[bug#32484] Add Numba and Scanpy

[bug#32484] Add Numba and Scanpy

[Ricardo Wurmus]

This patch series adds Scanpy, a toolkit for analyzing single-cell gene
expression data.  It depends on Numba, which requires llvmlite.
Unfortunately, llvmlite does not work with our regular llvm package.  It
needs a patched LLVM.

--
Ricardo

[bug#32484] [PATCH 1/4] gnu: Add python-llvmlite.

[Ricardo Wurmus]

* gnu/packages/llvm.scm (python-llvmlite): New variable.
---
 gnu/packages/llvm.scm | 53 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 52 insertions(+), 1 deletion(-)

diff --git a/gnu/packages/llvm.scm b/gnu/packages/llvm.scm
index 98592ad09..e9b7065ab 100644
--- a/gnu/packages/llvm.scm
+++ b/gnu/packages/llvm.scm
@@ -3,7 +3,7 @@
 ;;; Copyright © 2015 Mark H Weaver <mhw@netris.org>
 ;;; Copyright © 2015, 2017, 2018 Ludovic Courtès <ludo@gnu.org>
 ;;; Copyright © 2016 Dennis Mungai <dmngaie@gmail.com>
-;;; Copyright © 2016 Ricardo Wurmus <rekado@elephly.net>
+;;; Copyright © 2016, 2018 Ricardo Wurmus <rekado@elephly.net>
 ;;; Copyright © 2017 Roel Janssen <roel@gnu.org>
 ;;; Copyright © 2018 Marius Bakke <mbakke@fastmail.com>
 ;;;
@@ -29,6 +29,7 @@
   #:use-module (guix utils)
   #:use-module (guix build-system gnu)
   #:use-module (guix build-system cmake)
+  #:use-module (guix build-system python)
   #:use-module (gnu packages)
   #:use-module (gnu packages gcc)
   #:use-module (gnu packages bootstrap)           ;glibc-dynamic-linker
@@ -379,3 +380,53 @@ code analysis tools.")
        (patches (list (search-patch "llvm-for-extempore.patch")))))
     ;; Extempore refuses to build on architectures other than x86_64
     (supported-systems '("x86_64-linux"))))
+
+(define-public python-llvmlite
+  (package
+    (name "python-llvmlite")
+    (version "0.24.0")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (pypi-uri "llvmlite" version))
+       (sha256
+        (base32
+         "01zwjlc3c5mhrwmv4b73zgbskwqps9ly0nrh54bbj1f1l72f839j"))))
+    (build-system python-build-system)
+    (inputs
+     `(("llvm"
+        ,(package
+           (inherit llvm)
+           (source (origin
+                     (inherit (package-source llvm))
+                     (patches
+                      (list
+                       (origin
+                         (method url-fetch)
+                         (uri (string-append "https://raw.githubusercontent.com/numba/"
+                                             "llvmlite/v" version "/conda-recipes/"
+                                             "D47188-svml.patch"))
+                         (sha256
+                          (base32
+                           "0mrj24jvkv3hjcmyg98zmvmyl1znlh2j63rdr69f6g7s96d2pfv1")))
+                       (origin
+                         (method url-fetch)
+                         (uri (string-append "https://raw.githubusercontent.com/numba/"
+                                             "llvmlite/v" version "/conda-recipes/"
+                                             "twine_cfg_undefined_behavior.patch"))
+                         (sha256
+                          (base32
+                           "07h71n2m1mn9zcfgw04zglffknplb233zqbcd6pckq0wygkrxflp")))
+                       (origin
+                         (method url-fetch)
+                         (uri (string-append "https://raw.githubusercontent.com/numba/"
+                                             "llvmlite/v" version "/conda-recipes/"
+                                             "0001-Transforms-Add-missing-header-for-InstructionCombini.patch"))
+                         (sha256
+                          (base32
+                           "1pp0z9696l6j4dwz7ypjrm4vvkj0d3mlf1g8zmiyk08akw5lz0cb")))))))))))
+    (home-page "http://llvmlite.pydata.org")
+    (synopsis "Wrapper around basic LLVM functionality")
+    (description
+     "This package provides a Python binding to LLVM for use in Numba.")
+    (license license:bsd-3)))
-- 
2.18.0

[bug#32484] [PATCH 2/4] gnu: Add python-numba.

