(
artm.PerplexityScore(name='PerplexityScore',
dictionary=self.dictionary))
self.model.scores.add(
artm.SparsityPhiScore(name='SparsityPhiScore',
class_id='@default_class',
topic_names=self.specific))
self.model.scores.add(
artm.SparsityThetaScore(name='SparsityThetaScore',
topic_names=self.specific))
# Fraction of background words in the whole collection
self.model.scores.add(
artm.BackgroundTokensRatioScore(name='BackgroundTokensRatioScore',
class_id='@default_class'))
# Kernel characteristics
self.model.scores.add(
artm.TopicKernelScore(name='TopicKernelScore',
class_id='@default_class',
topic_names=self.specific,
probability_mass_threshold=0.5,
dictionary=self.dictionary))
# Looking at top tokens
self.model.scores.add(
artm.TopTokensScore(name='TopTokensScore',
class_id='@default_class',
num_tokens=100))
def define_model(n_topics: int, dictionary: artm.Dictionary,
sparse_theta: float, sparse_phi: float,
decorrelator_phi: float) -> artm.artm_model.ARTM:
"""
Define the ARTM model.
:param n_topics: number of topics.
:param dictionary: batch vectorizer dictionary.
:param sparse_theta: sparse theta parameter.
:param sparse_phi: sparse phi Parameter.
:param decorrelator_phi: decorellator phi Parameter.
:return: ARTM model.
"""
print("Defining the model.")
topic_names = ["topic_{}".format(i) for i in range(1, n_topics + 1)]
model_artm = artm.ARTM(
topic_names=topic_names,
cache_theta=True,
scores=[
artm.PerplexityScore(name="PerplexityScore",
dictionary=dictionary),
artm.SparsityPhiScore(name="SparsityPhiScore"),
artm.SparsityThetaScore(name="SparsityThetaScore"),
artm.TopicKernelScore(name="TopicKernelScore",
probability_mass_threshold=0.3),
artm.TopTokensScore(name="TopTokensScore", num_tokens=15)
],
regularizers=[
artm.SmoothSparseThetaRegularizer(name="SparseTheta",
tau=sparse_theta),
artm.SmoothSparsePhiRegularizer(name="SparsePhi", tau=sparse_phi),
artm.DecorrelatorPhiRegularizer(name="DecorrelatorPhi",
tau=decorrelator_phi)
])
return model_artm
def cluster_artm(text):
bach_vectorizer = artm.BatchVectorizer(data_path=text,
data_format='vowpal_wabbit', target_folder='batch_small',
batch_size=20)
T = 10 # количество тем
topic_names = ["sbj" + str(i) for i in range(T - 1)] + ["bcg"]
model_artm = artm.ARTM(num_topics=T, topic_names=topic_names, reuse_theta=True,
num_document_passes=1)
np.random.seed(1)
dictionary = artm.Dictionary()
dictionary.gather(data_path=bach_vectorizer.data_path)
model_artm.initialize(dictionary)
model_artm.scores.add(artm.TopTokensScore(name='metric1', num_tokens=15))
model_artm.regularizers.add(artm.SmoothSparsePhiRegularizer(name='smoothing', dictionary=dictionary,
topic_names='bcg', tau=1e5))
model_artm.fit_offline(batch_vectorizer=bach_vectorizer, num_collection_passes=6)
model_artm.regularizers.add(artm.SmoothSparsePhiRegularizer(name='stimulates',
dictionary=dictionary,
topic_names=["sbj" + str(i) for i in range(0, 29)],
tau=-1e5))
model_artm.fit_offline(batch_vectorizer=bach_vectorizer, num_collection_passes=6)
for topic_name in model_artm.topic_names:
with open('cluster_log_artm.txt', 'a') as f_in:
f_in.write(topic_name + ':')
for word in model_artm.score_tracker["metric1"].last_tokens[topic_name]:
f_in.write(word + ' ')
f_in.write('\n')
def create_and_learn_ARTM_decorPhi_modal(name="",
topic_number=750,
num_collection_passes=1,
weigths=[1., 1., 1., 1.],
decorTau=1.0):
batch_vectorizer_train = None
batch_vectorizer_train = artm.BatchVectorizer(data_path='./' + name,
data_format='vowpal_wabbit',
target_folder='folder' +
name)
dictionary = artm.Dictionary()
dictionary.gather(data_path=batch_vectorizer_train.data_path)
topic_names = ['topic_{}'.format(i) for i in range(topic_number)]
model = artm.ARTM(topic_names=topic_names,
class_ids={
'@text': weigths[0],
'@first': weigths[1],
'@second': weigths[2],
'@third': weigths[3]
},
cache_theta=True,
theta_columns_naming='title',
scores=[
artm.PerplexityScore(name='PerplexityScore',
dictionary=dictionary)
])
model.regularizers.add(
artm.DecorrelatorPhiRegularizer(
name='DecorrelatorPhi_modals',
tau=decorTau,
class_ids=['@first', '@second', '@third']))
model.initialize(dictionary=dictionary)
model.scores.add(artm.SparsityPhiScore(name='SparsityPhiScore'))
model.scores.add(artm.SparsityThetaScore(name='SparsityThetaScore'))
model.scores.add(
artm.TopicKernelScore(name='TopicKernelScore',
class_id='@text',
probability_mass_threshold=0.3))
model.scores.add(
artm.TopTokensScore(name='TopTokensScore',
num_tokens=6,
class_id='@text'))
model.scores.add(
artm.SparsityPhiScore(name='sparsity_phi_score', class_id='@third'))
model.num_document_passes = 1
model.fit_offline(batch_vectorizer=batch_vectorizer_train,
num_collection_passes=num_collection_passes)
theta_train = model.transform(batch_vectorizer=batch_vectorizer_train)
return model, theta_train
def _get_corpus_model(self,
corpus_vector_spaced,
clustering_method='artm'):
if 'gensim' == clustering_method:
return self._get_model_LSI(corpus_vector_spaced)
elif 'sklearn' == clustering_method:
return self._get_model_LDA(corpus_vector_spaced)
elif 'artm' == clustering_method:
batch_vectorizer = corpus_vector_spaced['batch_vectorizer']
dictionary = corpus_vector_spaced['dictionary']
topic_names = [
'topic_{}'.format(i) for i in range(self.num_of_clusters)
]
model_artm = artm.ARTM(
topic_names=topic_names,
cache_theta=True,
scores=[
artm.PerplexityScore(name='PerplexityScore',
dictionary=dictionary)
],
regularizers=[
artm.SmoothSparseThetaRegularizer(name='SparseTheta',
tau=-0.15)
])
model_artm.scores.add(
artm.SparsityPhiScore(name='SparsityPhiScore'))
model_artm.scores.add(
artm.SparsityThetaScore(name='SparsityThetaScore'))
model_artm.scores.add(
artm.TopicKernelScore(name='TopicKernelScore',
probability_mass_threshold=0.3))
model_artm.scores.add(artm.TopTokensScore(name='TopTokensScore',
num_tokens=10),
overwrite=True)
model_artm.regularizers.add(
artm.SmoothSparsePhiRegularizer(name='SparsePhi', tau=-0.1))
model_artm.regularizers['SparseTheta'].tau = -0.2
model_artm.regularizers.add(
artm.DecorrelatorPhiRegularizer(name='DecorrelatorPhi',
tau=1.5e+5))
model_artm.num_document_passes = 1
model_artm.initialize(dictionary)
model_artm.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=30)
return model_artm.transform(batch_vectorizer=batch_vectorizer).T
def create_thematic_model(checked_list, num_topics, num_tokens, phi_tau,
theta_tau, decorr_tau):
""" Create a thematic model """
gluing_bag_of_words(checked_list)
batch_vectorizer = artm.BatchVectorizer(data_path=COLLECTION_PATH,
data_format='vowpal_wabbit',
target_folder=TARGET_FOLDER,
batch_size=len(checked_list))
dictionary = artm.Dictionary(data_path=TARGET_FOLDER)
model = artm.ARTM(
num_topics=num_topics,
num_document_passes=len(checked_list),
dictionary=dictionary,
regularizers=[
artm.SmoothSparsePhiRegularizer(name='sparse_phi_regularizer',
tau=phi_tau),
artm.SmoothSparseThetaRegularizer(name='sparse_theta_regularizer',
tau=theta_tau),
artm.DecorrelatorPhiRegularizer(
name='decorrelator_phi_regularizer', tau=decorr_tau),
],
scores=[
artm.PerplexityScore(name='perplexity_score',
dictionary=dictionary),
artm.SparsityPhiScore(name='sparsity_phi_score'),
artm.SparsityThetaScore(name='sparsity_theta_score'),
artm.TopTokensScore(name='top_tokens_score', num_tokens=num_tokens)
])
model.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=len(checked_list))
top_tokens = model.score_tracker['top_tokens_score']
topic_dictionary = OrderedDict()
for topic_name in model.topic_names:
list_name = []
for (token, weight) in zip(top_tokens.last_tokens[topic_name],
top_tokens.last_weights[topic_name]):
list_name.append(token + '-' + str(round(weight, 3)))
topic_dictionary[str(topic_name)] = list_name
return model.score_tracker[
'perplexity_score'].last_value, model.score_tracker[
'sparsity_phi_score'].last_value, model.score_tracker[
'sparsity_theta_score'].last_value, topic_dictionary
def add_scores_to_model(current_dictionary, artm_model, n_top_tokens,
p_mass_threshold):
artm_model.scores.add(
artm.PerplexityScore(name='perplexity_score',
use_unigram_document_model=False,
dictionary=current_dictionary))
artm_model.scores.add(
artm.SparsityPhiScore(name='sparsity_phi_score', class_id='ngramm'))
artm_model.scores.add(artm.SparsityThetaScore(name='sparsity_theta_score'))
artm_model.scores.add(
artm.TopicKernelScore(name='topic_kernel_score',
class_id='ngramm',
probability_mass_threshold=p_mass_threshold))
artm_model.scores.add(
artm.TopTokensScore(name='top_tokens_score',
class_id='ngramm',
num_tokens=n_top_tokens))
def create_and_learn_PLSA(name="", topic_number=750, num_collection_passes=1):
batch_vectorizer_train = None
batch_vectorizer_train = artm.BatchVectorizer(data_path='./' + name,
data_format='vowpal_wabbit',
target_folder='folder' +
name)
dictionary = artm.Dictionary()
dictionary.gather(data_path=batch_vectorizer_train.data_path)
topic_names = ['topic_{}'.format(i) for i in range(topic_number)]
model_plsa = artm.ARTM(topic_names=topic_names,
class_ids={
'@text': 1.0,
'@first': 1.0,
'@second': 1.0,
'@third': 1.0
},
cache_theta=True,
theta_columns_naming='title',
scores=[
artm.PerplexityScore(name='PerplexityScore',
dictionary=dictionary)
])
model_plsa.initialize(dictionary=dictionary)
model_plsa.scores.add(artm.SparsityPhiScore(name='SparsityPhiScore'))
model_plsa.scores.add(artm.SparsityThetaScore(name='SparsityThetaScore'))
model_plsa.scores.add(
artm.TopicKernelScore(name='TopicKernelScore',
class_id='@text',
probability_mass_threshold=0.3))
model_plsa.scores.add(
artm.TopTokensScore(name='TopTokensScore',
num_tokens=6,
class_id='@text'))
model_plsa.num_document_passes = 1
model_plsa.fit_offline(batch_vectorizer=batch_vectorizer_train,
num_collection_passes=num_collection_passes)
theta_train = model_plsa.transform(batch_vectorizer=batch_vectorizer_train)
return model_plsa, theta_train
def pipeline_plsa_bigartm(lines,
TOPIC_NUMBER,
ngram_range,
topnwords,
LOGS_DATA_PATH="plsa.txt",
TARGET_FOLDER="plsa"):
make_file(lines, ngram_range, LOGS_DATA_PATH)
batch_vectorizer = artm.BatchVectorizer(data_path=LOGS_DATA_PATH,
data_format='vowpal_wabbit',
target_folder=TARGET_FOLDER)
model_artm = artm.ARTM(num_topics=TOPIC_NUMBER, cache_theta=True)
model_artm.initialize(dictionary=batch_vectorizer.dictionary)
model_artm.regularizers.add(
artm.SmoothSparsePhiRegularizer(name='SparsePhi', tau=0.05))
model_artm.regularizers.add(
artm.DecorrelatorPhiRegularizer(name='DecorrelatorPhi', tau=1.5e+5))
model_artm.regularizers.add(
artm.SmoothSparseThetaRegularizer(name='SparseTheta', tau=-0.01))
model_artm.scores.add(artm.SparsityPhiScore(name='SparsityPhiScore'))
model_artm.scores.add(artm.SparsityThetaScore(name='SparsityThetaScore'))
model_artm.scores.add(artm.TopTokensScore(name='TopTokensScore',
num_tokens=topnwords),
overwrite=True)
model_artm.scores.add(
artm.PerplexityScore(name='PerplexityScore',
dictionary=batch_vectorizer.dictionary))
model_artm.num_document_passes = 2
model_artm.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=15)
topic_names = {}
for topic_name in model_artm.topic_names:
topic_names[topic_name] = model_artm.score_tracker[
'TopTokensScore'].last_tokens[topic_name]
#return label_after_bigarm(model_artm), topic_names
return "nothing, sorry", topic_names
def create_model_with_background(dictionary, num_tokens, num_document_passes):
sm_phi_tau = 0.0001 * 1e-4
