Trained word2vec model on brown corpus and plotted clusters of embeddings

environment.yml

+name: text-mining
+channels:
+  - pytorch
+  - anaconda
+  - conda-forge
+  - defaults
+dependencies:
+  - _pytorch_select=0.1=cpu_0
+  - aiohttp=3.7.4=py37h2bbff1b_1
+  - argon2-cffi=20.1.0=py37hcc03f2d_2
+  - async-timeout=3.0.1=py37haa95532_0
+  - async_generator=1.10=py_0
+  - attrs=20.3.0=pyhd3deb0d_0
+  - backcall=0.2.0=py_0
+  - beautifulsoup4=4.9.3=pyhb0f4dca_0
+  - blas=1.0=mkl
+  - bleach=3.3.0=pyh44b312d_0
+  - boto=2.49.0=py37_0
+  - boto3=1.17.23=pyhd3eb1b0_0
+  - botocore=1.20.24=pyhd3eb1b0_1
+  - brotlipy=0.7.0=py37h2bbff1b_1003
+  - ca-certificates=2021.1.19=haa95532_1
+  - cachetools=4.2.1=pyhd3eb1b0_0
+  - certifi=2020.12.5=py37haa95532_0
+  - cffi=1.14.4=py37hcd4344a_0
+  - chardet=3.0.4=py37haa95532_1003
+  - click=7.1.2=pyhd3eb1b0_0
+  - colorama=0.4.4=pyhd3eb1b0_0
+  - cryptography=3.3.1=py37hcd4344a_1
+  - cudatoolkit=10.2.89=h74a9793_1
+  - cycler=0.10.0=py37_0
+  - decorator=4.4.2=py_0
+  - defusedxml=0.6.0=py_0
+  - entrypoints=0.3=pyhd8ed1ab_1003
+  - freetype=2.10.4=hd328e21_0
+  - gensim=3.8.3=py37hd77b12b_2
+  - google-api-core=1.25.1=pyhd3eb1b0_0
+  - google-auth=1.27.1=pyhd3eb1b0_0
+  - google-cloud-core=1.6.0=pyhd3eb1b0_0
+  - google-cloud-storage=1.36.1=pyhd3eb1b0_0
+  - google-crc32c=1.1.2=py37h2bbff1b_0
+  - google-resumable-media=1.2.0=pyhd3eb1b0_1
+  - googleapis-common-protos=1.52.0=py37h2eaa2aa_0
+  - icc_rt=2019.0.0=h0cc432a_1
+  - icu=58.2=ha925a31_3
+  - idna=2.10=pyhd3eb1b0_0
+  - importlib-metadata=3.7.0=py37h03978a9_0
+  - importlib_metadata=3.7.0=hd8ed1ab_0
+  - intel-openmp=2019.4=245
+  - ipykernel=5.3.4=py37h5ca1d4c_0
+  - ipython=7.19.0=py37hd4e2768_0
+  - ipython_genutils=0.2.0=pyhd3eb1b0_1
+  - ipywidgets=7.6.3=pyhd3deb0d_0
+  - jedi=0.17.2=py37haa95532_1
+  - jinja2=2.11.3=pyh44b312d_0
+  - jmespath=0.10.0=py_0
+  - joblib=1.0.0=pyhd3eb1b0_0
+  - jpeg=9b=hb83a4c4_2
+  - jsonschema=3.2.0=py_2
+  - jupyter_client=6.1.7=py_0
+  - jupyter_core=4.7.0=py37haa95532_0
+  - jupyterlab_pygments=0.1.2=pyh9f0ad1d_0
+  - jupyterlab_widgets=1.0.0=pyhd8ed1ab_1
+  - kiwisolver=1.3.1=py37hd77b12b_0
+  - libcrc32c=1.1.1=ha925a31_2
+  - libmklml=2019.0.5=haa95532_0
+  - libpng=1.6.37=h2a8f88b_0
+  - libprotobuf=3.14.0=h23ce68f_0
+  - libsodium=1.0.18=h62dcd97_0
+  - libtiff=4.1.0=h56a325e_1
+  - lz4-c=1.9.3=h2bbff1b_0
+  - m2w64-gcc-libgfortran=5.3.0=6
+  - m2w64-gcc-libs=5.3.0=7
+  - m2w64-gcc-libs-core=5.3.0=7
+  - m2w64-gmp=6.1.0=2
+  - m2w64-libwinpthread-git=5.0.0.4634.697f757=2
+  - markupsafe=1.1.1=py37hcc03f2d_3
+  - matplotlib=3.3.4=py37haa95532_0
+  - matplotlib-base=3.3.4=py37h49ac443_0
+  - mistune=0.8.4=py37hcc03f2d_1003
+  - mkl=2019.4=245
+  - mkl-service=2.3.0=py37h196d8e1_0
