[WIP] Add Dockerfile for gensim with wrappers (piskvorky#1368)

* added dockerfile

* remove fasttext from pip installs

* remove syntax errors

* remove unused imports

* modified dockerfile

* add subversion, locales

* use both python2 and python3

* upgrade numpy version

* add readme with relevant commands

* add fixed versions for wrapper dependencies

* made requested changes

* update readme

* change vw pin and remove docker-yml

* change vw version and make absolute paths for wrappers

* specify original gensim repo for download

* change maintainer

* correct missing slash

* use git clone for gensim

* correct gensim folder sequences

docker/Dockerfile

@@ -0,0 +1,145 @@
+FROM ubuntu:16.04
+
+MAINTAINER Parul Sethi <parul1sethi@gmail.com>
+
+ENV GENSIM_REPOSITORY https://github.com/RaRe-Technologies/gensim.git
+ENV GENSIM_VERSION 2.2.0
+
+# Installs python, pip and setup tools (with fixed versions)
+RUN apt-get update \
+    && apt-get install -y \
+    ant=1.9.6-1ubuntu1 \
+    cmake=3.5.1-1ubuntu3 \
+    default-jdk=2:1.8-56ubuntu2 \
+    g++=4:5.3.1-1ubuntu1 \
+    git=1:2.7.4-0ubuntu1 \
+    libboost-all-dev=1.58.0.1ubuntu1 \
+    libgsl-dev=2.1+dfsg-2 \
+    mercurial=3.7.3-1ubuntu1 \
+    python3=3.5.1-3 \
+    python3-pip=8.1.1-2ubuntu0.4 \
+    python3-setuptools=20.7.0-1 \
+    python=2.7.11-1 \
+    python-pip=8.1.1-2ubuntu0.4 \
+    python-setuptools=20.7.0-1 \
+    unzip=6.0-20ubuntu1 \
+    wget=1.17.1-1ubuntu1.1 \
+    subversion=1.9.3-2ubuntu1 \
+    locales=2.23-0ubuntu9 \
+    libopenblas-dev=0.2.18-1ubuntu1 \
+    libboost-program-options-dev=1.58.0.1ubuntu1 \
+    zlib1g-dev=1:1.2.8.dfsg-2ubuntu4.1
+
+# Setup python language
+RUN locale-gen en_US.UTF-8
+ENV LANG en_US.UTF-8
+ENV LC_CTYPE en_US.UTF-8
+ENV LC_ALL en_US.UTF-8
+
+# Upgrade pip
+RUN pip2 install --upgrade pip
+RUN pip3 install --upgrade pip
+
+# Install dependencies
+RUN pip2 install \
+    cython==0.25.2 \
+    jupyter==1.0.0 \
+    matplotlib==2.0.0 \
+    nltk==3.2.2 \
+    pandas==0.19.2 \
+    git+https://github.com/mila-udem/blocks.git@7beb788f1fcfc78d56c59a5edf9b4e8d98f8d7d9 \
+    -r https://raw.githubusercontent.com/mila-udem/blocks/stable/requirements.txt
+
+RUN pip3 install \
+    cython==0.25.2 \
+    jupyter==1.0.0 \
+    matplotlib==2.0.0 \
+    nltk==3.2.2 \
+    pandas==0.19.2 \
+    git+https://github.com/mila-udem/blocks.git@7beb788f1fcfc78d56c59a5edf9b4e8d98f8d7d9 \
+    -r https://raw.githubusercontent.com/mila-udem/blocks/stable/requirements.txt
+
+# avoid using old numpy version installed by blocks requirements
+RUN pip2 install -U numpy
+RUN pip3 install -U numpy
+
+# Download gensim from Github
+RUN git clone $GENSIM_REPOSITORY \
+    && cd /gensim \
+    && git checkout tags/$GENSIM_VERSION \
+    && pip2 install .[test] \
+    && python2 setup.py install \
+    && pip3 install .[test] \
+    && python3 setup.py install
+
+# Create gensim dependencies directory
+RUN mkdir /gensim/gensim_dependencies
+
+# Set ENV variables for wrappers
+ENV FT_HOME /gensim/gensim_dependencies/fastText
+ENV MALLET_HOME /gensim/gensim_dependencies/mallet
+ENV DTM_PATH /gensim/gensim_dependencies/dtm/dtm/main
+ENV VOWPAL_WABBIT_PATH /gensim/gensim_dependencies/vowpal_wabbit/vowpalwabbit/vw
+
+# For fixed version downloads of gensim wrappers dependencies 
+ENV FASTTEXT_VERSION f24a781021862f0e475a5fb9c55b7c1cec3b6e2e
