requirements.txt

# gym[atari,box2d,classic_control]==0.10.5
# it seems already installed
# imageio==2.3.0
# pyglet==1.2.4
altair # a declarative statistical visualization
ax-platform # adaptive experimentation platform
apache-airflow # a platform to programmatically author, schedule and monitor workflows
autogluon==0.0.9 # autoML for deep learning
beautifulsoup4==4.7.1
bcolz==1.2.1 # provides columnar, chunked data containers that can be compressed either in-memory and on-disk.
bokeh
cartopy==0.16.0
catboost==0.12.2 # A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression
contextily==0.99.0 # retrieve and write to disk tile maps from the internet into geospatial raster files (OSM)
dagit==0.6.6 # UI for dagster
dagster==0.6.6 # ETL, ML, Data Pipelines, and more.
dask[complete] #
datasketch==1.4.1
descartes==1.1.0 # is used by geopandas
hyperopt # Distributed Asynchronous Hyperparameter Optimization in Python
ipyvolume # draw 3d in jupyter
joblib==0.13.2 # lightweight pipelining (parallel computing and transparent disk-caching of functions and lazy re-evaluation)
joypy==v0.1.10 # joy division like visualization in matplotlib
jgraph==0.2.1 # An embeddable webGL graph visualization library.
gensim==3.7.1 # unsupervised topic modeling and natural language processing
geopandas==0.4.0
lightgbm==2.2.3 # A fast, distributed, high performance gradient boosting (GBDT, GBRT, GBM or MART)
luigi==2.8.7 # helps you build complex pipelines of batch jobs. It handles dependency resolution, workflow management, visualization etc. It also comes with Hadoop support built in.
mlflow==1.2.0 # platform for the machine learning lifecycle
mrcnn # Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
mxnet-cu102=1.6.0 # an ultra-scalable deep learning framework
newspaper3k==0.2.8 # Article scraping & curation
numpy-quaternion # adds a quaternion dtype to NumPy
numpyro==0.4.0 # is a small probabilistic programming library that provides a NumPy backend for Pyro
osmnx==0.9 # Retrieve, construct, analyze, and visualize street networks from OpenStreetMap
overpass==0 .0 # The friendly PIL fork (Python Imaging Library)
psycopg2-binary==2.8.4 # PostgreSQL database adapter for the Python programming language
pydotplus==2.0.2 # Python interface to Graphviz's Dot language?
pytorch_transformers # A library of state-of-the-art pretrained models for Natural Language Processing (NLP)
pyro-ppl[extras]==1.4.0 # Pyro is a flexible, scalable deep probabilistic programming library built on PyTorch
regex==2018.01.10 # is required by spacy
scrapy==1.7.3
simhash==1.9.0 #
surt==0.3.0
tables # managing hierarchical datasets (HDF5)
# tensorflow-gpu==2.0.0-beta1 # TODO: check compatibility
tfx # TensorFlow Extended (TFX) is an end-to-end platform for deploying production ML pipelines
toml #
torchbiggraph # A distributed system to learn embeddings of large graphs
xgboost==0.81 # Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library

# https://github.com/jd/tenacity
# retrying library
tenacity==5.0.2
# doesn't work on python3 :( and fails with error:
# vaex==0.3.10 # Out-of-Core DataFrames for Python, visualize and explore big tabular data at a billion rows per second.
wordcloud==1.5.0 # word cloud generator