From e14871949f9b5c3bd065edbb88aab87799219967 Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Sat, 27 May 2017 16:12:20 +0530
Subject: [PATCH 01/19] added dockerfile

---
 docker/Dockerfile                | 131 +++++++++++++++++++++++++++++++
 docker/check_fast_version.py     |  12 +++
 docker/docker-compose.yml        |   7 ++
 docker/start_jupyter_notebook.sh |   7 ++
 docker/wordrank_install.sh       |  19 +++++
 5 files changed, 176 insertions(+)
 create mode 100644 docker/Dockerfile
 create mode 100644 docker/check_fast_version.py
 create mode 100644 docker/docker-compose.yml
 create mode 100644 docker/start_jupyter_notebook.sh
 create mode 100644 docker/wordrank_install.sh

diff --git a/docker/Dockerfile b/docker/Dockerfile
new file mode 100644
index 0000000000..92804c2757
--- /dev/null
+++ b/docker/Dockerfile
@@ -0,0 +1,131 @@
+FROM ubuntu:16.04
+
+MAINTAINER Daniel Baptista Dias <danielbpdias@gmail.com>
+
+ENV GENSIM_REPOSITORY https://github.com/RaRe-Technologies/gensim/archive
+ENV GENSIM_VERSION master
+
+# 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 \
+    unzip=6.0-20ubuntu1 \
+    wget=1.17.1-1ubuntu1.1
+    libboost-program-options-dev \
+    libboost-python-dev \
+    zlib1g-dev
+
+# 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
+
+# Make some symlinks
+RUN cd /usr/bin \
+    && ln -s easy_install3 easy_install \
+    && ln -s pip3 pip
+
+# Upgrade pip
+RUN pip install --upgrade pip
+
+# Install dependencies
+RUN pip install \
+    annoy \
+    cython \
+    jupyter \
+    matplotlib \
+    nltk \
+    pandas \
+    pyemd \
+    sklearn \
+    fasttext \
+    testfixtures \
+    unittest2 \
+    git+git://github.com/mila-udem/fuel.git@stable \
+    git+git://github.com/mila-udem/blocks.git@stable \
+    -r https://raw.githubusercontent.com/mila-udem/blocks/stable/requirements.txt
+
+# Create gensim directory and dependencies directory
+RUN mkdir /gensim \
+    && mkdir /gensim_dependencies
+
+# Download gensim from Github
+RUN mkdir /gensim/download \
+    && cd /gensim/download \
+    && wget --quiet $GENSIM_REPOSITORY/$GENSIM_VERSION.zip \
+    && unzip $GENSIM_VERSION.zip \
+    && mv ./gensim-$GENSIM_VERSION/* /gensim \
+    && rm -rf /gensim/download \
+    && cd /gensim \
+    && python setup.py install
+
+# Set ENV variables for wrappers
+ENV FT_HOME gensim_dependencies/fastText
+ENV WR_HOME gensim_dependencies/wordrank
+ENV MALLET_HOME gensim_dependencies/mallet
+ENV DTM_PATH gensim_dependencies/dtm/bin/dtm-linux64
+ENV VOWPAL_WABBIT_PATH gensim_dependencies/vowpal_wabbit/vowpalwabbit/vw
+
+# Install custom dependencies
+
+# Install WordRank
+RUN cd /gensim_dependencies \
+    && git clone https://bitbucket.org/shihaoji/wordrank \
+    && cp /gensim/docker/wordrank_install.sh /gensim_dependencies/wordrank/install.sh \
+    && cd /gensim_dependencies/wordrank \
+    && sh ./install.sh
+
+# Install fastText
+RUN cd /gensim_dependencies \
+    && git clone https://github.com/facebookresearch/fastText.git \
+    && cd /gensim_dependencies/fastText \
+    && make
+
+# Install MorphologicalPriorsForWordEmbeddings
+RUN cd /gensim_dependencies \
+    && git clone https://github.com/rguthrie3/MorphologicalPriorsForWordEmbeddings.git
+
+# Install DTM
+RUN cd /gensim_dependencies \
+    && git clone https://github.com/magsilva/dtm.git
+
+# Install Mallet
+RUN mkdir /gensim_dependencies/mallet \
+    && mkdir /gensim_dependencies/download \
+    && cd /gensim_dependencies/download \
+    && wget --quiet http://mallet.cs.umass.edu/dist/mallet-2.0.8.zip \
+    && unzip mallet-2.0.8.zip \
+    && mv ./mallet-2.0.8/* /gensim_dependencies/mallet \
+    && rm -rf /gensim_dependencies/download \
+    && cd /gensim_dependencies/mallet \
+    && ant
+
+# Install Vowpal wabbit
+RUN cd /gensim_dependencies \
+    && git clone https://github.com/JohnLangford/vowpal_wabbit.git
+    && cd /gensim_dependencies/vowpal_wabbit \
+    && make
+    && make install
+
+# Start gensim
+
+# Run check script
+RUN python /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
\ No newline at end of file
diff --git a/docker/check_fast_version.py b/docker/check_fast_version.py
new file mode 100644
index 0000000000..b389eba8ae
--- /dev/null
+++ b/docker/check_fast_version.py
@@ -0,0 +1,12 @@
+import sys
+
+try:
+    from gensim.models.word2vec_inner import train_batch_sg, train_batch_cbow
+    from gensim.models.word2vec_inner import score_sentence_sg, score_sentence_cbow
+    from gensim.models.word2vec_inner import FAST_VERSION, MAX_WORDS_IN_BATCH
+
+    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)
diff --git a/docker/docker-compose.yml b/docker/docker-compose.yml
new file mode 100644
index 0000000000..84f5f2b712
--- /dev/null
+++ b/docker/docker-compose.yml
@@ -0,0 +1,7 @@
+version: '2'
+
+services:
+  gensim:
+    build: .
+    ports:
+      - 9000:9000
\ No newline at end of file
diff --git a/docker/start_jupyter_notebook.sh b/docker/start_jupyter_notebook.sh
new file mode 100644
index 0000000000..4c5946d056
--- /dev/null
+++ b/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
\ No newline at end of file
diff --git a/docker/wordrank_install.sh b/docker/wordrank_install.sh
new file mode 100644
index 0000000000..36a13e3007
--- /dev/null
+++ b/docker/wordrank_install.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+
+printf "1. clean up workspace\n"
+./clean.sh
+
+printf "\n2. install glove to construct cooccurrence matrix\n"
+wget http://nlp.stanford.edu/software/GloVe-1.0.tar.gz # if failed, check http://nlp.stanford.edu/projects/glove/ for the original version
+tar -xvzf GloVe-1.0.tar.gz; rm GloVe-1.0.tar.gz
+patch -p0 -i glove.patch
+cd glove; make clean all; cd ..
+
+printf "\n3. install hyperwords for evaluation\n"
+hg clone -r 56 https://bitbucket.org/omerlevy/hyperwords
+patch -p0 -i hyperwords.patch
+
+printf "\n4. build wordrank\n"
+export CC=gcc CXX=g++      # uncomment this line if you don't have an Intel compiler, but with gcc all #pragma simd are ignored as of now
+cmake .
+make clean all
\ No newline at end of file

