Custom modules for apache-arrow and feather support in Guix

python.scm

(define-module (nextjournal packages python)
  #:use-module (guix download)
  #:use-module (guix git-download)
  #:use-module ((guix licenses) #:prefix license:)
  #:use-module (guix packages)
  #:use-module (guix utils)
  #:use-module (guix build-system cmake)
  #:use-module (guix build-system gnu)
  #:use-module (guix build-system python)
  #:use-module (nextjournal packages compression)
  #:use-module (gnu packages)
  #:use-module (gnu packages boost)
  #:use-module (gnu packages check)
  #:use-module (gnu packages cmake)
  #:use-module (gnu packages compression)
  #:use-module (gnu packages jemalloc)
  #:use-module (gnu packages package-management)
  #:use-module (gnu packages python)
  #:use-module (gnu packages web))

(define-public apache-arrow
  (package
    (name "apache-arrow")
    (version "0.5.0")
    (source
      (origin
        (method git-fetch)
        (uri (git-reference
               (url "https://github.com/apache/arrow")
               (commit "apache-arrow-0.5.0")))
        (patches (search-patches "arrow-fix-build.patch"))
        (sha256
          (base32
            "104dqiz3kfianb85m2pr0xwzviggplnfhgr0hy9y0phf3h4sv4j7"))))
    (build-system cmake-build-system)
    (inputs
     `(("boost" ,boost)
       ("rapidjson" ,rapidjson)
       ("brotli" ,google-brotli)
       ("flatbuffers" ,flatbuffers)
       ("jemalloc" ,jemalloc)
       ; -DARROW_PYTHON
       ("python-3" ,python)
       ("python-numpy" ,python-numpy)))
    (arguments
       `(#:tests? #f
         #:phases
          (modify-phases %standard-phases
            (add-before 'configure 'enter-source-directory
              (lambda _ (chdir "cpp") #t))
            (add-after 'unpack 'set-env
              (lambda _
                (setenv "BOOST_ROOT" (assoc-ref %build-inputs "boost")) ; necessary?
                (setenv "BROTLI_HOME" (assoc-ref %build-inputs "brotli"))
                (setenv "FLATBUFFERS_HOME" (assoc-ref %build-inputs "flatbuffers"))
                (setenv "JEMALLOC_HOME" (assoc-ref %build-inputs "jemalloc"))
                (setenv "RAPIDJSON_HOME" (assoc-ref %build-inputs "rapidjson"))
                #t)))
         #:configure-flags (list "-DCMAKE_BUILD_TYPE=Release"
                                 "-DARROW_WITH_ZSTD=OFF"
                                 "-DARROW_WITH_LZ4=OFF"

                                 ;; Install to PREFIX/lib (the default is
                                 ;; PREFIX/lib64).
                                 (string-append "-DCMAKE_INSTALL_LIBDIR="
                                                (assoc-ref %outputs "out")
                                                "/lib")

                                 "-DARROW_PYTHON=ON"

                                 ;; XXX These Guix package offer static
                                 ;; libraries that are not position independent,
                                 ;; and ld fails to link them into the arrow .so
                                 "-DARROW_WITH_SNAPPY=OFF"
                                 "-DARROW_WITH_ZLIB=OFF"

                                 ;; Building the tests forces on all the
                                 ;; optional features and the use of static
                                 ;; libraries.
                                 "-DARROW_BUILD_TESTS=OFF"
                                 "-DARROW_BUILD_STATIC=OFF")))
    (home-page "https://arrow.apache.org/")
    (synopsis "Columnar in-memory analytics")
    (description "Apache Arrow is a columnar in-memory analytics layer
designed to accelerate big data. It houses a set of canonical in-memory
representations of flat and hierarchical data along with multiple
language-bindings for structure manipulation. It also provides IPC and common
algorithm implementations.")
    (license license:asl2.0)))

(define-public python-pyarrow
  (package
    (name "python-pyarrow")
    (version "0.5.0")
    (source
      (origin
       (method git-fetch)
       (uri (git-reference
             (url "https://github.com/apache/arrow")
             (commit "apache-arrow-0.5.0")))
       (sha256
         (base32
           "104dqiz3kfianb85m2pr0xwzviggplnfhgr0hy9y0phf3h4sv4j7"))))
    (build-system python-build-system)
    (arguments
     '(#:tests? #f ; XXX Test failures related to missing libhdfs, libhdfs3,
                   ; and "Unsupported numpy type 22".
       #:phases
       (modify-phases %standard-phases
         (add-after 'unpack 'enter-source-directory
           (lambda _ (chdir "python") #t))
         (add-after 'unpack 'set-env
           (lambda _
             ;; Fails if using pkg-config instead.
             (setenv "ARROW_HOME" (assoc-ref %build-inputs "apache-arrow")))))))
    (propagated-inputs
     `(("apache-arrow" ,apache-arrow)
       ("python-six" ,python-six)
       ("python-numpy" ,python-numpy)
       ("python-pandas" ,python-pandas)))
    (native-inputs
     `(("python-cython" ,python-cython)
       ("cmake" ,cmake)
       ("python-pytest" ,python-pytest)
       ("python-setuptools-scm" ,python-setuptools-scm)))
    (home-page "https://arrow.apache.org/docs/python/")
    (synopsis "Python library for Apache Arrow")
    (description "This library provides a Pythonic API wrapper for the reference
Arrow C++ implementation, along with tools for interoperability with pandas,
NumPy, and other traditional Python scientific computing packages.")
    (license license:asl2.0)))

