随笔分类 -  NLP代码记录

摘要:返回x,y的列表集合 正则 只保留汉字 获取句子的最大长度 句子转数字 ,输入是句子的列表 数字转句子 python def loadEmbeddingsFile(embedding_file_path): embeddings_dict = {} with open(embedding_file_ 阅读全文
posted @ 2019-09-21 15:54 FromZeroToOne 阅读(353) 评论(0) 推荐(0) 编辑
摘要:```python from gensim.models.keyedvectors import KeyedVectors model2 = KeyedVectors.load_word2vec_format('embedding1.txt', binary=False) ``` 阅读全文
posted @ 2019-09-21 15:53 FromZeroToOne 阅读(115) 评论(0) 推荐(0) 编辑
摘要:```python import pandas as pd stop_words = [] with open('data/stop_words.txt','r',encoding='utf-8') as f: lines = f.readlines() for i in lines: word = i.strip() stop_words.append(word) print(stop_word 阅读全文
posted @ 2019-09-21 15:44 FromZeroToOne 阅读(679) 评论(0) 推荐(0) 编辑
摘要:挖坑 阅读全文
posted @ 2019-08-27 16:56 FromZeroToOne 阅读(89) 评论(0) 推荐(0) 编辑

点击右上角即可分享
微信分享提示
🚀
回顶
收起
  1. 1 404 not found REOL
404 not found - REOL
00:00 / 00:00
An audio error has occurred.