unofficial mirror of guix-patches@gnu.org 
 help / color / mirror / code / Atom feed
* [bug#68789] [PATCH 1/2] gnu: Add python-unyt.
  2024-01-28 22:49 [bug#68789] [PATCH 0/2] gnu: Add python-pyjanitor Troy Figiel
@ 2024-01-28 21:47 ` Troy Figiel
  2024-01-28 22:13 ` [bug#68789] [PATCH 2/2] gnu: Add python-pyjanitor Troy Figiel
                   ` (5 subsequent siblings)
  6 siblings, 0 replies; 11+ messages in thread
From: Troy Figiel @ 2024-01-28 21:47 UTC (permalink / raw)
  To: 68789

* gnu/packages/python-science.scm (python-unyt): New variable.
---
 gnu/packages/python-science.scm | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/gnu/packages/python-science.scm b/gnu/packages/python-science.scm
index 9d72608de4..3013c77c34 100644
--- a/gnu/packages/python-science.scm
+++ b/gnu/packages/python-science.scm
@@ -42,6 +42,7 @@
 (define-module (gnu packages python-science)
   #:use-module ((guix licenses) #:prefix license:)
   #:use-module (gnu packages)
+  #:use-module (gnu packages astronomy)
   #:use-module (gnu packages base)
   #:use-module (gnu packages bioinformatics)
   #:use-module (gnu packages boost)
@@ -1217,6 +1218,34 @@ (define-public python-statannot
 annotations on an existing boxplots and barplots generated by seaborn.")
     (license license:expat)))
 
+(define-public python-unyt
+  (package
+    (name "python-unyt")
+    (version "3.0.1")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (pypi-uri "unyt" version))
+       (sha256
+        (base32 "00900bw24rxgcgwgxp9xlx0l5im96r1n5hn0r3mxvbdgc3lyyq48"))))
+    (build-system pyproject-build-system)
+    (propagated-inputs (list python-h5py ;optional import
+                             python-matplotlib ;optional import
+                             python-numpy
+                             python-sympy))
+    ;; python-astropy and python-pint are also optional imports, but we do not
+    ;; propagate them due to their sizes.
+    (native-inputs (list python-astropy python-pint python-pytest))
+    (home-page "https://unyt.readthedocs.io")
+    (synopsis "Library for working with data that has physical units")
+    (description
+     "Writing code that deals with data with physical units can be confusing.
+A function might return an array but at least with plain @code{numpy}, there
+is no way to easily tell what the units of the data are without somehow
+knowing a priori.  @code{unyt} handles this problem by providing a subclass of
+the @code{ndarray} class in @code{numpy} that is unit aware.")
+    (license license:bsd-3)))
+
 (define-public python-upsetplot
   (package
     (name "python-upsetplot")
-- 
2.42.0





^ permalink raw reply related	[flat|nested] 11+ messages in thread

* [bug#68789] [PATCH 2/2] gnu: Add python-pyjanitor.
  2024-01-28 22:49 [bug#68789] [PATCH 0/2] gnu: Add python-pyjanitor Troy Figiel
  2024-01-28 21:47 ` [bug#68789] [PATCH 1/2] gnu: Add python-unyt Troy Figiel
@ 2024-01-28 22:13 ` Troy Figiel
  2024-01-29 14:26 ` [bug#68789] [PATCH 0/2] " Sharlatan Hellseher
                   ` (4 subsequent siblings)
  6 siblings, 0 replies; 11+ messages in thread
From: Troy Figiel @ 2024-01-28 22:13 UTC (permalink / raw)
  To: 68789

* gnu/packages/python-science.scm (python-pyjanitor): New variable.
---
 gnu/packages/python-science.scm | 59 +++++++++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)

diff --git a/gnu/packages/python-science.scm b/gnu/packages/python-science.scm
index 3013c77c34..00b7e6cae1 100644
--- a/gnu/packages/python-science.scm
+++ b/gnu/packages/python-science.scm
@@ -48,6 +48,7 @@ (define-module (gnu packages python-science)
   #:use-module (gnu packages boost)
   #:use-module (gnu packages build-tools)
   #:use-module (gnu packages check)
+  #:use-module (gnu packages chemistry)
   #:use-module (gnu packages cpp)
   #:use-module (gnu packages crypto)
   #:use-module (gnu packages databases)
@@ -771,6 +772,64 @@ (define-public python-pandera
 @end itemize")
     (license license:expat)))
 