[Ricardo Wurmus]

* gnu/packages/python.scm (python-numba): New variable.
---
 gnu/packages/python.scm | 84 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 84 insertions(+)

diff --git a/gnu/packages/python.scm b/gnu/packages/python.scm
index 3db29e23f..7f343bdab 100644
--- a/gnu/packages/python.scm
+++ b/gnu/packages/python.scm
@@ -99,6 +99,7 @@
   #:use-module (gnu packages libevent)
   #:use-module (gnu packages libffi)
   #:use-module (gnu packages linux)
+  #:use-module (gnu packages llvm)
   #:use-module (gnu packages machine-learning)
   #:use-module (gnu packages man)
   #:use-module (gnu packages maths)
@@ -13889,3 +13890,86 @@ Let's Encrypt.")
 development that supports command line argument parsing, command string
 validation testing and application logic.")
     (license license:expat)))
+
+;; Make sure to upgrade python-llvmlite in (gnu packages llvm) together with
+;; python-numba.  They have a very unflexible relationship.
+(define-public python-numba
+  (package
+    (name "python-numba")
+    (version "0.39.0")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (pypi-uri "numba" version))
+       (sha256
+        (base32
+         "1bibvkwga1v8293i9ivl469d8bzgabn3vgr2ig7c1i68v8frsx07"))))
+    (build-system python-build-system)
+    (arguments
+     `(#:modules ((guix build utils)
+                  (guix build python-build-system)
+                  (ice-9 ftw)
+                  (srfi srfi-1)
+                  (srfi srfi-26))
+       #:phases
+       (modify-phases %standard-phases
+         (add-after 'unpack 'disable-proprietary-features
+           (lambda _
+             (setenv "NUMBA_DISABLE_HSA" "1")
+             (setenv "NUMBA_DISABLE_CUDA" "1")
+             #t))
+         (add-after 'unpack 'remove-failing-tests
+           (lambda _
+             ;; FIXME: these tests fail for unknown reasons:
+             ;; test_non_writable_pycache, test_non_creatable_pycache, and
+             ;; test_frozen (all in numba.tests.test_dispatcher.TestCache).
+             (substitute* "numba/tests/test_dispatcher.py"
+               (("def test(_non_writable_pycache)" _ m)
+                (string-append "def guix_skip" m))
+               (("def test(_non_creatable_pycache)" _ m)
+                (string-append "def guix_skip" m))
+               (("def test(_frozen)" _ m)
+                (string-append "def guix_skip" m)))
+
+             ;; These tests fail because we don't run the tests from the build
+             ;; directory: test_setup_py_distutils, test_setup_py_setuptools
+             ;; They ar in numba.tests.test_pycc.TestDistutilsSupport.
+             (substitute* "numba/tests/test_pycc.py"
+               (("def test(_setup_py_distutils|_setup_py_setuptools)" _ m)
+                (string-append "def guix_skip" m)))
+             #t))
+         (replace 'check
+           (lambda _
+             (let ((cwd (getcwd)))
+               (setenv "PYTHONPATH"
+                       (string-append cwd "/build/"
+                                      (find (cut string-prefix? "lib" <>)
+                                            (scandir (string-append cwd "/build")))
+                                      ":"
+                                      (getenv "PYTHONPATH")))
+               ;; Something is wrong with the PYTHONPATH when running the
+               ;; tests from the build directory, as it complains about not being
+               ;; able to import certain modules.
+               (with-directory-excursion "/tmp"
+                 (invoke "python3" "-m" "numba.runtests" "-v" "-m")))
+             #t)))))
+    (propagated-inputs
+     `(("python-llvmlite" ,python-llvmlite)
+       ("python-numpy" ,python-numpy)
+       ("python-singledispatch" ,python-singledispatch)))
+    ;; Needed for tests.
+    (inputs
+     `(("python-jinja2" ,python-jinja2)
+       ("python-pygments" ,python-pygments)))
+    (home-page "https://numba.pydata.org")
+    (synopsis "Compile Python code using LLVM")
+    (description "Numba gives you the power to speed up your applications with
+high performance functions written directly in Python.  With a few
+annotations, array-oriented and math-heavy Python code can be just-in-time
+compiled to native machine instructions, similar in performance to C, C++ and
+Fortran, without having to switch languages or Python interpreters.
+
+Numba works by generating optimized machine code using the LLVM compiler
+infrastructure at import time, runtime, or statically (using the included pycc
+tool).")
+    (license license:bsd-3)))
-- 
2.18.0

[bug#32484] [PATCH 3/4] gnu: Add python-anndata.

