diff --git a/.github/workflows/local-setup-test.yaml b/.github/workflows/local-setup-test.yaml index 23400a4..1b4b590 100644 --- a/.github/workflows/local-setup-test.yaml +++ b/.github/workflows/local-setup-test.yaml @@ -11,61 +11,21 @@ jobs: - uses: actions/setup-java@v4 with: distribution: "zulu" - java-version: "11" + java-version: "17" - name: Install poetry run: pipx install poetry - uses: actions/setup-python@v5 with: - python-version: "3.11" + python-version: "3.13" cache: "poetry" - name: Install Python Dependencies run: | poetry install - - name: Run local unit tests - run: | - poetry run python -m pytest tests/unit - - name: Run local integration tests - run: | - poetry run python -m pytest tests/integration - - windows: - runs-on: windows-latest - steps: - - uses: actions/checkout@v4 - - uses: actions/setup-java@v4 - with: - distribution: "zulu" - java-version: "11" - - name: Install poetry - run: pipx install poetry - - uses: actions/setup-python@v5 - with: - python-version: "3.11" - cache: "poetry" - - name: Install Hadoop for Windows - # See https://cwiki.apache.org/confluence/display/HADOOP2/WindowsProblems - # that recommends https://github.com/steveloughran/winutils - # that recommends https://github.com/cdarlint/winutils - # - # Setting environement variables: e.g. - # $env:HADOOP_HOME = "$pwd\winutils\hadoop-3.3.5" - # $env:Path += ";$pwd\winutils\hadoop-3.3.5\bin" - # requires a special handling: https://stackoverflow.com/questions/61858388/how-do-i-set-an-enviroment-variable-in-github-action-on-a-windows-server - # - # Reading / Writing to parquet through winutils requires Microsoft Visual C++ 2010 Service Pack 1 - # https://stackoverflow.com/questions/45947375/why-does-starting-a-streaming-query-lead-to-exitcodeexception-exitcode-1073741 - run: | - choco install vcredist2010 - git clone --depth 1 -b master https://github.com/cdarlint/winutils.git - echo "HADOOP_HOME=$pwd\winutils\hadoop-3.3.5" >> $env:GITHUB_ENV - echo ";$pwd\winutils\hadoop-3.3.5\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append - - - name: Test Hadoop Setup + - name: Run style and type checks run: | - winutils.exe chmod 777 D:\a\dataengineer-transformations-python\dataengineer-transformations-python - - name: Install Python Dependencies - run: | - poetry install + poetry run ruff format && poetry run ruff check + poetry run mypy --ignore-missing-imports --disallow-untyped-calls --disallow-untyped-defs --disallow-incomplete-defs \ + data_transformations tests - name: Run local unit tests run: | poetry run python -m pytest tests/unit diff --git a/.pylintrc b/.pylintrc deleted file mode 100644 index 3935cd2..0000000 --- a/.pylintrc +++ /dev/null @@ -1,9 +0,0 @@ -[MASTER] -disable= - C0114, - C0115, - C0116, - W0611, - W0603, - W0703, - W1514, diff --git a/README.md b/README.md index a451076..cef09eb 100644 --- a/README.md +++ b/README.md @@ -22,15 +22,15 @@ These jobs are using _PySpark_ to process larger volumes of data and are suppose Please make sure you have the following installed and can run them -- Python (3.11.X), you can use for example [pyenv](https://github.com/pyenv/pyenv#installation) to manage your python versions locally +- Python (3.13.X), you can use for example [pyenv](https://github.com/pyenv/pyenv#installation) to manage your python versions locally - [Poetry](https://python-poetry.org/docs/#installation) -- Java (11), you can use [sdkman](https://sdkman.io/) to install and manage java locally +- Java (17), you can use [sdkman](https://sdkman.io/) to install and manage java locally #### Windows users We recommend using WSL 2 on Windows for this exercise, due to the [lack of support](https://cwiki.apache.org/confluence/display/HADOOP2/WindowsProblems) of windows paths from Hadoop/Spark. -Follow instructions on the [Windows official page](https://learn.microsoft.com/en-us/windows/wsl/setup/environment) +Follow instructions on the [Windows official page](https://learn.microsoft.com/en-us/windows/wsl/setup/environment) and then the linux install. #### Install all dependencies @@ -60,7 +60,7 @@ poetry run pytest tests/integration poetry run mypy --ignore-missing-imports --disallow-untyped-calls --disallow-untyped-defs --disallow-incomplete-defs \ data_transformations tests -poetry run pylint data_transformations tests +poetry run ruff format && poetry run ruff check ``` ### Anything else? diff --git a/data_transformations/citibike/distance_transformer.py b/data_transformations/citibike/distance_transformer.py index fa3fb96..ab0c3b9 100644 --- a/data_transformations/citibike/distance_transformer.py +++ b/data_transformations/citibike/distance_transformer.py @@ -1,4 +1,4 @@ -from pyspark.sql import SparkSession, DataFrame +from pyspark.sql import DataFrame, SparkSession METERS_PER_FOOT = 0.3048 FEET_PER_MILE = 5280 @@ -10,11 +10,13 @@ def compute_distance(_spark: SparkSession, dataframe: DataFrame) -> DataFrame: return dataframe -def run(spark: SparkSession, input_dataset_path: str, transformed_dataset_path: str) -> None: +def run( + spark: SparkSession, input_dataset_path: str, transformed_dataset_path: str +) -> None: input_dataset = spark.read.parquet(input_dataset_path) input_dataset.show() dataset_with_distances = compute_distance(spark, input_dataset) dataset_with_distances.show() - dataset_with_distances.write.parquet(transformed_dataset_path, mode='append') + dataset_with_distances.write.parquet(transformed_dataset_path, mode="append") diff --git a/data_transformations/citibike/ingest.py b/data_transformations/citibike/ingest.py index d89350f..0df558b 100644 --- a/data_transformations/citibike/ingest.py +++ b/data_transformations/citibike/ingest.py @@ -10,7 +10,11 @@ def sanitize_columns(columns: List[str]) -> List[str]: def run(spark: SparkSession, ingest_path: str, transformation_path: str) -> None: logging.info("Reading text file from: %s", ingest_path) - input_df = spark.read.format("org.apache.spark.csv").option("header", True).csv(ingest_path) + input_df = ( + spark.read.format("org.apache.spark.csv") + .option("header", True) + .csv(ingest_path) + ) renamed_columns = sanitize_columns(input_df.columns) ref_df = input_df.toDF(*renamed_columns) ref_df.printSchema() diff --git a/jobs/citibike_distance_calculation.py b/jobs/citibike_distance_calculation.py index a487e30..5ab261b 100644 --- a/jobs/citibike_distance_calculation.py +++ b/jobs/citibike_distance_calculation.py @@ -1,14 +1,14 @@ import logging - import sys + from pyspark.sql import SparkSession from data_transformations.citibike import distance_transformer -LOG_FILENAME = 'project.log' +LOG_FILENAME = "project.log" APP_NAME = "Citibike Pipeline: Distance Calculation" -if __name__ == '__main__': +if __name__ == "__main__": logging.basicConfig(filename=LOG_FILENAME, level=logging.INFO) arguments = sys.argv print(f"Argument list passed: {arguments}") diff --git a/jobs/citibike_ingest.py b/jobs/citibike_ingest.py index 6d8ca9d..a803c30 100644 --- a/jobs/citibike_ingest.py +++ b/jobs/citibike_ingest.py @@ -1,18 +1,18 @@ import logging - import sys + from pyspark.sql import SparkSession from data_transformations.citibike import ingest -LOG_FILENAME = 'project.log' +LOG_FILENAME = "project.log" APP_NAME = "Citibike Pipeline: Ingest" -if __name__ == '__main__': +if __name__ == "__main__": logging.basicConfig(filename=LOG_FILENAME, level=logging.INFO) logging.info(sys.argv) - if len(sys.argv) is not 3: + if len(sys.argv) != 3: logging.warning("Input source and output path are required") sys.exit(1) diff --git a/jobs/word_count.py b/jobs/word_count.py index a148c67..73d050b 100644 --- a/jobs/word_count.py +++ b/jobs/word_count.py @@ -1,18 +1,18 @@ import logging - import sys + from pyspark.sql import SparkSession from data_transformations.wordcount import word_count_transformer -LOG_FILENAME = 'project.log' +LOG_FILENAME = "project.log" APP_NAME = "WordCount" -if __name__ == '__main__': +if __name__ == "__main__": logging.basicConfig(filename=LOG_FILENAME, level=logging.INFO) logging.info(sys.argv) - if len(sys.argv) is not 3: + if len(sys.argv) != 3: logging.warning("Input .txt file and output path are required") sys.exit(1) diff --git a/poetry.lock b/poetry.lock index cdfdaae..da796c7 100644 --- a/poetry.lock +++ b/poetry.lock @@ -1,48 +1,4 @@ -# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand. - -[[package]] -name = "astroid" -version = "2.15.8" -description = "An abstract syntax tree for Python with inference support." -optional = false -python-versions = ">=3.7.2" -files = [ - {file = "astroid-2.15.8-py3-none-any.whl", hash = "sha256:1aa149fc5c6589e3d0ece885b4491acd80af4f087baafa3fb5203b113e68cd3c"}, - {file = "astroid-2.15.8.tar.gz", hash = "sha256:6c107453dffee9055899705de3c9ead36e74119cee151e5a9aaf7f0b0e020a6a"}, -] - -[package.dependencies] -lazy-object-proxy = ">=1.4.0" -wrapt = {version = ">=1.14,<2", markers = "python_version >= \"3.11\""} - -[[package]] -name = "atomicwrites" -version = "1.4.1" -description = "Atomic file writes." -optional = false -python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*" -files = [ - {file = "atomicwrites-1.4.1.tar.gz", hash = "sha256:81b2c9071a49367a7f770170e5eec8cb66567cfbbc8c73d20ce5ca4a8d71cf11"}, -] - -[[package]] -name = "attrs" -version = "24.2.0" -description = "Classes Without Boilerplate" -optional = false -python-versions = ">=3.7" -files = [ - {file = "attrs-24.2.0-py3-none-any.whl", hash = "sha256:81921eb96de3191c8258c199618104dd27ac608d9366f5e35d011eae1867ede2"}, - {file = "attrs-24.2.0.tar.gz", hash = "sha256:5cfb1b9148b5b086569baec03f20d7b6bf3bcacc9a42bebf87ffaaca362f6346"}, -] - -[package.extras] -benchmark = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins", "pytest-xdist[psutil]"] -cov = ["cloudpickle", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"] -dev = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pre-commit", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"] -docs = ["cogapp", "furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier (<24.7)"] -tests = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"] -tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"] +# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand. [[package]] name = "colorama" @@ -50,166 +6,95 @@ version = "0.4.6" description = "Cross-platform colored terminal text." optional = false python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7" +groups = ["dev"] +markers = "sys_platform == \"win32\"" files = [ {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"}, {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"}, ] -[[package]] -name = "dill" -version = "0.3.9" -description = "serialize all of Python" -optional = false -python-versions = ">=3.8" -files = [ - {file = "dill-0.3.9-py3-none-any.whl", hash = "sha256:468dff3b89520b474c0397703366b7b95eebe6303f108adf9b19da1f702be87a"}, - {file = "dill-0.3.9.tar.gz", hash = "sha256:81aa267dddf68cbfe8029c42ca9ec6a4ab3b22371d1c450abc54422577b4512c"}, -] - -[package.extras] -graph = ["objgraph (>=1.7.2)"] -profile = ["gprof2dot (>=2022.7.29)"] - [[package]] name = "iniconfig" -version = "2.0.0" +version = "2.1.0" description = "brain-dead simple config-ini parsing" optional = false -python-versions = ">=3.7" -files = [ - {file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"}, - {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"}, -] - -[[package]] -name = "isort" -version = "5.13.2" -description = "A Python utility / library to sort Python imports." -optional = false -python-versions = ">=3.8.0" -files = [ - {file = "isort-5.13.2-py3-none-any.whl", hash = "sha256:8ca5e72a8d85860d5a3fa69b8745237f2939afe12dbf656afbcb47fe72d947a6"}, - {file = "isort-5.13.2.tar.gz", hash = "sha256:48fdfcb9face5d58a4f6dde2e72a1fb8dcaf8ab26f95ab49fab84c2ddefb0109"}, -] - -[package.extras] -colors = ["colorama (>=0.4.6)"] - -[[package]] -name = "lazy-object-proxy" -version = "1.10.0" -description = "A fast and thorough lazy object proxy." -optional = false python-versions = ">=3.8" +groups = ["dev"] files = [ - {file = "lazy-object-proxy-1.10.0.tar.gz", hash = "sha256:78247b6d45f43a52ef35c25b5581459e85117225408a4128a3daf8bf9648ac69"}, - {file = "lazy_object_proxy-1.10.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:855e068b0358ab916454464a884779c7ffa312b8925c6f7401e952dcf3b89977"}, - {file = "lazy_object_proxy-1.10.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7ab7004cf2e59f7c2e4345604a3e6ea0d92ac44e1c2375527d56492014e690c3"}, - {file = "lazy_object_proxy-1.10.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dc0d2fc424e54c70c4bc06787e4072c4f3b1aa2f897dfdc34ce1013cf3ceef05"}, - {file = "lazy_object_proxy-1.10.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:e2adb09778797da09d2b5ebdbceebf7dd32e2c96f79da9052b2e87b6ea495895"}, - {file = "lazy_object_proxy-1.10.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b1f711e2c6dcd4edd372cf5dec5c5a30d23bba06ee012093267b3376c079ec83"}, - {file = "lazy_object_proxy-1.10.0-cp310-cp310-win32.whl", hash = "sha256:76a095cfe6045c7d0ca77db9934e8f7b71b14645f0094ffcd842349ada5c5fb9"}, - {file = "lazy_object_proxy-1.10.0-cp310-cp310-win_amd64.whl", hash = "sha256:b4f87d4ed9064b2628da63830986c3d2dca7501e6018347798313fcf028e2fd4"}, - {file = "lazy_object_proxy-1.10.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:fec03caabbc6b59ea4a638bee5fce7117be8e99a4103d9d5ad77f15d6f81020c"}, - {file = "lazy_object_proxy-1.10.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:02c83f957782cbbe8136bee26416686a6ae998c7b6191711a04da776dc9e47d4"}, - {file = "lazy_object_proxy-1.10.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:009e6bb1f1935a62889ddc8541514b6a9e1fcf302667dcb049a0be5c8f613e56"}, - {file = "lazy_object_proxy-1.10.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:75fc59fc450050b1b3c203c35020bc41bd2695ed692a392924c6ce180c6f1dc9"}, - {file = "lazy_object_proxy-1.10.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:782e2c9b2aab1708ffb07d4bf377d12901d7a1d99e5e410d648d892f8967ab1f"}, - {file = "lazy_object_proxy-1.10.0-cp311-cp311-win32.whl", hash = "sha256:edb45bb8278574710e68a6b021599a10ce730d156e5b254941754a9cc0b17d03"}, - {file = "lazy_object_proxy-1.10.0-cp311-cp311-win_amd64.whl", hash = "sha256:e271058822765ad5e3bca7f05f2ace0de58a3f4e62045a8c90a0dfd2f8ad8cc6"}, - {file = "lazy_object_proxy-1.10.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:e98c8af98d5707dcdecc9ab0863c0ea6e88545d42ca7c3feffb6b4d1e370c7ba"}, - {file = "lazy_object_proxy-1.10.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:952c81d415b9b80ea261d2372d2a4a2332a3890c2b83e0535f263ddfe43f0d43"}, - {file = "lazy_object_proxy-1.10.0-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:80b39d3a151309efc8cc48675918891b865bdf742a8616a337cb0090791a0de9"}, - {file = "lazy_object_proxy-1.10.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:e221060b701e2aa2ea991542900dd13907a5c90fa80e199dbf5a03359019e7a3"}, - {file = "lazy_object_proxy-1.10.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:92f09ff65ecff3108e56526f9e2481b8116c0b9e1425325e13245abfd79bdb1b"}, - {file = "lazy_object_proxy-1.10.0-cp312-cp312-win32.whl", hash = "sha256:3ad54b9ddbe20ae9f7c1b29e52f123120772b06dbb18ec6be9101369d63a4074"}, - {file = "lazy_object_proxy-1.10.0-cp312-cp312-win_amd64.whl", hash = "sha256:127a789c75151db6af398b8972178afe6bda7d6f68730c057fbbc2e96b08d282"}, - {file = "lazy_object_proxy-1.10.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9e4ed0518a14dd26092614412936920ad081a424bdcb54cc13349a8e2c6d106a"}, - {file = "lazy_object_proxy-1.10.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5ad9e6ed739285919aa9661a5bbed0aaf410aa60231373c5579c6b4801bd883c"}, - {file = "lazy_object_proxy-1.10.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2fc0a92c02fa1ca1e84fc60fa258458e5bf89d90a1ddaeb8ed9cc3147f417255"}, - {file = "lazy_object_proxy-1.10.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:0aefc7591920bbd360d57ea03c995cebc204b424524a5bd78406f6e1b8b2a5d8"}, - {file = "lazy_object_proxy-1.10.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:5faf03a7d8942bb4476e3b62fd0f4cf94eaf4618e304a19865abf89a35c0bbee"}, - {file = "lazy_object_proxy-1.10.0-cp38-cp38-win32.whl", hash = "sha256:e333e2324307a7b5d86adfa835bb500ee70bfcd1447384a822e96495796b0ca4"}, - {file = "lazy_object_proxy-1.10.0-cp38-cp38-win_amd64.whl", hash = "sha256:cb73507defd385b7705c599a94474b1d5222a508e502553ef94114a143ec6696"}, - {file = "lazy_object_proxy-1.10.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:366c32fe5355ef5fc8a232c5436f4cc66e9d3e8967c01fb2e6302fd6627e3d94"}, - {file = "lazy_object_proxy-1.10.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2297f08f08a2bb0d32a4265e98a006643cd7233fb7983032bd61ac7a02956b3b"}, - {file = "lazy_object_proxy-1.10.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:18dd842b49456aaa9a7cf535b04ca4571a302ff72ed8740d06b5adcd41fe0757"}, - {file = "lazy_object_proxy-1.10.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:217138197c170a2a74ca0e05bddcd5f1796c735c37d0eee33e43259b192aa424"}, - {file = "lazy_object_proxy-1.10.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:9a3a87cf1e133e5b1994144c12ca4aa3d9698517fe1e2ca82977781b16955658"}, - {file = "lazy_object_proxy-1.10.0-cp39-cp39-win32.whl", hash = "sha256:30b339b2a743c5288405aa79a69e706a06e02958eab31859f7f3c04980853b70"}, - {file = "lazy_object_proxy-1.10.0-cp39-cp39-win_amd64.whl", hash = "sha256:a899b10e17743683b293a729d3a11f2f399e8a90c73b089e29f5d0fe3509f0dd"}, - {file = "lazy_object_proxy-1.10.0-pp310.pp311.pp312.pp38.pp39-none-any.whl", hash = "sha256:80fa48bd89c8f2f456fc0765c11c23bf5af827febacd2f523ca5bc1893fcc09d"}, -] - -[[package]] -name = "mccabe" -version = "0.7.0" -description = "McCabe checker, plugin for flake8" -optional = false -python-versions = ">=3.6" -files = [ - {file = "mccabe-0.7.0-py2.py3-none-any.whl", hash = "sha256:6c2d30ab6be0e4a46919781807b4f0d834ebdd6c6e3dca0bda5a15f863427b6e"}, - {file = "mccabe-0.7.0.tar.gz", hash = "sha256:348e0240c33b60bbdf4e523192ef919f28cb2c3d7d5c7794f74009290f236325"}, + {file = "iniconfig-2.1.0-py3-none-any.whl", hash = "sha256:9deba5723312380e77435581c6bf4935c94cbfab9b1ed33ef8d238ea168eb760"}, + {file = "iniconfig-2.1.0.tar.gz", hash = "sha256:3abbd2e30b36733fee78f9c7f7308f2d0050e88f0087fd25c2645f63c773e1c7"}, ] [[package]] name = "mypy" -version = "0.990" +version = "1.18.2" description = "Optional static typing for Python" optional = false -python-versions = ">=3.7" +python-versions = ">=3.9" +groups = ["dev"] files = [ - {file = "mypy-0.990-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:aaf1be63e0207d7d17be942dcf9a6b641745581fe6c64df9a38deb562a7dbafa"}, - {file = "mypy-0.990-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d555aa7f44cecb7ea3c0ac69d58b1a5afb92caa017285a8e9c4efbf0518b61b4"}, - {file = "mypy-0.990-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8f694d6d09a460b117dccb6857dda269188e3437c880d7b60fa0014fa872d1e9"}, - {file = "mypy-0.990-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:269f0dfb6463b8780333310ff4b5134425157ef0d2b1d614015adaf6d6a7eabd"}, - {file = "mypy-0.990-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:8798c8ed83aa809f053abff08664bdca056038f5a02af3660de00b7290b64c47"}, - {file = "mypy-0.990-cp310-cp310-win_amd64.whl", hash = "sha256:47a9955214615108c3480a500cfda8513a0b1cd3c09a1ed42764ca0dd7b931dd"}, - {file = "mypy-0.990-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:4a8a6c10f4c63fbf6ad6c03eba22c9331b3946a4cec97f008e9ffb4d3b31e8e2"}, - {file = "mypy-0.990-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cd2dd3730ba894ec2a2082cc703fbf3e95a08479f7be84912e3131fc68809d46"}, - {file = "mypy-0.990-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7da0005e47975287a92b43276e460ac1831af3d23032c34e67d003388a0ce8d0"}, - {file = "mypy-0.990-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:262c543ef24deb10470a3c1c254bb986714e2b6b1a67d66daf836a548a9f316c"}, - {file = "mypy-0.990-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:3ff201a0c6d3ea029d73b1648943387d75aa052491365b101f6edd5570d018ea"}, - {file = "mypy-0.990-cp311-cp311-win_amd64.whl", hash = "sha256:1767830da2d1afa4e62b684647af0ff79b401f004d7fa08bc5b0ce2d45bcd5ec"}, - {file = "mypy-0.990-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:6826d9c4d85bbf6d68cb279b561de6a4d8d778ca8e9ab2d00ee768ab501a9852"}, - {file = "mypy-0.990-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:46897755f944176fbc504178422a5a2875bbf3f7436727374724842c0987b5af"}, - {file = "mypy-0.990-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:0680389c34284287fe00e82fc8bccdea9aff318f7e7d55b90d967a13a9606013"}, - {file = "mypy-0.990-cp37-cp37m-win_amd64.whl", hash = "sha256:b08541a06eed35b543ae1a6b301590eb61826a1eb099417676ddc5a42aa151c5"}, - {file = "mypy-0.990-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:be88d665e76b452c26fb2bdc3d54555c01226fba062b004ede780b190a50f9db"}, - {file = "mypy-0.990-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9b8f4a8213b1fd4b751e26b59ae0e0c12896568d7e805861035c7a15ed6dc9eb"}, - {file = "mypy-0.990-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:2b6f85c2ad378e3224e017904a051b26660087b3b76490d533b7344f1546d3ff"}, - {file = "mypy-0.990-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1ee5f99817ee70254e7eb5cf97c1b11dda29c6893d846c8b07bce449184e9466"}, - {file = "mypy-0.990-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49082382f571c3186ce9ea0bd627cb1345d4da8d44a8377870f4442401f0a706"}, - {file = "mypy-0.990-cp38-cp38-win_amd64.whl", hash = "sha256:aba38e3dd66bdbafbbfe9c6e79637841928ea4c79b32e334099463c17b0d90ef"}, - {file = "mypy-0.990-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:9d851c09b981a65d9d283a8ccb5b1d0b698e580493416a10942ef1a04b19fd37"}, - {file = "mypy-0.990-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d847dd23540e2912d9667602271e5ebf25e5788e7da46da5ffd98e7872616e8e"}, - {file = "mypy-0.990-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:cc6019808580565040cd2a561b593d7c3c646badd7e580e07d875eb1bf35c695"}, - {file = "mypy-0.990-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2a3150d409609a775c8cb65dbe305c4edd7fe576c22ea79d77d1454acd9aeda8"}, - {file = "mypy-0.990-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:3227f14fe943524f5794679156488f18bf8d34bfecd4623cf76bc55958d229c5"}, - {file = "mypy-0.990-cp39-cp39-win_amd64.whl", hash = "sha256:c76c769c46a1e6062a84837badcb2a7b0cdb153d68601a61f60739c37d41cc74"}, - {file = "mypy-0.990-py3-none-any.whl", hash = "sha256:8f1940325a8ed460ba03d19ab83742260fa9534804c317224e5d4e5aa588e2d6"}, - {file = "mypy-0.990.tar.gz", hash = "sha256:72382cb609142dba3f04140d016c94b4092bc7b4d98ca718740dc989e5271b8d"}, + {file = "mypy-1.18.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c1eab0cf6294dafe397c261a75f96dc2c31bffe3b944faa24db5def4e2b0f77c"}, + {file = "mypy-1.18.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:7a780ca61fc239e4865968ebc5240bb3bf610ef59ac398de9a7421b54e4a207e"}, + {file = "mypy-1.18.2-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:448acd386266989ef11662ce3c8011fd2a7b632e0ec7d61a98edd8e27472225b"}, + {file = "mypy-1.18.2-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f9e171c465ad3901dc652643ee4bffa8e9fef4d7d0eece23b428908c77a76a66"}, + {file = "mypy-1.18.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:592ec214750bc00741af1f80cbf96b5013d81486b7bb24cb052382c19e40b428"}, + {file = "mypy-1.18.2-cp310-cp310-win_amd64.whl", hash = "sha256:7fb95f97199ea11769ebe3638c29b550b5221e997c63b14ef93d2e971606ebed"}, + {file = "mypy-1.18.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:807d9315ab9d464125aa9fcf6d84fde6e1dc67da0b6f80e7405506b8ac72bc7f"}, + {file = "mypy-1.18.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:776bb00de1778caf4db739c6e83919c1d85a448f71979b6a0edd774ea8399341"}, + {file = "mypy-1.18.2-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1379451880512ffce14505493bd9fe469e0697543717298242574882cf8cdb8d"}, + {file = "mypy-1.18.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1331eb7fd110d60c24999893320967594ff84c38ac6d19e0a76c5fd809a84c86"}, + {file = "mypy-1.18.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:3ca30b50a51e7ba93b00422e486cbb124f1c56a535e20eff7b2d6ab72b3b2e37"}, + {file = "mypy-1.18.2-cp311-cp311-win_amd64.whl", hash = "sha256:664dc726e67fa54e14536f6e1224bcfce1d9e5ac02426d2326e2bb4e081d1ce8"}, + {file = "mypy-1.18.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:33eca32dd124b29400c31d7cf784e795b050ace0e1f91b8dc035672725617e34"}, + {file = "mypy-1.18.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a3c47adf30d65e89b2dcd2fa32f3aeb5e94ca970d2c15fcb25e297871c8e4764"}, + {file = "mypy-1.18.2-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5d6c838e831a062f5f29d11c9057c6009f60cb294fea33a98422688181fe2893"}, + {file = "mypy-1.18.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:01199871b6110a2ce984bde85acd481232d17413868c9807e95c1b0739a58914"}, + {file = "mypy-1.18.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:a2afc0fa0b0e91b4599ddfe0f91e2c26c2b5a5ab263737e998d6817874c5f7c8"}, + {file = "mypy-1.18.2-cp312-cp312-win_amd64.whl", hash = "sha256:d8068d0afe682c7c4897c0f7ce84ea77f6de953262b12d07038f4d296d547074"}, + {file = "mypy-1.18.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:07b8b0f580ca6d289e69209ec9d3911b4a26e5abfde32228a288eb79df129fcc"}, + {file = "mypy-1.18.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:ed4482847168439651d3feee5833ccedbf6657e964572706a2adb1f7fa4dfe2e"}, + {file = "mypy-1.18.2-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c3ad2afadd1e9fea5cf99a45a822346971ede8685cc581ed9cd4d42eaf940986"}, + {file = "mypy-1.18.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a431a6f1ef14cf8c144c6b14793a23ec4eae3db28277c358136e79d7d062f62d"}, + {file = "mypy-1.18.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:7ab28cc197f1dd77a67e1c6f35cd1f8e8b73ed2217e4fc005f9e6a504e46e7ba"}, + {file = "mypy-1.18.2-cp313-cp313-win_amd64.whl", hash = "sha256:0e2785a84b34a72ba55fb5daf079a1003a34c05b22238da94fcae2bbe46f3544"}, + {file = "mypy-1.18.2-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:62f0e1e988ad41c2a110edde6c398383a889d95b36b3e60bcf155f5164c4fdce"}, + {file = "mypy-1.18.2-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:8795a039bab805ff0c1dfdb8cd3344642c2b99b8e439d057aba30850b8d3423d"}, + {file = "mypy-1.18.2-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6ca1e64b24a700ab5ce10133f7ccd956a04715463d30498e64ea8715236f9c9c"}, + {file = "mypy-1.18.2-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d924eef3795cc89fecf6bedc6ed32b33ac13e8321344f6ddbf8ee89f706c05cb"}, + {file = "mypy-1.18.2-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:20c02215a080e3a2be3aa50506c67242df1c151eaba0dcbc1e4e557922a26075"}, + {file = "mypy-1.18.2-cp314-cp314-win_amd64.whl", hash = "sha256:749b5f83198f1ca64345603118a6f01a4e99ad4bf9d103ddc5a3200cc4614adf"}, + {file = "mypy-1.18.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:25a9c8fb67b00599f839cf472713f54249a62efd53a54b565eb61956a7e3296b"}, + {file = "mypy-1.18.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c2b9c7e284ee20e7598d6f42e13ca40b4928e6957ed6813d1ab6348aa3f47133"}, + {file = "mypy-1.18.2-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d6985ed057513e344e43a26cc1cd815c7a94602fb6a3130a34798625bc2f07b6"}, + {file = "mypy-1.18.2-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:22f27105f1525ec024b5c630c0b9f36d5c1cc4d447d61fe51ff4bd60633f47ac"}, + {file = "mypy-1.18.2-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:030c52d0ea8144e721e49b1f68391e39553d7451f0c3f8a7565b59e19fcb608b"}, + {file = "mypy-1.18.2-cp39-cp39-win_amd64.whl", hash = "sha256:aa5e07ac1a60a253445797e42b8b2963c9675563a94f11291ab40718b016a7a0"}, + {file = "mypy-1.18.2-py3-none-any.whl", hash = "sha256:22a1748707dd62b58d2ae53562ffc4d7f8bcc727e8ac7cbc69c053ddc874d47e"}, + {file = "mypy-1.18.2.tar.gz", hash = "sha256:06a398102a5f203d7477b2923dda3634c36727fa5c237d8f859ef90c42a9924b"}, ] [package.dependencies] -mypy-extensions = ">=0.4.3" -typing-extensions = ">=3.10" +mypy_extensions = ">=1.0.0" +pathspec = ">=0.9.0" +typing_extensions = ">=4.6.0" [package.extras] dmypy = ["psutil (>=4.0)"] +faster-cache = ["orjson"] install-types = ["pip"] -python2 = ["typed-ast (>=1.4.0,<2)"] +mypyc = ["setuptools (>=50)"] reports = ["lxml"] [[package]] name = "mypy-extensions" -version = "1.0.0" +version = "1.1.0" description = "Type system extensions for programs checked with the mypy type checker." optional = false -python-versions = ">=3.5" +python-versions = ">=3.8" +groups = ["dev"] files = [ - {file = "mypy_extensions-1.0.0-py3-none-any.whl", hash = "sha256:4392f6c0eb8a5668a69e23d168ffa70f0be9ccfd32b5cc2d26a34ae5b844552d"}, - {file = "mypy_extensions-1.0.0.tar.gz", hash = "sha256:75dbf8955dc00442a438fc4d0666508a9a97b6bd41aa2f0ffe9d2f2725af0782"}, + {file = "mypy_extensions-1.1.0-py3-none-any.whl", hash = "sha256:1be4cccdb0f2482337c4743e60421de3a356cd97508abadd57d47403e94f5505"}, + {file = "mypy_extensions-1.1.0.tar.gz", hash = "sha256:52e68efc3284861e772bbcd66823fde5ae21fd2fdb51c62a211403730b916558"}, ] [[package]] @@ -218,6 +103,7 @@ version = "1.26.4" description = "Fundamental package for array computing in Python" optional = false python-versions = ">=3.9" +groups = ["main"] files = [ {file = "numpy-1.26.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9ff0f4f29c51e2803569d7a51c2304de5554655a60c5d776e35b4a41413830d0"}, {file = "numpy-1.26.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2e4ee3380d6de9c9ec04745830fd9e2eccb3e6cf790d39d7b98ffd19b0dd754a"}, @@ -259,68 +145,83 @@ files = [ [[package]] name = "packaging" -version = "24.1" +version = "25.0" description = "Core utilities for Python packages" optional = false python-versions = ">=3.8" +groups = ["dev"] files = [ - {file = "packaging-24.1-py3-none-any.whl", hash = "sha256:5b8f2217dbdbd2f7f384c41c628544e6d52f2d0f53c6d0c3ea61aa5d1d7ff124"}, - {file = "packaging-24.1.tar.gz", hash = "sha256:026ed72c8ed3fcce5bf8950572258698927fd1dbda10a5e981cdf0ac37f4f002"}, + {file = "packaging-25.0-py3-none-any.whl", hash = "sha256:29572ef2b1f17581046b3a2227d5c611fb25ec70ca1ba8554b24b0e69331a484"}, + {file = "packaging-25.0.tar.gz", hash = "sha256:d443872c98d677bf60f6a1f2f8c1cb748e8fe762d2bf9d3148b5599295b0fc4f"}, ] [[package]] name = "pandas" -version = "2.2.3" +version = "2.3.3" description = "Powerful data structures for data analysis, time series, and statistics" optional = false python-versions = ">=3.9" +groups = ["main"] files = [ - {file = "pandas-2.2.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1948ddde24197a0f7add2bdc4ca83bf2b1ef84a1bc8ccffd95eda17fd836ecb5"}, - {file = "pandas-2.2.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:381175499d3802cde0eabbaf6324cce0c4f5d52ca6f8c377c29ad442f50f6348"}, - {file = "pandas-2.2.3-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d9c45366def9a3dd85a6454c0e7908f2b3b8e9c138f5dc38fed7ce720d8453ed"}, - {file = "pandas-2.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:86976a1c5b25ae3f8ccae3a5306e443569ee3c3faf444dfd0f41cda24667ad57"}, - {file = "pandas-2.2.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:b8661b0238a69d7aafe156b7fa86c44b881387509653fdf857bebc5e4008ad42"}, - {file = "pandas-2.2.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:37e0aced3e8f539eccf2e099f65cdb9c8aa85109b0be6e93e2baff94264bdc6f"}, - {file = "pandas-2.2.3-cp310-cp310-win_amd64.whl", hash = "sha256:56534ce0746a58afaf7942ba4863e0ef81c9c50d3f0ae93e9497d6a41a057645"}, - {file = "pandas-2.2.