def extract_relevant_cybergeo_fulltext(kwLimit): resdir = "res/cybergeo_full/" # corpus = utils.get_data( "SELECT id FROM cybergeo WHERE fulltext_keywords IS NOT NULL AND fulltext_keywords!='' LIMIT 10;", "mysql" ) occurence_dicos = utils.import_kw_dico_req( "SELECT id,fulltext_keywords FROM cybergeo WHERE fulltext_keywords IS NOT NULL AND fulltext_keywords!='' LIMIT 10;", "mysql", ) [relevantkw, relevant_dico] = kwFunctions.extract_relevant_keywords(corpus, kwLimit, occurence_dicos) # export as csv utils.export_dico_csv(relevant_dico, resdir + "relevantDico_kw" + str(kwLimit), False) export_dico_num_csv(relevantkw, resdir + "termhoods_kw" + str(kwLimit), False)
def extract_relevant_cybergeo(kwLimit, database): corpus = utils.get_data( "SELECT cybergeo.id FROM refdesc INNER JOIN cybergeo ON cybergeo.id=refdesc.id WHERE abstract_keywords IS NOT NULL AND abstract_keywords!='';", database, ) print(corpus) occurence_dicos = utils.import_kw_dico_req( "SELECT cybergeo.id,abstract_keywords FROM refdesc INNER JOIN cybergeo ON cybergeo.id=refdesc.id WHERE abstract_keywords IS NOT NULL AND abstract_keywords!='';", database, ) print(occurence_dicos) [relevantkw, relevant_dico] = kwFunctions.extract_relevant_keywords(corpus, kwLimit, occurence_dicos) utils.export_dico_csv(relevant_dico, "res/cybergeo/relevantDico_kwLimit" + str(kwLimit), False) utils.export_dico_num_csv(relevantkw, "res/cybergeo/kw_" + str(kwLimit), False)
def extract_relevant_cybergeo(kwLimit, database): corpus = utils.get_data( 'SELECT cybergeo.id FROM refdesc INNER JOIN cybergeo ON cybergeo.id=refdesc.id WHERE abstract_keywords IS NOT NULL AND abstract_keywords!=\'\';', database) print(corpus) occurence_dicos = utils.import_kw_dico_req( 'SELECT cybergeo.id,abstract_keywords FROM refdesc INNER JOIN cybergeo ON cybergeo.id=refdesc.id WHERE abstract_keywords IS NOT NULL AND abstract_keywords!=\'\';', database) print(occurence_dicos) [relevantkw, relevant_dico ] = kwFunctions.extract_relevant_keywords(corpus, kwLimit, occurence_dicos) utils.export_dico_csv(relevant_dico, 'res/cybergeo/relevantDico_kwLimit' + str(kwLimit), False) utils.export_dico_num_csv(relevantkw, 'res/cybergeo/kw_' + str(kwLimit), False)
def extract_relevant_cybergeo_fulltext(kwLimit): resdir = 'res/cybergeo_full/' # corpus = utils.get_data( 'SELECT id FROM cybergeo WHERE fulltext_keywords IS NOT NULL AND fulltext_keywords!=\'\' LIMIT 10;', 'mysql') occurence_dicos = utils.import_kw_dico_req( 'SELECT id,fulltext_keywords FROM cybergeo WHERE fulltext_keywords IS NOT NULL AND fulltext_keywords!=\'\' LIMIT 10;', 'mysql') [relevantkw, relevant_dico ] = kwFunctions.extract_relevant_keywords(corpus, kwLimit, occurence_dicos) # export as csv utils.export_dico_csv(relevant_dico, resdir + 'relevantDico_kw' + str(kwLimit), False) export_dico_num_csv(relevantkw, resdir + 'termhoods_kw' + str(kwLimit), False)