+(define-public python-pyjanitor
+  (package
+    (name "python-pyjanitor")
+    (version "0.26.0")
+    (source
+     (origin
+       ;; The build requires the mkdocs directory for the description in
+       ;; setup.py. This is not included in the PyPI tarball.
+       (method git-fetch)
+       (uri (git-reference
+             (url "https://github.com/pyjanitor-devs/pyjanitor")
+             (commit (string-append "v" version))))
+       (file-name (git-file-name name version))
+       (sha256
+        (base32 "1f8xbl1k9l2z56bapp7v6bd3016zrk48igcaz6hb553r6yfl7vfx"))))
+    (build-system pyproject-build-system)
+    ;; Pyjanitor has an extensive test suite. For quick debugging, the tests
+    ;; marked turtle can be skipped using "-m" "not turtle".
+    (arguments
+     (list
+      #:test-flags '(list
+                     ;; Tries to connect to the internet.
+                     "-k"
+                     "not test_is_connected"
+
+                     ;; PySpark has not been packaged yet.
+                     "--ignore"
+                     "tests/spark")
+      #:phases #~(modify-phases %standard-phases
+                   (add-before 'check 'set-env-ci
+                     (lambda _
+                       ;; Some tests are skipped if the JANITOR_CI_MACHINE
+                       ;; variable is not set.
+                       (setenv "JANITOR_CI_MACHINE" "1"))))))
+    (propagated-inputs (list python-multipledispatch
+                             python-natsort
+                             python-pandas-flavor
+                             python-scipy
+
+                             ;; Optional imports.
+                             python-biopython ;biology submodule
+                             python-unyt)) ;engineering submodule
+    (native-inputs (list python-pytest
+
+                         ;; Optional imports. We do not propagate them due to
+                         ;; their size.
+                         python-numba ;speedup of joins
+                         rdkit)) ;chemistry submodule
+    (home-page "https://github.com/pyjanitor-devs/pyjanitor")
+    (synopsis "Tools for cleaning and transforming pandas DataFrames")
+    (description
+     "@code{pyjanitor} provides a set of data cleaning routines for
+@code{pandas} DataFrames.  These routines extend the method chaining API
+defined by @code{pandas} for a subset of its methods.  Originally, this
+package was a port of the R package by the same name and it is inspired by the
+ease-of-use and expressiveness of the @code{dplyr} package.")
+    (license license:expat)))
+
 (define-public python-pythran
   (package
     (name "python-pythran")
-- 
2.42.0





^ permalink raw reply related	[flat|nested] 11+ messages in thread

* [bug#68789] [PATCH 0/2] gnu: Add python-pyjanitor.
@ 2024-01-28 22:49 Troy Figiel
  2024-01-28 21:47 ` [bug#68789] [PATCH 1/2] gnu: Add python-unyt Troy Figiel
                   ` (6 more replies)
  0 siblings, 7 replies; 11+ messages in thread
From: Troy Figiel @ 2024-01-28 22:49 UTC (permalink / raw)
  To: 68789

This patch series adds python-pyjanitor and its dependency python-unyt.