From b5e27b5f2e693525d0754d27bfb4372c075fa0fa Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Sat, 27 May 2017 16:56:35 +0530
Subject: [PATCH 02/19] remove fasttext from pip installs

---
 docker/Dockerfile | 1 -
 1 file changed, 1 deletion(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index 92804c2757..b5c90c70c5 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -49,7 +49,6 @@ RUN pip install \
     pandas \
     pyemd \
     sklearn \
-    fasttext \
     testfixtures \
     unittest2 \
     git+git://github.com/mila-udem/fuel.git@stable \

From e653d3f88a8de31245c94afb64ab209c2a9230b9 Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Sat, 27 May 2017 17:08:10 +0530
Subject: [PATCH 03/19] remove syntax errors

---
 docker/Dockerfile | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index b5c90c70c5..fe7f64b3d3 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -20,7 +20,7 @@ RUN apt-get update \
     python3-pip=8.1.1-2ubuntu0.4 \
     python3-setuptools=20.7.0-1 \
     unzip=6.0-20ubuntu1 \
-    wget=1.17.1-1ubuntu1.1
+    wget=1.17.1-1ubuntu1.1 \
     libboost-program-options-dev \
     libboost-python-dev \
     zlib1g-dev
@@ -112,9 +112,9 @@ RUN mkdir /gensim_dependencies/mallet \
 
 # Install Vowpal wabbit
 RUN cd /gensim_dependencies \
-    && git clone https://github.com/JohnLangford/vowpal_wabbit.git
+    && git clone https://github.com/JohnLangford/vowpal_wabbit.git \
     && cd /gensim_dependencies/vowpal_wabbit \
-    && make
+    && make \
     && make install
 
 # Start gensim

From a40b1dfbf2e930f0f580f678b238baae55ed712b Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Sat, 27 May 2017 23:07:16 +0530
Subject: [PATCH 04/19] remove unused imports

---
 docker/check_fast_version.py | 2 --
 1 file changed, 2 deletions(-)

diff --git a/docker/check_fast_version.py b/docker/check_fast_version.py
index b389eba8ae..f988f49433 100644
--- a/docker/check_fast_version.py
+++ b/docker/check_fast_version.py
@@ -1,8 +1,6 @@
 import sys
 
 try:
-    from gensim.models.word2vec_inner import train_batch_sg, train_batch_cbow
-    from gensim.models.word2vec_inner import score_sentence_sg, score_sentence_cbow
     from gensim.models.word2vec_inner import FAST_VERSION, MAX_WORDS_IN_BATCH
 
     print('FAST_VERSION ok ! Retrieved with value ', FAST_VERSION)

From 330b9ad214a21c7d5c021faf4e985b852f7fd8a4 Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Mon, 12 Jun 2017 17:35:25 +0530
Subject: [PATCH 05/19] modified dockerfile

---
 docker/Dockerfile            | 45 +++++++++++++++++++-----------------
 docker/check_fast_version.py |  2 +-
 2 files changed, 25 insertions(+), 22 deletions(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index fe7f64b3d3..0c9cd60ef7 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -2,8 +2,9 @@ FROM ubuntu:16.04
 
 MAINTAINER Daniel Baptista Dias <danielbpdias@gmail.com>
 
-ENV GENSIM_REPOSITORY https://github.com/RaRe-Technologies/gensim/archive
-ENV GENSIM_VERSION master
+ENV GENSIM_REPOSITORY https://github.com/parulsethi/gensim/archive
+ENV GENSIM_BRANCH gensim_docker
+ENV PYTHONPATH "/usr/local/lib/python3/dist-packages:/usr/local/lib/python3.5/site-packages:/usr/lib/python3/dist-packages"
 
 # Installs python, pip and setup tools (with fixed versions)
 RUN apt-get update \
@@ -21,6 +22,7 @@ RUN apt-get update \
     python3-setuptools=20.7.0-1 \
     unzip=6.0-20ubuntu1 \
     wget=1.17.1-1ubuntu1.1 \
+    libopenblas-dev \
     libboost-program-options-dev \
     libboost-python-dev \
     zlib1g-dev
@@ -41,18 +43,19 @@ RUN pip install --upgrade pip
 
