{"id":12845,"date":"2020-03-03T16:01:21","date_gmt":"2020-03-03T10:31:21","guid":{"rendered":"https:\/\/www.mygreatlearning.com\/blog\/nltk-tutorial-with-python\/"},"modified":"2024-10-15T00:25:22","modified_gmt":"2024-10-14T18:55:22","slug":"nltk-tutorial-with-python","status":"publish","type":"post","link":"https:\/\/www.mygreatlearning.com\/blog\/nltk-tutorial-with-python\/","title":{"rendered":"Natural Language Toolkit (NLTK) Tutorial with Python"},"content":{"rendered":"\n

What is NLTK?<\/span><\/strong><\/h2>\n\n\n\n

NLTK is a standard python library with prebuilt functions and utilities for the ease of use and implementation. It is one of the most used libraries for natural language processing and computational linguistics.<\/p>\n\n\n\n

NLTK Installation Process<\/strong><\/h3>\n\n\n\n

With a system running windows OS and having python preinstalled<\/p>\n\n\n\n

Open a command prompt and type:<\/p>\n\n\n\n

pip install nltk<\/p>\n\n\n\n

Note: <\/p>\n\n\n\n

!pip install nltk<\/strong>
will download nltk in a specific file\/editor for the current session
nltk dataset download<\/strong><\/p>\n\n\n\n

There are several datasets which can be used with nltk. To use them, we need to download them.
We can download them by executing this:
#code
import nltk
nltk.download()<\/p>\n\n\n\n

Click download in the pop up<\/p>\n\n\n\n

Once it downloads, we are set to go.<\/p>\n\n\n\n

Accessing a dataset in NLTK<\/span><\/strong><\/h2>\n\n\n\n

A dataset is referred to as corpus in nltk.<\/p>\n\n\n\n

A corpus is essentially a collection of sentences which serves as an input. For further processing a corpus is broken down into smaller pieces and processed which we would see in later sections.<\/p>\n\n\n\n

There are several of them which we downloaded in the earlier step, but we have used the movie_reviews corpus for the demonstration.<\/p>\n\n\n\n

\nimport nltk\nfrom nltk.corpus import movie_reviews\nmovie_reviews.words()<\/code><\/pre>\n\n\n\n
<\/p>\n\n\n\n
So now we are all setup for some real time text processing using nltk.<\/p>\n\n\n\n
Data pre-processing <\/span><\/strong><\/h2>\n\n\n\n
Data pre-processing is the process of making the machine understand things better or making the input more machine understandable. Some standard practices for doing that are:<\/p>\n\n\n\n
1.Tokenization<\/span><\/strong><\/h3>\n\n\n\n
Tokenization is the process of breaking text up into smaller chunks as per our requirements.<\/p>\n\n\n\n
nltk has a cool submodule \u201ctokenize\u201d which we will be using. <\/p>\n\n\n\n