Troy Figiel (2):
  gnu: Add python-unyt.
  gnu: Add python-pyjanitor.

 gnu/packages/python-science.scm | 88 +++++++++++++++++++++++++++++++++
 1 file changed, 88 insertions(+)


base-commit: 08ed3ec64ecd571d92d497b2493f5c0225102c99
-- 
2.42.0





^ permalink raw reply	[flat|nested] 11+ messages in thread

* [bug#68789] [PATCH 0/2] gnu: Add python-pyjanitor.
  2024-01-28 22:49 [bug#68789] [PATCH 0/2] gnu: Add python-pyjanitor Troy Figiel
  2024-01-28 21:47 ` [bug#68789] [PATCH 1/2] gnu: Add python-unyt Troy Figiel
  2024-01-28 22:13 ` [bug#68789] [PATCH 2/2] gnu: Add python-pyjanitor Troy Figiel
@ 2024-01-29 14:26 ` Sharlatan Hellseher
  2024-01-29 17:18   ` Troy Figiel
  2024-01-29 18:16 ` [bug#68789] [PATCH 1/2] gnu: Add python-unyt Troy Figiel
                   ` (3 subsequent siblings)
  6 siblings, 1 reply; 11+ messages in thread
From: Sharlatan Hellseher @ 2024-01-29 14:26 UTC (permalink / raw)
  To: Troy Figiel; +Cc: 68789

[-- Attachment #1: Type: text/plain, Size: 626 bytes --]


Hi Troy,

Thank you for the patches!

I'm in the process of packaging python-yt in (gnu packages astronomy)
and I've noticed that python-unyt is part of it which brought me here
:-) I started reviewing this issue so.

One note - you introduced a module cycle which was not before
astronomy->python-science->astronomy. If the requirement of
python-astropy is soft let's silent it for now.

Also I've already updated the whole chain depending on python-astropy
after it's update to 6.0.0, letting you know if your work requires fresh
Astropy version. It will be in review on 20th next month.

What do you think?

Regards,
Oleg

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 832 bytes --]

^ permalink raw reply	[flat|nested] 11+ messages in thread

* [bug#68789] [PATCH 0/2] gnu: Add python-pyjanitor.
  2024-01-29 14:26 ` [bug#68789] [PATCH 0/2] " Sharlatan Hellseher
@ 2024-01-29 17:18   ` Troy Figiel
  2024-01-29 17:31     ` Sharlatan Hellseher
  0 siblings, 1 reply; 11+ messages in thread
From: Troy Figiel @ 2024-01-29 17:18 UTC (permalink / raw)
  To: Sharlatan Hellseher; +Cc: 68789


[-- Attachment #1.1.1: Type: text/plain, Size: 685 bytes --]

Hi Oleg,

Thanks for the check!

On 2024-01-29 15:26, Sharlatan Hellseher wrote:
> One note - you introduced a module cycle which was not before
> astronomy->python-science->astronomy. If the requirement of
> python-astropy is soft let's silent it for now.

Removing the python-astropy dependency should be fine for python-unyt. I
agree that avoiding module cycles would be better. If I recall
correctly, Astropy was only used in tests, because it has a similar
submodule dealing with physical units.

The build was successful and the cycle did not show up in the linter.
How did you find it? Did you happen to notice it when you saw the imports?

Best wishes,

Troy

[-- Attachment #1.1.2: OpenPGP public key --]
[-- Type: application/pgp-keys, Size: 6367 bytes --]

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply	[flat|nested] 11+ messages in thread

* [bug#68789] [PATCH 0/2] gnu: Add python-pyjanitor.
  2024-01-29 17:18   ` Troy Figiel
@ 2024-01-29 17:31     ` Sharlatan Hellseher
  2024-01-29 18:13       ` Troy Figiel
  0 siblings, 1 reply; 11+ messages in thread
From: Sharlatan Hellseher @ 2024-01-29 17:31 UTC (permalink / raw)
  To: Troy Figiel; +Cc: 68789

[-- Attachment #1: Type: text/plain, Size: 561 bytes --]

Hi,


How did you find it? Did you happen to notice it when you saw the imports?
>

It's usually pops up in issues with efforts to break modules cycles
e.g.  https://issues.guix.gnu.org/54539.

I'm not quite sure how it is critical right now, but there was a discussion
that cycles in modules slow down ~guix pull~.

Let's comment astropy out with some notes about optional test dependency
and potential module cycle.

Looking forward for v2, patches look good.

If you have wider plan of upcoming patches please share to coordinate
efforts ;-).

