cX>dZddlZddlZddlZddlZddlmZddlm Z m Z ej e Z e dkreejdeje dd ejed ejZed d deddeddededdededdededdedddg ed!d"eded#d$ed%ed&d'eded(d)eded*d+e,ed-d.edddg ed/d0edddg ed1d2eZejdkrdZejsd3e_ndZejsd4e_e ejZe eejej ej!ej"ej#ejeej$ej%dej&5 Z'ej(r)ej(Z)e'j*+e)ej,6nej-d7dZ)e'.e)d8zej,dkr e'j*+e)d9zd6ne'j*+e)d:zd;6ej/rej/Z0e'/e0e d Use text data from to train the model -output Use to save the resulting word vectors / word clusters -size Set size of word vectors; default is 100 -window Set max skip length between words; default is 5 -sample Set threshold for occurrence of words. Those that appear with higher frequency in the training data will be randomly down-sampled; default is 1e-3, useful range is (0, 1e-5) -hs Use Hierarchical Softmax; default is 0 (not used) -negative Number of negative examples; default is 5, common values are 3 - 10 (0 = not used) -threads Use threads (default 3) -iter Run more training iterations (default 5) -min_count This will discard words that appear less than times; default is 5 -alpha Set the starting learning rate; default is 0.025 for skip-gram and 0.05 for CBOW -binary Save the resulting vectors in binary moded; default is 0 (off) -cbow Use the continuous bag of words model; default is 1 (use 0 for skip-gram model) -accuracy Compute accuracy of the resulting model analogical inference power on questions file See an example of questions file at https://code.google.com/p/word2vec/source/browse/trunk/questions-words.txt Example: python -m gensim.scripts.word2vec_standalone -train data.txt -output vec.txt -size 200 -sample 1e-4 -binary 0 -iter 3 N)seterr)Word2Vec LineSentence__main__z:%(asctime)s : %(threadName)s : %(levelname)s : %(message)s)formatlevelz running %s raise)allz-trainz0Use text data from file TRAIN to train the modelT)helprequiredz-outputz2Use file OUTPUT to save the resulting word vectors)r z-windowz6Set max skip length WINDOW between words; default is 5)r typedefaultz-sizez(Set size of word vectors; default is 100dz-samplezSet threshold for occurrence of words. Those that appear with higher frequency in the training data will be randomly down-sampled; default is 1e-3, useful range is (0, 1e-5)gMbP?z-hsz1Use Hierarchical Softmax; default is 0 (not used))r rrchoicesz -negativezRNumber of negative examples; default is 5, common values are 3 - 10 (0 = not used)z-threadszUse THREADS threads (default 3)z-iterz(Run more training iterations (default 5)z -min_countzKThis will discard words that appear less than MIN_COUNT times; default is 5z-alphazPSet the starting learning rate; default is 0.025 for skip-gram and 0.05 for CBOW)r rz-cbowzOUse the continuous bag of words model; default is 1 (use 0 for skip-gram model)z-binaryz=Save the resulting vectors in binary mode; default is 0 (off)z -accuracyz6Use questions from file ACCURACY to evaluate the modelg?g?) vector_size min_countworkerswindowsamplealphasghsnegative cbow_meanepochs)binary.z.modelz .model.binz .model.txtFzfinished running %s)3__doc__loggingos.pathossysargparsenumpyrgensim.models.word2vecrr getLogger__name__logger basicConfigINFOinfojoinargvArgumentParserparser add_argumentintfloat parse_argsargscbowskipgramrtraincorpussizerthreadsrrrritermodeloutputoutfilewvsave_word2vec_formatr splitsaveaccuracyquestions_filepathbasenameBlib/python3.11/site-packages/gensim/scripts/word2vec_standalone.pyrNs,,^ 99999999  8 $ $ zNFG[cjcopppp KK chhsx00111 Fw $X $ & &F 'Ydhiii  (\]]]  (`gjtuvvv &PWZdghhh :D """   G !aV n !  )JQT^_``` &PWZdefff h ! i  g !aV W !aV  *bccc     D yA~z DJz DJ \$* % %F HDI{4;djX 7T]a    E  { P+ %%gdk%BBBB*""3''* 7X%&&& ;!  P H ) )'L*@ ) N N N N H ) )'L*@ ) O O O }' ~&&& KK%rw'7'7 'D'DEEEEE]NFNFrL