Fix NLTK warnings

Added punkt and stopwords modules to README.
louislefevre · Apr 7, 2021 · 878f289 · 878f289
1 parent d3aee8a
commit 878f289
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -42,3 +42,6 @@ The program can be initialised by running *start.py*, which accepts parameters i
 - [matplotlib](https://pypi.org/project/matplotlib/)
 - [nltk](https://pypi.org/project/nltk/)
 - [num2words](https://pypi.org/project/num2words/)
+- [punkt (nltk module)](http://www.nltk.org/api/nltk.tokenize.html?highlight=punkt)
+- [stopwords (nltk module)](https://www.nltk.org/api/nltk.corpus.html)  
+*NLTK modules are downloaded automatically at runtime*
diff --git a/retrieval/util/TextProcessor.py b/retrieval/util/TextProcessor.py
@@ -3,8 +3,8 @@
 from nltk.corpus import stopwords
 from nltk.stem import PorterStemmer
 from num2words import num2words
-nltk.download('punkt')
-nltk.download('stopwords')
+nltk.download('punkt', quiet=True)
+nltk.download('stopwords', quiet=True)
 
 
 def clean_collection(collection: dict[int, str]) -> dict[int, list[str]]: