Make utils pip installable using setup.py

- Added pip wheel metadata to gitignore
- Created the setup.py file exposing only the utils_nlp directory
- updated setup documentation Specifying that windows installation breaks
- add steps to use pip to install repo
- update pip install documentation to use ssh and avoid asking for name and password 2. Point to the right egg file
- match version number to August from review comment in init.py
- Add Manifest.in to source distribution
- Update documentation warning users of windows installation issues

.gitignore

@@ -34,6 +34,7 @@ MANIFEST
 # Installer logs
 pip-log.txt
 pip-delete-this-directory.txt
+pip-wheel-metadata/
 
 # Unit test / coverage reports
 htmlcov/

MANIFEST.in

@@ -0,0 +1,8 @@
+graft utils_nlp
+
+global-exclude *.py[cod] __pycache__ *.so *.dylib
+
+exclude README.md
+exclude SETUP.md
+exclude CONTRIBUTING.md
+

SETUP.md

@@ -25,7 +25,8 @@ Depending on the type of NLP system and the notebook that needs to be run, there
 
 ### Requirements
 
-* A machine running Linux, MacOS or Windows.
+* A machine running Linux, MacOS or Windows.  
+    > NOTE: Windows machine are not **FULLY SUPPORTED**. Please use at your own risk.  
 * Miniconda or Anaconda with Python version >= 3.6. 
     * This is pre-installed on Azure DSVM such that one can run the following steps directly. To setup on your local machine, [Miniconda](https://docs.conda.io/en/latest/miniconda.html) is a quick way to get started.
     * It is recommended to update conda to the latest version: `conda update -n base -c defaults conda`
@@ -69,4 +70,15 @@ We can register our created conda environment to appear as a kernel in the Jupyt
     conda activate my_env_name
     python -m ipykernel install --user --name my_env_name --display-name "Python (my_env_name)"
 
-If you are using the DSVM, you can [connect to JupyterHub](https://docs.microsoft.com/en-us/azure/machine-learning/data-science-virtual-machine/dsvm-ubuntu-intro#jupyterhub-and-jupyterlab) by browsing to `https://your-vm-ip:8000`.
+If you are using the DSVM, you can [connect to JupyterHub](https://docs.microsoft.com/en-us/azure/machine-learning/data-science-virtual-machine/dsvm-ubuntu-intro#jupyterhub-and-jupyterlab) by browsing to `https://your-vm-ip:8000`.  
+
+## Install this repository via PIP
+A [setup.py](setup.py) file is provied in order to simplify the installation of this utilities in this repo from the main directory. 
+
+    pip install -e utils_nlp
+
+It is also possible to install directly from Github.
+
+    pip install -e  git+git@github.com:microsoft/nlp.git@master#egg=utils_nlp
+
+**NOTE** - The pip installation does not install any of the necessary package dependencies, it is expected that conda will be used as shown above to setup the environment for the utilities being used.

__init__.py

@@ -0,0 +1,15 @@
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+
+__title__ = "Microsoft NLP"
+__version__ = "2019.08"
+__author__ = "NLPDev Team at Microsoft"
+__license__ = "MIT"
+__copyright__ = "Copyright 2018-present Microsoft Corporation"
+
+# Synonyms
+TITLE = __title__
+VERSION = __version__
+AUTHOR = __author__
+LICENSE = __license__
+COPYRIGHT = __copyright__

setup.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python
+# -*- encoding: utf-8 -*-
+from __future__ import absolute_import
+from __future__ import print_function
+
+import io
+
+import re
+from glob import glob
+from os.path import basename, dirname, join, splitext
+
+from setuptools import find_packages, setup
+
+VERSION = __import__("__init__").VERSION
+
+
+def read(*names, **kwargs):
+    with io.open(
+        join(dirname(__file__), *names),
+        encoding=kwargs.get("encoding", "utf8"),
+    ) as fh:
+        return fh.read()
+
+
+setup(
+    name="utils_nlp",
+    version=VERSION,
+    license="MIT License",
+    description="NLP Utility functions that are used for best practices in building state-of-the-art NLP methods and scenarios. Developed by Microsoft AI CAT",
+    long_description="%s\n%s"
+    % (
+        re.compile("^.. start-badges.*^.. end-badges", re.M | re.S).sub(
+            "", read("README.md")
+        ),
+        re.sub(":[a-z]+:`~?(.*?)`", r"``\1``", read("CONTRIBUTING.md")),
+    ),
+    author="AI CAT",
+    author_email="teamsharat@microsoft.com",
+    url="https://github.com/microsoft/nlp",
+    packages=["utils_nlp"],
+    include_package_data=True,
+    zip_safe=True,
+    classifiers=[
+        # complete classifier list: http://pypi.python.org/pypi?%3Aaction=list_classifiers
+        "Development Status :: 5 - Production/Stable",
+        "Intended Audience :: Developers",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: Unix",
+        "Operating System :: POSIX",
+        "Operating System :: Microsoft :: Windows",
+        "Programming Language :: Python :: 3.6",
+        "Programming Language :: Python :: 3.7",
+        "Programming Language :: Python :: Implementation :: CPython",
+        "Programming Language :: Python :: Implementation :: PyPy",
+        "Topic :: Text Processing :: Linguistic",
+        "Topic :: Utilities",
+        "Intended Audience :: Science/Research",
+        "Intended Audience :: Developers",
+        "Intended Audience :: Education",
+        "Intended Audience :: Financial and Insurance Industry",
+        "Intended Audience :: Healthcare Industry",
+        "Intended Audience :: Information Technology",
+        "Intended Audience :: Telecommunications Industry",
+    ],
+    project_urls={
+        "Documentation": "https://github.com/microsoft/nlp/",
+        "Issue Tracker": "https://github.com/microsoft/nlp/issues",
+    },
+    keywords=[
+        "Microsoft NLP",
+        "Natural Language Processing",
+        "Text Processing",
+        "Word Embedding",
+    ],
+    python_requires=">=3.6",
+    install_requires=[],
+    dependency_links=[],
+    extras_require={},
+    setup_requires=[],
+)