 # Install dependencies
 RUN pip install \
-    annoy \
-    cython \
-    jupyter \
-    matplotlib \
-    nltk \
-    pandas \
-    pyemd \
-    sklearn \
+    annoy==1.8.3 \
+    cython==0.25.2 \
+    jupyter==1.0.0 \
+    matplotlib==2.0.0 \
+    morfessor==2.0.2a4 \
+    nltk==3.2.2 \
+    pandas==0.19.2 \
+    pyemd==0.4.3 \
+    scikit-learn==0.18.1 \
     testfixtures \
     unittest2 \
-    git+git://github.com/mila-udem/fuel.git@stable \
-    git+git://github.com/mila-udem/blocks.git@stable \
+    git+https://github.com/mila-udem/fuel.git@stable \
+    git+https://github.com/mila-udem/blocks.git@stable \
     -r https://raw.githubusercontent.com/mila-udem/blocks/stable/requirements.txt
 
 # Create gensim directory and dependencies directory
@@ -62,9 +65,9 @@ RUN mkdir /gensim \
 # Download gensim from Github
 RUN mkdir /gensim/download \
     && cd /gensim/download \
-    && wget --quiet $GENSIM_REPOSITORY/$GENSIM_VERSION.zip \
-    && unzip $GENSIM_VERSION.zip \
-    && mv ./gensim-$GENSIM_VERSION/* /gensim \
+    && wget --quiet $GENSIM_REPOSITORY/$GENSIM_BRANCH.zip \
+    && unzip $GENSIM_BRANCH.zip \
+    && mv ./gensim-$GENSIM_BRANCH/* /gensim \
     && rm -rf /gensim/download \
     && cd /gensim \
     && python setup.py install
@@ -78,6 +81,12 @@ ENV VOWPAL_WABBIT_PATH gensim_dependencies/vowpal_wabbit/vowpalwabbit/vw
 
 # Install custom dependencies
 
+# Install fastText
+RUN cd /gensim_dependencies \
+    && git clone https://github.com/facebookresearch/fastText.git \
+    && cd /gensim_dependencies/fastText \
+    && make
+
 # Install WordRank
 RUN cd /gensim_dependencies \
     && git clone https://bitbucket.org/shihaoji/wordrank \
@@ -85,12 +94,6 @@ RUN cd /gensim_dependencies \
     && cd /gensim_dependencies/wordrank \
     && sh ./install.sh
 
-# Install fastText
-RUN cd /gensim_dependencies \
-    && git clone https://github.com/facebookresearch/fastText.git \
-    && cd /gensim_dependencies/fastText \
-    && make
-
 # Install MorphologicalPriorsForWordEmbeddings
 RUN cd /gensim_dependencies \
     && git clone https://github.com/rguthrie3/MorphologicalPriorsForWordEmbeddings.git
diff --git a/docker/check_fast_version.py b/docker/check_fast_version.py
index f988f49433..958c59852d 100644
--- a/docker/check_fast_version.py
+++ b/docker/check_fast_version.py
@@ -1,7 +1,7 @@
 import sys
 
 try:
-    from gensim.models.word2vec_inner import FAST_VERSION, MAX_WORDS_IN_BATCH
+    from gensim.models.word2vec_inner import FAST_VERSION
 
     print('FAST_VERSION ok ! Retrieved with value ', FAST_VERSION)
     sys.exit()

From 800aae69cc8754d9f1f91abaef89c3825e1cde52 Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Tue, 13 Jun 2017 22:05:30 +0530
Subject: [PATCH 06/19] add subversion, locales

---
 docker/Dockerfile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index 0c9cd60ef7..ffffcd430f 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -4,7 +4,6 @@ MAINTAINER Daniel Baptista Dias <danielbpdias@gmail.com>
 
 ENV GENSIM_REPOSITORY https://github.com/parulsethi/gensim/archive
 ENV GENSIM_BRANCH gensim_docker
-ENV PYTHONPATH "/usr/local/lib/python3/dist-packages:/usr/local/lib/python3.5/site-packages:/usr/lib/python3/dist-packages"
 
 # Installs python, pip and setup tools (with fixed versions)
 RUN apt-get update \
@@ -22,6 +21,8 @@ RUN apt-get update \
     python3-setuptools=20.7.0-1 \
     unzip=6.0-20ubuntu1 \
     wget=1.17.1-1ubuntu1.1 \
+    subversion \
+    locales \
     libopenblas-dev \
     libboost-program-options-dev \
     libboost-python-dev \

From 498ae7900610e68d742a843b865255b0fa7879fd Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Mon, 19 Jun 2017 16:16:29 +0530
Subject: [PATCH 07/19] use both python2 and python3

---
 docker/Dockerfile | 76 ++++++++++++++++++++++++++---------------------
 1 file changed, 42 insertions(+), 34 deletions(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index ffffcd430f..9ea7f23b94 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -19,13 +19,15 @@ RUN apt-get update \
     python3=3.5.1-3 \
     python3-pip=8.1.1-2ubuntu0.4 \
     python3-setuptools=20.7.0-1 \
+    python \
+    python-pip \
+    python-setuptools \
     unzip=6.0-20ubuntu1 \
     wget=1.17.1-1ubuntu1.1 \
     subversion \
     locales \
     libopenblas-dev \
     libboost-program-options-dev \
-    libboost-python-dev \
     zlib1g-dev
 
