Update requirements.txt

requirements.txt

@@ -3,166 +3,74 @@
 # NOTE: all essential packages must be placed under a section named 'ESSENTIAL ...'
 # so that the script `./scripts/check_requirements_and_setup.py` can find them.
 
-#### ESSENTIAL LIBRARIES FOR MAIN FUNCTIONALITY ####
-
-# This installs Pytorch for CUDA 8 only. If you are using a newer version,
-# please visit http://pytorch.org/ and install the relevant version.
+# ESSENTIAL LIBRARIES FOR MAIN FUNCTIONALITY
 torch>=0.4.1,<0.5.0
-
-# Parameter parsing (but not on Windows).
 jsonnet==0.10.0 ; sys.platform != 'win32'
-
-# Adds an @overrides decorator for better documentation and error checking when using subclasses.
 overrides
-
-# Used by some old code.  We moved away from it because it's too slow, but some old code still
-# imports this.
 nltk
-
-# Mainly used for the faster tokenizer.
 spacy>=2.0,<2.1
-
-# Used by span prediction models.
 numpy
-
-# Used for reading configuration info out of numpy-style docstrings.
 numpydoc==0.8.0
-
-# Used in coreference resolution evaluation metrics.
 scipy
 scikit-learn
-
-# Write logs for training visualisation with the Tensorboard application
-# Install the Tensorboard application separately (part of tensorflow) to view them.
 tensorboardX==1.2
-
-# Required by torch.utils.ffi
 cffi==1.11.2
-
-# aws commandline tools for running on Docker remotely.
-# second requirement is to get botocore < 1.11, to avoid the below bug
 awscli>=1.11.91
-
-# Accessing files from S3 directly.
 boto3
-
-# REST interface for models
 flask==0.12.4
 flask-cors==3.0.3
 gevent==1.3.6
-
-# Used by semantic parsing code to strip diacritics from unicode strings.
 unidecode
-
-# Used by semantic parsing code to parse SQL
 parsimonious==0.8.0
-
-# Used by semantic parsing code to format and postprocess SQL
 sqlparse==0.2.4
-
-# For text normalization
 ftfy
 
-#### ESSENTIAL LIBRARIES USED IN SCRIPTS ####
-
-# Plot graphs for learning rate finder
+# ESSENTIAL LIBRARIES USED IN SCRIPTS
 matplotlib==2.2.3
-
-# Used for downloading datasets over HTTP
 requests>=2.18
-
-# progress bars in data cleaning scripts
 tqdm>=4.19
-
-# In SQuAD eval script, we use this to see if we likely have some tokenization problem.
 editdistance
-
-# For pretrained model weights
 h5py
-
-# For timezone utilities
 pytz==2017.3
-
-# Reads Universal Dependencies files.
 conllu==0.11
 
-#### ESSENTIAL TESTING-RELATED PACKAGES ####
-
-# We'll use pytest to run our tests; this isn't really necessary to run the code, but it is to run
-# the tests.  With this here, you can run the tests with `py.test` from the base directory.
+# ESSENTIAL TESTING-RELATED PACKAGES
 pytest
-
-# Allows marking tests as flaky, to be rerun if they fail
 flaky
-
-# Required to mock out `requests` calls
 responses>=0.7
-
-# For mocking s3.
 moto==1.3.4
 
-#### TESTING-RELATED PACKAGES ####
-
-# Checks style, syntax, and other useful errors.
+# TESTING-RELATED PACKAGES
 pylint==1.8.1
-
-# Tutorial notebooks
-# see: https://github.com/jupyter/jupyter/issues/370 for ipykernel
 ipykernel<5.0.0
 jupyter
-
-# Static type checking
 mypy==0.521
-
-# Allows generation of coverage reports with pytest.
 pytest-cov
-
-# Allows codecov to generate coverage reports
 coverage
 codecov
-
-# Required to run sanic tests
 aiohttp
 
-#### DOC-RELATED PACKAGES ####
-
-# Builds our documentation.
+# DOC-RELATED PACKAGES
 sphinx==1.5.3
-
-# Watches the documentation directory and rebuilds on changes.
 sphinx-autobuild
-
-# doc theme
 sphinx_rtd_theme
-
-# Only used to convert our readme to reStructuredText on Pypi.
 pypandoc
-
-# Pypi uploads
 twine==1.11.0
 
-#### GENERATOR-RELATED PACKAGES ####
-
-# Used by AddSent.
+# GENERATOR-RELATED PACKAGES
 psutil
 pattern
-
-# Used by SWAG.
 allennlp
 num2words
 
-#for working on hugging face transformers and gradio
+# FOR WORKING ON HUGGING FACE TRANSFORMERS AND GRADIO
 gradio
-torch
 transformers
 
-#for PDF
+# FOR PDF
 PyPDF2
 pdfminer.six
 pdfplumber
 pdf2image
 Pillow
 pytesseract
-poppler-utils
-tesseract-ocr
-libtesseract-dev