Regards,
Oleg

[-- Attachment #2: Type: text/html, Size: 1592 bytes --]

^ permalink raw reply	[flat|nested] 11+ messages in thread

* [bug#68789] [PATCH 0/2] gnu: Add python-pyjanitor.
  2024-01-29 17:31     ` Sharlatan Hellseher
@ 2024-01-29 18:13       ` Troy Figiel
  0 siblings, 0 replies; 11+ messages in thread
From: Troy Figiel @ 2024-01-29 18:13 UTC (permalink / raw)
  To: Sharlatan Hellseher; +Cc: 68789


[-- Attachment #1.1.1: Type: text/plain, Size: 869 bytes --]

Now that you mention it, there are quite a few cycles. To name a few:

- astronomy->python-science->python-xyz->astronomy
- databases->python-xyz->databases
- bioinformatics->python-science->bioinformatics

On 2024-01-29 18:31, Sharlatan Hellseher wrote:
> If you have wider plan of upcoming patches please share to coordinate
> efforts ;-).

There is only the guix-devel list, right? No Python specific list?

When it comes to the Python ecosystem, I have been looking at

- python-shap
- python-cocotb (#68153)
- ruff

Unfortunately, ruff has caused me some headaches since it uses a Rust
workspace definition. I will probably have to write guix-devel for
advice sooner or later.

I've also still had some Golang packages on my radar, since long-term I
would like to see opentofu and gotenberg included. That might be going
off-topic a bit :-)

[-- Attachment #1.1.2: OpenPGP public key --]
[-- Type: application/pgp-keys, Size: 6367 bytes --]

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply	[flat|nested] 11+ messages in thread

* [bug#68789] [PATCH 1/2] gnu: Add python-unyt.
  2024-01-28 22:49 [bug#68789] [PATCH 0/2] gnu: Add python-pyjanitor Troy Figiel
                   ` (2 preceding siblings ...)
  2024-01-29 14:26 ` [bug#68789] [PATCH 0/2] " Sharlatan Hellseher
@ 2024-01-29 18:16 ` Troy Figiel
  2024-01-29 18:17 ` [bug#68789] [PATCH 2/2] gnu: Add python-pyjanitor Troy Figiel
                   ` (2 subsequent siblings)
  6 siblings, 0 replies; 11+ messages in thread
From: Troy Figiel @ 2024-01-29 18:16 UTC (permalink / raw)
  To: 68789

* gnu/packages/python-science.scm (python-unyt): New variable.
---
 gnu/packages/python-science.scm | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/gnu/packages/python-science.scm b/gnu/packages/python-science.scm
index f775d46349..3390b918a4 100644
--- a/gnu/packages/python-science.scm
+++ b/gnu/packages/python-science.scm
@@ -1287,6 +1287,35 @@ (define-public python-statannot
 annotations on an existing boxplots and barplots generated by seaborn.")
     (license license:expat)))
 
+(define-public python-unyt
+  (package
+    (name "python-unyt")
+    (version "3.0.1")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (pypi-uri "unyt" version))
+       (sha256
+        (base32 "00900bw24rxgcgwgxp9xlx0l5im96r1n5hn0r3mxvbdgc3lyyq48"))))
+    (build-system pyproject-build-system)
+    ;; Astropy is an optional import, but we do not include it as it creates a
+    ;; module cycle: astronomy->python-science->astronomy.
+    (propagated-inputs (list python-h5py ;optional import
+                             python-matplotlib ;optional import
+                             python-numpy
+                             python-sympy))
+    ;; Pint is optional, but we do not propagate it due to its size.
+    (native-inputs (list python-pint python-pytest))
+    (home-page "https://unyt.readthedocs.io")
+    (synopsis "Library for working with data that has physical units")
+    (description
+     "Writing code that deals with data with physical units can be confusing.
+A function might return an array but at least with plain @code{numpy}, there
+is no way to easily tell what the units of the data are without somehow
+knowing a priori.  @code{unyt} handles this problem by providing a subclass of
+the @code{ndarray} class in @code{numpy} that is unit aware.")
+    (license license:bsd-3)))
+
 (define-public python-upsetplot
   (package
     (name "python-upsetplot")
-- 
2.42.0