 # Setup python language
@@ -34,34 +36,34 @@ ENV LANG en_US.UTF-8
 ENV LC_CTYPE en_US.UTF-8
 ENV LC_ALL en_US.UTF-8
 
-# Make some symlinks
-RUN cd /usr/bin \
-    && ln -s easy_install3 easy_install \
-    && ln -s pip3 pip
-
 # Upgrade pip
-RUN pip install --upgrade pip
+RUN pip2 install --upgrade pip
+RUN pip3 install --upgrade pip
 
 # Install dependencies
-RUN pip install \
-    annoy==1.8.3 \
+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/fuel.git@stable \
+    git+https://github.com/mila-udem/blocks.git@stable \
+    -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 \
-    morfessor==2.0.2a4 \
     nltk==3.2.2 \
     pandas==0.19.2 \
-    pyemd==0.4.3 \
-    scikit-learn==0.18.1 \
-    testfixtures \
-    unittest2 \
     git+https://github.com/mila-udem/fuel.git@stable \
     git+https://github.com/mila-udem/blocks.git@stable \
     -r https://raw.githubusercontent.com/mila-udem/blocks/stable/requirements.txt
 
 # Create gensim directory and dependencies directory
 RUN mkdir /gensim \
-    && mkdir /gensim_dependencies
+    && mkdir /gensim/gensim_dependencies
 
 # Download gensim from Github
 RUN mkdir /gensim/download \
@@ -71,60 +73,66 @@ RUN mkdir /gensim/download \
     && mv ./gensim-$GENSIM_BRANCH/* /gensim \
     && rm -rf /gensim/download \
     && cd /gensim \
-    && python setup.py install
+    && pip2 install .[test] \
+    && pip3 install .[test] \
+    && python2 setup.py install \
+    && python3 setup.py install
 
 # Set ENV variables for wrappers
 ENV FT_HOME gensim_dependencies/fastText
 ENV WR_HOME gensim_dependencies/wordrank
 ENV MALLET_HOME gensim_dependencies/mallet
-ENV DTM_PATH gensim_dependencies/dtm/bin/dtm-linux64
+ENV DTM_PATH gensim_dependencies/dtm/dtm/main
 ENV VOWPAL_WABBIT_PATH gensim_dependencies/vowpal_wabbit/vowpalwabbit/vw
 
 # Install custom dependencies
 
 # Install fastText
-RUN cd /gensim_dependencies \
+RUN cd /gensim/gensim_dependencies \
     && git clone https://github.com/facebookresearch/fastText.git \
-    && cd /gensim_dependencies/fastText \
+    && cd /gensim/gensim_dependencies/fastText \
     && make
 
 # Install WordRank
-RUN cd /gensim_dependencies \
+RUN cd /gensim/gensim_dependencies \
     && git clone https://bitbucket.org/shihaoji/wordrank \
-    && cp /gensim/docker/wordrank_install.sh /gensim_dependencies/wordrank/install.sh \
-    && cd /gensim_dependencies/wordrank \
+    && cp /gensim/docker/wordrank_install.sh /gensim/gensim_dependencies/wordrank/install.sh \
+    && cd /gensim/gensim_dependencies/wordrank \
     && sh ./install.sh
 
 # Install MorphologicalPriorsForWordEmbeddings
-RUN cd /gensim_dependencies \
+RUN cd /gensim/gensim_dependencies \
     && git clone https://github.com/rguthrie3/MorphologicalPriorsForWordEmbeddings.git
 
 # Install DTM
-RUN cd /gensim_dependencies \
-    && git clone https://github.com/magsilva/dtm.git
+RUN cd /gensim/gensim_dependencies \
+    && git clone https://github.com/blei-lab/dtm.git \
+    && cd /gensim/gensim_dependencies/dtm/dtm \
+    && make
 
 # Install Mallet
-RUN mkdir /gensim_dependencies/mallet \
-    && mkdir /gensim_dependencies/download \
-    && cd /gensim_dependencies/download \
+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-2.0.8.zip \
     && unzip mallet-2.0.8.zip \
-    && mv ./mallet-2.0.8/* /gensim_dependencies/mallet \
-    && rm -rf /gensim_dependencies/download \
-    && cd /gensim_dependencies/mallet \
+    && mv ./mallet-2.0.8/* /gensim/gensim_dependencies/mallet \
+    && rm -rf /gensim/gensim_dependencies/download \
+    && cd /gensim/gensim_dependencies/mallet \
     && ant
 
 # Install Vowpal wabbit
-RUN cd /gensim_dependencies \
+RUN cd /gensim/gensim_dependencies \
     && git clone https://github.com/JohnLangford/vowpal_wabbit.git \
-    && cd /gensim_dependencies/vowpal_wabbit \
+    && cd /gensim/gensim_dependencies/vowpal_wabbit \
     && make \
     && make install
 
 # Start gensim
 
 # Run check script
-RUN python /gensim/docker/check_fast_version.py
+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

From 9afaca74eb73f001fe1b7ec21537850ce7bc247c Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Wed, 21 Jun 2017 14:20:54 +0530
Subject: [PATCH 08/19] upgrade numpy version

---
 docker/Dockerfile | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index 9ea7f23b94..0b1f1d6139 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -47,7 +47,6 @@ RUN pip2 install \
     matplotlib==2.0.0 \
     nltk==3.2.2 \
     pandas==0.19.2 \
-    git+https://github.com/mila-udem/fuel.git@stable \
     git+https://github.com/mila-udem/blocks.git@stable \
     -r https://raw.githubusercontent.com/mila-udem/blocks/stable/requirements.txt
 