+ENV MORPHOLOGICALPRIORSFORWORDEMBEDDINGS_VERSION ec2e37a3bcb8bd7b56b75b043c47076bc5decf22
+ENV DTM_VERSION 67139e6f526b2bc33aef56dc36176a1b8b210056
+ENV MALLET_VERSION 2.0.8
+ENV VOWPAL_WABBIT_VERSION 69ecc2847fa0c876c6e0557af409f386f0ced59a
+
+# Install custom dependencies
+
+# TODO: Install wordrank (need to install mpich/openmpi with multithreading enabled)
+
+# Install fastText
+RUN cd /gensim/gensim_dependencies \
+    && git clone https://github.com/facebookresearch/fastText.git \
+    && cd /gensim/gensim_dependencies/fastText \
+    && git checkout $FASTTEXT_VERSION \
+    && make
+
+# Install MorphologicalPriorsForWordEmbeddings
+RUN cd /gensim/gensim_dependencies \
+    && git clone https://github.com/rguthrie3/MorphologicalPriorsForWordEmbeddings.git \
+    && cd /gensim/gensim_dependencies/MorphologicalPriorsForWordEmbeddings \
+    && git checkout $MORPHOLOGICALPRIORSFORWORDEMBEDDINGS_VERSION
+
+# Install DTM
+RUN cd /gensim/gensim_dependencies \
+    && git clone https://github.com/blei-lab/dtm.git \
+    && cd /gensim/gensim_dependencies/dtm/dtm \
+    && git checkout $DTM_VERSION \
+    && make
+
+# Install Mallet
+RUN mkdir /gensim/gensim_dependencies/mallet \
+    && mkdir /gensim/gensim_dependencies/download \
+    && cd /gensim/gensim_dependencies/download \
+    && wget --quiet http://mallet.cs.umass.edu/dist/mallet-$MALLET_VERSION.zip \
+    && unzip mallet-$MALLET_VERSION.zip \
+    && mv ./mallet-$MALLET_VERSION/* /gensim/gensim_dependencies/mallet \
+    && rm -rf /gensim/gensim_dependencies/download \
+    && cd /gensim/gensim_dependencies/mallet \
+    && ant
+
+# Install Vowpal wabbit
+RUN cd /gensim/gensim_dependencies \
+    && git clone https://github.com/JohnLangford/vowpal_wabbit.git \
+    && cd /gensim/gensim_dependencies/vowpal_wabbit \
+    && git checkout $VOWPAL_WABBIT_VERSION \
+    && make \
+    && make install
+
+# Start gensim
+
+# Run check script
+RUN python2 /gensim/docker/check_fast_version.py
+RUN python3 /gensim/docker/check_fast_version.py
+
+# Add running permission to startup script
+RUN chmod +x /gensim/docker/start_jupyter_notebook.sh
+
+# Define the starting command for this container and expose its running port
+CMD sh -c '/gensim/docker/start_jupyter_notebook.sh 9000'
+EXPOSE 9000

docker/README.md

@@ -0,0 +1,21 @@
+# Build gensim image
+
+In docker directory run the following command to build the image locally:
+
+```
+docker build -t gensim .
+```
+
+# Run ipython notebook with installed gensim
+
+Just execute:
+
+```
+docker run -p 9000:9000 gensim
+```
+
+# Run the interactive bash mode
+
+```
+docker run -it gensim /bin/bash
+```

docker/check_fast_version.py

@@ -0,0 +1,10 @@
+import sys
+
+try:
+    from gensim.models.word2vec_inner import FAST_VERSION
+
+    print('FAST_VERSION ok ! Retrieved with value ', FAST_VERSION)
+    sys.exit()
+except ImportError:
+    print('Failed... fall back to plain numpy (20-80x slower training than the above)')
+    sys.exit(-1)

docker/start_jupyter_notebook.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+PORT=$1
+NOTEBOOK_DIR=/gensim/docs/notebooks
+DEFAULT_URL=/notebooks/gensim%20Quick%20Start.ipynb
+
+jupyter notebook --no-browser --ip=* --port=$PORT --allow-root --notebook-dir=$NOTEBOOK_DIR --NotebookApp.token=\"\" --NotebookApp.default_url=$DEFAULT_URL