added requirements.txt

README.md

@@ -3,7 +3,7 @@
 This python project was created as part of the article "Natural Language Processing in diagnostic texts from
 nephropathology".
 
-The paper can be found [here](LINK).
+The paper can be found (soon) [here](LINK).
 
 The scripts ```database_preparation/data_preparation_pipeline.py```, ```TextClustering/clustering_pipeline.py```
 and ```TextClassification/classification_pipeline.py``` gives an idea of how this project can be used with other datasets.
@@ -18,7 +18,7 @@ Feel free to use and adapt the scripts to your own needs.
 
 ## Requirements
 
-For preprocessing, the project requires some nltk corporas:
+```database_preparation/preprocess.py``` requires some nltk corporas:
 ```
 import nltk
 nltk.download('stopwords')

requirements.txt

+numpy==1.21.0
+gensim==4.2.0
+pandas==1.4.2
+matplotlib==3.5.1
+tqdm==4.64.0
+scikit-learn==1.1.1
+hdbscan==0.8.28
+nltk==3.7
+seaborn==0.11.2
+validclust==0.1.1
+tensorflow-gpu==2.6.0
+wordcloud==1.8.2.2
+joblib==1.1.0
+scipy==1.7.3
+yake==0.4.8
+openpyxl==3.0.10
+googletrans==3.1.0a0
+datasets==2.3.2
+transformers==4.21.0.dev0
+dataclasses==0.8
+pyarrow==8.0.0
+keras==2.6.0
+torch==1.11.0
+hanta==0.2.0
\ No newline at end of file