sp_phi_tau = -0.0001 * 1e-4
decor_phi_tau = 1
specific_topics = ['topic {}'.format(i) for i in range(1, 20)]
topic_names = specific_topics + ["background"]
scores = [
artm.PerplexityScore(name='PerplexityScore', dictionary=dictionary),
artm.TopTokensScore(
name='TopTokensScore', num_tokens=10, class_id='plain_text'
), # web version of Palmetto works only with <= 10 tokens
artm.SparsityPhiScore(name='SparsityPhiScore'),
artm.SparsityThetaScore(name='SparsityThetaScore'),
artm.TopicKernelScore(name='TopicKernelScore',
probability_mass_threshold=0.3,
class_id='plain_text')
]
model = artm.ARTM(topic_names=specific_topics + ["background"],
regularizers=[],
cache_theta=True,
scores=scores,
class_ids={'plain_text': 1.0})
model.regularizers.add(
artm.SmoothSparsePhiRegularizer(name='SparsePhi',
tau=-sp_phi_tau,
topic_names=specific_topics))
model.regularizers.add(
artm.SmoothSparsePhiRegularizer(name='SmoothPhi',
tau=sm_phi_tau,
topic_names=["background"]))
# model.regularizers.add(artm.DecorrelatorPhiRegularizer(name='DecorrelatorPhi', tau=decor_phi_tau))
model.initialize(dictionary=dictionary)
model.num_document_passes = num_document_passes
return model
def create_model(dictionary, num_tokens, num_document_passes):
tn = ['topic {}'.format(i) for i in range(1, 20)]
scores = [
artm.PerplexityScore(name='PerplexityScore', dictionary=dictionary),
artm.TopTokensScore(
name='TopTokensScore', num_tokens=10
), # web version of Palmetto works only with <= 10 tokens
artm.SparsityPhiScore(name='SparsityPhiScore'),
artm.SparsityThetaScore(name='SparsityThetaScore')
]
model = artm.ARTM(topic_names=tn,
regularizers=[],
cache_theta=True,
scores=scores)
model.initialize(dictionary=dictionary)
model.num_document_passes = num_document_passes
return model
def add_scores_to_model(artm_model,
dictionary,
n_top_tokens,
p_mass_threshold,
class_name,
_debug_print=False):
if _debug_print:
print '[{}] adding scores'.format(datetime.now())
artm_model.scores.add(
artm.PerplexityScore(name='perplexity_score', dictionary=dictionary))
artm_model.scores.add(
artm.SparsityPhiScore(name='ss_phi_score', class_id=class_name))
artm_model.scores.add(artm.SparsityThetaScore(name='ss_theta_score'))
artm_model.scores.add(
artm.TopicKernelScore(name='topic_kernel_score',
class_id=class_name,
probability_mass_threshold=p_mass_threshold))
artm_model.scores.add(
artm.TopTokensScore(name='top_tokens_score',
class_id=class_name,
num_tokens=n_top_tokens))
def init_score_tracker(model_artm, my_dictionary, class_id='text'):
model_artm.scores.add(artm.PerplexityScore(name='PerplexityScore',
dictionary=my_dictionary),
overwrite=True)
model_artm.scores.add(artm.SparsityPhiScore(name='SparsityPhiScore',
class_id=class_id),
overwrite=True)
model_artm.scores.add(artm.SparsityThetaScore(name='SparsityThetaScore'),
overwrite=True)
model_artm.scores.add(artm.TopTokensScore(name="top_words",
num_tokens=200,
class_id=class_id),
overwrite=True)
model_artm.scores.add(artm.TopicKernelScore(
name='TopicKernelScore',
class_id=class_id,
probability_mass_threshold=0.6),
overwrite=True)
print('Scores are set!')
COOC_FILE = os.path.join(BASE_DIR, "cooc_tf")
VOCAB_FILE = os.path.join(DATA_DIR, "vocab")
start = time.time()
bv = artm.BatchVectorizer(data_path=BATCHES_DIR, data_format="batches")
dictionary = artm.Dictionary()
dictionary.load(DICTIONARY_FILE)
cooc_dict = artm.Dictionary()
cooc_dict.gather(data_path=BATCHES_DIR,
cooc_file_path=COOC_FILE,
vocab_file_path=VOCAB_FILE,
symmetric_cooc_values=True)
coherence_score = artm.TopTokensScore(name='TopTokensCoherenceScore',
dictionary=cooc_dict,
num_tokens=15)
model_artm = artm.LDA(num_topics=N_TOPICS)
model_artm._internal_model.scores.add(
artm.TopTokensScore(name="top_words", num_tokens=10))
model_artm._internal_model.scores.add(coherence_score)
model_artm._internal_model.scores.add(
artm.PerplexityScore(name='perplexity_score', dictionary=bv.dictionary))
model_artm._internal_model.scores.add(
artm.SparsityPhiScore(name='sparsity_phi_score'))
model_artm._internal_model.scores.add(
artm.SparsityThetaScore(name='sparsity_theta_score'))
model_artm.initialize(dictionary=dictionary)
def train(self):
vocabulary_file = self._prepare_texts_full(
) if self.analyze_full_doc == True else self._prepare_texts_from_summary(
)
target_folder = self._get_bigARTM_dir()
batch_vectorizer = artm.BatchVectorizer(data_path=vocabulary_file,
data_format='vowpal_wabbit',
target_folder=target_folder,
batch_size=100)
dict_path = self._get_dictionary_path()
dict_file = '{}.dict'.format(dict_path)
if os.path.isfile(dict_file):
os.remove(dict_file)
my_dictionary = artm.Dictionary()
my_dictionary.gather(data_path=target_folder,
vocab_file_path=vocabulary_file)
my_dictionary.save(dictionary_path=dict_path)
my_dictionary.load(dictionary_path=dict_file)
T = self.num_of_topics
topic_names = ["sbj" + str(i) for i in range(T - 1)] + ["bcg"]
self.model_artm = artm.ARTM(num_topics=T,
topic_names=topic_names,
class_ids={
"text": 1,
"doc_guid": 1
},
dictionary=my_dictionary,
cache_theta=True)
self.model_artm.initialize(dictionary=my_dictionary)
self.model_artm.scores.add(
artm.TopTokensScore(name="text_words",
num_tokens=15,
class_id="text"))
self.model_artm.scores.add(
artm.TopTokensScore(name="doc_guid_words",
num_tokens=15,
class_id="doc_guid"))
self.model_artm.regularizers.add(
artm.SmoothSparsePhiRegularizer(name='SparsePhi',
tau=1e5,
dictionary=my_dictionary,
class_ids="text",
topic_names="bcg"))
self.model_artm.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=30)
self.model_artm.regularizers.add(
artm.SmoothSparsePhiRegularizer(
name='SparsePhi-1e5',
tau=-1e5,
dictionary=my_dictionary,
class_ids="text",