@@ -57,10 +56,13 @@ RUN pip3 install \
     matplotlib==2.0.0 \
     nltk==3.2.2 \
     pandas==0.19.2 \
-    git+https://github.com/mila-udem/fuel.git@stable \
     git+https://github.com/mila-udem/blocks.git@stable \
     -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
+
 # Create gensim directory and dependencies directory
 RUN mkdir /gensim \
     && mkdir /gensim/gensim_dependencies
@@ -74,8 +76,8 @@ RUN mkdir /gensim/download \
     && rm -rf /gensim/download \
     && cd /gensim \
     && pip2 install .[test] \
-    && pip3 install .[test] \
     && python2 setup.py install \
+    && pip3 install .[test] \
     && python3 setup.py install
 
 # Set ENV variables for wrappers
@@ -139,4 +141,4 @@ 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
\ No newline at end of file
+EXPOSE 9000

From 19ce3ca20d77dfe375b0d23353971fb6637e3319 Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Thu, 22 Jun 2017 21:15:08 +0530
Subject: [PATCH 09/19] add readme with relevant commands

---
 docker/README.md | 49 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)
 create mode 100644 docker/README.md

diff --git a/docker/README.md b/docker/README.md
new file mode 100644
index 0000000000..e024e1ee52
--- /dev/null
+++ b/docker/README.md
@@ -0,0 +1,49 @@
+# Build gensim image
+
+In docker directory run the following command to build the image locally:
+
+```
+docker build -t gensim .
+````
+
+After that, you will need to search the gensim_image_id and tag the image using:
+
+```
+# check the image
+docker image ls
+
+# generage the tag
+docker tag [gensim_image_id] [my_user]/gensim:latest
+```
+
+Run the interactive bash mode:
+
+```
+docker run -it [my_user]/gensim /bin/bash
+```
+
+Run gensim tests in the interactive bash mode:
+
+```
+# run tests with desired python version
+cd gensim
+python2 setup.py test
+```
+
+To push the image to docker hub:
+
+```
+# login to docker hub
+docker login
+
+# push image to docker hub
+docker push [my_user]/gensim
+```
+
+# Run gensim image from anywhere
+
+Just execute:
+
+```
+docker run -p 9000:9000 [my_user]/gensim
+```
\ No newline at end of file

From ee3c4cfb9a5fa0f35a64ed6b2342face14b8faf3 Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Sun, 25 Jun 2017 23:03:38 +0530
Subject: [PATCH 10/19] add fixed versions for wrapper dependencies

---
 docker/Dockerfile | 46 ++++++++++++++++++++++++++++++----------------
 1 file changed, 30 insertions(+), 16 deletions(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index 0b1f1d6139..05c9778c0d 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -2,8 +2,8 @@ FROM ubuntu:16.04
 
 MAINTAINER Daniel Baptista Dias <danielbpdias@gmail.com>
 
-ENV GENSIM_REPOSITORY https://github.com/parulsethi/gensim/archive
-ENV GENSIM_BRANCH gensim_docker
+ENV GENSIM_REPOSITORY https://codeload.github.com/RaRe-Technologies/gensim/zip
+ENV GENSIM_VERSION 2.2.0
 
 # Installs python, pip and setup tools (with fixed versions)
 RUN apt-get update \
@@ -47,7 +47,7 @@ RUN pip2 install \
     matplotlib==2.0.0 \
     nltk==3.2.2 \
     pandas==0.19.2 \
-    git+https://github.com/mila-udem/blocks.git@stable \
+    git+https://github.com/mila-udem/blocks.git@7beb788f1fcfc78d56c59a5edf9b4e8d98f8d7d9 \
     -r https://raw.githubusercontent.com/mila-udem/blocks/stable/requirements.txt
 
 RUN pip3 install \
@@ -56,7 +56,7 @@ RUN pip3 install \
     matplotlib==2.0.0 \
     nltk==3.2.2 \
     pandas==0.19.2 \
-    git+https://github.com/mila-udem/blocks.git@stable \
+    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
@@ -70,9 +70,9 @@ RUN mkdir /gensim \
 # Download gensim from Github
 RUN mkdir /gensim/download \
     && cd /gensim/download \
-    && wget --quiet $GENSIM_REPOSITORY/$GENSIM_BRANCH.zip \
-    && unzip $GENSIM_BRANCH.zip \
-    && mv ./gensim-$GENSIM_BRANCH/* /gensim \
+    && wget --quiet $GENSIM_REPOSITORY/$GENSIM_VERSION \
+    && unzip $GENSIM_VERSION \
+    && mv ./gensim-$GENSIM_VERSION/* /gensim \
     && rm -rf /gensim/download \
     && cd /gensim \
     && pip2 install .[test] \
@@ -81,11 +81,19 @@ RUN mkdir /gensim/download \
     && python3 setup.py install
 
 # Set ENV variables for wrappers
-ENV FT_HOME gensim_dependencies/fastText
-ENV WR_HOME gensim_dependencies/wordrank
-ENV MALLET_HOME gensim_dependencies/mallet
-ENV DTM_PATH gensim_dependencies/dtm/dtm/main
-ENV VOWPAL_WABBIT_PATH gensim_dependencies/vowpal_wabbit/vowpalwabbit/vw
+ENV FT_HOME ~/gensim/gensim_dependencies/fastText
+ENV WR_HOME ~/gensim/gensim_dependencies/wordrank
+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 WORDRANK_VERSION 44f3f7786f76c79c083dfad9d64e20bacfb4a0b0
+ENV MORPHOLOGICALPRIORSFORWORDEMBEDDINGS_VERSION ec2e37a3bcb8bd7b56b75b043c47076bc5decf22
+ENV DTM_VERSION 67139e6f526b2bc33aef56dc36176a1b8b210056
+ENV MALLET_VERSION 2.0.8
+ENV VOWPAL_WABBIT_VERSION 9f61108b7ed53311024f884f6b55887c938391f9
 
