def lda():
data = pd.read_csv("./lda_model/process.csv", encoding="utf-8", header=None)
# data[2] = data[1].apply(lambda x: re.split(r'\s*', x))
data[2] = data[1].apply(lambda x: x.split(' '))
corpora_documents = []
# print(data[2])
for item_str in data[2]:
# print(item_str)
corpora_documents.append(item_str)
del corpora_documents[0]
print(corpora_documents[0])
dict_1 = corpora.Dictionary(corpora_documents)
dict_1.save('./lda_model/dict_v2')
dict_corpora = [dict_1.doc2bow(i) for i in corpora_documents]
print('字典构建完成')
# 向量的每一个元素代表了一个word在这篇文档中出现的次数
# print(corpus)
from gensim.corpora.mmcorpus import MmCorpus
MmCorpus.serialize('ths_corpora.mm', dict_corpora)
tfidf = models.TfidfModel(dict_corpora)
corpus_tfidf = tfidf[dict_corpora]
tfidf.save("./lda_model/my_model.tfidf")
np.random.seed(SOME_FIXED_SEED)
lda = models.LdaModel(corpus_tfidf, num_topics=78, id2word=dict_1, iterations=1000)
# # #
lda.save('./lda_model/mylda_v2')
lda.show_topics()
def create_corpus(src, out_dir, no_below=20, keep_words=_DEFAULT_KEEP_WORDS):
"""\
"""
wordid_filename = os.path.join(out_dir, 'cables_wordids.pickle')
bow_filename = os.path.join(out_dir, 'cables_bow.mm')
tfidf_filename = os.path.join(out_dir, 'cables_tfidf.mm')
predicate = None # Could be set to something like pred.origin_filter(pred.origin_germany)
# 1. Create word dict
dct = Dictionary()
dct_handler = DictionaryHandler(dct)
handler = create_filter(dct_handler)
handle_source(src, handler, predicate)
dct.filter_extremes(no_below=no_below, no_above=0.1, keep_n=keep_words)
dct.save(wordid_filename)
# 2. Reiterate through the cables and create the vector space
corpus_handler = CorpusHandler(out_dir, dct=dct, allow_dict_updates=False)
handler = create_filter(corpus_handler)
handle_source(src, handler, predicate)
# 3. Load corpus
mm = MmCorpus(bow_filename)
# 4. Create TF-IDF model
tfidf = TfidfModel(mm, id2word=dct, normalize=True)
# 5. Save the TF-IDF model
MmCorpus.serialize(tfidf_filename, tfidf[mm], progress_cnt=10000)
def create_corpus(src, out_dir, no_below=20, keep_words=_DEFAULT_KEEP_WORDS):
"""\
"""
wordid_filename = os.path.join(out_dir, 'cables_wordids.pickle')
bow_filename = os.path.join(out_dir, 'cables_bow.mm')
tfidf_filename = os.path.join(out_dir, 'cables_tfidf.mm')
predicate = None # Could be set to something like pred.origin_filter(pred.origin_germany)
# 1. Create word dict
dct = Dictionary()
dct_handler = DictionaryHandler(dct)
handler = create_filter(dct_handler)
handle_source(src, handler, predicate)
dct.filter_extremes(no_below=no_below, no_above=0.1, keep_n=keep_words)
dct.save(wordid_filename)
# 2. Reiterate through the cables and create the vector space
corpus_handler = CorpusHandler(out_dir, dct=dct, allow_dict_updates=False)
handler = create_filter(corpus_handler)
handle_source(src, handler, predicate)
# 3. Load corpus
mm = MmCorpus(bow_filename)
# 4. Create TF-IDF model
tfidf = TfidfModel(mm, id2word=dct, normalize=True)
# 5. Save the TF-IDF model
MmCorpus.serialize(tfidf_filename, tfidf[mm], progress_cnt=10000)
def save_corpus(cls, tokens_file, corpus_file, dictionary_path):
print "Instantiating corpus"
corpus = UserCorpus(tokens_file)
print "Filtering extremes"
corpus.dictionary.filter_extremes(no_below=20, no_above=0.1, keep_n=100000)
print "Serializing corpus"
MmCorpus.serialize(corpus_file, corpus, progress_cnt=10000)
print "Serializing dictionary"
corpus.dictionary.save_as_text(dictionary_path)
def train(self, corpus, chunksize=10000, use_temp_files=True):
"""
train the underlying linear mappings.