topic_names=["sbj" + str(i) for i in range(T - 1)]))
self.model_artm.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=15)
self.training_done = True
model_artm.scores.add(
artm.TopicKernelScore(name='TopicKernelScore',
probability_mass_threshold=0.3))
model_artm.regularizers.add(
artm.SmoothSparsePhiRegularizer(name='SparsePhi', tau=-0.1))
model_artm.regularizers.add(
artm.DecorrelatorPhiRegularizer(name='DecorrelatorPhi', tau=1.5e+5))
model_artm.regularizers.add(
artm.TopicSelectionThetaRegularizer(name='TopicSelection', tau=0.25))
model_artm.regularizers['SparsePhi'].tau = -0.5
model_artm.regularizers['SparseTheta'].tau = -0.5
model_artm.regularizers['DecorrelatorPhi'].tau = 1e+5
model_artm.scores.add(artm.TopTokensScore(name='TopTokensScore',
num_tokens=10))
model_artm.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=40)
ex = model_artm.get_theta()
for i, el in enumerate(ex.sum(axis=1)):
if el == 0:
ex = ex.drop('topic_' + str(i), axis=0)
resultARTM = []
for i in ex:
resultARTM.append(np.argmax(ex[i]))
resultLSA = make_lsa_from_text(textArray)
resultTT = make_tt_from_text(textArray)
# 129 total
T = 10
class_priority = {"@default_class": 1, "@ngram_2": 2, "@ngram_3": 6}
model = artm.ARTM(num_topics=T,
topic_names=["sbj" + str(i) for i in range(T)],
class_ids=class_priority)
model.scores.add(
artm.PerplexityScore(name='my_fisrt_perplexity_score',
use_unigram_document_model=False,
dictionary=batch_vectorizer.dictionary))
model.scores.add(
artm.SparsityPhiScore(name='SparsityPhiScore', class_id="@default_class"))
model.scores.add(artm.SparsityThetaScore(name='SparsityThetaScore'))
model.scores.add(
artm.TopTokensScore(name="top_words", num_tokens=15, class_id="@ngram_3"))
model.initialize(batch_vectorizer.dictionary)
model.fit_offline(batch_vectorizer=batch_vectorizer, num_collection_passes=10)
print model.score_tracker['my_fisrt_perplexity_score'].value
print "SparsityPhiScore: " + str(
model.score_tracker["SparsityPhiScore"].last_value)
print "SparsityThetaScore: " + str(
model.score_tracker["SparsityThetaScore"].last_value)
for topic_name in model.topic_names:
print topic_name + ': ',
tokens = model.score_tracker["top_words"].last_tokens
modelPLSA = artm.ARTM(topic_names=['topic_{}'.format(i) for i in xrange(100)],
scores=[
artm.PerplexityScore(
name='PerplexityScore',
use_unigram_document_model=False,
dictionary=batch_vectorizer.dictionary,
class_ids=["text"]),
artm.SparsityPhiScore(name='SparsityPhiScore',
class_id="text"),
artm.SparsityThetaScore(name='SparsityThetaScore'),
artm.TopicKernelScore(name='TopicKernelScore',
probability_mass_threshold=0.3,
class_id="text"),
artm.TopTokensScore(name='TopTokensScore',
num_tokens=100,
class_id="text")
],
cache_theta=True)
modelPLSA.initialize(dictionary=batch_vectorizer.dictionary)
modelPLSA.num_document_passes = 5
modelPLSA.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=30)
print "===========================PLSA PerplexityScore start===================================="
print modelPLSA.score_tracker['PerplexityScore'].value
print "===========================PLSA PerplexityScore end======================================"
def test_func():
# constants
num_tokens = 15
alpha = 0.01
beta = 0.02
num_collection_passes = 15
num_document_passes = 1
num_topics = 15
vocab_size = 6906
num_docs = 3430
zero_eps = 0.001
data_path = os.environ.get('BIGARTM_UNITTEST_DATA')
batches_folder = tempfile.mkdtemp()
try:
batch_vectorizer = artm.BatchVectorizer(data_path=data_path,
data_format='bow_uci',
collection_name='kos',
target_folder=batches_folder)
dictionary = artm.Dictionary()
dictionary.gather(data_path=batch_vectorizer.data_path)
model_artm = artm.ARTM(num_topics=num_topics,
dictionary=dictionary,
cache_theta=True,
reuse_theta=True)
model_artm.regularizers.add(
artm.SmoothSparsePhiRegularizer(name='SparsePhi', tau=beta))
model_artm.regularizers.add(
artm.SmoothSparseThetaRegularizer(name='SparseTheta', tau=alpha))
model_artm.scores.add(
artm.SparsityThetaScore(name='SparsityThetaScore'))
model_artm.scores.add(
artm.PerplexityScore(name='PerplexityScore',
dictionary=dictionary))
model_artm.scores.add(artm.SparsityPhiScore(name='SparsityPhiScore'))
model_artm.scores.add(
artm.TopTokensScore(name='TopTokensScore', num_tokens=num_tokens))
model_lda = artm.LDA(num_topics=num_topics,
alpha=alpha,
beta=beta,
dictionary=dictionary,
cache_theta=True)
model_lda.initialize(dictionary=dictionary)
model_artm.num_document_passes = num_document_passes
model_lda.num_document_passes = num_document_passes
model_artm.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=num_collection_passes)
model_lda.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=num_collection_passes)
for i in range(num_collection_passes):
assert abs(model_artm.score_tracker['SparsityPhiScore'].value[i] -
model_lda.sparsity_phi_value[i]) < zero_eps
for i in range(num_collection_passes):
assert abs(
model_artm.score_tracker['SparsityThetaScore'].value[i] -
model_lda.sparsity_theta_value[i]) < zero_eps
for i in range(num_collection_passes):
assert abs(model_artm.score_tracker['PerplexityScore'].value[i] -
model_lda.perplexity_value[i]) < zero_eps
lda_tt = model_lda.get_top_tokens(num_tokens=num_tokens)
assert len(lda_tt) == num_topics
for i in range(num_topics):
for j in range(num_tokens):
assert model_artm.score_tracker['TopTokensScore'].last_tokens[
model_artm.topic_names[i]][j] == lda_tt[i][j]
lda_tt = model_lda.get_top_tokens(num_tokens=num_tokens,
with_weights=True)
for i in range(num_tokens):
assert abs(model_artm.score_tracker['TopTokensScore'].last_weights[
model_artm.topic_names[0]][i] - lda_tt[0][i][1]) < zero_eps
model_lda.fit_online(batch_vectorizer=batch_vectorizer)
