【独家发布】【kindle】Applied Text Analysis with Python（2017）

相似文件 换一批

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

如果喜欢该文档，欢迎点击头像下方的“+加关注”并订阅【kindle电子书】文库，https://bbs.pinggu.org/forum.php?mod=collection&action=view&ctid=3186


Applied Text Analysis with Python

本帖隐藏的内容

Applied Text Analysis with Python_ Enabling Language Aware Data Products with Ma.rar (4.38 MB) 本附件包括：

• Applied Text Analysis with Python_ Enabling Language Aware Data Products with Machine Learning.mobi

2017-5-2 19:05:47 上传

Benjamin Bengfort, Tony Ojeda, Rebecca Bilbro

O’Reilly Media


The programming landscape of natural language processing has changed dramatically in the past few years. Machine learning approaches now require mature tools like Python’s scikit-learn to apply models to text at scale. This practical guide shows programmers and data scientists who have an intermediate-level understanding of Python and a basic understanding of machine learning and natural language processing how to become more proficient in these two exciting areas of data science.

This book presents a concise, focused, and applied approach to text analysis with Python, and covers topics including text ingestion and wrangling, basic machine learning on text, classification for text analysis, entity resolution, and text visualization. Applied Text Analysis with Python will enable you to design and develop language-aware data products.

You’ll learn how and why machine learning algorithms make decisions about language to analyze text; how to ingest, wrangle, and preprocess language data; and how the three primary text analysis libraries in Python work in concert. Ultimately, this book will enable you to design and develop language-aware data products.

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏219 回帖

关键词：Analysis Applied Analysi python alysis action practical learning natural require

https://github.com/foxbook/atap/tree/master/snippets/ch03

1. from nltk import pos_tag, sent_tokenize, wordpunct_tokenize
   
2. 
   
3. def sents(paragraph):
   
4.     for sentence in sent_tokenize(paragraph):
   
5.         yield sentence
   
6. 
   
7. def tokenize(paragraph):
   
8.     for sentence in sents(paragraph):
   
9.         yield pos_tag(wordpunct_tokenize(sentence))
   
10. 
    
11. sample_text = "The old building is scheduled for demolition. The contractors will begin building a new structure next month."
    
12. print(list(tokenize(sample_text)))

复制代码

1. from nltk import sent_tokenize
   
2. 
   
3. def sents(paragraph):
   
4.     for sentence in sent_tokenize(paragraph):
   
5.         yield sentence
   
6. 
   
7. def parse(textfile):
   
8.     with open(textfile, 'r') as f:
   
9.         text = f.read()
   
10.         return list(sents(text))
    
11. 
    
12. print(parse("zen.txt"))
    
13. print(parse("rhyme.txt"))

复制代码

谢谢分享

谢谢楼主分享！

谢谢分享！

非常感谢！

谢谢分享