@param corpus is a gensim corpus compatible format
@param use_temp_files determines whether to use temporary files to store the intermediate representations of
the corpus to train the next layer. Setting flag True will not greatly affect memory usage, but will temporarily
require a significant amount of disk space. Using temp files will strongly speed up training, especially as the
number of layers increases.
"""
ln.info("Training mSDA with %s layers. ")
if not use_temp_files:
ln.warn("Training without temporary files. May take a long time!")
self.reduction_layer.train(corpus, chunksize=chunksize)
current_representation = self.reduction_layer[corpus]
for layer_num, layer in enumerate(self.mda_layers):
# We feed the corpus through all intermediate layers to get the current representation
# that representation is then used to train the next layer
# this is memory-independent, but will probably be very slow.
ln.info("Training layer %s.", layer_num)
layer.train(current_representation, chunksize=chunksize)
if layer_num < len(self.mda_layers) - 1:
current_representation = layer[current_representation]
else:
ln.info("Using temporary files to speed up training.")
ln.info("Beginning training on %s layers." %
(len(self.mda_layers) + 1))
self.reduction_layer.train(corpus, chunksize=chunksize)
# serializing intermediate representation
MmCorpus.serialize(".msda_intermediate.mm",
self.reduction_layer[corpus],
progress_cnt=chunksize)
# load corpus to train next layer
current_representation = MmCorpus(".msda_intermediate.mm")
for layer_num, layer in enumerate(self.mda_layers):
layer.train(current_representation, chunksize=chunksize)
os.remove(".msda_intermediate.mm")
os.remove(".msda_intermediate.mm.index")
if layer_num < len(self.mda_layers) - 1:
MmCorpus.serialize(".msda_intermediate.mm",
layer[current_representation],
progress_cnt=chunksize)
current_representation = MmCorpus(".msda_intermediate.mm")
ln.info("mSDA finished training.")
def convert_corpus_to_sparse_tfidf(
metadata_index_outpath: Path,
vectorized_corpus_outpath: Path,
path_to_jsonl_index: Path = BIOPAPERS_JSON_PATH,
path_to_bow: Path = BOW_PATH,
tfidf_vectorizer: Path = TFIDF_VECTORIZER,
):
"""
Convert corpora of a specific category into a tfidf sparse matrix.
It saves:
1. MM Corpus sparse matrix indexed by id
2. metadata index as gz pickle file.
Parameters
----------
metadata_index_outpath: Path
Path to metadata index (without extension)
vectorized_corpus_outpath: Path
Path to corpus matrix, does not require extension
path_to_jsonl_index: Path
Path to jsonl_index for that specific category
path_to_bow: Path
Path to BOW dictionary
tfidf_vectorizer:
Path to TFIDF model for vectorization of BOW corpus
"""
# Load dictionary
if path_to_bow.exists():
bow_dictionary = Dictionary.load(str(path_to_bow))
else:
bow_dictionary = create_bow_from_biopapers()
# Load tfidf model:
if tfidf_vectorizer.exists():
tfidf_model = TfidfModel.load(str(tfidf_vectorizer))
else:
tfidf_model = create_tfidf_from_papers()
# Add pickle suffix:
metadata_index_outpath = metadata_index_outpath.with_suffix(".jsonl")
# Load corpus generator:
tfidf_corpus = BiopapersCorpus(
bow_dictionary=bow_dictionary,
path_to_JSONL_index=path_to_jsonl_index,
tfidf_vectorizer=tfidf_model,
metadata_index_outpath=metadata_index_outpath,
)
# Save corpus and index to file:
MmCorpus.serialize(str(vectorized_corpus_outpath), tfidf_corpus)
def main(training_datafile, output_path):
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
logger = logging.getLogger('Archive.gensim')
filters = [strip_punctuation, strip_multiple_whitespaces, strip_numeric, remove_stopwords, strip_short]
logger.info('Creating Corpus object...')