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:66108071e1b935240e74525006034333f98bcdb87ea116de573a6a0dccb6c039"}, - {file = "pandas-2.2.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7c2875855b0ff77b2a64a0365e24455d9990730d6431b9e0ee18ad8acee13dbd"}, - {file = "pandas-2.2.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cd8d0c3be0515c12fed0bdbae072551c8b54b7192c7b1fda0ba56059a0179698"}, - {file = "pandas-2.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c124333816c3a9b03fbeef3a9f230ba9a737e9e5bb4060aa2107a86cc0a497fc"}, - {file = "pandas-2.2.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:63cc132e40a2e084cf01adf0775b15ac515ba905d7dcca47e9a251819c575ef3"}, - {file = "pandas-2.2.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:29401dbfa9ad77319367d36940cd8a0b3a11aba16063e39632d98b0e931ddf32"}, - {file = "pandas-2.2.3-cp311-cp311-win_amd64.whl", hash = "sha256:3fc6873a41186404dad67245896a6e440baacc92f5b716ccd1bc9ed2995ab2c5"}, - {file = "pandas-2.2.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b1d432e8d08679a40e2a6d8b2f9770a5c21793a6f9f47fdd52c5ce1948a5a8a9"}, - {file = "pandas-2.2.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a5a1595fe639f5988ba6a8e5bc9649af3baf26df3998a0abe56c02609392e0a4"}, - {file = "pandas-2.2.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5de54125a92bb4d1c051c0659e6fcb75256bf799a732a87184e5ea503965bce3"}, - {file = "pandas-2.2.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fffb8ae78d8af97f849404f21411c95062db1496aeb3e56f146f0355c9989319"}, - {file = "pandas-2.2.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6dfcb5ee8d4d50c06a51c2fffa6cff6272098ad6540aed1a76d15fb9318194d8"}, - {file = "pandas-2.2.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:062309c1b9ea12a50e8ce661145c6aab431b1e99530d3cd60640e255778bd43a"}, - {file = "pandas-2.2.3-cp312-cp312-win_amd64.whl", hash = "sha256:59ef3764d0fe818125a5097d2ae867ca3fa64df032331b7e0917cf5d7bf66b13"}, - {file = "pandas-2.2.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:f00d1345d84d8c86a63e476bb4955e46458b304b9575dcf71102b5c705320015"}, - {file = "pandas-2.2.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:3508d914817e153ad359d7e069d752cdd736a247c322d932eb89e6bc84217f28"}, - {file = "pandas-2.2.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:22a9d949bfc9a502d320aa04e5d02feab689d61da4e7764b62c30b991c42c5f0"}, - {file = "pandas-2.2.3-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f3a255b2c19987fbbe62a9dfd6cff7ff2aa9ccab3fc75218fd4b7530f01efa24"}, - {file = "pandas-2.2.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:800250ecdadb6d9c78eae4990da62743b857b470883fa27f652db8bdde7f6659"}, - {file = "pandas-2.2.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6374c452ff3ec675a8f46fd9ab25c4ad0ba590b71cf0656f8b6daa5202bca3fb"}, - {file = "pandas-2.2.3-cp313-cp313-win_amd64.whl", hash = "sha256:61c5ad4043f791b61dd4752191d9f07f0ae412515d59ba8f005832a532f8736d"}, - {file = "pandas-2.2.3-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:3b71f27954685ee685317063bf13c7709a7ba74fc996b84fc6821c59b0f06468"}, - {file = "pandas-2.2.3-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:38cf8125c40dae9d5acc10fa66af8ea6fdf760b2714ee482ca691fc66e6fcb18"}, - {file = "pandas-2.2.3-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ba96630bc17c875161df3818780af30e43be9b166ce51c9a18c1feae342906c2"}, - {file = "pandas-2.2.3-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1db71525a1538b30142094edb9adc10be3f3e176748cd7acc2240c2f2e5aa3a4"}, - {file = "pandas-2.2.3-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:15c0e1e02e93116177d29ff83e8b1619c93ddc9c49083f237d4312337a61165d"}, - {file = "pandas-2.2.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:ad5b65698ab28ed8d7f18790a0dc58005c7629f227be9ecc1072aa74c0c1d43a"}, - {file = "pandas-2.2.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:bc6b93f9b966093cb0fd62ff1a7e4c09e6d546ad7c1de191767baffc57628f39"}, - {file = "pandas-2.2.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5dbca4c1acd72e8eeef4753eeca07de9b1db4f398669d5994086f788a5d7cc30"}, - {file = "pandas-2.2.3-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8cd6d7cc958a3910f934ea8dbdf17b2364827bb4dafc38ce6eef6bb3d65ff09c"}, - {file = "pandas-2.2.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:99df71520d25fade9db7c1076ac94eb994f4d2673ef2aa2e86ee039b6746d20c"}, - {file = "pandas-2.2.3-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:31d0ced62d4ea3e231a9f228366919a5ea0b07440d9d4dac345376fd8e1477ea"}, - {file = "pandas-2.2.3-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:7eee9e7cea6adf3e3d24e304ac6b8300646e2a5d1cd3a3c2abed9101b0846761"}, - {file = "pandas-2.2.3-cp39-cp39-win_amd64.whl", hash = "sha256:4850ba03528b6dd51d6c5d273c46f183f39a9baf3f0143e566b89450965b105e"}, - {file = "pandas-2.2.3.tar.gz", hash = "sha256:4f18ba62b61d7e192368b84517265a99b4d7ee8912f8708660fb4a366cc82667"}, + {file = "pandas-2.3.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:376c6446ae31770764215a6c937f72d917f214b43560603cd60da6408f183b6c"}, + {file = "pandas-2.3.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e19d192383eab2f4ceb30b412b22ea30690c9e618f78870357ae1d682912015a"}, + {file = "pandas-2.3.3-cp310-cp310-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5caf26f64126b6c7aec964f74266f435afef1c1b13da3b0636c7518a1fa3e2b1"}, + {file = "pandas-2.3.3-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:dd7478f1463441ae4ca7308a70e90b33470fa593429f9d4c578dd00d1fa78838"}, + {file = "pandas-2.3.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:4793891684806ae50d1288c9bae9330293ab4e083ccd1c5e383c34549c6e4250"}, + {file = "pandas-2.3.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:28083c648d9a99a5dd035ec125d42439c6c1c525098c58af0fc38dd1a7a1b3d4"}, + {file = "pandas-2.3.3-cp310-cp310-win_amd64.whl", hash = "sha256:503cf027cf9940d2ceaa1a93cfb5f8c8c7e6e90720a2850378f0b3f3b1e06826"}, + {file = "pandas-2.3.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:602b8615ebcc4a0c1751e71840428ddebeb142ec02c786e8ad6b1ce3c8dec523"}, + {file = "pandas-2.3.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:8fe25fc7b623b0ef6b5009149627e34d2a4657e880948ec3c840e9402e5c1b45"}, + {file = "pandas-2.3.3-cp311-cp311-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b468d3dad6ff947df92dcb32ede5b7bd41a9b3cceef0a30ed925f6d01fb8fa66"}, + {file = "pandas-2.3.3-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b98560e98cb334799c0b07ca7967ac361a47326e9b4e5a7dfb5ab2b1c9d35a1b"}, + {file = "pandas-2.3.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:1d37b5848ba49824e5c30bedb9c830ab9b7751fd049bc7914533e01c65f79791"}, + {file = "pandas-2.3.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:db4301b2d1f926ae677a751eb2bd0e8c5f5319c9cb3f88b0becbbb0b07b34151"}, + {file = "pandas-2.3.3-cp311-cp311-win_amd64.whl", hash = "sha256:f086f6fe114e19d92014a1966f43a3e62285109afe874f067f5abbdcbb10e59c"}, + {file = "pandas-2.3.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:6d21f6d74eb1725c2efaa71a2bfc661a0689579b58e9c0ca58a739ff0b002b53"}, + {file = "pandas-2.3.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:3fd2f887589c7aa868e02632612ba39acb0b8948faf5cc58f0850e165bd46f35"}, + {file = "pandas-2.3.3-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ecaf1e12bdc03c86ad4a7ea848d66c685cb6851d807a26aa245ca3d2017a1908"}, + {file = "pandas-2.3.3-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b3d11d2fda7eb164ef27ffc14b4fcab16a80e1ce67e9f57e19ec0afaf715ba89"}, + {file = "pandas-2.3.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:a68e15f780eddf2b07d242e17a04aa187a7ee12b40b930bfdd78070556550e98"}, + {file = "pandas-2.3.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:371a4ab48e950033bcf52b6527eccb564f52dc826c02afd9a1bc0ab731bba084"}, + {file = "pandas-2.3.3-cp312-cp312-win_amd64.whl", hash = "sha256:a16dcec078a01eeef8ee61bf64074b4e524a2a3f4b3be9326420cabe59c4778b"}, + {file = "pandas-2.3.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:56851a737e3470de7fa88e6131f41281ed440d29a9268dcbf0002da5ac366713"}, + {file = "pandas-2.3.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:bdcd9d1167f4885211e401b3036c0c8d9e274eee67ea8d0758a256d60704cfe8"}, + {file = "pandas-2.3.3-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e32e7cc9af0f1cc15548288a51a3b681cc2a219faa838e995f7dc53dbab1062d"}, + {file = "pandas-2.3.3-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:318d77e0e42a628c04dc56bcef4b40de67918f7041c2b061af1da41dcff670ac"}, + {file = "pandas-2.3.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:4e0a175408804d566144e170d0476b15d78458795bb18f1304fb94160cabf40c"}, + {file = "pandas-2.3.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:93c2d9ab0fc11822b5eece72ec9587e172f63cff87c00b062f6e37448ced4493"}, + {file = "pandas-2.3.3-cp313-cp313-win_amd64.whl", hash = "sha256:f8bfc0e12dc78f777f323f55c58649591b2cd0c43534e8355c51d3fede5f4dee"}, + {file = "pandas-2.3.3-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:75ea25f9529fdec2d2e93a42c523962261e567d250b0013b16210e1d40d7c2e5"}, + {file = "pandas-2.3.3-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:74ecdf1d301e812db96a465a525952f4dde225fdb6d8e5a521d47e1f42041e21"}, + {file = "pandas-2.3.3-cp313-cp313t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6435cb949cb34ec11cc9860246ccb2fdc9ecd742c12d3304989017d53f039a78"}, + {file = "pandas-2.3.3-cp313-cp313t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:900f47d8f20860de523a1ac881c4c36d65efcb2eb850e6948140fa781736e110"}, + {file = "pandas-2.3.3-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:a45c765238e2ed7d7c608fc5bc4a6f88b642f2f01e70c0c23d2224dd21829d86"}, + {file = "pandas-2.3.