Installation

pip3 install gtcacs

python3.8

numpy==1.19.5scikit-learn==0.24.1scipy==1.6.1tensorflow==2.4.1tqdm==4.58.0

Usage

fromsklearn.datasetsimportfetch_20newsgroupsfromgtcacs.topic_modelingimportGTCACS# load datasetcorpus,labels=fetch_20newsgroups(subset='all',return_X_y=True,download_if_missing=False)# set stop wordseng_stopwords= {'i','me','my','myself','we','our','ours','ourselves','you',"you're","you've","you'll","you'd",'your','yours','yourself','yourselves','he','him','his','himself','she',"she's",'her','hers','herself','it',"it's",'its','itself','they','them','their','theirs','themselves','what','which','who','whom','this','that',"that'll",'these','those','am','is','are','was','were','be','been','being','have','has','had','having','do','does','did','doing','a','an','the','and','but','if','or','because','as','until','while','of','at','by','for','with','about','against','between','into','through','during','before','after','above','below','to','from','up','down','in','out','on','off','over','under','again','further','then','once','here','there','when','where','why','how','all','any','both','each','few','more','most','other','some','such','no','nor','not','only','own','same','so','than','too','very','s','t','can','will','just','don',"don't",'should',"should've",'now','d','ll','m','o','re','ve','y','ain','aren',"aren't",'couldn',"couldn't",'didn',"didn't",'doesn',"doesn't",'hadn',"hadn't",'hasn',"hasn't",'haven',"haven't",'isn',"isn't",'ma','mightn',"mightn't",'mustn',"mustn't",'needn',"needn't",'shan',"shan't",'shouldn',"shouldn't",'wasn',"wasn't",'weren',"weren't",'won',"won't",'wouldn',"wouldn't"}# instantiate the GTCACS objectgtcacs_obj=GTCACS(num_topics=20,# number of topicsmax_num_words=50,# maximum number of terms to considermax_df=0.95,# maximum document frequencymin_df=15,# minimum document frequencystopwords=eng_stopwords,# stopwords setngram_range=(1,2),# range for ngrammax_features=None,# maximum number of terms to consider (max vocabulary size)lowercase=True,# flag for convert to lowercasenum_epoches=5,# number of epochsbatch_size=128,# number of documents in a batchgen_learning_rate=0.005,# learning rate for optimize the generative partdiscr_learning_rate=0.005,# learning rate for optimize the discriminative partrandom_seed_size=100,# dimension of generator input layergenerator_hidden_dim=512,# dimension of generator hidden layerdocument_dim=None,# dimension of generator output layer and discriminator's input/output layerlatent_space_dim=64,# dimension of discriminator latent spacediscriminator_hidden_dim=256# dimension of discriminator hidden layer)# compuation on corpus (dimensional reduction, clustering, summarization)gtcacs_obj.extract_topics(corpus=corpus)# get the extracted clusters of wordstopics=gtcacs_obj.get_topics_words()fori,topicinenumerate(topics):print(">>> TOPIC",i+1,topic)# get the topics distribution scores for each documentcorpus_transf=gtcacs_obj.get_topics_distribution_scores()print(corpus_transf)

License