corpus = ArchiveCorpus(datafile=training_datafile, preprocess=filters)
filename = ''.join(training_datafile.split('/')[-1])
if not os.path.exists(output_path):
os.makedirs(output_path)
outfile_path = os.path.join(output_path, filename)
logger.info('Saving corpus to disk: {}.mm'.format(filename))
MmCorpus.serialize('{}.mm'.format(outfile_path), corpus, progress_cnt=1000)
logger.info('Saving dictionary to disk: {}.dict'.format(filename))
corpus.dictionary.save('{}.dict'.format(outfile_path))
def create_corpus(column, shortname, type_n):
my_corpus = Corpus_Column(fname, column)
dicti = my_corpus.dictionary
#shortname1 has only freq < 5 removed others have filter_extremes
once_ids = [tokenid for tokenid, docfreq in dicti.dfs.iteritems() if docfreq < 5]
dicti.filter_tokens(bad_ids=once_ids)
#dicti.filter_extremes()
dicti.compactify()
dicti.save(path_join(cache_dir, "%s_%s_nltk_filtered_dic.pickle" % (type_n, shortname)))
MmCorpus.serialize(path_join(cache_dir, "%s_%s_nltk_filtered.corpus.mtx" % (type_n, shortname)), my_corpus, id2word=dicti)
print my_corpus.dictionary
print "50 most used in %s" % column
i = 0
for k, v in sorted(dicti.dfs.items(), key=operator.itemgetter(1), reverse=True):
if i < 50:
print dicti[k], v
i = i + 1
def __iter__(self):
self.titles = []
for title, tokens in itertools.islice(iter_wiki(self.dump_file), self.clip_docs):
self.titles.append(title)
yield self.dictionary.doc2bow(tokens)
def __len__(self):
return self.clip_docs
# create a stream of bag-of-words vectors
wiki_corpus = WikiCorpus(fileLocation+'enwiki-latest-pages-articles.xml.bz2', id2word_wiki)
vector = next(iter(wiki_corpus))
print(vector) # print the first vector in the stream
MmCorpus.serialize(fileLocation+'wikiModels/wiki_bow.mm', wiki_corpus)
mm_corpus = MmCorpus(fileLocation+'wikiModels/wiki_bow.mm')
print(mm_corpus)
clipped_corpus = gensim.utils.ClippedCorpus(mm_corpus, 4000)
lda_model = gensim.models.LdaModel(clipped_corpus, num_topics=10, id2word=id2word_wiki, passes=4)
# store all trained models to disk
lda_model.save(fileLocation+'wikiModels/lda_wiki.model')
#lsi_model.save('./data/lsi_wiki.model')
#tfidf_model.save('./data/tfidf_wiki.model')
id2word_wiki.save(fileLocation+'wikiModels/wiki.dictionary')
loaded_lda_model = gensim.models.LdaModel.load(fileLocation+'wikiModels/lda_wiki.model')
preprocessor = Preprocessor(use_stemming=False, dictionary=dictionary)
corpusname = "brown"
corpus = [
preprocessor.preprocess(" ".join(text), return_bow=True)
for text in brown.sents()
]
preprocessor.dictionary.filter_extremes(15, 0.1, 30000)
corpus = [
preprocessor.preprocess(" ".join(text),
allow_update=False,
return_bow=True) for text in brown.sents()
]
ln.debug("saving/loading corpus")
save = MmCorpus.serialize("test.mm", corpus)
corpus = MmCorpus("test.mm")
dimensions = 2000
params = [{"num_layers": 5, "noise": 0.7}, {"num_layers": 3, "noise": 0.3}][0]
ln.info("training mSDA with %s dimensions. params: %s" % (dimensions, params))
model = mSDAWrapper.train(corpus, dimensions, dictionary, params)
paramstring = "_".join(["%s-%s" % (k, v) for k, v in params.items()])
savestring = "mSDA_%s_%s_" % (corpusname, paramstring)
model.save(savestring)
msda_wrapper = mSDAWrapper(savestring, preprocessor)