 # Install custom dependencies
 
@@ -93,6 +101,7 @@ ENV VOWPAL_WABBIT_PATH gensim_dependencies/vowpal_wabbit/vowpalwabbit/vw
 RUN cd /gensim/gensim_dependencies \
     && git clone https://github.com/facebookresearch/fastText.git \
     && cd /gensim/gensim_dependencies/fastText \
+    && git checkout $FASTTEXT_VERSION \
     && make
 
 # Install WordRank
@@ -100,25 +109,29 @@ RUN cd /gensim/gensim_dependencies \
     && git clone https://bitbucket.org/shihaoji/wordrank \
     && cp /gensim/docker/wordrank_install.sh /gensim/gensim_dependencies/wordrank/install.sh \
     && cd /gensim/gensim_dependencies/wordrank \
+    && git checkout $WORDRANK_VERSION \
     && sh ./install.sh
 
 # Install MorphologicalPriorsForWordEmbeddings
 RUN cd /gensim/gensim_dependencies \
-    && git clone https://github.com/rguthrie3/MorphologicalPriorsForWordEmbeddings.git
+    && git clone https://github.com/rguthrie3/MorphologicalPriorsForWordEmbeddings.git \
+    && cd /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-2.0.8.zip \
-    && unzip mallet-2.0.8.zip \
-    && mv ./mallet-2.0.8/* /gensim/gensim_dependencies/mallet \
+    && 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
@@ -127,6 +140,7 @@ RUN mkdir /gensim/gensim_dependencies/mallet \
 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
 

From 9fd041e36b996c7f74dff5f6bdfee20d9c4560cb Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Thu, 29 Jun 2017 17:18:58 +0530
Subject: [PATCH 11/19] made requested changes

---
 docker/Dockerfile          | 18 +++++-------------
 docker/README.md           | 12 +-----------
 docker/wordrank_install.sh | 19 -------------------
 3 files changed, 6 insertions(+), 43 deletions(-)
 delete mode 100644 docker/wordrank_install.sh

diff --git a/docker/Dockerfile b/docker/Dockerfile
index 05c9778c0d..fee0ba5285 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -82,21 +82,21 @@ RUN mkdir /gensim/download \
 
 # Set ENV variables for wrappers
 ENV FT_HOME ~/gensim/gensim_dependencies/fastText
-ENV WR_HOME ~/gensim/gensim_dependencies/wordrank
 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 WORDRANK_VERSION 44f3f7786f76c79c083dfad9d64e20bacfb4a0b0
 ENV MORPHOLOGICALPRIORSFORWORDEMBEDDINGS_VERSION ec2e37a3bcb8bd7b56b75b043c47076bc5decf22
 ENV DTM_VERSION 67139e6f526b2bc33aef56dc36176a1b8b210056
 ENV MALLET_VERSION 2.0.8
-ENV VOWPAL_WABBIT_VERSION 9f61108b7ed53311024f884f6b55887c938391f9
+ENV VOWPAL_WABBIT_VERSION ba51ab08fa0c3b8d29cbb8cb87472b3ebd24cd55
 
 # 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 \
@@ -104,18 +104,10 @@ RUN cd /gensim/gensim_dependencies \
     && git checkout $FASTTEXT_VERSION \
     && make
 
-# Install WordRank
-RUN cd /gensim/gensim_dependencies \
-    && git clone https://bitbucket.org/shihaoji/wordrank \
-    && cp /gensim/docker/wordrank_install.sh /gensim/gensim_dependencies/wordrank/install.sh \
-    && cd /gensim/gensim_dependencies/wordrank \
-    && git checkout $WORDRANK_VERSION \
-    && sh ./install.sh
-
 # Install MorphologicalPriorsForWordEmbeddings
 RUN cd /gensim/gensim_dependencies \
     && git clone https://github.com/rguthrie3/MorphologicalPriorsForWordEmbeddings.git \
-    && cd /gensim_dependencies/MorphologicalPriorsForWordEmbeddings \
+    && cd /gensim/gensim_dependencies/MorphologicalPriorsForWordEmbeddings \
     && git checkout $MORPHOLOGICALPRIORSFORWORDEMBEDDINGS_VERSION
 
 # Install DTM
@@ -140,7 +132,7 @@ RUN mkdir /gensim/gensim_dependencies/mallet \
 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 \
+    && git checkout $VOWPAL_WABBIT_VERSION \
     && make \
     && make install
 
