From ce1f163284359951926decafcf507581d6293314 Mon Sep 17 00:00:00 2001
From: Dongwoo Arthur Kim <arthur.k@kakaocorp.com>
Date: Mon, 19 Jun 2017 16:56:16 +0900
Subject: [PATCH] Add requirements.txt, .gitignore, corpora simple shortcut.

---
 .gitignore       | 103 +++++++++++++++++++++++++++++++++++++++++++++++
 README.md        |   6 +--
 requirements.txt |   4 ++
 3 files changed, 110 insertions(+), 3 deletions(-)
 create mode 100644 .gitignore
 create mode 100644 requirements.txt

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..55bc9f0
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,103 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# 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/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+corpora
+logdir
+preprocessed
diff --git a/README.md b/README.md
index 0256c23..006b67a 100644
--- a/README.md
+++ b/README.md
@@ -26,6 +26,9 @@ I don't intend to replicate the paper exactly. Rather, I aim to implement the ma
 
 ## Training
 * STEP 1. Download [IWSLT 2016 German–English parallel corpus](https://wit3.fbk.eu/download.php?release=2016-01&type=texts&slang=de&tlang=en) and extract it to `corpora/` folder.
+```sh
+wget -qO- --show-progress https://wit3.fbk.eu/archive/2016-01//texts/de/en/de-en.tgz | tar xz; mv de-en corpora
+```
 * STEP 2. Adjust hyper parameters in `hyperparams.py` if necessary.
 * STEP 3. Run `prepro.py` to generate vocabulary files to the `preprocessed` folder.
 * STEP 4. Run `train.py` or download the [pretrained files](https://u42868014.dl.dropboxusercontent.com/u/42868014/transformer/logdir.zip).
@@ -86,6 +89,3 @@ got: Oh yeah you all are incredibly
 source: Dies ist nicht meine Meinung Das sind Fakten<br>
 expected: This is not my opinion These are the facts<br>
 got: This is not my opinion These are facts
-
-
-
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..c806b13
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,4 @@
+nltk>=3.2.4
+numpy>=1.13.0
+regex>=2017.6.7
+tensorflow>=1.2.0