mirror of
https://github.com/elastic/eland.git
synced 2025-07-11 00:02:14 +08:00
* Support Pandas 2 (#742) * Fix test setup to match pandas 2.0 demands * Use the now deprecated _append method (Better solution might exist) * Deal with numeric_only being removed in metrics test * Skip mad metric for other pandas versions * Account for differences between pandas versions in describe methods * Run black * Check Pandas version first * Mirror behaviour of installed Pandas version when running value_counts * Allow passing arguments to the individual asserters * Fix for method _construct_axes_from_arguments no longer existing * Skip mad metric if it does not exist * Account for pandas 2.0 timestamp default behaviour * Deal with empty vs other inferred data types * Account for default datetime precision change * Run Black * Solution for differences in inferred_type only * Fix csv and json issues * Skip two doctests * Passing a set as indexer is no longer allowed * Don't validate output where it differs between Pandas versions in the environment * Update test matrix and packaging metadata * Update version of Python in the docs * Update Python version in demo notebook * Match noxfile * Symmetry * Fix trailing comma in JSON * Revert some changes in setup.py to fix building the documentation * Revert "Revert some changes in setup.py to fix building the documentation" This reverts commit ea9879753129d8d8390b3cbbce57155a8b4fb346. * Use PANDAS_VERSION from eland.common * Still skip the doctest, but make the output pandas 2 instead of 1 * Still skip doctest, but switch to pandas 2 output * Prepare for pandas 3 * Reference the right column * Ignore output in tests but switch to pandas 2 output * Add line comment about NBVAL_IGNORE_OUTPUT * Restore missing line and add stderr cell * Use non-private method instead * Fix indentation and parameter issues * If index is not specified, and pandas 1 is present, set it to True From pandas 2 and upwards, index is set to None by default * Run black * Newer version of black might have different opinions? * Add line comment * Remove unused import * Add reason for ignore statement * Add reason for skip --------- Co-authored-by: Quentin Pradet <quentin.pradet@elastic.co> (cherry picked from commit 75c57b077532c459a9490613cbf7b37215c27fae) * Return input_field_names as list as required by Pandas 2 --------- Co-authored-by: Bart Broere <mail@bartbroere.eu> Co-authored-by: Quentin Pradet <quentin.pradet@elastic.co>
104 lines
3.5 KiB
Python
104 lines
3.5 KiB
Python
# Licensed to Elasticsearch B.V. under one or more contributor
|
|
# license agreements. See the NOTICE file distributed with
|
|
# this work for additional information regarding copyright
|
|
# ownership. Elasticsearch B.V. licenses this file to you under
|
|
# the Apache License, Version 2.0 (the "License"); you may
|
|
# not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing,
|
|
# software distributed under the License is distributed on an
|
|
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
|
# KIND, either express or implied. See the License for the
|
|
# specific language governing permissions and limitations
|
|
# under the License.
|
|
|
|
# flake8: noqa
|
|
|
|
from codecs import open
|
|
from os import path
|
|
|
|
from setuptools import find_packages, setup
|
|
|
|
here = path.abspath(path.dirname(__file__))
|
|
about = {}
|
|
with open(path.join(here, "eland", "_version.py"), "r", "utf-8") as f:
|
|
exec(f.read(), about)
|
|
|
|
CLASSIFIERS = [
|
|
"Development Status :: 5 - Production/Stable",
|
|
"License :: OSI Approved :: Apache Software License",
|
|
"Environment :: Console",
|
|
"Operating System :: OS Independent",
|
|
"Intended Audience :: Developers",
|
|
"Intended Audience :: Science/Research",
|
|
"Operating System :: OS Independent",
|
|
"Programming Language :: Python",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3 :: Only",
|
|
"Programming Language :: Python :: 3.9",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Topic :: Scientific/Engineering",
|
|
]
|
|
|
|
# Remove all raw HTML from README for long description
|
|
with open(path.join(here, "README.md"), "r", "utf-8") as f:
|
|
lines = f.read().split("\n")
|
|
last_html_index = 0
|
|
for i, line in enumerate(lines):
|
|
if line == "</p>":
|
|
last_html_index = i + 1
|
|
long_description = "\n".join(lines[last_html_index:])
|
|
|
|
extras = {
|
|
"xgboost": ["xgboost>=0.90,<2"],
|
|
"scikit-learn": ["scikit-learn>=1.3,<1.4"],
|
|
"lightgbm": ["lightgbm>=2,<4"],
|
|
"pytorch": [
|
|
"requests<3",
|
|
"torch==2.3.1",
|
|
"tqdm",
|
|
"sentence-transformers>=2.1.0,<=2.7.0",
|
|
# sentencepiece is a required dependency for the slow tokenizers
|
|
# https://huggingface.co/transformers/v4.4.2/migration.html#sentencepiece-is-removed-from-the-required-dependencies
|
|
"transformers[sentencepiece]>=4.47.0",
|
|
],
|
|
}
|
|
extras["all"] = list({dep for deps in extras.values() for dep in deps})
|
|
|
|
setup(
|
|
name=about["__title__"],
|
|
version=about["__version__"],
|
|
description=about["__description__"],
|
|
long_description=long_description,
|
|
long_description_content_type="text/markdown",
|
|
url=about["__url__"],
|
|
author=about["__author__"],
|
|
author_email=about["__author_email__"],
|
|
maintainer=about["__maintainer__"],
|
|
maintainer_email=about["__maintainer_email__"],
|
|
license="Apache-2.0",
|
|
classifiers=CLASSIFIERS,
|
|
keywords="elastic eland pandas python",
|
|
packages=find_packages(include=["eland", "eland.*"]),
|
|
install_requires=[
|
|
"elasticsearch>=8.3,<9",
|
|
"pandas>=1.5,<3",
|
|
"matplotlib>=3.6",
|
|
"numpy>=1.2.0,<2",
|
|
"packaging",
|
|
],
|
|
entry_points={
|
|
"console_scripts": "eland_import_hub_model=eland.cli.eland_import_hub_model:main"
|
|
},
|
|
python_requires=">=3.9,<3.13",
|
|
package_data={"eland": ["py.typed"]},
|
|
include_package_data=True,
|
|
zip_safe=False,
|
|
extras_require=extras,
|
|
)
|