[Ricardo Wurmus]

* gnu/packages/python.scm (python-anndata): New variable.
---
 gnu/packages/python.scm | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/gnu/packages/python.scm b/gnu/packages/python.scm
index 7f343bdab..2838d2ae5 100644
--- a/gnu/packages/python.scm
+++ b/gnu/packages/python.scm
@@ -13973,3 +13973,29 @@ Numba works by generating optimized machine code using the LLVM compiler
 infrastructure at import time, runtime, or statically (using the included pycc
 tool).")
     (license license:bsd-3)))
+
+(define-public python-anndata
+  (package
+    (name "python-anndata")
+    (version "0.6.9")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (pypi-uri "anndata" version))
+       (sha256
+        (base32
+         "1fh461xyyc7pcrjfgd013bdc2alf53r46ss3gfw3431mbb1gappi"))))
+    (build-system python-build-system)
+    (propagated-inputs
+     `(("python-h5py" ,python-h5py)
+       ("python-natsort" ,python-natsort)
+       ("python-pandas" ,python-pandas)
+       ("python-scipy" ,python-scipy)))
+    (home-page "https://github.com/theislab/anndata")
+    (synopsis "Annotated data for data analysis pipelines")
+    (description "Anndata is a package for simple (functional) high-level APIs
+for data analysis pipelines.  In this context, it provides an efficient,
+scalable way of keeping track of data together with learned annotations and
+reduces the code overhead typically encountered when using a mostly
+object-oriented library such as @code{scikit-learn}.")
+    (license license:bsd-3)))
-- 
2.18.0

[bug#32484] [PATCH 4/4] gnu: Add python-scanpy.

[Ricardo Wurmus]

* gnu/packages/bioinformatics.scm (python-scanpy): New variable.
---
 gnu/packages/bioinformatics.scm | 36 +++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index dce8ab62f..ef9d81435 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -13406,3 +13406,39 @@ conversions, region filtering, FASTA sequence extraction and more.")
       ;; gffread is under Expat, but gclib is under Artistic 2.0
       (license (list license:expat
                      license:artistic2.0)))))
+
+(define-public python-scanpy
+  (package
+    (name "python-scanpy")
+    (version "1.2.2")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (pypi-uri "scanpy" version))
+       (sha256
+        (base32
+         "1ak7bxms5a0yvf65prppq2g38clkv7c7jnjbnfpkh3xxv7q512jz"))))
+    (build-system python-build-system)
+    (propagated-inputs
+     `(("python-anndata" ,python-anndata)
+       ("python-igraph" ,python-igraph)
+       ("python-numba" ,python-numba)
+       ("python-joblib" ,python-joblib)
+       ("python-natsort" ,python-natsort)
+       ("python-networkx" ,python-networkx)
+       ("python-statsmodels" ,python-statsmodels)
+       ("python-scikit-learn" ,python-scikit-learn)
+       ("python-matplotlib" ,python-matplotlib)
+       ("python-pandas" ,python-pandas)
+       ("python-scipy" ,python-scipy)
+       ("python-seaborn" ,python-seaborn)
+       ("python-h5py" ,python-h5py)
+       ("python-tables" ,python-tables)))
+    (home-page "http://github.com/theislab/scanpy")
+    (synopsis "Single-Cell Analysis in Python.")
+    (description "Scanpy is a scalable toolkit for analyzing single-cell gene
+expression data.  It includes preprocessing, visualization, clustering,
+pseudotime and trajectory inference and differential expression testing.  The
+Python-based implementation efficiently deals with datasets of more than one
+million cells.")
+    (license license:bsd-3)))
-- 
2.18.0

bug#32484: [PATCH 4/4] gnu: Add python-scanpy.

[Ricardo Wurmus]

> * gnu/packages/bioinformatics.scm (python-scanpy): New variable.

I pushed this (and the other three patches) to the master branch with
commit c7fe888b4.

--
Ricardo