phi = model_lda.phi_
assert phi.shape == (vocab_size, num_topics)
theta = model_lda.get_theta()
assert theta.shape == (num_topics, num_docs)
assert model_lda.library_version.count('.') == 2 # major.minor.patch
model_lda = artm.LDA(num_topics=num_topics,
alpha=alpha,
beta=([0.1] * num_topics),
dictionary=dictionary,
cache_theta=True)
assert model_lda._internal_model.regularizers.size() == num_topics + 1
finally:
shutil.rmtree(batches_folder)
def __init__(self,
dictionary,
class_ids,
tmp_files_path='',
theta_columns_naming='title',
cache_theta = True,
num_levels=None,
level_names=None,
num_topics=None,
topic_names=None,
num_backgrounds=None,
background_names=None,
smooth_background_tau=None,
decorrelate_phi_tau=None,
parent_topics_proportion=None,
spars_psi_tau=None,
smooth_theta_fit=1.0,
num_collection_passes=1,
num_tokens=10):
self.model = artm.hARTM(dictionary=dictionary,
class_ids=class_ids,
theta_columns_naming=theta_columns_naming,
tmp_files_path=tmp_files_path,
cache_theta=cache_theta)
self.level_names = _generate_names(num_levels, level_names, 'level')
topic_names = _generate_names_levels(len(self.level_names), num_topics, topic_names, 'topic')
background_names = _generate_names_levels(len(self.level_names), num_backgrounds, background_names, 'background')
for topic_names_level, background_names_level in zip(topic_names, background_names):
topic_names_level = topic_names_level + background_names_level
level = self.model.add_level(num_topics=len(topic_names_level), topic_names=topic_names_level)
if smooth_background_tau is not None:
for level, background_names_level in zip(self.model, background_names):
level.regularizers.add(artm.SmoothSparsePhiRegularizer('SPhi_back',
tau=smooth_background_tau,
gamma=0,
topic_names=background_names_level))
if decorrelate_phi_tau is not None:
for level in self.model:
level.regularizers.add(artm.DecorrelatorPhiRegularizer('DPhi', tau=decorrelate_phi_tau, gamma=0))
if (parent_topics_proportion is not None) and (spars_psi_tau is not None):
for level, parent_topics_proportion_level in zip(self.model[1:], parent_topics_proportion):
for topic_name, parent_topic_proportion in parent_topics_proportion_level.items():
level.regularizers.add(artm.HierarchySparsingThetaRegularizer(name=f'HSTheta_{topic_name}',
topic_names=topic_name,
tau=spars_psi_tau,
parent_topic_proportion=parent_topic_proportion))
self.smooth_theta_fit = smooth_theta_fit
self.num_collection_passes = num_collection_passes
for level in self.model:
for class_id, weight in class_ids.items():
if weight > 0:
level.scores.add(artm.TopTokensScore(name=f'TT_{class_id}', class_id=class_id, num_tokens=num_tokens))
linewidth=2)
plt.xlabel('Iterations count')
plt.ylabel('PLSA perp. (blue), ARTM perp. (red)')
plt.grid(True)
plt.show()
print_measures(model_plsa, model_artm)
# настройка параметров регуляризаторов
model_artm.regularizers['SparsePhi'].tau = -0.2
model_artm.regularizers['SparseTheta'].tau = -0.2
model_artm.regularizers['DecorrelatorPhi'].tau = 2.5e+5
# top token score возвращает наиболее вероятные слова топиков
model_plsa.scores.add(artm.TopTokensScore(name='TopTokensScore', num_tokens=7))
model_artm.scores.add(artm.TopTokensScore(name='TopTokensScore', num_tokens=7))
# дообучение
model_plsa.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=25)
model_artm.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=25)
print_measures(model_plsa, model_artm)
# повышение разреженности матриц по ходу обучения
plt.plot(range(model_plsa.num_phi_updates),
model_plsa.score_tracker['SparsityPhiScore'].value,
'b--',
range(model_artm.num_phi_updates),
model_artm.score_tracker['SparsityPhiScore'].value,
dictionary = batch_vectorizer.dictionary
topic_num = 10
tokens_num = 100
print("ARTM training")
topic_names = ['topic_{}'.format(i) for i in range(topic_num)]
model_artm = artm.ARTM(topic_names=topic_names, dictionary=dictionary, cache_theta=True)
model_plsa = artm.ARTM(topic_names=topic_names, cache_theta=True,
scores=[artm.PerplexityScore(name='PerplexityScore', dictionary=dictionary)])
model_lda = artm.LDA(num_topics=topic_num)
model_artm.scores.add(artm.PerplexityScore(name='perplexity_score', dictionary=dictionary))
model_artm.scores.add(artm.SparsityPhiScore(name='sparsity_phi_score'))
model_artm.scores.add(artm.SparsityThetaScore(name='sparsity_theta_score'))
model_artm.scores.add(artm.TopTokensScore(name='top_tokens_score', num_tokens=tokens_num))
model_artm.scores.add(artm.TopicKernelScore(name='topic_kernel_score', probability_mass_threshold=0.3))
model_artm.scores.add(artm.BackgroundTokensRatioScore(name='background_tokens_ratio_score'))
model_artm.scores.add(artm.ClassPrecisionScore(name='class_precision_score'))
model_artm.scores.add(artm.TopicMassPhiScore(name='topic_mass_phi_score'))
model_plsa.scores.add(artm.PerplexityScore(name='perplexity_score', dictionary=dictionary))
model_plsa.scores.add(artm.SparsityPhiScore(name='sparsity_phi_score'))
model_plsa.scores.add(artm.SparsityThetaScore(name='sparsity_theta_score'))
model_plsa.scores.add(artm.TopTokensScore(name='top_tokens_score'))
model_plsa.scores.add(artm.TopicKernelScore(name='topic_kernel_score', probability_mass_threshold=0.3))
model_plsa.scores.add(artm.BackgroundTokensRatioScore(name='background_tokens_ratio_score'))
model_plsa.scores.add(artm.ClassPrecisionScore(name='class_precision_score'))
model_plsa.scores.add(artm.TopicMassPhiScore(name='topic_mass_phi_score'))
model_artm.regularizers.add(artm.SmoothSparsePhiRegularizer(name='sparse_phi_regularizer'))
def test_func():
data_path = os.environ.get('BIGARTM_UNITTEST_DATA')
batches_folder = tempfile.mkdtemp()
dump_folder = tempfile.mkdtemp()
try:
