Removing stopwords with NLTK in Python



The process of converting data into something a computer can understand is preprocessing. One of the main forms of preprocessing is filtering out unnecessary data. In natural language processing, useless words (data) are called stop words.

What are stop words?

Stop- words. Stop word — it is a commonly used word (eg, “the”, “a”, “an”, “in”) that the search engine has been programmed to ignore both when indexing records for search and when retrieving them. as a result of a search query.

We would not want these words to take up space in our database or take up precious processing time. To do this, we can easily remove them by keeping a list of words that you think are stop words. The NLTK (Natural Language Toolkit) in python contains a list of stop words stored in 16 different languages. You can find them in the nltk_data directory.  home / pratima / nltk_data / corpora / stopwords — this is the address of the directory (don`t forget to change the name of your home directory)

To check the stop word list, you can enter the following commands in the python shell.

 import nltk from nltk.corpus import stopwords set (stopwords.words (`english`)) 

{& # 39 ; we & # 39 ;, & # 39; her & # 39;, & # 39; between & # 39;, & # 39; ourselves & # 39;, & # 39; but & # 39;, & # 39; again & # 39; , & # 39; there & # 39;, & # 39; o & # 39;, & # 39; once & # 39;, & # 39; during & # 39;, & # 39; outside & # 39;, & # 39 ; very & # 39 ;, & # 39; have & # 39;, & # 39; with & # 39;, & # 39; they are & # 39;, & # 39; your & # 39;, & # 39; an & # 39;, & # 39; be & # 39;, & # 39; some & # 39;, & # 39; for & # 39;, & # 39; do & # 39;, & # 39; its & # 39;, & # 39; yours & # 39;, & # 39; such & # 39;, & # 39; into & # 39; , & # 39; of & # 39 ;, & # 39; most & # 39;, & # 39; most & # 39;, & # 39; other & # 39;, & # 39; off & # 39;, & # 39; is & # 39 ;, & # 39; s & # 39 ;, & # 39; am & # 39 ;, & # 39; or & # 39 ;, & # 39; who & # 39 ;, & # 39; as & # 39 ;, & # 39; from & # 39 ;, & # 39; to him, to everyone, to that, to ourselves, to, below, we, we, these, yours, him, to, not , “Neither”, “I”, “were”, “her”, “more”, “he himself”, “this”, “down”, “must”, “our”, “them”, “bye”, “Above & # 39;, & # 39; both & # 39;, & # 39; up & # 39;, & # 39; up to & # 39;, & # 39; our & # 39;, & # 39; had & # 39;, & # 39; she & # 39;, & # 39; all & # 39;, & # 39; no & # 39;, & # 39; when & # 39;, & # 39; in & # 39;, & # 39; any & # 39;, & # 39; up to & # 39; , & # 39; im & # 39;, & # 39; the same & # 39;, & # 39; and & # 39;, & # 39; was & # 39;, & # 39; have & # 39;, & # 39; in & # 39 ;, & # 39; will be & # 39 ;, & # 39; at & # 39;, & # 39; does & # 39 ;, & # 39; you & # 39;, & # 39; then & # 39 ;, & # 39; that & # 39;, & # 39; because “what”, “above”, “why”, “so”, “maybe”, “did”, “not”, “now”, “under”, “he”, “you”, “herself”, “Has”, “just”, “where”, “too”, “only”, “I”, “which”, “those”, “I”, “after”, “several”, “whom”, “t & # 39;, & # 39; being & # 39;, & # 39; if & # 39;, & # 39; their & # 39;, & # 39; my & # 39;, & # 39; against & # 39;, & # 39; a & # 39;, & # 39; by & # 39;, & # 39; do & # 39;, & # 39; this & # 39;, & # 39; like & # 39;, & # 39; further & # 39;, & # 39; was & # 39; here then n & # 39;}

Note. You can even change the list by adding words of your choice in English .txt. file in the stopwords directory.

Deleting stop words with NLTK

The following program removes stop words from a piece of text:

from nltk.corpus import stopwords

from nltk.tokenize import word_tokenize

 

example_sent = "This is a sample sentence, showing off the stop words filtration."

 

stop_words = set (stopwords.words ( < code class = "string"> `english` ))

  

word_tokens = word_tokenize (example_sent)

 

filtered_sentence = [w for w in word_tokens if not w in stop_words]

 

filtered_sentence = []

 

for w in word_tokens:

if w not in stop_words:

filtered_sentence.append (w)

 

print (word_tokens)

print (filtered_sentence)

Output:

 [`This`,` is`, `a`,` sample`, `sentence`,`, `,` showing`, `off`,` the`, `stop`,` words`, `filtration`,` .`] [`This`,` sample`, `sentence`,`, `,` showing` , `stop`,` words`, `filtration`,` .`] 

Executing stop words in the file

In the below code text.txt is the original input file, which should be remove stop words. Filtertext.txt is the output file. This can be done with the following code:

import io

from nltk.corpus import stopwords

from nltk.tokenize import word_tokenize

# word_tokenize takes a string as input, not a file.

stop_words = set (stopwords.words ( `english` ))

file1 = open ( "tex t.txt " )

line = file1.read () # Use this to read the contents of a file as a stream:

words = line.split ()

for r in words:

if not r in stop_words:

appendFile = open ( `filteredtext.txt` , `a` )

  appendFile.write ( "" + r)

appendFile.close ()

In this way, we improve the efficiency of the processed content by removing words that do not affect future operations.

This article is provided by Pratima Upadhyay . If you are as Python.Engineering and would like to contribute, you can also write an article using contribute.python.engineering or by posting the article [email protected] … See my article appearing on the Python.Engineering homepage and help other geeks.

Please post comments if you find anything wrong or if you would like to share more information on the topic discussed above.