Containerization and import cleanup, code formatting

.dir-locals.el

@@ -0,0 +1,18 @@
+(
+ (python-mode . (
+                 (eval .
+                       (progn
+                           ;; set path to the python modules directory
+                           (add-to-list 'exec-path (concat (locate-dominating-file default-directory dir-locals-file) "bin/"))
+                           ;; configure inferior python shell.
+                           (setq-local python-shell-interpreter "pythondocker")
+                           (setq-local python-shell-interpreter-interactive-arg "-i")
+                           (setq-local python-shell-completion-native-enable nil)
+                           (setq-local lsp-pyls-plugins-mypy-enabled t)
+                           (setq-local lsp-pyls-plugins-mypy.live_mode t)
+                           (setq-local lsp-pyls-plugins-black-enabled t)
+                           (setq-local lsp-pyls-plugins-isort-enabled t)
+                           )
+                       )
+                 ))
+ )

.gitignore

@@ -0,0 +1,209 @@
+# Created by https://www.toptal.com/developers/gitignore/api/linux,python,emacs
+# Edit at https://www.toptal.com/developers/gitignore?templates=linux,python,emacs
+
+### Emacs ###
+# -*- mode: gitignore; -*-
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+auto-save-list
+tramp
+.\#*
+
+# Org-mode
+.org-id-locations
+*_archive
+ltximg/**
+
+# flymake-mode
+*_flymake.*
+
+# eshell files
+/eshell/history
+/eshell/lastdir
+
+# elpa packages
+/elpa/
+
+# reftex files
+*.rel
+
+# AUCTeX auto folder
+/auto/
+
+# cask packages
+.cask/
+dist/
+
+# Flycheck
+flycheck_*.el
+
+# server auth directory
+/server/
+
+# projectiles files
+.projectile
+
+# directory configuration
+.dir-locals.el
+
+# network security
+/network-security.data
+
+
+### Linux ###
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+pytestdebug.log
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+doc/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+pythonenv*
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# profiling data
+.prof
+
+# End of https://www.toptal.com/developers/gitignore/api/linux,python,emacs

Dockerfile

@@ -0,0 +1,31 @@
+ARG TAG=3.8
+
+FROM python:$TAG
+ENV PYTHONUNBUFFERED 1
+
+ARG USER
+ARG USER_ID
+ARG GROUP_ID
+ARG WORKDIR
+
+RUN apt-get update \
+    && apt-get clean \
+    && apt-get update -qqq \
+    && apt-get install -y -q build-essential graphviz graphviz-dev \
+    && apt-get install -y -q ffmpeg libsm6 libxext6 \
+    && pip install --upgrade pip \
+    && pip install Cython scipy
+
+RUN groupadd --gid 1000 $USER
+RUN useradd --create-home --uid $USER_ID --gid $GROUP_ID $USER
+
+USER ${USER}
+ENV PATH "$PATH:/home/$USER/.local/bin"
+
+COPY ./requirements.txt requirements.txt
+RUN pip install --user -r requirements.txt
+
+RUN pip install --user torch==1.7.1+cpu torchvision==0.8.2+cpu torchaudio==0.7.2 \
+    -f https://download.pytorch.org/whl/torch_stable.html
+
+WORKDIR $WORKDIR

Makefile

@@ -0,0 +1,27 @@
+##
+# ETM
+#
+# @file
+# @version 0.1
+
+user := $(shell whoami)
+userid := $(shell id -u)
+groupid := $(shell id -g)
+workdir := $(shell pwd)
+
+.PHONY: build
+build:
+	docker-compose build \
+	--build-arg USER=$(user) \
+	--build-arg USER_ID=${userid} \
+	--build-arg GROUP_ID=$(groupid) \
+	--build-arg WORKDIR=$(workdir)
+
+.PHONY: clean-container
+clean-container:
+	docker rmi etm_etm
+
+.PHONY: clean-python
+clean-python:
+	rm -rf __pycache__
+# end

README.md

@@ -6,8 +6,19 @@ ETM defines words and topics in the same embedding space. The likelihood of a wo
 
 ## Dependencies
 
-+ python 3.6.7
-+ pytorch 1.1.0
++ python 3.8.7
++ pytorch 1.7.1
+
+## Optional
+
++ docker
++ docker-compose
+
+### Build Docker Image
+
+``` sh
+make build
+```
 
 ## Datasets
 
@@ -20,7 +31,7 @@ All the datasets are pre-processed and can be found below:
 + https://bitbucket.org/franrruiz/data_stopwords_largev_2/src/master/ (this one contains stop words and was used to showcase robustness of ETM to stop words.)
 + https://bitbucket.org/franrruiz/data_20ng_largev/src/master/
 
-All the scripts to pre-process a given dataset for ETM can be found in the folder 'scripts'. The script for 20NewsGroup is self-contained as it uses scikit-learn. If you want to run ETM on your own dataset, follow the script for New York Times (given as example) called data_nyt.py  
+All the scripts to pre-process a given dataset for ETM can be found in the folder 'scripts'. The script for 20NewsGroup is self-contained as it uses scikit-learn. If you want to run ETM on your own dataset, follow the script for New York Times (given as example) called data_nyt.py
 
 ## To Run
 
@@ -38,14 +49,20 @@ To learn interpretable topics using ETM with pre-fitted word embeddings (called
 
 + first fit the word embeddings. For example to use simple skipgram you can run
 ```
-python skipgram.py --data_file PATH_TO_DATA --emb_file PATH_TO_EMBEDDINGS --dim_rho 300 --iters 50 --window_size 4 
+python skipgram.py --data_file PATH_TO_DATA --emb_file PATH_TO_EMBEDDINGS --dim_rho 300 --iters 50 --window_size 4
 ```
 
-+ then run the following 
++ then run the following
 ```
 python main.py --mode train --dataset 20ng --data_path data/20ng --emb_path PATH_TO_EMBEDDINGS --num_topics 50 --train_embeddings 0 --epochs 1000
 ```
 
+## To Run in a Container
+
+``` sh
+docker-compose run --rm etm python main.py --mode train --dataset 20ng --data_path data/20ng --num_topics 50 --train_embeddings 1 --epochs 1000
+```
+
 ## Citation
 
 ```
@@ -56,4 +73,3 @@ python main.py --mode train --dataset 20ng --data_path data/20ng --emb_path PATH
   year={2019}
 }
 ```
-

bin/pyls

@@ -0,0 +1,4 @@
+#!/bin/bash
+set -e
+# docker-compose build ml &> /dev/null
+exec docker-compose run --name etm_python --rm --no-deps -T etm pyls

bin/pythondocker

@@ -0,0 +1,3 @@
+#!/bin/bash
+set -e
+exec docker exec -it etm_python python $@