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:c4fc4c21971a1a9f4bdb4c73978c7f7256caa3e62b323f70d6cb80db583350bc"}, + {file = "pandas-2.3.3-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:ee15f284898e7b246df8087fc82b87b01686f98ee67d85a17b7ab44143a3a9a0"}, + {file = "pandas-2.3.3-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:1611aedd912e1ff81ff41c745822980c49ce4a7907537be8692c8dbc31924593"}, + {file = "pandas-2.3.3-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6d2cefc361461662ac48810cb14365a365ce864afe85ef1f447ff5a1e99ea81c"}, + {file = "pandas-2.3.3-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ee67acbbf05014ea6c763beb097e03cd629961c8a632075eeb34247120abcb4b"}, + {file = "pandas-2.3.3-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:c46467899aaa4da076d5abc11084634e2d197e9460643dd455ac3db5856b24d6"}, + {file = "pandas-2.3.3-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:6253c72c6a1d990a410bc7de641d34053364ef8bcd3126f7e7450125887dffe3"}, + {file = "pandas-2.3.3-cp314-cp314-win_amd64.whl", hash = "sha256:1b07204a219b3b7350abaae088f451860223a52cfb8a6c53358e7948735158e5"}, + {file = "pandas-2.3.3-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:2462b1a365b6109d275250baaae7b760fd25c726aaca0054649286bcfbb3e8ec"}, + {file = "pandas-2.3.3-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:0242fe9a49aa8b4d78a4fa03acb397a58833ef6199e9aa40a95f027bb3a1b6e7"}, + {file = "pandas-2.3.3-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a21d830e78df0a515db2b3d2f5570610f5e6bd2e27749770e8bb7b524b89b450"}, + {file = "pandas-2.3.3-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2e3ebdb170b5ef78f19bfb71b0dc5dc58775032361fa188e814959b74d726dd5"}, + {file = "pandas-2.3.3-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:d051c0e065b94b7a3cea50eb1ec32e912cd96dba41647eb24104b6c6c14c5788"}, + {file = "pandas-2.3.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:3869faf4bd07b3b66a9f462417d0ca3a9df29a9f6abd5d0d0dbab15dac7abe87"}, + {file = "pandas-2.3.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c503ba5216814e295f40711470446bc3fd00f0faea8a086cbc688808e26f92a2"}, + {file = "pandas-2.3.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a637c5cdfa04b6d6e2ecedcb81fc52ffb0fd78ce2ebccc9ea964df9f658de8c8"}, + {file = "pandas-2.3.3-cp39-cp39-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:854d00d556406bffe66a4c0802f334c9ad5a96b4f1f868adf036a21b11ef13ff"}, + {file = "pandas-2.3.3-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:bf1f8a81d04ca90e32a0aceb819d34dbd378a98bf923b6398b9a3ec0bf44de29"}, + {file = "pandas-2.3.3-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:23ebd657a4d38268c7dfbdf089fbc31ea709d82e4923c5ffd4fbd5747133ce73"}, + {file = "pandas-2.3.3-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:5554c929ccc317d41a5e3d1234f3be588248e61f08a74dd17c9eabb535777dc9"}, + {file = "pandas-2.3.3-cp39-cp39-win_amd64.whl", hash = "sha256:d3e28b3e83862ccf4d85ff19cf8c20b2ae7e503881711ff2d534dc8f761131aa"}, + {file = "pandas-2.3.3.tar.gz", hash = "sha256:e05e1af93b977f7eafa636d043f9f94c7ee3ac81af99c13508215942e64c993b"}, ] [package.dependencies] -numpy = {version = ">=1.23.2", markers = "python_version == \"3.11\""} +numpy = {version = ">=1.26.0", markers = "python_version >= \"3.12\""} python-dateutil = ">=2.8.2" pytz = ">=2020.1" tzdata = ">=2022.7" @@ -351,162 +252,158 @@ test = ["hypothesis (>=6.46.1)", "pytest (>=7.3.2)", "pytest-xdist (>=2.2.0)"] xml = ["lxml (>=4.9.2)"] [[package]] -name = "platformdirs" -version = "4.3.6" -description = "A small Python package for determining appropriate platform-specific dirs, e.g. a `user data dir`." +name = "pathspec" +version = "0.12.1" +description = "Utility library for gitignore style pattern matching of file paths." optional = false python-versions = ">=3.8" +groups = ["dev"] files = [ - {file = "platformdirs-4.3.6-py3-none-any.whl", hash = "sha256:73e575e1408ab8103900836b97580d5307456908a03e92031bab39e4554cc3fb"}, - {file = "platformdirs-4.3.6.tar.gz", hash = "sha256:357fb2acbc885b0419afd3ce3ed34564c13c9b95c89360cd9563f73aa5e2b907"}, + {file = "pathspec-0.12.1-py3-none-any.whl", hash = "sha256:a0d503e138a4c123b27490a4f7beda6a01c6f288df0e4a8b79c7eb0dc7b4cc08"}, + {file = "pathspec-0.12.1.tar.gz", hash = "sha256:a482d51503a1ab33b1c67a6c3813a26953dbdc71c31dacaef9a838c4e29f5712"}, ] -[package.extras] -docs = ["furo (>=2024.8.6)", "proselint (>=0.14)", "sphinx (>=8.0.2)", "sphinx-autodoc-typehints (>=2.4)"] -test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=8.3.2)", "pytest-cov (>=5)", "pytest-mock (>=3.14)"] -type = ["mypy (>=1.11.2)"] - [[package]] name = "pluggy" -version = "1.5.0" +version = "1.6.0" description = "plugin and hook calling mechanisms for python" optional = false -python-versions = ">=3.8" +python-versions = ">=3.9" +groups = ["dev"] files = [ - {file = "pluggy-1.5.0-py3-none-any.whl", hash = "sha256:44e1ad92c8ca002de6377e165f3e0f1be63266ab4d554740532335b9d75ea669"}, - {file = "pluggy-1.5.0.tar.gz", hash = "sha256:2cffa88e94fdc978c4c574f15f9e59b7f4201d439195c3715ca9e2486f1d0cf1"}, + {file = "pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746"}, + {file = "pluggy-1.6.0.tar.gz", hash = "sha256:7dcc130b76258d33b90f61b658791dede3486c3e6bfb003ee5c9bfb396dd22f3"}, ] [package.extras] dev = ["pre-commit", "tox"] -testing = ["pytest", "pytest-benchmark"] - -[[package]] -name = "py" -version = "1.11.0" -description = "library with cross-python path, ini-parsing, io, code, log facilities" -optional = false -python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*" -files = [ - {file = "py-1.11.0-py2.py3-none-any.whl", hash = "sha256:607c53218732647dff4acdfcd50cb62615cedf612e72d1724fb1a0cc6405b378"}, - {file = "py-1.11.0.tar.gz", hash = "sha256:51c75c4126074b472f746a24399ad32f6053d1b34b68d2fa41e558e6f4a98719"}, -] +testing = ["coverage", "pytest", "pytest-benchmark"] [[package]] name = "py4j" -version = "0.10.9.7" +version = "0.10.9.9" description = "Enables Python programs to dynamically access arbitrary Java objects" optional = false python-versions = "*" +groups = ["main"] files = [ - {file = "py4j-0.10.9.7-py2.py3-none-any.whl", hash = "sha256:85defdfd2b2376eb3abf5ca6474b51ab7e0de341c75a02f46dc9b5976f5a5c1b"}, - {file = "py4j-0.10.9.7.tar.gz", hash = "sha256:0b6e5315bb3ada5cf62ac651d107bb2ebc02def3dee9d9548e3baac644ea8dbb"}, + {file = "py4j-0.10.9.9-py2.py3-none-any.whl", hash = "sha256:c7c26e4158defb37b0bb124933163641a2ff6e3a3913f7811b0ddbe07ed61533"}, + {file = "py4j-0.10.9.9.tar.gz", hash = "sha256:f694cad19efa5bd1dee4f3e5270eb406613c974394035e5bfc4ec1aba870b879"}, ] [[package]] name = "pyarrow" -version = "12.0.1" +version = "21.0.0" description = "Python library for Apache Arrow" optional = false -python-versions = ">=3.7" +python-versions = ">=3.9" +groups = ["main"] files = [ - {file = "pyarrow-12.0.1-cp310-cp310-macosx_10_14_x86_64.whl", hash = "sha256:6d288029a94a9bb5407ceebdd7110ba398a00412c5b0155ee9813a40d246c5df"}, - {file = "pyarrow-12.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:345e1828efdbd9aa4d4de7d5676778aba384a2c3add896d995b23d368e60e5af"}, - {file = "pyarrow-12.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8d6009fdf8986332b2169314da482baed47ac053311c8934ac6651e614deacd6"}, - {file = "pyarrow-12.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2d3c4cbbf81e6dd23fe921bc91dc4619ea3b79bc58ef10bce0f49bdafb103daf"}, - {file = "pyarrow-12.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:cdacf515ec276709ac8042c7d9bd5be83b4f5f39c6c037a17a60d7ebfd92c890"}, - {file = "pyarrow-12.0.1-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:749be7fd2ff260683f9cc739cb862fb11be376de965a2a8ccbf2693b098db6c7"}, - {file = "pyarrow-12.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:6895b5fb74289d055c43db3af0de6e16b07586c45763cb5e558d38b86a91e3a7"}, - {file = "pyarrow-12.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1887bdae17ec3b4c046fcf19951e71b6a619f39fa674f9881216173566c8f718"}, - {file = "pyarrow-12.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e2c9cb8eeabbadf5fcfc3d1ddea616c7ce893db2ce4dcef0ac13b099ad7ca082"}, - {file = "pyarrow-12.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:ce4aebdf412bd0eeb800d8e47db854f9f9f7e2f5a0220440acf219ddfddd4f63"}, - {file = "pyarrow-12.0.1-cp37-cp37m-macosx_10_14_x86_64.whl", hash = "sha256:e0d8730c7f6e893f6db5d5b86eda42c0a130842d101992b581e2138e4d5663d3"}, - {file = "pyarrow-12.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:43364daec02f69fec89d2315f7fbfbeec956e0d991cbbef471681bd77875c40f"}, - {file = "pyarrow-12.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:051f9f5ccf585f12d7de836e50965b3c235542cc896959320d9776ab93f3b33d"}, - {file = "pyarrow-12.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:be2757e9275875d2a9c6e6052ac7957fbbfc7bc7370e4a036a9b893e96fedaba"}, - {file = "pyarrow-12.0.1-cp38-cp38-macosx_10_14_x86_64.whl", hash = "sha256:cf812306d66f40f69e684300f7af5111c11f6e0d89d6b733e05a3de44961529d"}, - {file = "pyarrow-12.0.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:459a1c0ed2d68671188b2118c63bac91eaef6fc150c77ddd8a583e3c795737bf"}, - {file = "pyarrow-12.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:85e705e33eaf666bbe508a16fd5ba27ca061e177916b7a317ba5a51bee43384c"}, - {file = "pyarrow-12.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9120c3eb2b1f6f516a3b7a9714ed860882d9ef98c4b17edcdc91d95b7528db60"}, - {file = "pyarrow-12.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:c780f4dc40460015d80fcd6a6140de80b615349ed68ef9adb653fe351778c9b3"}, - {file = "pyarrow-12.0.1-cp39-cp39-macosx_10_14_x86_64.whl", hash = "sha256:a3c63124fc26bf5f95f508f5d04e1ece8cc23a8b0af2a1e6ab2b1ec3fdc91b24"}, - {file = "pyarrow-12.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b13329f79fa4472324f8d32dc1b1216616d09bd1e77cfb13104dec5463632c36"}, - {file = "pyarrow-12.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bb656150d3d12ec1396f6dde542db1675a95c0cc8366d507347b0beed96e87ca"}, - {file = "pyarrow-12.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6251e38470da97a5b2e00de5c6a049149f7b2bd62f12fa5dbb9ac674119ba71a"}, - {file = "pyarrow-12.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:3de26da901216149ce086920547dfff5cd22818c9eab67ebc41e863a5883bac7"}, - {file = "pyarrow-12.0.1.tar.gz", hash = "sha256:cce317fc96e5b71107bf1f9f184d5e54e2bd14bbf3f9a3d62819961f0af86fec"}, + {file = "pyarrow-21.0.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:e563271e2c5ff4d4a4cbeb2c83d5cf0d4938b891518e676025f7268c6fe5fe26"}, + {file = "pyarrow-21.0.0-cp310-cp310-macosx_12_0_x86_64.whl", hash = "sha256:fee33b0ca46f4c85443d6c450357101e47d53e6c3f008d658c27a2d020d44c79"}, + {file = "pyarrow-21.0.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:7be45519b830f7c24b21d630a31d48bcebfd5d4d7f9d3bdb49da9cdf6d764edb"}, + {file = "pyarrow-21.0.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:26bfd95f6bff443ceae63c65dc7e048670b7e98bc892210acba7e4995d3d4b51"}, + {file = "pyarrow-21.0.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:bd04ec08f7f8bd113c55868bd3fc442a9db67c27af098c5f814a3091e71cc61a"}, + {file = "pyarrow-21.0.