diff --git a/docker/README.md b/docker/README.md
index e024e1ee52..40cf8cd6ba 100644
--- a/docker/README.md
+++ b/docker/README.md
@@ -30,17 +30,7 @@ cd gensim
 python2 setup.py test
 ```
 
-To push the image to docker hub:
-
-```
-# login to docker hub
-docker login
-
-# push image to docker hub
-docker push [my_user]/gensim
-```
-
-# Run gensim image from anywhere
+# Run ipython notebook with installed gensim
 
 Just execute:
 
diff --git a/docker/wordrank_install.sh b/docker/wordrank_install.sh
deleted file mode 100644
index 36a13e3007..0000000000
--- a/docker/wordrank_install.sh
+++ /dev/null
@@ -1,19 +0,0 @@
-#!/bin/bash
-
-printf "1. clean up workspace\n"
-./clean.sh
-
-printf "\n2. install glove to construct cooccurrence matrix\n"
-wget http://nlp.stanford.edu/software/GloVe-1.0.tar.gz # if failed, check http://nlp.stanford.edu/projects/glove/ for the original version
-tar -xvzf GloVe-1.0.tar.gz; rm GloVe-1.0.tar.gz
-patch -p0 -i glove.patch
-cd glove; make clean all; cd ..
-
-printf "\n3. install hyperwords for evaluation\n"
-hg clone -r 56 https://bitbucket.org/omerlevy/hyperwords
-patch -p0 -i hyperwords.patch
-
-printf "\n4. build wordrank\n"
-export CC=gcc CXX=g++      # uncomment this line if you don't have an Intel compiler, but with gcc all #pragma simd are ignored as of now
-cmake .
-make clean all
\ No newline at end of file

From 1cc3398e6cb3fd3ed5ecf9937a01fb4195286cce Mon Sep 17 00:00:00 2001
From: Menshikh Ivan <menshikh.iv@gmail.com>
Date: Thu, 29 Jun 2017 20:44:15 +0500
Subject: [PATCH 12/19] update readme

---
 docker/README.md | 28 +++++-----------------------
 1 file changed, 5 insertions(+), 23 deletions(-)

diff --git a/docker/README.md b/docker/README.md
index 40cf8cd6ba..c577413a87 100644
--- a/docker/README.md
+++ b/docker/README.md
@@ -4,36 +4,18 @@ In docker directory run the following command to build the image locally:
 
 ```
 docker build -t gensim .
-````
-
-After that, you will need to search the gensim_image_id and tag the image using:
-
 ```
-# check the image
-docker image ls
 
-# generage the tag
-docker tag [gensim_image_id] [my_user]/gensim:latest
-```
+# Run ipython notebook with installed gensim
 
-Run the interactive bash mode:
+Just execute:
 
 ```
-docker run -it [my_user]/gensim /bin/bash
+docker run -p 9000:9000 gensim
 ```
 
-Run gensim tests in the interactive bash mode:
+# Run the interactive bash mode
 
