mirror of
https://github.com/microsoft/FLAML.git
synced 2026-02-09 02:09:16 +08:00
50334f2c52
* add basic support to Spark dataframe add support to SynapseML LightGBM model update to pyspark>=3.2.0 to leverage pandas_on_Spark API * clean code, add TODOs * add sample_train_data for pyspark.pandas dataframe, fix bugs * improve some functions, fix bugs * fix dict change size during iteration * update model predict * update LightGBM model, update test * update SynapseML LightGBM params * update synapseML and tests * update TODOs * Added support to roc_auc for spark models * Added support to score of spark estimator * Added test for automl score of spark estimator * Added cv support to pyspark.pandas dataframe * Update test, fix bugs * Added tests * Updated docs, tests, added a notebook * Fix bugs in non-spark env * Fix bugs and improve tests * Fix uninstall pyspark * Fix tests error * Fix java.lang.OutOfMemoryError: Java heap space * Fix test_performance * Update test_sparkml to test_0sparkml to use the expected spark conf * Remove unnecessary widgets in notebook * Fix iloc java.lang.StackOverflowError * fix pre-commit * Added params check for spark dataframes * Refactor code for train_test_split to a function * Update train_test_split_pyspark * Refactor if-else, remove unnecessary code * Remove y from predict, remove mem control from n_iter compute * Update workflow * Improve _split_pyspark * Fix test failure of too short training time * Fix typos, improve docstrings * Fix index errors of pandas_on_spark, add spark loss metric * Fix typo of ndcgAtK * Update NDCG metrics and tests * Remove unuseful logger * Use cache and count to ensure consistent indexes * refactor for merge maain * fix errors of refactor * Updated SparkLightGBMEstimator and cache * Updated config2params * Remove unused import * Fix unknown parameters * Update default_estimator_list * Add unit tests for spark metrics
133 lines
3.6 KiB
Python
133 lines
3.6 KiB
Python
import setuptools
|
|
import os
|
|
|
|
here = os.path.abspath(os.path.dirname(__file__))
|
|
|
|
with open("README.md", "r", encoding="UTF-8") as fh:
|
|
long_description = fh.read()
|
|
|
|
|
|
# Get the code version
|
|
version = {}
|
|
with open(os.path.join(here, "flaml/version.py")) as fp:
|
|
exec(fp.read(), version)
|
|
__version__ = version["__version__"]
|
|
|
|
install_requires = [
|
|
"NumPy>=1.17.0rc1",
|
|
"lightgbm>=2.3.1",
|
|
"xgboost>=0.90",
|
|
"scipy>=1.4.1",
|
|
"pandas>=1.1.4",
|
|
"scikit-learn>=0.24",
|
|
]
|
|
|
|
|
|
setuptools.setup(
|
|
name="FLAML",
|
|
version=__version__,
|
|
author="Microsoft Corporation",
|
|
author_email="hpo@microsoft.com",
|
|
description="A fast library for automated machine learning and tuning",
|
|
long_description=long_description,
|
|
long_description_content_type="text/markdown",
|
|
url="https://github.com/microsoft/FLAML",
|
|
packages=setuptools.find_packages(include=["flaml*"]),
|
|
package_data={
|
|
"flaml.default": ["*/*.json"],
|
|
},
|
|
include_package_data=True,
|
|
install_requires=install_requires,
|
|
extras_require={
|
|
"notebook": [
|
|
"jupyter",
|
|
"matplotlib",
|
|
"openml==0.10.2",
|
|
],
|
|
"spark": [
|
|
"pyspark>=3.2.0",
|
|
"joblibspark>=0.5.0",
|
|
],
|
|
"test": [
|
|
"flake8>=3.8.4",
|
|
"thop",
|
|
"pytest>=6.1.1",
|
|
"coverage>=5.3",
|
|
"pre-commit",
|
|
"torch",
|
|
"torchvision",
|
|
"catboost>=0.26",
|
|
"rgf-python",
|
|
"optuna==2.8.0",
|
|
"openml==0.10.2",
|
|
"statsmodels>=0.12.2",
|
|
"psutil==5.8.0",
|
|
"dataclasses",
|
|
"transformers[torch]",
|
|
"datasets",
|
|
"nltk",
|
|
"rouge_score",
|
|
"hcrystalball==0.1.10",
|
|
"seqeval",
|
|
"pytorch-forecasting>=0.9.0,<=0.10.1",
|
|
"mlflow",
|
|
"pyspark>=3.2.0",
|
|
"joblibspark>=0.5.0",
|
|
"nbconvert",
|
|
"nbformat",
|
|
"ipykernel",
|
|
"pytorch-lightning<1.9.1", # test_forecast_panel
|
|
],
|
|
"catboost": ["catboost>=0.26"],
|
|
"blendsearch": ["optuna==2.8.0"],
|
|
"ray": [
|
|
"ray[tune]~=1.13",
|
|
],
|
|
"azureml": [
|
|
"azureml-mlflow",
|
|
],
|
|
"nni": [
|
|
"nni",
|
|
],
|
|
"vw": [
|
|
"vowpalwabbit>=8.10.0, <9.0.0",
|
|
],
|
|
"hf": [
|
|
"transformers[torch]==4.26",
|
|
"datasets",
|
|
"nltk",
|
|
"rouge_score",
|
|
"seqeval",
|
|
],
|
|
"nlp": [ # for backward compatibility; hf is the new option name
|
|
"transformers[torch]==4.26",
|
|
"datasets",
|
|
"nltk",
|
|
"rouge_score",
|
|
"seqeval",
|
|
],
|
|
"ts_forecast": [
|
|
"holidays<0.14", # to prevent installation error for prophet
|
|
"prophet>=1.0.1",
|
|
"statsmodels>=0.12.2",
|
|
"hcrystalball==0.1.10",
|
|
],
|
|
"forecast": [
|
|
"holidays<0.14", # to prevent installation error for prophet
|
|
"prophet>=1.0.1",
|
|
"statsmodels>=0.12.2",
|
|
"hcrystalball==0.1.10",
|
|
"pytorch-forecasting>=0.9.0",
|
|
],
|
|
"benchmark": ["catboost>=0.26", "psutil==5.8.0", "xgboost==1.3.3"],
|
|
"openai": ["openai==0.23.1", "diskcache", "optuna==2.8.0"],
|
|
"synapse": ["joblibspark>=0.5.0", "optuna==2.8.0", "pyspark>=3.2.0"],
|
|
},
|
|
classifiers=[
|
|
"Programming Language :: Python :: 3",
|
|
"License :: OSI Approved :: MIT License",
|
|
"Operating System :: OS Independent",
|
|
],
|
|
python_requires=">=3.6",
|
|
)
|