Script 'mail_helper' called by obssrc Hello community, here is the log from the commit of package python-dask for openSUSE:Factory checked in at 2022-03-31 17:18:33 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/python-dask (Old) and /work/SRC/openSUSE:Factory/.python-dask.new.1900 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Package is "python-dask" Thu Mar 31 17:18:33 2022 rev:51 rq:965275 version:2022.3.0 Changes: -------- --- /work/SRC/openSUSE:Factory/python-dask/python-dask.changes 2022-02-02 22:45:01.142065626 +0100 +++ /work/SRC/openSUSE:Factory/.python-dask.new.1900/python-dask.changes 2022-03-31 17:19:04.509010532 +0200 @@ -1,0 +2,58 @@ +Sun Mar 27 19:18:19 UTC 2022 - Ben Greiner <code@bnavigator.de> + +- dask.dataframe requires dask.bag (revealed by swifter test suite) + +------------------------------------------------------------------- +Fri Mar 25 19:02:53 UTC 2022 - Ben Greiner <code@bnavigator.de> + +- Update to 2022.3.0 + * Bag: add implementation for reservoir sampling + * Add ma.count to Dask array + * Change to_parquet default to compression="snappy" + * Add weights parameter to dask.array.reduction + * Add ddf.compute_current_divisions to get divisions on a sorted + index or column + * Pass __name__ and __doc__ through on DelayedLeaf + * Raise exception for not implemented merge how option + * Move Bag.map_partitions to Blockwise + * Improve error messages for malformed config files + * Revise column-projection optimization to capture common + dask-sql patterns + * Useful error for empty divisions + * Scipy 1.8.0 compat: copy private classes into + dask/array/stats.py +- Release 2022.2.1 + * Add aggregate functions first and last to + dask.dataframe.pivot_table + * Add std() support for datetime64 dtype for pandas-like objects + * Add materialized task counts to HighLevelGraph and Layer html + reprs + * Do not allow iterating a DataFrameGroupBy + * Fix missing newline after info() call on empty DataFrame + * Add groupby.compute as a not implemented method + * Improve multi dataframe join performance + * Include bool type for Index + * Allow ArrowDatasetEngine subclass to override pandas->arrow + conversion also for partitioned write + * Increase performance of k-diagonal extraction in da.diag() and + da.diagonal() + * Change linspace creation to match numpy when num equal to 0 + * Tokenize dataclasses + * Update tokenize to treat dict and kwargs differently +- Release 2022.2.0 + * Add region to to_zarr when using existing array + * Add engine_kwargs support to dask.dataframe.to_sql + * Add include_path_column arg to read_json + * Add expand_dims to Dask array + * Add scheduler option to assert_eq utilities + * Fix eye inconsistency with NumPy for dtype=None + * Fix concatenate inconsistency with NumPy for axis=None + * Type annotations, part 1 + * Really allow any iterable to be passed as a meta + * Use map_partitions (Blockwise) in to_parquet +- Update dask-fix8169-pandas13.patch +- Add dask-py310-test.patch -- gh#dask/dask#8566 +- Make the distributed/dask update sync requirement even more + obvious. + +------------------------------------------------------------------- Old: ---- dask-2022.1.1.tar.gz New: ---- dask-2022.3.0.tar.gz dask-py310-test.patch ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ python-dask.spec ++++++ --- /var/tmp/diff_new_pack.lheM9s/_old 2022-03-31 17:19:05.293001689 +0200 +++ /var/tmp/diff_new_pack.lheM9s/_new 2022-03-31 17:19:05.297001644 +0200 @@ -31,32 +31,33 @@ %bcond_without test %endif %if "%{flavor}" == "test-py310" -%define psuffix -test-py310" +%define psuffix -test-py310 %define skip_python38 1 %define skip_python39 1 %bcond_without test %endif %if "%{flavor}" == "" -# https://github.com/dask/distributed/issues/5350, https://github.com/dask/distributed/issues/5460 -%define skip_python310 1 %bcond_with test %endif %{?!python_module:%define python_module() python3-%{**}} %define skip_python2 1 -%define ghversiontag 2022.01.1 +# ===> Note: python-dask MUST be updated in sync with python-distributed! <=== +%define ghversiontag 2022.03.0 Name: python-dask%{psuffix} -# Note: please always update together with python-distributed! -Version: 2022.1.1 +# ===> Note: python-dask MUST be updated in sync with python-distributed! <=== +Version: 2022.3.0 Release: 0 Summary: Minimal task scheduling abstraction License: BSD-3-Clause URL: https://dask.org Source0: https://files.pythonhosted.org/packages/source/d/dask/dask-%{version}.tar.gz Source1: https://github.com/dask/dask/raw/%{ghversiontag}/conftest.py -# PATCH-FIX-UPSTREAM dask-fix8169-pandas13.patch -- gh#dask/dask#8169 +# PATCH-FIX-UPSTREAM dask-fix8169-pandas13.patch -- gh#dask/dask#8169, gh#dask/dask#8851 Patch0: dask-fix8169-pandas13.patch -BuildRequires: %{python_module base >= 3.7} +# PATCH-FIX-UPSTREAM dask-py310-test.patch -- gh#dask/dask#8566 +Patch1: https://github.com/dask/dask/pull/8566/commits/c329509fc9e78925682c9a0d5c579... +BuildRequires: %{python_module base >= 3.8} BuildRequires: %{python_module packaging >= 20.0} BuildRequires: %{python_module setuptools} BuildRequires: fdupes @@ -210,6 +211,7 @@ Summary: Pandas-like DataFrame data structure for dask Requires: %{name} = %{version} Requires: %{name}-array = %{version} +Requires: %{name}-bag = %{version} Requires: python-numpy >= 1.18 # Patch0 requires pandas 1.3+ -- https://github.com/dask/dask/issues/8169 Requires: python-pandas >= 1.3 @@ -257,7 +259,7 @@ Summary: Diagnostics for dask Requires: %{name} = %{version} Requires: python-Jinja2 -Requires: python-bokeh >= 2.1.1 +Requires: python-bokeh >= 2.4.2 %description diagnostics A flexible library for parallel computing in Python. @@ -316,7 +318,7 @@ %prep %autosetup -p1 -n dask-%{version} cp %{SOURCE1} ./ -sed -i '/addopts/ {s/--durations=10//; s/--color=yes//}' setup.cfg +sed -i '/addopts/d' setup.cfg chmod a-x dask/dataframe/io/orc/utils.py %build @@ -354,15 +356,17 @@ # requires otherwise optional pyarrow (not available on TW) donttest+=" or (test_parquet and (test_chunksize or test_extra_file))" if [[ $(getconf LONG_BIT) -eq 32 ]]; then - # https://github.com/dask/dask/issues/8169 - donttest+=" or test_categorize_info" + # https://github.com/dask/dask/issues/8620 donttest+=" or test_query_with_meta" fi -# https://github.com/dask/dask/issues/8639 -donttest+=" or test__get_paths" # (rarely) flaky on obs donttest+=" or test_local_scheduler" -%pytest --pyargs dask -rfEs -m "not network" -k "not ($donttest)" -n auto +donttest+=" or (test_threaded and test_interrupt)" +# perhaps? rh#1968947#c4 +donttest+=" or test_select_from_select" +# tries to get an IP address +donttest+=" or test_map_partitions_df_input" +%pytest --pyargs dask -n auto -r fE -m "not network" -k "not ($donttest)" --reruns 3 --reruns-delay 3 %endif %if !%{with test} ++++++ _multibuild ++++++ --- /var/tmp/diff_new_pack.lheM9s/_old 2022-03-31 17:19:05.325001328 +0200 +++ /var/tmp/diff_new_pack.lheM9s/_new 2022-03-31 17:19:05.329001283 +0200 @@ -1,6 +1,6 @@ <multibuild> <package>test-py38</package> <package>test-py39</package> - <!-- package>test-py310</package --> + <package>test-py310</package> </multibuild> ++++++ dask-2022.1.1.tar.gz -> dask-2022.3.0.tar.gz ++++++ /work/SRC/openSUSE:Factory/python-dask/dask-2022.1.1.tar.gz /work/SRC/openSUSE:Factory/.python-dask.new.1900/dask-2022.3.0.tar.gz differ: char 5, line 1 ++++++ dask-fix8169-pandas13.patch ++++++ --- /var/tmp/diff_new_pack.lheM9s/_old 2022-03-31 17:19:05.369000832 +0200 +++ /var/tmp/diff_new_pack.lheM9s/_new 2022-03-31 17:19:05.373000786 +0200 @@ -1,8 +1,10 @@ -Index: dask-2021.9.1/dask/dataframe/backends.py -=================================================================== ---- dask-2021.9.1.orig/dask/dataframe/backends.py -+++ dask-2021.9.1/dask/dataframe/backends.py -@@ -356,7 +356,7 @@ class ShuffleGroupResult(SimpleSizeof, d +--- + dask/dataframe/backends.py | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/dask/dataframe/backends.py ++++ b/dask/dataframe/backends.py +@@ -352,7 +352,7 @@ class ShuffleGroupResult(SimpleSizeof, d @group_split_dispatch.register((pd.DataFrame, pd.Series, pd.Index)) def group_split_pandas(df, c, k, ignore_index=False): indexer, locations = pd._libs.algos.groupsort_indexer( @@ -11,4 +13,37 @@ ) df2 = df.take(indexer) locations = locations.cumsum() +--- a/dask/dataframe/tests/test_dataframe.py ++++ b/dask/dataframe/tests/test_dataframe.py +@@ -3,6 +3,7 @@ + import xml.etree.ElementTree + from itertools import product + from operator import add ++import platform + + import numpy as np + import pandas as pd +@@ -3597,6 +3598,12 @@ + # Verbose=False + buf = StringIO() + ddf.info(buf=buf, verbose=True) ++ ++ if platform.architecture()[0] == "32bit": ++ memory_usage = "312.0" ++ else: ++ memory_usage = "496.0" ++ + expected = ( + "<class 'dask.dataframe.core.DataFrame'>\n" + "Int64Index: 4 entries, 0 to 3\n" +@@ -3607,7 +3614,7 @@ + " 1 y 4 non-null category\n" + " 2 z 4 non-null object\n" + "dtypes: category(1), object(1), int64(1)\n" +- "memory usage: 496.0 bytes\n" ++ "memory usage: {} bytes\n".format(memory_usage) + ) + assert buf.getvalue() == expected + +(No newline at EOF) ++++++ dask-py310-test.patch ++++++ From c329509fc9e78925682c9a0d5c579101da740d43 Mon Sep 17 00:00:00 2001 From: Jim Crist-Harif <jcristharif@gmail.com> Date: Thu, 24 Mar 2022 16:00:42 -0500 Subject: [PATCH] Fixup distributed test --- dask/tests/test_distributed.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dask/tests/test_distributed.py b/dask/tests/test_distributed.py index 55804293748..fcd5fc5419a 100644 --- a/dask/tests/test_distributed.py +++ b/dask/tests/test_distributed.py @@ -259,7 +259,7 @@ async def f(): z = await y.persist() assert len(z.dask) == 1 - asyncio.get_event_loop().run_until_complete(f()) + asyncio.run(f()) @gen_cluster(client=True)