;; Does it really not matter that apache-arrow's libarrow_python.so is
;; built using Python 3?
(define-public python2-pyarrow
  (package-with-python2 python-pyarrow))

(define-public flatbuffers
  (package
    (name "flatbuffers")
    (version "1.7.1")
    (source
      (origin
        (method url-fetch)
        (uri (string-append "https://github.com/google/flatbuffers/archive/v"
                            version ".tar.gz"))
        (sha256
         (base32
          "129hzbx8ag7fvv4606wgaydkk11pdaagkr4pdxsk985bpg7wv38g"))))
    (build-system cmake-build-system)
    (home-page "https://google.github.io/flatbuffers/")
    (synopsis "Memory-efficient serialization library")
    (description "FlatBuffers is a cross platform serialization library for C++,
C#, C, Go, Java, JavaScript, PHP, and Python.  It was originally created at
Google for game development and other performance-critical applications.")
    (license license:asl2.0)))

(define-public python-feather-format
  (package
    (name "python-feather-format")
    (version "0.4.0")
    (source
      (origin
        (method url-fetch)
        (uri (pypi-uri "feather-format" version))
        (sha256
         (base32
          "1adivm5w5ji4qv7hq7942vqlk8l2wgw87bdlsia771z14z3zp857"))))
    (build-system python-build-system)
    (propagated-inputs
     `(("python-pandas" ,python-pandas)
       ("python-pyarrow" ,python-pyarrow)))
    (home-page "https://github.com/wesm/feather")
    (synopsis "Wrapper library to the Feather file format")
    (description "This package provides a Python wrapper library to the
Apache Arrow-based Feather file format.")
    (license license:asl2.0)))

(define-public python2-feather-format
  (package-with-python2 python-feather-format))

(define-public python-nbformat-4.3
  (package
    (name "python-nbformat")
    (version "4.3.0")
    (source
     (origin
       (method url-fetch)
       (uri (pypi-uri "nbformat" version))
       (sha256
        (base32
         "12s7j4qja8b5bs1kyw5dzmrqbjxxj8wk52cyasbiqbv7fblcrssz"))))
    (build-system python-build-system)
    (arguments `(#:tests? #f)) ; no test target
    (propagated-inputs
     `(("python-ipython-genutils" ,python-ipython-genutils)
       ("python-jsonschema" ,python-jsonschema)
       ("python-jupyter-core" ,python-jupyter-core)
       ("python-traitlets" ,python-traitlets)))
    (home-page "http://jupyter.org")
    (synopsis "Jupyter Notebook format")
    (description "This package provides the reference implementation of the
Jupyter Notebook format and Python APIs for working with notebooks.")
    (license license:bsd-3)))

(define-public python2-nbformat-4.3
  (package-with-python2 python-nbformat))

(define-public python-plotly
  (package
    (name "python-plotly")
    (version "2.0.14")
    (source
      (origin
        (method url-fetch)
        (uri (pypi-uri "plotly" version))
        (sha256
         (base32
          "038x99hss8g9wvvnq1dpncw5bdsqkiffkhmbpjhiq3mf2ysdmhnf"))))
    (build-system python-build-system)
    (arguments
     '(;; Tests fail as shown below. Are they even included in the PyPi release?
       ;; TypeError: clientresp() missing 1 required positional argument: 'data'
       #:tests? #f
       #:phases
       (modify-phases %standard-phases
         (add-before 'check 'set-HOME
           ;; The test suite wants to write to $HOME.
           (lambda _
             (setenv "HOME" "/tmp"))))))
    (propagated-inputs
     `(("python-decorator" ,python-decorator)
       ("python-nbformat" ,python-nbformat-4.3)
       ("python-pytz" ,python-pytz)
       ("python-requests" ,python-requests)
       ("python-six" ,python-six)))
    (home-page "https://plot.ly/python/")
    (synopsis "Interactive plotting library for Python")
    (description "Plotly's Python graphing library makes interactive,
publication-quality graphs online.  Examples of how to make line plots, scatter
plots, area charts, bar charts, error bars, box plots, histograms, heatmaps,
subplots, multiple-axes, polar charts, and bubble charts. ")
    (license license:expat)))

(define-public python2-plotly
  (package-with-python2 python-plotly))