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:9b0b14b49ac10654332a805aedfc0147fb3469cbf8ea951b3d040dab12372594"}, + {file = "pyarrow-21.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:9d9f8bcb4c3be7738add259738abdeddc363de1b80e3310e04067aa1ca596634"}, + {file = "pyarrow-21.0.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:c077f48aab61738c237802836fc3844f85409a46015635198761b0d6a688f87b"}, + {file = "pyarrow-21.0.0-cp311-cp311-macosx_12_0_x86_64.whl", hash = "sha256:689f448066781856237eca8d1975b98cace19b8dd2ab6145bf49475478bcaa10"}, + {file = "pyarrow-21.0.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:479ee41399fcddc46159a551705b89c05f11e8b8cb8e968f7fec64f62d91985e"}, + {file = "pyarrow-21.0.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:40ebfcb54a4f11bcde86bc586cbd0272bac0d516cfa539c799c2453768477569"}, + {file = "pyarrow-21.0.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8d58d8497814274d3d20214fbb24abcad2f7e351474357d552a8d53bce70c70e"}, + {file = "pyarrow-21.0.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:585e7224f21124dd57836b1530ac8f2df2afc43c861d7bf3d58a4870c42ae36c"}, + {file = "pyarrow-21.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:555ca6935b2cbca2c0e932bedd853e9bc523098c39636de9ad4693b5b1df86d6"}, + {file = "pyarrow-21.0.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:3a302f0e0963db37e0a24a70c56cf91a4faa0bca51c23812279ca2e23481fccd"}, + {file = "pyarrow-21.0.0-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:b6b27cf01e243871390474a211a7922bfbe3bda21e39bc9160daf0da3fe48876"}, + {file = "pyarrow-21.0.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:e72a8ec6b868e258a2cd2672d91f2860ad532d590ce94cdf7d5e7ec674ccf03d"}, + {file = "pyarrow-21.0.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:b7ae0bbdc8c6674259b25bef5d2a1d6af5d39d7200c819cf99e07f7dfef1c51e"}, + {file = "pyarrow-21.0.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:58c30a1729f82d201627c173d91bd431db88ea74dcaa3885855bc6203e433b82"}, + {file = "pyarrow-21.0.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:072116f65604b822a7f22945a7a6e581cfa28e3454fdcc6939d4ff6090126623"}, + {file = "pyarrow-21.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:cf56ec8b0a5c8c9d7021d6fd754e688104f9ebebf1bf4449613c9531f5346a18"}, + {file = "pyarrow-21.0.0-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:e99310a4ebd4479bcd1964dff9e14af33746300cb014aa4a3781738ac63baf4a"}, + {file = "pyarrow-21.0.0-cp313-cp313-macosx_12_0_x86_64.whl", hash = "sha256:d2fe8e7f3ce329a71b7ddd7498b3cfac0eeb200c2789bd840234f0dc271a8efe"}, + {file = "pyarrow-21.0.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:f522e5709379d72fb3da7785aa489ff0bb87448a9dc5a75f45763a795a089ebd"}, + {file = "pyarrow-21.0.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:69cbbdf0631396e9925e048cfa5bce4e8c3d3b41562bbd70c685a8eb53a91e61"}, + {file = "pyarrow-21.0.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:731c7022587006b755d0bdb27626a1a3bb004bb56b11fb30d98b6c1b4718579d"}, + {file = "pyarrow-21.0.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:dc56bc708f2d8ac71bd1dcb927e458c93cec10b98eb4120206a4091db7b67b99"}, + {file = "pyarrow-21.0.0-cp313-cp313-win_amd64.whl", hash = "sha256:186aa00bca62139f75b7de8420f745f2af12941595bbbfa7ed3870ff63e25636"}, + {file = "pyarrow-21.0.0-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:a7a102574faa3f421141a64c10216e078df467ab9576684d5cd696952546e2da"}, + {file = "pyarrow-21.0.0-cp313-cp313t-macosx_12_0_x86_64.whl", hash = "sha256:1e005378c4a2c6db3ada3ad4c217b381f6c886f0a80d6a316fe586b90f77efd7"}, + {file = "pyarrow-21.0.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:65f8e85f79031449ec8706b74504a316805217b35b6099155dd7e227eef0d4b6"}, + {file = "pyarrow-21.0.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:3a81486adc665c7eb1a2bde0224cfca6ceaba344a82a971ef059678417880eb8"}, + {file = "pyarrow-21.0.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:fc0d2f88b81dcf3ccf9a6ae17f89183762c8a94a5bdcfa09e05cfe413acf0503"}, + {file = "pyarrow-21.0.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:6299449adf89df38537837487a4f8d3bd91ec94354fdd2a7d30bc11c48ef6e79"}, + {file = "pyarrow-21.0.0-cp313-cp313t-win_amd64.whl", hash = "sha256:222c39e2c70113543982c6b34f3077962b44fca38c0bd9e68bb6781534425c10"}, + {file = "pyarrow-21.0.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:a7f6524e3747e35f80744537c78e7302cd41deee8baa668d56d55f77d9c464b3"}, + {file = "pyarrow-21.0.0-cp39-cp39-macosx_12_0_x86_64.whl", hash = "sha256:203003786c9fd253ebcafa44b03c06983c9c8d06c3145e37f1b76a1f317aeae1"}, + {file = "pyarrow-21.0.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:3b4d97e297741796fead24867a8dabf86c87e4584ccc03167e4a811f50fdf74d"}, + {file = "pyarrow-21.0.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:898afce396b80fdda05e3086b4256f8677c671f7b1d27a6976fa011d3fd0a86e"}, + {file = "pyarrow-21.0.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:067c66ca29aaedae08218569a114e413b26e742171f526e828e1064fcdec13f4"}, + {file = "pyarrow-21.0.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:0c4e75d13eb76295a49e0ea056eb18dbd87d81450bfeb8afa19a7e5a75ae2ad7"}, + {file = "pyarrow-21.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:cdc4c17afda4dab2a9c0b79148a43a7f4e1094916b3e18d8975bfd6d6d52241f"}, + {file = "pyarrow-21.0.0.tar.gz", hash = "sha256:5051f2dccf0e283ff56335760cbc8622cf52264d67e359d5569541ac11b6d5bc"}, ] -[package.dependencies] -numpy = ">=1.16.6" +[package.extras] +test = ["cffi", "hypothesis", "pandas", "pytest", "pytz"] [[package]] -name = "pylint" -version = "2.17.7" -description = "python code static checker" +name = "pygments" +version = "2.19.2" +description = "Pygments is a syntax highlighting package written in Python." optional = false -python-versions = ">=3.7.2" +python-versions = ">=3.8" +groups = ["dev"] files = [ - {file = "pylint-2.17.7-py3-none-any.whl", hash = "sha256:27a8d4c7ddc8c2f8c18aa0050148f89ffc09838142193fdbe98f172781a3ff87"}, - {file = "pylint-2.17.7.tar.gz", hash = "sha256:f4fcac7ae74cfe36bc8451e931d8438e4a476c20314b1101c458ad0f05191fad"}, + {file = "pygments-2.19.2-py3-none-any.whl", hash = "sha256:86540386c03d588bb81d44bc3928634ff26449851e99741617ecb9037ee5ec0b"}, + {file = "pygments-2.19.2.tar.gz", hash = "sha256:636cb2477cec7f8952536970bc533bc43743542f70392ae026374600add5b887"}, ] -[package.dependencies] -astroid = ">=2.15.8,<=2.17.0-dev0" -colorama = {version = ">=0.4.5", markers = "sys_platform == \"win32\""} -dill = {version = ">=0.3.6", markers = "python_version >= \"3.11\""} -isort = ">=4.2.5,<6" -mccabe = ">=0.6,<0.8" -platformdirs = ">=2.2.0" -tomlkit = ">=0.10.1" - [package.extras] -spelling = ["pyenchant (>=3.2,<4.0)"] -testutils = ["gitpython (>3)"] +windows-terminal = ["colorama (>=0.4.6)"] [[package]] name = "pyspark" -version = "3.5.1" +version = "4.0.1" description = "Apache Spark Python API" optional = false -python-versions = ">=3.8" +python-versions = ">=3.9" +groups = ["main"] files = [ - {file = "pyspark-3.5.1.tar.gz", hash = "sha256:dd6569e547365eadc4f887bf57f153e4d582a68c4b490de475d55b9981664910"}, + {file = "pyspark-4.0.1.tar.gz", hash = "sha256:9d1f22d994f60369228397e3479003ffe2dd736ba79165003246ff7bd48e2c73"}, ] [package.dependencies] -py4j = "0.10.9.7" +py4j = "0.10.9.9" [package.extras] -connect = ["googleapis-common-protos (>=1.56.4)", "grpcio (>=1.56.0)", "grpcio-status (>=1.56.0)", "numpy (>=1.15)", "pandas (>=1.0.5)", "pyarrow (>=4.0.0)"] -ml = ["numpy (>=1.15)"] -mllib = ["numpy (>=1.15)"] -pandas-on-spark = ["numpy (>=1.15)", "pandas (>=1.0.5)", "pyarrow (>=4.0.0)"] -sql = ["numpy (>=1.15)", "pandas (>=1.0.5)", "pyarrow (>=4.0.0)"] +connect = ["googleapis-common-protos (>=1.65.0)", "grpcio (>=1.67.0)", "grpcio-status (>=1.67.0)", "numpy (>=1.21)", "pandas (>=2.0.0)", "pyarrow (>=11.0.0)"] +ml = ["numpy (>=1.21)"] +mllib = ["numpy (>=1.21)"] +pandas-on-spark = ["numpy (>=1.21)", "pandas (>=2.0.0)", "pyarrow (>=11.0.0)"] +sql = ["numpy (>=1.21)", "pandas (>=2.0.0)", "pyarrow (>=11.0.0)"] [[package]] name = "pytest" -version = "6.2.5" +version = "8.4.2" description = "pytest: simple powerful testing with Python" optional = false -python-versions = ">=3.6" +python-versions = ">=3.9" +groups = ["dev"] files = [ - {file = "pytest-6.2.5-py3-none-any.whl", hash = "sha256:7310f8d27bc79ced999e760ca304d69f6ba6c6649c0b60fb0e04a4a77cacc134"}, - {file = "pytest-6.2.5.tar.gz", hash = "sha256:131b36680866a76e6781d13f101efb86cf674ebb9762eb70d3082b6f29889e89"}, + {file = "pytest-8.4.2-py3-none-any.whl", hash = "sha256:872f880de3fc3a5bdc88a11b39c9710c3497a547cfa9320bc3c5e62fbf272e79"}, + {file = "pytest-8.4.2.tar.gz", hash = "sha256:86c0d0b93306b961d58d62a4db4879f27fe25513d4b969df351abdddb3c30e01"}, ] [package.dependencies] -atomicwrites = {version = ">=1.0", markers = "sys_platform == \"win32\""} -attrs = ">=19.2.0" -colorama = {version = "*", markers = "sys_platform == \"win32\""} -iniconfig = "*" -packaging = "*" -pluggy = ">=0.12,<2.0" -py = ">=1.8.2" -toml = "*" +colorama = {version = ">=0.4", markers = "sys_platform == \"win32\""} +iniconfig = ">=1" +packaging = ">=20" +pluggy = ">=1.5,<2" +pygments = ">=2.7.2" [package.extras] -testing = ["argcomplete", "hypothesis (>=3.56)", "mock", "nose", "requests", "xmlschema"] +dev = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "requests", "setuptools", "xmlschema"] [[package]] name = "python-dateutil" @@ -514,6 +411,7 @@ version = "2.9.0.post0" description = "Extensions to the standard Python datetime module" optional = false python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7" +groups = ["main"] files = [ {file = "python-dateutil-2.9.0.post0.tar.gz", hash = "sha256:37dd54208da7e1cd875388217d5e00ebd4179249f90fb72437e91a35459a0ad3"}, {file = "python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427"}, @@ -524,150 +422,82 @@ six = ">=1.5" [[package]] name = "pytz" -version = "2024.2" +version = "2025.2" description = "World timezone definitions, modern and historical" optional = false python-versions = "*" +groups = ["main"] files = [ - {file = "pytz-2024.2-py2.py3-none-any.whl", hash = "sha256:31c7c1817eb7fae7ca4b8c7ee50c72f93aa2dd863de768e1ef4245d426aa0725"}, - {file = "pytz-2024.2.tar.gz", hash = "sha256:2aa355083c50a0f93fa581709deac0c9ad65cca8a9e9beac660adcbd493c798a"}, + {file = "pytz-2025.2-py2.py3-none-any.whl", hash = "sha256:5ddf76296dd8c44c26eb8f4b6f35488f3ccbf6fbbd7adee0b7262d43f0ec2f00"}, + {file = "pytz-2025.2.tar.gz", hash = "sha256:360b9e3dbb49a209c21ad61809c7fb453643e048b38924c765813546746e81c3"}, ] [[package]] -name = "six" -version = "1.16.0" -description = "Python 2 and 3 compatibility utilities" +name = "ruff" +version = "0.14.0" +description = "An extremely fast Python linter and code formatter, written in Rust." optional = false -python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*" -files = [ - {file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"}, - {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"}, -] - -[[package]] -name = "toml" -version = "0.10.2" -description = "Python Library for Tom's Obvious, Minimal Language" -optional = false -python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*" +python-versions = ">=3.7" +groups = ["dev"] files = [ - {file = "toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b"}, - {file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"}, + {file = "ruff-0.14.0-py3-none-linux_armv6l.whl", hash = "sha256:58e15bffa7054299becf4bab8a1187062c6f8cafbe9f6e39e0d5aface455d6b3"}, + {file = "ruff-0.14.0-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:838d1b065f4df676b7c9957992f2304e41ead7a50a568185efd404297d5701e8"}, + {file = "ruff-0.14.