+  - mkl_fft=1.2.0=py37h45dec08_0
+  - mkl_random=1.0.4=py37h343c172_0
+  - msys2-conda-epoch=20160418=1
+  - multidict=5.1.0=py37h2bbff1b_2
+  - nbclient=0.5.3=pyhd8ed1ab_0
+  - nbconvert=6.0.7=py37h03978a9_3
+  - nbformat=5.1.2=pyhd8ed1ab_1
+  - nest-asyncio=1.4.3=pyhd8ed1ab_0
+  - ninja=1.10.2=py37h6d14046_0
+  - nltk=3.5=py_0
+  - notebook=6.2.0=py37h03978a9_0
+  - numpy=1.19.2=py37hadc3359_0
+  - numpy-base=1.19.2=py37ha3acd2a_0
+  - olefile=0.46=py37_0
+  - openssl=1.1.1j=h2bbff1b_0
+  - packaging=20.9=pyh44b312d_0
+  - pandas=1.2.2=py37hf11a4ad_0
+  - pandoc=2.11.4=h8ffe710_0
+  - pandocfilters=1.4.2=py_1
+  - parso=0.7.0=py_0
+  - pickleshare=0.7.5=pyhd3eb1b0_1003
+  - pillow=8.1.0=py37h4fa10fc_0
+  - pip=20.3.3=py37haa95532_0
+  - prometheus_client=0.9.0=pyhd3deb0d_0
+  - prompt-toolkit=3.0.8=py_0
+  - protobuf=3.14.0=py37hd77b12b_1
+  - pyasn1=0.4.8=py_0
+  - pyasn1-modules=0.2.8=py_0
+  - pycparser=2.20=py_2
+  - pygments=2.7.4=pyhd3eb1b0_0
+  - pyopenssl=20.0.1=pyhd3eb1b0_1
+  - pyparsing=2.4.7=pyh9f0ad1d_0
+  - pyqt=5.9.2=py37h6538335_2
+  - pyrsistent=0.17.3=py37hcc03f2d_2
+  - pysocks=1.7.1=py37_1
+  - python=3.7.9=h60c2a47_0
+  - python-dateutil=2.8.1=py_0
+  - python_abi=3.7=1_cp37m
+  - pytorch=1.6.0=cpu_py37h538a6d7_0
+  - pytz=2021.1=pyhd3eb1b0_0
+  - pywin32=227=py37he774522_1
+  - pywinpty=0.5.7=py37hc8dfbb8_1
+  - pyzmq=20.0.0=py37hd77b12b_1
+  - qt=5.9.7=vc14h73c81de_0
+  - regex=2020.11.13=py37h2bbff1b_0
+  - requests=2.25.1=pyhd3eb1b0_0
+  - rsa=4.7.2=pyhd3eb1b0_1
+  - s3transfer=0.3.4=pyhd3eb1b0_0
+  - scikit-learn=0.23.2=py37h47e9c7a_0
+  - scipy=1.5.2=py37h9439919_0
+  - send2trash=1.5.0=py_0
+  - setuptools=51.3.3=py37haa95532_4
+  - sip=4.19.8=py37h6538335_0
+  - six=1.15.0=py37haa95532_0
+  - smart_open=4.2.0=pyhd3eb1b0_0
+  - soupsieve=2.0.1=py_0
+  - sqlite=3.33.0=h2a8f88b_0
+  - terminado=0.9.2=py37h03978a9_0
+  - testpath=0.4.4=py_0
+  - threadpoolctl=2.1.0=pyh5ca1d4c_0
+  - tk=8.6.10=he774522_0
+  - torchvision=0.7.0=py37_cu102
+  - tornado=6.1=py37h2bbff1b_0
+  - tqdm=4.55.1=pyhd3eb1b0_0
+  - traitlets=5.0.5=py_0
+  - typing-extensions=3.7.4.3=0
+  - typing_extensions=3.7.4.3=py_0
+  - urllib3=1.26.3=pyhd3eb1b0_0
+  - vc=14.2=h21ff451_1
+  - vs2015_runtime=14.27.29016=h5e58377_2
+  - wcwidth=0.2.5=py_0
+  - webencodings=0.5.1=py_1
+  - wheel=0.36.2=pyhd3eb1b0_0
+  - widgetsnbextension=3.5.1=py37h03978a9_4
+  - win_inet_pton=1.1.0=py37haa95532_0
+  - wincertstore=0.2=py37_0
+  - winpty=0.4.3=4
+  - xz=5.2.5=h62dcd97_0
+  - yarl=1.5.1=py37he774522_0
+  - zeromq=4.3.3=ha925a31_3
+  - zipp=3.4.0=py_0
+  - zlib=1.2.11=h62dcd97_4
+  - zstd=1.4.5=h04227a9_0
+  - pip:
+    - autocorrect==2.3.0
+    - lxml==4.6.2
+prefix: C:\Users\robin\anaconda3\envs\text-mining