 ```
-# run tests with desired python version
-cd gensim
-python2 setup.py test
-```
-
-# Run ipython notebook with installed gensim
-
-Just execute:
-
+docker run -it gensim /bin/bash
 ```
-docker run -p 9000:9000 [my_user]/gensim
-```
\ No newline at end of file

From 4825a47395c10b62e6cad804314159c70f9b26f2 Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Thu, 29 Jun 2017 21:34:41 +0530
Subject: [PATCH 13/19] change vw pin and remove docker-yml

---
 docker/Dockerfile         | 24 ++++++++++++------------
 docker/docker-compose.yml |  7 -------
 2 files changed, 12 insertions(+), 19 deletions(-)
 delete mode 100644 docker/docker-compose.yml

diff --git a/docker/Dockerfile b/docker/Dockerfile
index fee0ba5285..2e196e6396 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -2,8 +2,8 @@ FROM ubuntu:16.04
 
 MAINTAINER Daniel Baptista Dias <danielbpdias@gmail.com>
 
-ENV GENSIM_REPOSITORY https://codeload.github.com/RaRe-Technologies/gensim/zip
-ENV GENSIM_VERSION 2.2.0
+ENV GENSIM_REPOSITORY https://github.com/parulsethi/gensim/archive
+ENV GENSIM_VERSION gensim_docker
 
 # Installs python, pip and setup tools (with fixed versions)
 RUN apt-get update \
@@ -19,16 +19,16 @@ RUN apt-get update \
     python3=3.5.1-3 \
     python3-pip=8.1.1-2ubuntu0.4 \
     python3-setuptools=20.7.0-1 \
-    python \
-    python-pip \
-    python-setuptools \
+    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 \
-    locales \
-    libopenblas-dev \
-    libboost-program-options-dev \
-    zlib1g-dev
+    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
@@ -70,8 +70,8 @@ RUN mkdir /gensim \
 # Download gensim from Github
 RUN mkdir /gensim/download \
     && cd /gensim/download \
-    && wget --quiet $GENSIM_REPOSITORY/$GENSIM_VERSION \
-    && unzip $GENSIM_VERSION \
+    && wget --quiet $GENSIM_REPOSITORY/$GENSIM_VERSION.zip \
+    && unzip $GENSIM_VERSION.zip \
     && mv ./gensim-$GENSIM_VERSION/* /gensim \
     && rm -rf /gensim/download \
     && cd /gensim \
diff --git a/docker/docker-compose.yml b/docker/docker-compose.yml
deleted file mode 100644
index 84f5f2b712..0000000000
--- a/docker/docker-compose.yml
+++ /dev/null
@@ -1,7 +0,0 @@
-version: '2'
-
-services:
-  gensim:
-    build: .
-    ports:
-      - 9000:9000
\ No newline at end of file

From d0f09bb43616aca8be8e75c7495a9902d115ee5c Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Fri, 30 Jun 2017 12:48:31 +0530
Subject: [PATCH 14/19] change vw version and make absolute paths for wrappers

---
 docker/Dockerfile | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index 2e196e6396..7b193b94af 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -81,17 +81,17 @@ RUN mkdir /gensim/download \
     && python3 setup.py install
 
 # 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
+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 ba51ab08fa0c3b8d29cbb8cb87472b3ebd24cd55
+ENV VOWPAL_WABBIT_VERSION 69ecc2847fa0c876c6e0557af409f386f0ced59a
 
 # Install custom dependencies
 

From 36a5025b9862af872e6a673be4c582761f01893c Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Fri, 30 Jun 2017 14:45:57 +0530
Subject: [PATCH 15/19] specify original gensim repo for download

---
 docker/Dockerfile | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index 7b193b94af..b82dd40990 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -2,8 +2,9 @@ FROM ubuntu:16.04
 
 MAINTAINER Daniel Baptista Dias <danielbpdias@gmail.com>
 
-ENV GENSIM_REPOSITORY https://github.com/parulsethi/gensim/archive
-ENV GENSIM_VERSION gensim_docker
+ENV GENSIM_REPOSITORY https://github.com/RaRe-Technologies/gensim/archive
+ENV GENSIM_VERSION 2.2.0
+ENV GENSIM_BRANCH master
 
 # Installs python, pip and setup tools (with fixed versions)
 RUN apt-get update \
@@ -70,11 +71,12 @@ RUN mkdir /gensim \
 # Download gensim from Github
 RUN mkdir /gensim/download \
     && cd /gensim/download \
-    && wget --quiet $GENSIM_REPOSITORY/$GENSIM_VERSION.zip \
-    && unzip $GENSIM_VERSION.zip \
-    && mv ./gensim-$GENSIM_VERSION/* /gensim \
+    && wget --quiet $GENSIM_REPOSITORY/$GENSIM_BRANCH.zip \
+    && unzip $GENSIM_BRANCH.zip \
+    && mv ./gensim-$GENSIM_BRANCH/* /gensim \
     && rm -rf /gensim/download \
     && cd /gensim \
+    && git checkout tags/GENSIM_VERSION
     && pip2 install .[test] \
     && python2 setup.py install \
     && pip3 install .[test] \

From 2db28f4e309b37bee13a7a7edf12114bfcf959f9 Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Fri, 30 Jun 2017 14:52:50 +0530
Subject: [PATCH 16/19] change maintainer

---
 docker/Dockerfile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index b82dd40990..be0631599f 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -1,6 +1,6 @@
 FROM ubuntu:16.04
 
-MAINTAINER Daniel Baptista Dias <danielbpdias@gmail.com>
+MAINTAINER Parul Sethi <parul1sethi@gmail.com>
 
 ENV GENSIM_REPOSITORY https://github.com/RaRe-Technologies/gensim/archive
 ENV GENSIM_VERSION 2.2.0
@@ -76,7 +76,7 @@ RUN mkdir /gensim/download \
     && mv ./gensim-$GENSIM_BRANCH/* /gensim \
     && rm -rf /gensim/download \
     && cd /gensim \
-    && git checkout tags/GENSIM_VERSION
+    && git checkout tags/$GENSIM_VERSION
     && pip2 install .[test] \
     && python2 setup.py install \
     && pip3 install .[test] \

From 25865a9df6147a6215c19abfd8df138e6961c3ce Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Fri, 30 Jun 2017 14:56:12 +0530
Subject: [PATCH 17/19] correct missing slash

---
 docker/Dockerfile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index be0631599f..1543630b5b 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -76,7 +76,7 @@ RUN mkdir /gensim/download \
     && mv ./gensim-$GENSIM_BRANCH/* /gensim \
     && rm -rf /gensim/download \
     && cd /gensim \
-    && git checkout tags/$GENSIM_VERSION
+    && git checkout tags/$GENSIM_VERSION \
     && pip2 install .[test] \
     && python2 setup.py install \
     && pip3 install .[test] \

From 1add68de716280150e00747ce37ed44806d633de Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Fri, 30 Jun 2017 15:32:16 +0530
Subject: [PATCH 18/19] use git clone for gensim

---
 docker/Dockerfile | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index 1543630b5b..41e347146a 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -2,9 +2,8 @@ FROM ubuntu:16.04
 
 MAINTAINER Parul Sethi <parul1sethi@gmail.com>
 
-ENV GENSIM_REPOSITORY https://github.com/RaRe-Technologies/gensim/archive
+ENV GENSIM_REPOSITORY https://github.com/RaRe-Technologies/gensim.git
 ENV GENSIM_VERSION 2.2.0
-ENV GENSIM_BRANCH master
 
 # Installs python, pip and setup tools (with fixed versions)
 RUN apt-get update \
@@ -69,12 +68,7 @@ RUN mkdir /gensim \
     && mkdir /gensim/gensim_dependencies
 
 # Download gensim from Github
-RUN mkdir /gensim/download \
-    && cd /gensim/download \
-    && wget --quiet $GENSIM_REPOSITORY/$GENSIM_BRANCH.zip \
-    && unzip $GENSIM_BRANCH.zip \
-    && mv ./gensim-$GENSIM_BRANCH/* /gensim \
-    && rm -rf /gensim/download \
+RUN git clone $GENSIM_REPOSITORY \
     && cd /gensim \
     && git checkout tags/$GENSIM_VERSION \
     && pip2 install .[test] \

From ce4656d0be7d37d573ca4f54b722fbddffff2d3f Mon Sep 17 00:00:00 2001
From: parulsethi <parul1sethi@gmail.com>
Date: Fri, 30 Jun 2017 16:07:43 +0530
Subject: [PATCH 19/19] correct gensim folder sequences

---
 docker/Dockerfile | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index 41e347146a..46f9944a68 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -63,10 +63,6 @@ RUN pip3 install \
 RUN pip2 install -U numpy
 RUN pip3 install -U numpy
 
-# Create gensim directory and dependencies directory
-RUN mkdir /gensim \
-    && mkdir /gensim/gensim_dependencies
-
 # Download gensim from Github
 RUN git clone $GENSIM_REPOSITORY \
     && cd /gensim \
@@ -76,6 +72,9 @@ RUN git clone $GENSIM_REPOSITORY \
     && 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