^ permalink raw reply related	[flat|nested] 11+ messages in thread

* [bug#68789] [PATCH 2/2] gnu: Add python-pyjanitor.
  2024-01-28 22:49 [bug#68789] [PATCH 0/2] gnu: Add python-pyjanitor Troy Figiel
                   ` (3 preceding siblings ...)
  2024-01-29 18:16 ` [bug#68789] [PATCH 1/2] gnu: Add python-unyt Troy Figiel
@ 2024-01-29 18:17 ` Troy Figiel
  2024-01-29 18:18 ` [bug#68789] [PATCH v2 0/2] " Troy Figiel
  2024-01-29 23:01 ` bug#68789: [PATCH " Sharlatan Hellseher
  6 siblings, 0 replies; 11+ messages in thread
From: Troy Figiel @ 2024-01-29 18:17 UTC (permalink / raw)
  To: 68789

* gnu/packages/python-science.scm (python-pyjanitor): New variable.
---
 gnu/packages/python-science.scm | 59 +++++++++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)

diff --git a/gnu/packages/python-science.scm b/gnu/packages/python-science.scm
index 3390b918a4..643fb69f3f 100644
--- a/gnu/packages/python-science.scm
+++ b/gnu/packages/python-science.scm
@@ -47,6 +47,7 @@ (define-module (gnu packages python-science)
   #:use-module (gnu packages boost)
   #:use-module (gnu packages build-tools)
   #:use-module (gnu packages check)
+  #:use-module (gnu packages chemistry)
   #:use-module (gnu packages cpp)
   #:use-module (gnu packages crypto)
   #:use-module (gnu packages databases)
@@ -840,6 +841,64 @@ (define-public python-pandera
 @end itemize")
     (license license:expat)))
 
+(define-public python-pyjanitor
+  (package
+    (name "python-pyjanitor")
+    (version "0.26.0")
+    (source
+     (origin
+       ;; The build requires the mkdocs directory for the description in
+       ;; setup.py. This is not included in the PyPI tarball.
+       (method git-fetch)
+       (uri (git-reference
+             (url "https://github.com/pyjanitor-devs/pyjanitor")
+             (commit (string-append "v" version))))
+       (file-name (git-file-name name version))
+       (sha256
+        (base32 "1f8xbl1k9l2z56bapp7v6bd3016zrk48igcaz6hb553r6yfl7vfx"))))
+    (build-system pyproject-build-system)
+    ;; Pyjanitor has an extensive test suite. For quick debugging, the tests
+    ;; marked turtle can be skipped using "-m" "not turtle".
+    (arguments
+     (list
+      #:test-flags '(list
+                     ;; Tries to connect to the internet.
+                     "-k"
+                     "not test_is_connected"
+
+                     ;; PySpark has not been packaged yet.
+                     "--ignore"
+                     "tests/spark")
+      #:phases #~(modify-phases %standard-phases
+                   (add-before 'check 'set-env-ci
+                     (lambda _
+                       ;; Some tests are skipped if the JANITOR_CI_MACHINE
+                       ;; variable is not set.
+                       (setenv "JANITOR_CI_MACHINE" "1"))))))
+    (propagated-inputs (list python-multipledispatch
+                             python-natsort
+                             python-pandas-flavor
+                             python-scipy
+
+                             ;; Optional imports.
+                             python-biopython ;biology submodule
+                             python-unyt)) ;engineering submodule
+    (native-inputs (list python-pytest
+
+                         ;; Optional imports. We do not propagate them due to
+                         ;; their size.
+                         python-numba ;speedup of joins
+                         rdkit)) ;chemistry submodule
+    (home-page "https://github.com/pyjanitor-devs/pyjanitor")
+    (synopsis "Tools for cleaning and transforming pandas DataFrames")
+    (description
+     "@code{pyjanitor} provides a set of data cleaning routines for
+@code{pandas} DataFrames.  These routines extend the method chaining API
+defined by @code{pandas} for a subset of its methods.  Originally, this
+package was a port of the R package by the same name and it is inspired by the
+ease-of-use and expressiveness of the @code{dplyr} package.")
+    (license license:expat)))
+
 (define-public python-pythran
   (package
     (name "python-pythran")
-- 
2.42.0