def get_synonyms(word):
def save(self, fname):
self.model.save(fname)
ln.info("preprocessing corpus")
dictionary = Dictionary()
preprocessor = Preprocessor(use_stemming=False, dictionary=dictionary)
corpusname = "brown"
corpus = [preprocessor.preprocess(" ".join(text), return_bow=True) for text in brown.sents()]
preprocessor.dictionary.filter_extremes(15, 0.1, 30000)
corpus = [preprocessor.preprocess(" ".join(text), allow_update=False, return_bow=True) for text in brown.sents()]
ln.debug("saving/loading corpus")
save = MmCorpus.serialize("test.mm", corpus)
corpus = MmCorpus("test.mm")
dimensions = 2000
params = [{"num_layers": 5, "noise": 0.7},
{"num_layers": 3, "noise": 0.3}][0]
ln.info("training mSDA with %s dimensions. params: %s" % (dimensions, params))
model = mSDAWrapper.train(corpus, dimensions, dictionary, params)
paramstring = "_".join(["%s-%s" % (k, v) for k, v in params.items()])
savestring = "mSDA_%s_%s_" % (corpusname, paramstring)
model.save(savestring)
msda_wrapper = mSDAWrapper(savestring, preprocessor)
if len(sys.argv) < 3:
print globals()["__doc__"] % locals()
sys.exit(1)
input, output = sys.argv[1:3]
if len(sys.argv) > 3:
keep_words = int(sys.argv[3])
else:
keep_words = DEFAULT_DICT_SIZE
# build dictionary. only keep 100k most frequent words (out of total ~8.2m unique tokens)
# takes about 9h on a macbook pro, for 3.5m articles (june 2011 wiki dump)
wiki = WikiCorpus(input, keep_words=keep_words)
# save dictionary and bag-of-words (term-document frequency matrix)
# another ~9h
wiki.dictionary.save_as_text(output + "_wordids.txt")
MmCorpus.serialize(output + "_bow.mm", wiki, progress_cnt=10000)
del wiki
# initialize corpus reader and word->id mapping
id2token = Dictionary.load_from_text(output + "_wordids.txt")
mm = MmCorpus(output + "_bow.mm")
# build tfidf,
# ~30min
from gensim.models import TfidfModel
tfidf = TfidfModel(mm, id2word=id2token, normalize=True)
# save tfidf vectors in matrix market format
# ~2h; result file is 15GB! bzip2'ed down to 4.5GB
MmCorpus.serialize(output + "_tfidf.mm", tfidf[mm], progress_cnt=10000)
print "we will lemmatize ('you were'->'be/VB')"
mname = prefix + '_lemmatized_tfidf'
else:
print "you don't have pattern: we will tokenize ('you were'->'you','were')"
mname = prefix + '_tokenized_tfidf'
try:
id2token = Dictionary.load_from_text(mname + '_wordids.txt')
mm = MmCorpus(mname + '_bow.mm')
print ">>> Loaded corpus from serialized files"
except:
print ">>> Extracting articles..."
corpus = CDS_Corpus(FOLDER)
corpus.dictionary.save_as_text(mname + '_wordids.txt')
print ">>> Saved dictionary as " + mname + "_wordids.txt"
MmCorpus.serialize(mname + '_bow.mm', corpus, progress_cnt=1000)
print ">>> Saved MM corpus as " + mname + "_bow.mm"
id2token = Dictionary.load_from_text(mname + '_wordids.txt')
mm = MmCorpus(mname + '_bow.mm')
del corpus
print ">>> Using TF-IDF"
tfidf = models.TfidfModel(mm, id2word=id2token, normalize=True)
corpus_tfidf = tfidf[mm]
lda = models.ldamodel.LdaModel(corpus=corpus_tfidf, id2word=id2token,
num_topics=N_TOPICS, alpha='auto',
update_every=1, chunksize=800, passes=50)
f = open(mname + '.ldamodel', 'w')
cPickle.dump(lda, f)
def __init__(self, docs, topic_number=500):
