Data science server installation script

install.sh

mkdir -p ~/anaconda_install
wget https://repo.continuum.io/archive/Anaconda2-4.2.0-Linux-x86_64.sh -O ~/anaconda_install/anaconda.sh
bash ~/anaconda_install/anaconda.sh -b -p $HOME/anaconda2
export PATH="$HOME/anaconda2/bin:$PATH"
echo 'PATH="$HOME/anaconda2/bin:$PATH"' >> ~/.bashrc

conda upgrade -y scikit-learn

apt-get update && apt-get install -y git build-essential g++ && apt-get clean

apt-get install -y libfreetype6-dev
apt-get install -y libglib2.0-0 libxext6 libsm6 libxrender1 libfontconfig1 --fix-missing

# Install XGBoost
cd /usr/local/src && git clone --recursive https://github.com/dmlc/xgboost.git && cd xgboost && sh build.sh && cd python-package && python setup.py install

# Vowpal Wabbit
apt-get install -y libboost-program-options-dev zlib1g-dev libboost-python-dev
cd /usr/lib/x86_64-linux-gnu/ && rm -f libboost_python.a && rm -f libboost_python.so
ln -sf libboost_python-py34.so libboost_python.so && ln -sf libboost_python-py34.a libboost_python.a
pip install vowpalwabbit

# Tensorflow and Keras
conda install -y tensorflow && pip install keras && KERAS_BACKEND=tensorflow

# NLTK Downloader no longer continues smoothly after an error, so we explicitly list
# the corpuses that work
python -m nltk.downloader -d /usr/share/nltk_data abc alpino \
    averaged_perceptron_tagger basque_grammars biocreative_ppi bllip_wsj_no_aux \
    book_grammars brown brown_tei cess_cat cess_esp chat80 city_database cmudict \
    comparative_sentences comtrans conll2000 conll2002 conll2007 crubadan dependency_treebank \
    europarl_raw floresta framenet_v15 gazetteers genesis gutenberg hmm_treebank_pos_tagger \
    ieer inaugural indian jeita kimmo knbc large_grammars lin_thesaurus mac_morpho machado \
    masc_tagged maxent_ne_chunker maxent_treebank_pos_tagger moses_sample movie_reviews \
    mte_teip5 names nps_chat omw opinion_lexicon paradigms \
    pil pl196x ppattach problem_reports product_reviews_1 product_reviews_2 propbank \
    pros_cons ptb punkt qc reuters rslp rte sample_grammars semcor sentence_polarity \
    sentiwordnet shakespeare sinica_treebank smultron snowball_data spanish_grammars \
    state_union stopwords subjectivity swadesh switchboard tagsets timit toolbox treebank \
    twitter_samples udhr2 udhr unicode_samples universal_tagset universal_treebanks_v20 \
    verbnet webtext word2vec_sample wordnet wordnet_ic words ycoe && \

# Stop-words
pip install stop-words

pip install joblib gensim spacy seaborn

pip install pymongo mongoengine

pip install tqdm

pip install python-crfsuite
ln -sf libstdc++.so.6.0.20 ~/anaconda2/lib/libstdc++.so
ln -sf libstdc++.so.6.0.20 ~/anaconda2/lib/libstdc++.so.6