^ permalink raw reply related	[flat|nested] 11+ messages in thread

* [bug#68789] [PATCH v2 0/2] gnu: Add python-pyjanitor.
  2024-01-28 22:49 [bug#68789] [PATCH 0/2] gnu: Add python-pyjanitor Troy Figiel
                   ` (4 preceding siblings ...)
  2024-01-29 18:17 ` [bug#68789] [PATCH 2/2] gnu: Add python-pyjanitor Troy Figiel
@ 2024-01-29 18:18 ` Troy Figiel
  2024-01-29 23:01 ` bug#68789: [PATCH " Sharlatan Hellseher
  6 siblings, 0 replies; 11+ messages in thread
From: Troy Figiel @ 2024-01-29 18:18 UTC (permalink / raw)
  To: 68789

This is the updated patch series. I have rebased it on the current master and made the suggested changes.

Troy Figiel (2):
  gnu: Add python-unyt.
  gnu: Add python-pyjanitor.

 gnu/packages/python-science.scm | 88 +++++++++++++++++++++++++++++++++
 1 file changed, 88 insertions(+)


base-commit: 21e4d6cd6913eca131f2c0fd0cd509fc843c7eb8
-- 
2.42.0





^ permalink raw reply	[flat|nested] 11+ messages in thread

* bug#68789: [PATCH 0/2] gnu: Add python-pyjanitor.
  2024-01-28 22:49 [bug#68789] [PATCH 0/2] gnu: Add python-pyjanitor Troy Figiel
                   ` (5 preceding siblings ...)
  2024-01-29 18:18 ` [bug#68789] [PATCH v2 0/2] " Troy Figiel
@ 2024-01-29 23:01 ` Sharlatan Hellseher
  6 siblings, 0 replies; 11+ messages in thread
From: Sharlatan Hellseher @ 2024-01-29 23:01 UTC (permalink / raw)
  To: 68789-done

[-- Attachment #1: Type: text/plain, Size: 405 bytes --]


Modifications applied:

- python-unyt :: rephrase description, partly sourced and combined from
  <https://packages.debian.org/sid/python3-unyt>,
  <https://unyt.readthedocs.io/en/stable/>

- python-pyjanitor :: speed up tests with python-pytest-xdist (~x3
  faster on 16x threads), remove blank lines, disable exact tests
  related to PySpark.

Pushed as 370b79b4f5..cde0adaacd to master.

Thanks,
Oleg

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 832 bytes --]

^ permalink raw reply	[flat|nested] 11+ messages in thread

end of thread, other threads:[~2024-01-29 23:04 UTC | newest]

Thread overview: 11+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-01-28 22:49 [bug#68789] [PATCH 0/2] gnu: Add python-pyjanitor Troy Figiel
2024-01-28 21:47 ` [bug#68789] [PATCH 1/2] gnu: Add python-unyt Troy Figiel
2024-01-28 22:13 ` [bug#68789] [PATCH 2/2] gnu: Add python-pyjanitor Troy Figiel
2024-01-29 14:26 ` [bug#68789] [PATCH 0/2] " Sharlatan Hellseher
2024-01-29 17:18   ` Troy Figiel
2024-01-29 17:31     ` Sharlatan Hellseher
2024-01-29 18:13       ` Troy Figiel
2024-01-29 18:16 ` [bug#68789] [PATCH 1/2] gnu: Add python-unyt Troy Figiel
2024-01-29 18:17 ` [bug#68789] [PATCH 2/2] gnu: Add python-pyjanitor Troy Figiel
2024-01-29 18:18 ` [bug#68789] [PATCH v2 0/2] " Troy Figiel
2024-01-29 23:01 ` bug#68789: [PATCH " Sharlatan Hellseher

Code repositories for project(s) associated with this public inbox

	https://git.savannah.gnu.org/cgit/guix.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).