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:703799d059ba50f745605b04638fa7e9682cc3da084b2092feee63500ff3d9b8"}, + {file = "ruff-0.14.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3ba9a8925e90f861502f7d974cc60e18ca29c72bb0ee8bfeabb6ade35a3abde7"}, + {file = "ruff-0.14.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e41f785498bd200ffc276eb9e1570c019c1d907b07cfb081092c8ad51975bbe7"}, + {file = "ruff-0.14.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:30a58c087aef4584c193aebf2700f0fbcfc1e77b89c7385e3139956fa90434e2"}, + {file = "ruff-0.14.0-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:f8d07350bc7af0a5ce8812b7d5c1a7293cf02476752f23fdfc500d24b79b783c"}, + {file = "ruff-0.14.0-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:eec3bbbf3a7d5482b5c1f42d5fc972774d71d107d447919fca620b0be3e3b75e"}, + {file = "ruff-0.14.0-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:16b68e183a0e28e5c176d51004aaa40559e8f90065a10a559176713fcf435206"}, + {file = "ruff-0.14.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eb732d17db2e945cfcbbc52af0143eda1da36ca8ae25083dd4f66f1542fdf82e"}, + {file = "ruff-0.14.0-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:c958f66ab884b7873e72df38dcabee03d556a8f2ee1b8538ee1c2bbd619883dd"}, + {file = "ruff-0.14.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:7eb0499a2e01f6e0c285afc5bac43ab380cbfc17cd43a2e1dd10ec97d6f2c42d"}, + {file = "ruff-0.14.0-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:4c63b2d99fafa05efca0ab198fd48fa6030d57e4423df3f18e03aa62518c565f"}, + {file = "ruff-0.14.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:668fce701b7a222f3f5327f86909db2bbe99c30877c8001ff934c5413812ac02"}, + {file = "ruff-0.14.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:a86bf575e05cb68dcb34e4c7dfe1064d44d3f0c04bbc0491949092192b515296"}, + {file = "ruff-0.14.0-py3-none-win32.whl", hash = "sha256:7450a243d7125d1c032cb4b93d9625dea46c8c42b4f06c6b709baac168e10543"}, + {file = "ruff-0.14.0-py3-none-win_amd64.whl", hash = "sha256:ea95da28cd874c4d9c922b39381cbd69cb7e7b49c21b8152b014bd4f52acddc2"}, + {file = "ruff-0.14.0-py3-none-win_arm64.whl", hash = "sha256:f42c9495f5c13ff841b1da4cb3c2a42075409592825dada7c5885c2c844ac730"}, + {file = "ruff-0.14.0.tar.gz", hash = "sha256:62ec8969b7510f77945df916de15da55311fade8d6050995ff7f680afe582c57"}, ] [[package]] -name = "tomlkit" -version = "0.13.2" -description = "Style preserving TOML library" +name = "six" +version = "1.17.0" +description = "Python 2 and 3 compatibility utilities" optional = false -python-versions = ">=3.8" +python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7" +groups = ["main"] files = [ - {file = "tomlkit-0.13.2-py3-none-any.whl", hash = "sha256:7a974427f6e119197f670fbbbeae7bef749a6c14e793db934baefc1b5f03efde"}, - {file = "tomlkit-0.13.2.tar.gz", hash = "sha256:fff5fe59a87295b278abd31bec92c15d9bc4a06885ab12bcea52c71119392e79"}, + {file = "six-1.17.0-py2.py3-none-any.whl", hash = "sha256:4721f391ed90541fddacab5acf947aa0d3dc7d27b2e1e8eda2be8970586c3274"}, + {file = "six-1.17.0.tar.gz", hash = "sha256:ff70335d468e7eb6ec65b95b99d3a2836546063f63acc5171de367e834932a81"}, ] [[package]] name = "typing-extensions" -version = "4.12.2" -description = "Backported and Experimental Type Hints for Python 3.8+" +version = "4.15.0" +description = "Backported and Experimental Type Hints for Python 3.9+" optional = false -python-versions = ">=3.8" +python-versions = ">=3.9" +groups = ["dev"] files = [ - {file = "typing_extensions-4.12.2-py3-none-any.whl", hash = "sha256:04e5ca0351e0f3f85c6853954072df659d0d13fac324d0072316b67d7794700d"}, - {file = "typing_extensions-4.12.2.tar.gz", hash = "sha256:1a7ead55c7e559dd4dee8856e3a88b41225abfe1ce8df57b7c13915fe121ffb8"}, + {file = "typing_extensions-4.15.0-py3-none-any.whl", hash = "sha256:f0fa19c6845758ab08074a0cfa8b7aecb71c999ca73d62883bc25cc018c4e548"}, + {file = "typing_extensions-4.15.0.tar.gz", hash = "sha256:0cea48d173cc12fa28ecabc3b837ea3cf6f38c6d1136f85cbaaf598984861466"}, ] [[package]] name = "tzdata" -version = "2024.2" +version = "2025.2" description = "Provider of IANA time zone data" optional = false python-versions = ">=2" +groups = ["main"] files = [ - {file = "tzdata-2024.2-py2.py3-none-any.whl", hash = "sha256:a48093786cdcde33cad18c2555e8532f34422074448fbc874186f0abd79565cd"}, - {file = "tzdata-2024.2.tar.gz", hash = "sha256:7d85cc416e9382e69095b7bdf4afd9e3880418a2413feec7069d533d6b4e31cc"}, -] - -[[package]] -name = "wrapt" -version = "1.16.0" -description = "Module for decorators, wrappers and monkey patching." -optional = false -python-versions = ">=3.6" -files = [ - {file = "wrapt-1.16.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ffa565331890b90056c01db69c0fe634a776f8019c143a5ae265f9c6bc4bd6d4"}, - {file = "wrapt-1.16.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e4fdb9275308292e880dcbeb12546df7f3e0f96c6b41197e0cf37d2826359020"}, - {file = "wrapt-1.16.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bb2dee3874a500de01c93d5c71415fcaef1d858370d405824783e7a8ef5db440"}, - {file = "wrapt-1.16.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2a88e6010048489cda82b1326889ec075a8c856c2e6a256072b28eaee3ccf487"}, - {file = "wrapt-1.16.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ac83a914ebaf589b69f7d0a1277602ff494e21f4c2f743313414378f8f50a4cf"}, - {file = "wrapt-1.16.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:73aa7d98215d39b8455f103de64391cb79dfcad601701a3aa0dddacf74911d72"}, - {file = "wrapt-1.16.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:807cc8543a477ab7422f1120a217054f958a66ef7314f76dd9e77d3f02cdccd0"}, - {file = "wrapt-1.16.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:bf5703fdeb350e36885f2875d853ce13172ae281c56e509f4e6eca049bdfb136"}, - {file = "wrapt-1.16.0-cp310-cp310-win32.whl", hash = "sha256:f6b2d0c6703c988d334f297aa5df18c45e97b0af3679bb75059e0e0bd8b1069d"}, - {file = "wrapt-1.16.0-cp310-cp310-win_amd64.whl", hash = "sha256:decbfa2f618fa8ed81c95ee18a387ff973143c656ef800c9f24fb7e9c16054e2"}, - {file = "wrapt-1.16.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:1a5db485fe2de4403f13fafdc231b0dbae5eca4359232d2efc79025527375b09"}, - {file = "wrapt-1.16.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:75ea7d0ee2a15733684badb16de6794894ed9c55aa5e9903260922f0482e687d"}, - {file = "wrapt-1.16.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a452f9ca3e3267cd4d0fcf2edd0d035b1934ac2bd7e0e57ac91ad6b95c0c6389"}, - {file = "wrapt-1.16.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:43aa59eadec7890d9958748db829df269f0368521ba6dc68cc172d5d03ed8060"}, - {file = "wrapt-1.16.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:72554a23c78a8e7aa02abbd699d129eead8b147a23c56e08d08dfc29cfdddca1"}, - {file = "wrapt-1.16.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:d2efee35b4b0a347e0d99d28e884dfd82797852d62fcd7ebdeee26f3ceb72cf3"}, - {file = "wrapt-1.16.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:6dcfcffe73710be01d90cae08c3e548d90932d37b39ef83969ae135d36ef3956"}, - {file = "wrapt-1.16.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:eb6e651000a19c96f452c85132811d25e9264d836951022d6e81df2fff38337d"}, - {file = "wrapt-1.16.0-cp311-cp311-win32.whl", hash = "sha256:66027d667efe95cc4fa945af59f92c5a02c6f5bb6012bff9e60542c74c75c362"}, - {file = "wrapt-1.16.0-cp311-cp311-win_amd64.whl", hash = "sha256:aefbc4cb0a54f91af643660a0a150ce2c090d3652cf4052a5397fb2de549cd89"}, - {file = "wrapt-1.16.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:5eb404d89131ec9b4f748fa5cfb5346802e5ee8836f57d516576e61f304f3b7b"}, - {file = "wrapt-1.16.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:9090c9e676d5236a6948330e83cb89969f433b1943a558968f659ead07cb3b36"}, - {file = "wrapt-1.16.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:94265b00870aa407bd0cbcfd536f17ecde43b94fb8d228560a1e9d3041462d73"}, - {file = "wrapt-1.16.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f2058f813d4f2b5e3a9eb2eb3faf8f1d99b81c3e51aeda4b168406443e8ba809"}, - {file = "wrapt-1.16.0-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:98b5e1f498a8ca1858a1cdbffb023bfd954da4e3fa2c0cb5853d40014557248b"}, - {file = "wrapt-1.16.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:14d7dc606219cdd7405133c713f2c218d4252f2a469003f8c46bb92d5d095d81"}, - {file = "wrapt-1.16.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:49aac49dc4782cb04f58986e81ea0b4768e4ff197b57324dcbd7699c5dfb40b9"}, - {file = "wrapt-1.16.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:418abb18146475c310d7a6dc71143d6f7adec5b004ac9ce08dc7a34e2babdc5c"}, - {file = "wrapt-1.16.0-cp312-cp312-win32.whl", hash = "sha256:685f568fa5e627e93f3b52fda002c7ed2fa1800b50ce51f6ed1d572d8ab3e7fc"}, - {file = "wrapt-1.16.0-cp312-cp312-win_amd64.whl", hash = "sha256:dcdba5c86e368442528f7060039eda390cc4091bfd1dca41e8046af7c910dda8"}, - {file = "wrapt-1.16.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:d462f28826f4657968ae51d2181a074dfe03c200d6131690b7d65d55b0f360f8"}, - {file = "wrapt-1.16.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a33a747400b94b6d6b8a165e4480264a64a78c8a4c734b62136062e9a248dd39"}, - {file = "wrapt-1.16.0-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b3646eefa23daeba62643a58aac816945cadc0afaf21800a1421eeba5f6cfb9c"}, - {file = "wrapt-1.16.