# Create a dictionary representation of the documents.
print('training LSI models with topic number = ' + str(topic_number))
if (not os.path.isfile('./lsi/lsi_dict.dict')):
print('creating dict')
dictionary = Dictionary(docs)
dictionary.save('./lsi/lsi_dict.dict')
else:
print('dict already exists')
dictionary = Dictionary.load("./lsi/lsi_dict.dict")
self.dictionary = dictionary
# Create corpora
if (not os.path.isfile('./lsi/lsi_corpus.mm')):
# Filter out words that occur less than 20 documents, or more than 50% of the documents.
print('creating bow corpus')
dictionary.filter_extremes(no_below=20, no_above=0.5)
corpus = [dictionary.doc2bow(doc) for doc in docs]
MmCorpus.serialize("lsi/lsi_corpus.mm", corpus)
else:
print('bow corpus already exists')
corpus = MmCorpus("./lsi/lsi_corpus.mm")
self.tfidf = models.TfidfModel(corpus)
if (not os.path.isfile('./lsi/lsi_tf_corpus.mm')):
print('creating tf corpus')
tf_corp = self.tfidf[corpus]
MmCorpus.serialize("lsi/lsi_tf_corpus.mm", tf_corp)
else:
print('tf corpus already exists')
tf_corp = MmCorpus("./lsi/lsi_tf_corpus.mm")
# Make a index to word dictionary.
temp = dictionary[0] # This is only to "load" the dictionary.
id2word = dictionary.id2token
#Create the models and vectors
if (not os.path.isfile('./lsi/lsi_bow_model' + str(topic_number) +
'.model')):
print('creating bow model')
bow_model = models.LsiModel(corpus=corpus,
num_topics=topic_number,
id2word=id2word)
bow_model.save('lsi/lsi_bow_model' + str(topic_number) + '.model')
else:
print('bow model already exists')
bow_model = models.LsiModel.load('./lsi/lsi_bow_model' +
str(topic_number) + '.model')
bow_vector = bow_model[corpus]
self.bow_model = bow_model
if (not os.path.isfile('./lsi/lsi_tf_model' + str(topic_number) +
'.model')):
print('creating tfidf model')
tf_model = models.LsiModel(corpus=tf_corp,
num_topics=topic_number,
id2word=id2word)
tf_model.save('./lsi/lsi_tf_model' + str(topic_number) + '.model')
else:
print('tfidf model already exists')
tf_model = models.LsiModel.load('./lsi/lsi_tf_model' +
str(topic_number) + '.model')
tf_vector = tf_model[tf_corp]
self.tf_model = tf_model
#Create indices
if (not os.path.isfile('./lsi/lsi_bow_model' + str(topic_number) +
'.index')):
print('creating bow index')
bow_index = similarities.MatrixSimilarity(
bow_vector) # index corpus in bow LSI space
bow_index.save('lsi/lsi_bow_model' + str(topic_number) + '.index')
else:
print('bow index already exists')
bow_index = similarities.MatrixSimilarity.load(
'./lsi/lsi_bow_model' + str(topic_number) + '.index')
self.bow_index = bow_index
if (not os.path.isfile('./lsi/lsi_tf_model' + str(topic_number) +
'.index')):
print('creating tf index')
tf_index = similarities.MatrixSimilarity(
tf_vector) # index corpus in tf LSI space
tf_index.save('lsi/lsi_tf_model' + str(topic_number) + '.index')
else:
print('tf index already exists')
tf_index = similarities.MatrixSimilarity.load(
'./lsi/lsi_tf_model' + str(topic_number) + '.index')
self.tf_index = tf_index
print('model created!')
files. Only `.txt` files will be taken into account.
dataset_name : str
A name for the directory where the processed corpus is to be placed.