batch_vectorizer = artm.BatchVectorizer(data_path=data_path,
data_format='bow_uci',
collection_name='kos',
target_folder=batches_folder)
model_1 = artm.ARTM(num_processors=7,
cache_theta=True,
num_document_passes=5,
reuse_theta=True,
seed=10,
num_topics=15,
class_ids={'@default_class': 1.0},
theta_name='THETA',
dictionary=batch_vectorizer.dictionary)
model_2 = artm.ARTM(num_processors=7,
cache_theta=False,
num_document_passes=5,
reuse_theta=False,
seed=10,
num_topics=15,
class_ids={'@default_class': 1.0},
dictionary=batch_vectorizer.dictionary)
for model in [model_1, model_2]:
model.scores.add(
artm.PerplexityScore(name='perp',
dictionary=batch_vectorizer.dictionary))
model.scores.add(artm.SparsityThetaScore(name='sp_theta', eps=0.1))
model.scores.add(artm.TopTokensScore(name='top_tok',
num_tokens=10))
model.scores.add(
artm.SparsityPhiScore(name='sp_nwt',
model_name=model.model_nwt))
model.scores.add(
artm.TopicKernelScore(name='kernel',
topic_names=model.topic_names[0:5],
probability_mass_threshold=0.4))
topic_pairs = {}
for topic_name_1 in model.topic_names:
for topic_name_2 in model.topic_names:
if topic_name_1 not in topic_pairs:
topic_pairs[topic_name_1] = {}
topic_pairs[topic_name_1][
topic_name_2] = numpy.random.randint(0, 3)
model.regularizers.add(
artm.DecorrelatorPhiRegularizer(name='decor',
tau=100000.0,
topic_pairs=topic_pairs))
model.regularizers.add(
artm.SmoothSparsePhiRegularizer(
name='smsp_phi',
tau=-0.5,
gamma=0.3,
dictionary=batch_vectorizer.dictionary))
model.regularizers.add(
artm.SmoothSparseThetaRegularizer(name='smsp_theta',
tau=0.1,
doc_topic_coef=[2.0] *
model.num_topics))
model.regularizers.add(
artm.SmoothPtdwRegularizer(name='sm_ptdw', tau=0.1))
# learn first model and dump it on disc
model.fit_offline(batch_vectorizer, num_collection_passes=10)
model.fit_online(batch_vectorizer, update_every=1)
model.dump_artm_model(os.path.join(dump_folder, 'target'))
params = {}
with open(os.path.join(dump_folder, 'target', 'parameters.json'),
'r') as fin:
params = json.load(fin)
_assert_json_params(params)
# create second model from the dump and check the results are equal
model_new = artm.load_artm_model(
os.path.join(dump_folder, 'target'))
_assert_params_equality(model, model_new)
_assert_scores_equality(model, model_new)
_assert_regularizers_equality(model, model_new)
_assert_score_values_equality(model, model_new)
_assert_matrices_equality(model, model_new)
# continue learning of both models
model.fit_offline(batch_vectorizer, num_collection_passes=3)
model.fit_online(batch_vectorizer, update_every=1)
model_new.fit_offline(batch_vectorizer, num_collection_passes=3)
model_new.fit_online(batch_vectorizer, update_every=1)
# check new results are also equal
_assert_params_equality(model, model_new)
_assert_scores_equality(model, model_new)
_assert_regularizers_equality(model, model_new)
_assert_score_values_equality(model, model_new)
_assert_matrices_equality(model, model_new)
shutil.rmtree(os.path.join(dump_folder, 'target'))
finally:
shutil.rmtree(batches_folder)
shutil.rmtree(dump_folder)
subd = "islam-newsru"
batch_vectorizer = artm.BatchVectorizer(data_path=path + "\\" + subd + "\\" +
"batches",
data_format='batches')
modelARTM = artm.ARTM(
topic_names=['topic_{}'.format(i) for i in xrange(100)],
scores=[
artm.PerplexityScore(name='PerplexityScore',
use_unigram_document_model=False,
dictionary=batch_vectorizer.dictionary),
artm.SparsityPhiScore(name='SparsityPhiScore', class_id='text'),
#artm.SparsityThetaScore(name='SparsityThetaScore'),
#artm.TopicKernelScore(name='TopicKernelScore', probability_mass_threshold=0.3),
artm.TopTokensScore(name='TopTokensScore',
class_id='text',
num_tokens=10,
dictionary=batch_vectorizer.dictionary)
],
cache_theta=True)
#modelARTM.regularizers.add(artm.SmoothSparseThetaRegularizer(name='SparseTheta', tau=-0.15))
modelARTM.regularizers.add(
artm.SmoothSparsePhiRegularizer(name='SparsePhi', tau=-0.51))
#modelARTM.regularizers.add(artm.DecorrelatorPhiRegularizer(name='DecorrelatorPhi', tau=1.5e+5))
modelARTM.initialize(dictionary=batch_vectorizer.dictionary)
modelARTM.num_document_passes = 1
modelARTM.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=20)
def test_func():
# constants
dictionary_name = 'dictionary'
num_tokens = 11
probability_mass_threshold = 0.9
sp_reg_tau = -0.1
decor_tau = 1.5e+5
num_collection_passes = 15
num_document_passes = 1
num_topics = 15
vocab_size = 6906
num_docs = 3430
data_path = os.path.abspath(os.path.join(os.getcwd(), os.pardir))
batches_folder = tempfile.mkdtemp()
sp_zero_eps = 0.001
sparsity_phi_value = [
0.034, 0.064, 0.093, 0.120, 0.145, 0.170, 0.194, 0.220, 0.246, 0.277,
0.312, 0.351, 0.390, 0.428, 0.464
]
sparsity_theta_value = [0.0] * num_collection_passes
perp_zero_eps = 2.0
perplexity_value = [
6873, 2590, 2685, 2578, 2603, 2552, 2536, 2481, 2419, 2331, 2235, 2140,
2065, 2009, 1964
]
top_zero_eps = 0.0001
top_tokens_num_tokens = [num_tokens * num_topics] * num_collection_passes
top_tokens_topic_0_tokens = [
u'party', u'state', u'campaign', u'tax', u'political', u'republican',
u'senate', u'candidate', u'democratic', u'court', u'president'
]
top_tokens_topic_0_weights = [
0.0209, 0.0104, 0.0094, 0.0084, 0.0068, 0.0067, 0.0065, 0.0058, 0.0053,
0.0053, 0.0051
]
ker_zero_eps = 0.01
topic_kernel_topic_0_contrast = 0.96
topic_kernel_topic_0_purity = 0.014
topic_kernel_topic_0_size = 18.0
topic_kernel_average_size = [
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.13, 0.53, 1.6, 3.33, 7.13, 12.067,
19.53, 27.8
]
topic_kernel_average_contrast = [
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.12, 0.25, 0.7, 0.96, 0.96, 0.96,
0.96, 0.97
]
topic_kernel_average_purity = [
