# To use recent corenlp: https://github.com/stanfordnlp/python-stanford-corenlp # 1. pip install stanford-corenlp # 2. download java crsion # 3. export CORENLP_HOME=/Users/wonseok/utils/stanford-corenlp-full-2018-10-05 # from stanza.nlp.corenlp import CoreNLPClient # client = CoreNLPClient(server='http://localhost:9000', default_annotators='ssplit,tokenize'.split(',')) import corenlp client = corenlp.CoreNLPClient(annotators='ssplit,tokenize'.split(',')) nlu1 = "What position does the player who played for butler cc (ks) play??" path_db = './data_and_model' db_name = 'dev' data_table = load_jsonl('./data_and_model/dev.tables.jsonl') table_name = 'table_1_10015132_11' n_Q = 100000 if args.infer_loop else 1 for i in range(n_Q): if n_Q > 1: nlu1 = input('Type question: ') '''pr_sql_i, pr_ans = infer( nlu1, table_name, data_table, path_db, db_name, model, model_bert, bert_config, max_seq_length=args.max_seq_length, num_target_layers=args.num_target_layers, beam_size=1, show_table=False, show_answer_only=False ) ''' pr_sql_i, pr_ans = infernew(dev_loader, dev_data,
# 2. download java crsion # 3. export CORENLP_HOME=/Users/wonseok/utils/stanford-corenlp-full-2018-10-05 # from stanza.nlp.corenlp import CoreNLPClient # client = CoreNLPClient(server='http://localhost:9000', default_annotators='ssplit,tokenize'.split(',')) import corenlp import corenlp import os os.environ["CORENLP_HOME"] = './models/stanford-corenlp-4.0.0' client = corenlp.CoreNLPClient(annotators='ssplit,tokenize'.split(',')) path_db = './data/WikiSQL-1.1/data' db_name = 'dev' data_table = load_jsonl('./data/WikiSQL-1.1/data/dev.tables.jsonl') while True: nlu1 = input("Enter query to be executed : ") table_name = input("Enter table name : ") pr_sql_i, pr_ans = infer(nlu1, table_name, data_table, path_db, db_name, model, model_bert, bert_config, max_seq_length=args.max_seq_length, num_target_layers=args.num_target_layers, beam_size=1,
# # client = corenlp.CoreNLPClient(annotators='ssplit,tokenize'.split(',')) '''2020/12/02修改:infer分词函数''' # from nltk.tokenize.stanford import CoreNLPTokenizer # sttok = CoreNLPTokenizer('http://localhost:9000') #注意端口号要对应启动stanza的端口号 # import jieba # nlu1 = "长沙2011年平均每天成交量是3.17,那么近一周的成交量是多少" # path_db = 'data_and_model' # db_name = 'dev' # data_table = load_jsonl('./data_and_model/dev.tables.json') # table_name = 'Table_69cc8c0c334311e98692542696d6e445' nlu1 = "你知不知道股票代码等于002043且时间等于现金流量表的数据值是?" path_db = 'data_and_model' db_name = 'test' data_table = load_jsonl('data_and_model/test.tables.json') table_name = 'Table_financial_statements' n_Q = 100000 if args.infer_loop else 1 for i in range(n_Q): if n_Q > 1: nlu1 = input('Type question: ') pr_sql_i, pr_ans = infer(nlu1, table_name, data_table, path_db, db_name, model, model_bert, bert_config, max_seq_length=args.max_seq_length, num_target_layers=args.num_target_layers,
# 2. download java crsion # 3. export CORENLP_HOME=/Users/wonseok/utils/stanford-corenlp-full-2018-10-05 # from stanza.nlp.corenlp import CoreNLPClient # client = CoreNLPClient(server='http://localhost:9000', default_annotators='ssplit,tokenize'.split(',')) import corenlp client = corenlp.CoreNLPClient(annotators='ssplit,tokenize'.split(','), start_server=False, endpoint='http://localhost:9004') nlu1 = "Which company have more than 100 employees?" path_db = './data_and_model' db_name = 'train' data_table = load_jsonl('./data_and_model/train_knowledge.jsonl') table_name = 'sqlite_master' n_Q = 100000 if args.infer_loop else 1 for i in range(n_Q): if n_Q > 1: nlu1 = input('Type question: ') pr_sql_i, pr_ans = infer(nlu1, table_name, data_table, path_db, db_name, model, model_bert, bert_config, max_seq_length=args.max_seq_length, num_target_layers=args.num_target_layers,