"""
# Parse command line arguments
parser = argparse.ArgumentParser()
parser.add_argument("-docs_dir", type=str)
parser.add_argument("-dataset_name", type=str)
args = vars(parser.parse_args())
documents_dir = args["docs_dir"]
dataset_name = args["dataset_name"]
document_paths = [
os.path.join(documents_dir, d) for d in os.listdir(documents_dir)
if d.endswith(".txt")
]
# Write document index to id mapping
doc_ids = [
d.replace(".txt", "") for d in os.listdir(documents_dir)
if d.endswith(".txt")
]
doc_idxs = {i: doc_ids[i] for i in range(len(doc_ids))}
os.makedirs(os.path.dirname(doc_idxs_file.format(id=dataset_name)))
with open(doc_idxs_file.format(id=dataset_name), "w") as f:
json.dump(doc_idxs, f, indent=2)
# Create tokenizer and tokenize corpus in a single pass
corpus_file = corpus_file.format(id=dataset_name)
tokenizer_file = tokenizer_file.format(id=dataset_name)
os.makedirs(os.path.dirname(corpus_file), exist_ok=True)
corpus_builder = IterativeCorpusBuilder(document_paths, 2 * 10**6)
MmCorpus.serialize(fname=corpus_file, corpus=corpus_builder)
corpus_builder.tokenizer.save(tokenizer_file)
metadata_queue = []
class MetadataRemovedCorpus:
def __init__(self, corpus):
self.corpus = corpus
def __iter__(self):
for doc, metadata in self.corpus:
metadata_queue.append(metadata)
yield doc
tfidf_corpus = tfidf[MetadataRemovedCorpus(wiki_corpus)]
class MetadataAddedCorpus:
def __init__(self, corpus):
self.corpus = corpus
self.metadata = True
def __iter__(self):
for doc in self.corpus:
yield doc, metadata_queue.pop()
tfidf_metadata_corpus = MetadataAddedCorpus(tfidf_corpus)
if vector_format == 'tfidf':
corpus = tfidf_metadata_corpus
elif vector_format == 'bow':
corpus = wiki_corpus
MmCorpus.serialize(mm_fname, corpus, progress_cnt=10000, metadata=True)
from gensim.corpora import WikiCorpus
from gensim.corpora.mmcorpus import MmCorpus
if __name__ == '__main__':
# Log both to a file and the console
log_name = 'tut4.log'
logger = logging.getLogger()
logger.setLevel(logging.INFO)
fh = logging.FileHandler(log_name)
fh.setLevel(logging.INFO)
ch = logging.StreamHandler()
ch.setLevel(logging.INFO)
formatter = logging.Formatter('%(asctime)s : %(levelname)s : %(message)s')
ch.setFormatter(formatter)
fh.setFormatter(formatter)
logger.addHandler(ch)
logger.addHandler(fh)
logger.info("running %s" % ' '.join(sys.argv))
fname = 'simplewiki-20120313-pages-articles.xml.bz2'
wiki = WikiCorpus(fname)
# save dictionary and bag-of-words (term-document frequency matrix)
output = 'simple_wiki'
wiki.dictionary.save_as_text(output + '_wordids.txt')
MmCorpus.serialize(output + '_bow.mm', wiki, progress_cnt=10000)
del wiki
# optional argv[3] = keep_words
if len(sys.argv) < 3:
print globals()['__doc__'] % locals()
#sys.exit(1)
input, output = sys.argv[1:3]
if len(sys.argv) > 3:
keep_words = int(sys.argv[3])
else:
keep_words = DEFAULT_DICT_SIZE
# build dictionary. only keep 100k most frequent words (out of total ~900k unique tokens)
enron = EnronCorpus(input, keep_words=keep_words)
# save dictionary and bag-of-words (term-document frequency matrix)
enron.dictionary.save_as_text(output + '_wordids.txt')
MmCorpus.serialize(output + '_bow.mm', enron, progress_cnt=10000)
del enron
# initialize corpus reader and word->id mapping
id2token = Dictionary.load_from_text(output + '_wordids.txt')
mm = MmCorpus(output + '_bow.mm')
# build tfidf
from gensim.models import TfidfModel
tfidf = TfidfModel(mm, id2word=id2token, normalize=True)
# save tfidf vectors in matrix market format
MmCorpus.serialize(output + '_tfidf.mm', tfidf[mm], progress_cnt=10000)
logger.info("finished running %s" % program)
def build_corpus(dictionary):
MmCorpus.serialize(CORPUS_FILE, BowCorpus(wiki_index.ARTICLES_FILE, dictionary))
return MmCorpus(CORPUS_FILE)