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.01, 0.01, 0.015, 0.017, 0.02,
0.03, 0.04, 0.05
]
len_last_document_ids = 10
try:
data_path = os.path.abspath(os.path.join(os.getcwd(), os.pardir))
batch_vectorizer = None
batch_vectorizer = artm.BatchVectorizer(data_path=data_path,
data_format='bow_uci',
collection_name='kos',
target_folder=batches_folder)
model = artm.ARTM(
topic_names=['topic_{}'.format(i) for i in xrange(num_topics)],
cache_theta=True)
model.gather_dictionary(dictionary_name, batch_vectorizer.data_path)
model.initialize(dictionary_name=dictionary_name)
model.regularizers.add(
artm.SmoothSparsePhiRegularizer(name='SparsePhi', tau=sp_reg_tau))
model.regularizers.add(
artm.DecorrelatorPhiRegularizer(name='DecorrelatorPhi',
tau=decor_tau))
model.scores.add(artm.SparsityThetaScore(name='SparsityThetaScore'))
model.scores.add(
artm.PerplexityScore(name='PerplexityScore',
use_unigram_document_model=False,
dictionary_name=dictionary_name))
model.scores.add(artm.SparsityPhiScore(name='SparsityPhiScore'))
model.scores.add(
artm.TopTokensScore(name='TopTokensScore', num_tokens=num_tokens))
model.scores.add(
artm.TopicKernelScore(
name='TopicKernelScore',
probability_mass_threshold=probability_mass_threshold))
model.scores.add(artm.ThetaSnippetScore(name='ThetaSnippetScore'))
model.num_document_passes = num_document_passes
model.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=num_collection_passes)
for i in xrange(num_collection_passes):
assert abs(model.score_tracker['SparsityPhiScore'].value[i] -
sparsity_phi_value[i]) < sp_zero_eps
for i in xrange(num_collection_passes):
assert abs(model.score_tracker['SparsityThetaScore'].value[i] -
sparsity_theta_value[i]) < sp_zero_eps
for i in xrange(num_collection_passes):
assert abs(model.score_tracker['PerplexityScore'].value[i] -
perplexity_value[i]) < perp_zero_eps
for i in xrange(num_collection_passes):
assert model.score_tracker['TopTokensScore'].num_tokens[
i] == top_tokens_num_tokens[i]
for i in xrange(num_tokens):
assert model.score_tracker['TopTokensScore'].last_tokens[
model.topic_names[0]][i] == top_tokens_topic_0_tokens[i]
assert abs(model.score_tracker['TopTokensScore'].last_weights[
model.topic_names[0]][i] -
top_tokens_topic_0_weights[i]) < top_zero_eps
assert len(model.score_tracker['TopicKernelScore'].last_tokens[
model.topic_names[0]]) > 0
assert abs(topic_kernel_topic_0_contrast -
model.score_tracker['TopicKernelScore'].last_contrast[
model.topic_names[0]]) < ker_zero_eps
assert abs(topic_kernel_topic_0_purity -
model.score_tracker['TopicKernelScore'].last_purity[
model.topic_names[0]]) < ker_zero_eps
assert abs(topic_kernel_topic_0_size -
model.score_tracker['TopicKernelScore'].last_size[
model.topic_names[0]]) < ker_zero_eps
for i in xrange(num_collection_passes):
assert abs(
model.score_tracker['TopicKernelScore'].average_size[i] -
topic_kernel_average_size[i]) < ker_zero_eps
assert abs(
model.score_tracker['TopicKernelScore'].average_contrast[i] -
topic_kernel_average_contrast[i]) < ker_zero_eps
assert abs(
model.score_tracker['TopicKernelScore'].average_purity[i] -
topic_kernel_average_purity[i]) < ker_zero_eps
model.fit_online(batch_vectorizer=batch_vectorizer)
info = model.info
assert info is not None
assert len(info.config.topic_name) == num_topics
assert len(info.score) == len(model.score_tracker)
assert len(info.regularizer) == len(model.regularizers.data)
assert len(info.cache_entry) > 0
temp = model.score_tracker['ThetaSnippetScore'].last_document_ids
assert len_last_document_ids == len(temp)
assert len(model.score_tracker['ThetaSnippetScore'].last_snippet[
temp[0]]) == num_topics
phi = model.get_phi()
assert phi.shape == (vocab_size, num_topics)
theta = model.get_theta()
assert theta.shape == (num_topics, num_docs)
finally:
shutil.rmtree(batches_folder)
def test_func():
# constants
num_tokens = 11
probability_mass_threshold = 0.9
sp_reg_tau = -0.1
decor_tau = 1.5e+5
decor_rel_tau = 0.3
num_collection_passes = 15
num_document_passes = 1
num_topics = 15
vocab_size = 6906
num_docs = 3430
data_path = os.environ.get('BIGARTM_UNITTEST_DATA')
batches_folder = tempfile.mkdtemp()
sp_zero_eps = 0.001
sparsity_phi_value = [
0.034, 0.064, 0.093, 0.120, 0.145, 0.170, 0.194, 0.220, 0.246, 0.277,
0.312, 0.351, 0.390, 0.428, 0.464
]
sparsity_phi_rel_value = [
0.442, 0.444, 0.444, 0.446, 0.448, 0.449, 0.458, 0.468, 0.476, 0.488,
0.501, 0.522, 0.574, 0.609, 0.670
]
sparsity_theta_value = [0.0] * num_collection_passes
perp_zero_eps = 2.0
perplexity_value = [
6873, 2590, 2685, 2578, 2603, 2552, 2536, 2481, 2419, 2331, 2235, 2140,
2065, 2009, 1964
]
perplexity_rel_value = [
6873, 2667, 2458, 2323, 2150, 2265, 2015, 1967, 1807, 1747, 1713, 1607,
1632, 1542, 1469
]
top_zero_eps = 0.0001
top_tokens_num_tokens = [num_tokens * num_topics] * num_collection_passes
top_tokens_topic_0_tokens = [
u'party', u'state', u'campaign', u'tax', u'political', u'republican',
u'senate', u'candidate', u'democratic', u'court', u'president'
]
top_tokens_topic_0_weights = [
0.0209, 0.0104, 0.0094, 0.0084, 0.0068, 0.0067, 0.0065, 0.0058, 0.0053,
0.0053, 0.0051
]
ker_zero_eps = 0.02
topic_kernel_topic_0_contrast = 0.96
topic_kernel_topic_0_purity = 0.014
topic_kernel_topic_0_size = 18.0
topic_kernel_average_size = [
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.13, 0.6, 1.6, 3.53, 7.15, 12.6,
20.4, 29.06
]
topic_kernel_average_contrast = [
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.12, 0.31, 0.7, 0.96, 0.96, 0.96,
0.96, 0.97
]
topic_kernel_average_purity = [
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.01, 0.01, 0.015, 0.017, 0.02,
0.03, 0.04, 0.05
]
len_last_document_ids = 10
try:
batch_vectorizer = artm.BatchVectorizer(data_path=data_path,
data_format='bow_uci',
collection_name='kos',
target_folder=batches_folder)
dictionary = artm.Dictionary()
dictionary.gather(data_path=batch_vectorizer.data_path)
model = artm.ARTM(
topic_names=['topic_{}'.format(i) for i in range(num_topics)],
dictionary=dictionary.name,
cache_theta=True)
model.regularizers.add(
artm.SmoothSparsePhiRegularizer(name='SparsePhi', tau=sp_reg_tau))
model.regularizers.add(
artm.DecorrelatorPhiRegularizer(name='DecorrelatorPhi',
tau=decor_tau))
model.scores.add(artm.SparsityThetaScore(name='SparsityThetaScore'))
model.scores.add(
artm.PerplexityScore(name='PerplexityScore',
use_unigram_document_model=False,
dictionary=dictionary))
model.scores.add(artm.SparsityPhiScore(name='SparsityPhiScore'))
model.scores.add(
artm.TopTokensScore(name='TopTokensScore', num_tokens=num_tokens))
model.scores.add(
artm.TopicKernelScore(
name='TopicKernelScore',
probability_mass_threshold=probability_mass_threshold))
model.scores.add(artm.ThetaSnippetScore(name='ThetaSnippetScore'))
model.num_document_passes = num_document_passes
model.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=num_collection_passes)
for i in range(num_collection_passes):
assert abs(model.score_tracker['SparsityPhiScore'].value[i] -
sparsity_phi_value[i]) < sp_zero_eps
for i in range(num_collection_passes):
assert abs(model.score_tracker['SparsityThetaScore'].value[i] -
sparsity_theta_value[i]) < sp_zero_eps
for i in range(num_collection_passes):
assert abs(model.score_tracker['PerplexityScore'].value[i] -
perplexity_value[i]) < perp_zero_eps
for i in range(num_collection_passes):
assert model.score_tracker['TopTokensScore'].num_tokens[
i] == top_tokens_num_tokens[i]
for i in range(num_tokens):
assert model.score_tracker['TopTokensScore'].last_tokens[
model.topic_names[0]][i] == top_tokens_topic_0_tokens[i]
assert abs(model.score_tracker['TopTokensScore'].last_weights[
model.topic_names[0]][i] -
top_tokens_topic_0_weights[i]) < top_zero_eps
assert len(model.score_tracker['TopicKernelScore'].last_tokens[
model.topic_names[0]]) > 0
assert abs(topic_kernel_topic_0_contrast -
model.score_tracker['TopicKernelScore'].last_contrast[
model.topic_names[0]]) < ker_zero_eps
assert abs(topic_kernel_topic_0_purity -
model.score_tracker['TopicKernelScore'].last_purity[
model.topic_names[0]]) < ker_zero_eps
assert abs(topic_kernel_topic_0_size -
model.score_tracker['TopicKernelScore'].last_size[
model.topic_names[0]]) < ker_zero_eps
for i in range(num_collection_passes):
assert abs(
model.score_tracker['TopicKernelScore'].average_size[i] -
topic_kernel_average_size[i]) < ker_zero_eps
assert abs(
model.score_tracker['TopicKernelScore'].average_contrast[i] -
topic_kernel_average_contrast[i]) < ker_zero_eps
assert abs(
model.score_tracker['TopicKernelScore'].average_purity[i] -
topic_kernel_average_purity[i]) < ker_zero_eps
model.fit_online(batch_vectorizer=batch_vectorizer)
info = model.info
assert info is not None
assert len(info.config.topic_name) == num_topics
assert len(info.score) >= len(model.score_tracker)
assert len(info.regularizer) == len(model.regularizers.data)
assert len(info.cache_entry) > 0
temp = model.score_tracker['ThetaSnippetScore'].last_document_ids
assert len_last_document_ids == len(temp)
assert len(model.score_tracker['ThetaSnippetScore'].last_snippet[
temp[0]]) == num_topics
phi = model.get_phi()
assert phi.shape == (vocab_size, num_topics)
theta = model.get_theta()
assert theta.shape == (num_topics, num_docs)
assert model.library_version.count('.') == 2 # major.minor.patch
# test relative coefficients for Phi matrix regularizers
model = artm.ARTM(num_topics=num_topics,
dictionary=dictionary.name,
cache_theta=False)
model.regularizers.add(
artm.DecorrelatorPhiRegularizer(name='DecorrelatorPhi',
tau=decor_rel_tau))
model.regularizers['DecorrelatorPhi'].gamma = 0.0
model.scores.add(
artm.PerplexityScore(name='PerplexityScore',
use_unigram_document_model=False,
dictionary=dictionary))
model.scores.add(artm.SparsityPhiScore(name='SparsityPhiScore'))
model.num_document_passes = num_document_passes
model.fit_offline(batch_vectorizer=batch_vectorizer,
num_collection_passes=num_collection_passes)
for i in range(num_collection_passes):
assert abs(model.score_tracker['SparsityPhiScore'].value[i] -
sparsity_phi_rel_value[i]) < sp_zero_eps
for i in range(num_collection_passes):
assert abs(model.score_tracker['PerplexityScore'].value[i] -
perplexity_rel_value[i]) < perp_zero_eps
finally:
shutil.rmtree(batches_folder)
os.environ[
'ARTM_SHARED_LIBRARY'] = '/home/ainur/PycharmProjects/doc2vec_test/bigartm/bigartm/build/lib/libartm.so'
BATCHES_FOLDER = 'data/pydata_batches'
HABR_DATA_PATH = 'habrahabr_corpus_multimodal.txt'
DICT_PATH = 'dictionary.dict'
VOCAB_PATH = 'vocabulary.txt'
print("Start")
batch_vec = artm.BatchVectorizer(data_path=HABR_DATA_PATH,
data_format='vowpal_wabbit',
collection_name='habr',
target_folder=BATCHES_FOLDER,
vocabulary=VOCAB_PATH,
batch_size=100,
class_ids={'@word': 1})
# batch_vec = artm.BatchVectorizer(data_path=BATCHES_FOLDER, data_format='batches', vocabulary=VOCAB_PATH, gather_dictionary=True)
print("BAtch")
dictionary = artm.Dictionary(data_path=BATCHES_FOLDER)
dictionary.save_text(dictionary_path=DICT_PATH)
model = artm.ARTM(
num_topics=10,
num_document_passes=10, #10 проходов по документу
dictionary=dictionary,
scores=[artm.TopTokensScore(name='top_tokens_score')])
model.fit_offline(batch_vectorizer=batch_vec, num_collection_passes=10)
top_tokens = model.score_tracker['top_tokens_score']
# print('Sparsity Phi:{1:.3f} (ARTM)'.format(
# model_artm.score_tracker['SparsityPhiScore'].last_value))
