PATENT_TERMS2 = [
'compris', 'detect', 'first', 'second', 'mean', 'one', 'said', 'unit',
'least', 'sensor', 'angel', 'determin', 'base'
]
PATENT_TERMS_CAS_SAMPLE = ['청구항', 'vehicl', 'first', 'second']
PATENT_TERMS_NUMBER = []
for i in range(50):
PATENT_TERMS_CAS_SAMPLE.append(str(i))
PATENT_TERMS.append(str(i))
PATENT_TERMS2.append(str(i))
PATENT_TERMS_NUMBER.append(str(i))
for_extracting_excel_documents = lda.LDA_KWK('non-meaning_string',
given_pass_num=PASS_TIMES,
given_topic_num=ALL_TOPIC_NUMBER,
given_words_num=WORD_NUMBER)
Corpus_Excel = lda.Generate_with_Excel_CORPUS(for_extracting_excel_documents,
excel_location=ALL_LOCATION,
idx=IDX,
sheet_num=SHEET_NUMBER)
LDACLASS_Corpus_Excel = lda.LDA_KWK(Corpus_Excel,
given_pass_num=PASS_TIMES,
given_topic_num=ALL_TOPIC_NUMBER,
given_words_num=WORD_NUMBER,
given_patent_term=PATENT_TERMS2,
given_all_flag=ALL_MULTIPLE_VALUE)
print("Generating All Doc LDA Processing")
LDACLASS_Corpus_Excel.Generate_LDA()
LDACLASS_Corpus_Excel.Split_Topics_with_Terms()
print("Done")
result.append(tb(i))
print("End extracting document from given excel - document")
return result
def t(GWE):
result = []
for items in GWE:
result.append(tb(" ".join(items.texts[0])))
return result
for_extracting_excel_documents = lda.LDA_KWK('non-meaning_string',
given_pass_num=PASS_TIMES,
given_topic_num=ALL_TOPIC_NUMBER,
given_words_num=WORD_NUMBER)
GWE = lda.Generate_with_Excel(for_extracting_excel_documents,
excel_location=ALL_LOCATION,
idx=IDX,
sheet_num=SHEET_NUMBER,
given_patent_term=PATENT_TERMS2,
given_all_flag=ALL_MULTIPLE_VALUE)
lda.Processing_Entire_Class(GWE)
bloblist = t(GWE)
# print(bloblist)
temp = []