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ebf019be5c09d400cf7b024aa52b1f3aeebeff51550d007e92c3c1c4afc2a40"}, - {file = "wrapt-1.16.0-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:0d2691979e93d06a95a26257adb7bfd0c93818e89b1406f5a28f36e0d8c1e1fc"}, - {file = "wrapt-1.16.0-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:1acd723ee2a8826f3d53910255643e33673e1d11db84ce5880675954183ec47e"}, - {file = "wrapt-1.16.0-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:bc57efac2da352a51cc4658878a68d2b1b67dbe9d33c36cb826ca449d80a8465"}, - {file = "wrapt-1.16.0-cp36-cp36m-win32.whl", hash = "sha256:da4813f751142436b075ed7aa012a8778aa43a99f7b36afe9b742d3ed8bdc95e"}, - {file = "wrapt-1.16.0-cp36-cp36m-win_amd64.whl", hash = "sha256:6f6eac2360f2d543cc875a0e5efd413b6cbd483cb3ad7ebf888884a6e0d2e966"}, - {file = "wrapt-1.16.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:a0ea261ce52b5952bf669684a251a66df239ec6d441ccb59ec7afa882265d593"}, - {file = "wrapt-1.16.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7bd2d7ff69a2cac767fbf7a2b206add2e9a210e57947dd7ce03e25d03d2de292"}, - {file = "wrapt-1.16.0-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9159485323798c8dc530a224bd3ffcf76659319ccc7bbd52e01e73bd0241a0c5"}, - {file = "wrapt-1.16.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a86373cf37cd7764f2201b76496aba58a52e76dedfaa698ef9e9688bfd9e41cf"}, - {file = "wrapt-1.16.0-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:73870c364c11f03ed072dda68ff7aea6d2a3a5c3fe250d917a429c7432e15228"}, - {file = "wrapt-1.16.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:b935ae30c6e7400022b50f8d359c03ed233d45b725cfdd299462f41ee5ffba6f"}, - {file = "wrapt-1.16.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:db98ad84a55eb09b3c32a96c576476777e87c520a34e2519d3e59c44710c002c"}, - {file = "wrapt-1.16.0-cp37-cp37m-win32.whl", hash = "sha256:9153ed35fc5e4fa3b2fe97bddaa7cbec0ed22412b85bcdaf54aeba92ea37428c"}, - {file = "wrapt-1.16.0-cp37-cp37m-win_amd64.whl", hash = "sha256:66dfbaa7cfa3eb707bbfcd46dab2bc6207b005cbc9caa2199bcbc81d95071a00"}, - {file = "wrapt-1.16.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1dd50a2696ff89f57bd8847647a1c363b687d3d796dc30d4dd4a9d1689a706f0"}, - {file = "wrapt-1.16.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:44a2754372e32ab315734c6c73b24351d06e77ffff6ae27d2ecf14cf3d229202"}, - {file = "wrapt-1.16.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8e9723528b9f787dc59168369e42ae1c3b0d3fadb2f1a71de14531d321ee05b0"}, - {file = "wrapt-1.16.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:dbed418ba5c3dce92619656802cc5355cb679e58d0d89b50f116e4a9d5a9603e"}, - {file = "wrapt-1.16.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:941988b89b4fd6b41c3f0bfb20e92bd23746579736b7343283297c4c8cbae68f"}, - {file = "wrapt-1.16.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:6a42cd0cfa8ffc1915aef79cb4284f6383d8a3e9dcca70c445dcfdd639d51267"}, - {file = "wrapt-1.16.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:1ca9b6085e4f866bd584fb135a041bfc32cab916e69f714a7d1d397f8c4891ca"}, - {file = "wrapt-1.16.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:d5e49454f19ef621089e204f862388d29e6e8d8b162efce05208913dde5b9ad6"}, - {file = "wrapt-1.16.0-cp38-cp38-win32.whl", hash = "sha256:c31f72b1b6624c9d863fc095da460802f43a7c6868c5dda140f51da24fd47d7b"}, - {file = "wrapt-1.16.0-cp38-cp38-win_amd64.whl", hash = "sha256:490b0ee15c1a55be9c1bd8609b8cecd60e325f0575fc98f50058eae366e01f41"}, - {file = "wrapt-1.16.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9b201ae332c3637a42f02d1045e1d0cccfdc41f1f2f801dafbaa7e9b4797bfc2"}, - {file = "wrapt-1.16.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:2076fad65c6736184e77d7d4729b63a6d1ae0b70da4868adeec40989858eb3fb"}, - {file = "wrapt-1.16.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c5cd603b575ebceca7da5a3a251e69561bec509e0b46e4993e1cac402b7247b8"}, - {file = "wrapt-1.16.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b47cfad9e9bbbed2339081f4e346c93ecd7ab504299403320bf85f7f85c7d46c"}, - {file = "wrapt-1.16.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f8212564d49c50eb4565e502814f694e240c55551a5f1bc841d4fcaabb0a9b8a"}, - {file = "wrapt-1.16.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:5f15814a33e42b04e3de432e573aa557f9f0f56458745c2074952f564c50e664"}, - {file = "wrapt-1.16.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:db2e408d983b0e61e238cf579c09ef7020560441906ca990fe8412153e3b291f"}, - {file = "wrapt-1.16.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:edfad1d29c73f9b863ebe7082ae9321374ccb10879eeabc84ba3b69f2579d537"}, - {file = "wrapt-1.16.0-cp39-cp39-win32.whl", hash = "sha256:ed867c42c268f876097248e05b6117a65bcd1e63b779e916fe2e33cd6fd0d3c3"}, - {file = "wrapt-1.16.0-cp39-cp39-win_amd64.whl", hash = "sha256:eb1b046be06b0fce7249f1d025cd359b4b80fc1c3e24ad9eca33e0dcdb2e4a35"}, - {file = "wrapt-1.16.0-py3-none-any.whl", hash = "sha256:6906c4100a8fcbf2fa735f6059214bb13b97f75b1a61777fcf6432121ef12ef1"}, - {file = "wrapt-1.16.0.tar.gz", hash = "sha256:5f370f952971e7d17c7d1ead40e49f32345a7f7a5373571ef44d800d06b1899d"}, + {file = "tzdata-2025.2-py2.py3-none-any.whl", hash = "sha256:1a403fada01ff9221ca8044d701868fa132215d84beb92242d9acd2147f667a8"}, + {file = "tzdata-2025.2.tar.gz", hash = "sha256:b60a638fcc0daffadf82fe0f57e53d06bdec2f36c4df66280ae79bce6bd6f2b9"}, ] [metadata] -lock-version = "2.0" -python-versions = "~3.11" -content-hash = "6bf8024dc21c85ad7da388c4ca88361e5d79e383d41e195727b56c54985c4b5e" +lock-version = "2.1" +python-versions = ">=3.13" +content-hash = "a81af164cacf2a93ae2e4a4b16d994bd64caf6c6ee15296cfe70b65d00338fcf" diff --git a/pyproject.toml b/pyproject.toml index 87589fb..876ab97 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -6,17 +6,76 @@ authors = ["ThoughtWorks "] license = "Apache-License-2.0" [tool.poetry.dependencies] -numpy = "^1.20.2" pandas = "^2.0.0" -pyarrow = "^12.0.0" -pyspark = "3.5.1" -python = "~3.11" +pyarrow = "^21.0.0" +pyspark = "~4.0.0" +python = ">=3.13" -[tool.poetry.dev-dependencies] -pylint = "^2.8.2" -pytest = "^6.2.4" -mypy = "^0.990" +[tool.poetry.group.dev.dependencies] +pytest = "^8.2.4" +mypy = "^1.18.0" +ruff = "^0.14.0" [build-system] requires = ["poetry-core>=1.0.0"] build-backend = "poetry.core.masonry.api" + + +[tool.ruff] +include = ["data_transformations/**", "jobs/**", "tests/**"] +line-length = 88 +indent-width = 4 +target-version = "py313" + +[tool.ruff.lint] +select = [ + "E", # pycodestyle errors + "F", # pycodestyle errors + "W", # pycodestyle warnings + "B", # flake8-bugbear + "C4", # flake8-comprehensions + "I", # isort + "N", # pep8-naming + "S", # flake8-bandit + "T20", # flake8-print + "SIM", # flake8-simplify + "ARG", # flake8-unused-arguments + "PTH", # flake8-use-pathlib + "ERA", # eradicate + "PL", # pylint + "RUF", # ruff-specific rules +] + +ignore = [ + "E501", # line too long, handled by black + "B008", # do not perform function calls in argument defaults + "C901", # too complex + "S101", # use of assert detected + "PLR0913", # too many arguments + "PLR0912", # too many branches + "PLR0915", # too many statements + "PLR2004", # magic value used in comparison + "T201", # print found +] + +# Allow unused variables when underscore-prefixed. +dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$" + +[tool.ruff.lint.isort] +known-first-party = ["data_transformations"] + +[tool.ruff.lint.mccabe] +max-complexity = 10 + +[tool.ruff.lint.pylint] +max-args = 5 +max-branches = 12 +max-returns = 6 +max-statements = 50 + +[tool.ruff.format] +# black aligned +quote-style = "double" +indent-style = "space" +skip-magic-trailing-comma = false +line-ending = "auto" \ No newline at end of file diff --git a/tests/integration/test_distance_transformer.py b/tests/integration/test_distance_transformer.py index 323c696..4d684de 100644 --- a/tests/integration/test_distance_transformer.py +++ b/tests/integration/test_distance_transformer.py @@ -4,7 +4,7 @@ import pytest from pyspark.sql import SparkSession -from pyspark.sql.types import StructField, DoubleType +from pyspark.sql.types import DoubleType, StructField from data_transformations.citibike import distance_transformer @@ -42,7 +42,7 @@ 27937, "Subscriber", 1984, - 2 + 2, ], [ 1496, @@ -59,7 +59,7 @@ 15933, "Customer", 1971, - 1 + 1, ], [ 1067, @@ -76,14 +76,15 @@ 27084, "Subscriber", 1990, - 2 - ] + 2, + ], ] def test_should_maintain_all_data_it_reads(spark_session: SparkSession) -> None: given_ingest_folder, given_transform_folder = __create_ingest_and_transform_folders( - spark_session) + spark_session + ) given_dataframe = spark_session.read.parquet(given_ingest_folder) distance_transformer.run(spark_session, given_ingest_folder, given_transform_folder) @@ -98,9 +99,12 @@ def test_should_maintain_all_data_it_reads(spark_session: SparkSession) -> None: @pytest.mark.skip -def test_should_add_distance_column_with_calculated_distance(spark_session: SparkSession) -> None: +def test_should_add_distance_column_with_calculated_distance( + spark_session: SparkSession, +) -> None: given_ingest_folder, given_transform_folder = __create_ingest_and_transform_folders( - spark_session) + spark_session + ) distance_transformer.run(spark_session, given_ingest_folder, given_transform_folder) actual_dataframe = spark_session.read.parquet(given_transform_folder) @@ -110,10 +114,10 @@ def test_should_add_distance_column_with_calculated_distance(spark_session: Spar SAMPLE_DATA[1] + [0.92], SAMPLE_DATA[2] + [1.99], ], - BASE_COLUMNS + ['distance'] + [*BASE_COLUMNS, "distance"], ) - expected_distance_schema = StructField('distance', DoubleType(), nullable=True) - actual_distance_schema = actual_dataframe.schema['distance'] + expected_distance_schema = StructField("distance", DoubleType(), nullable=True) + actual_distance_schema = actual_dataframe.schema["distance"] assert expected_distance_schema == actual_distance_schema assert expected_dataframe.collect() == actual_dataframe.collect() @@ -124,5 +128,5 @@ def __create_ingest_and_transform_folders(spark: SparkSession) -> Tuple[str, str ingest_folder = "%s%singest" % (base_path, os.path.sep) transform_folder = "%s%stransform" % (base_path, os.path.sep) ingest_dataframe = spark.createDataFrame(SAMPLE_DATA, BASE_COLUMNS) - ingest_dataframe.write.parquet(ingest_folder, mode='overwrite') + ingest_dataframe.write.parquet(ingest_folder, mode="overwrite") return ingest_folder, transform_folder diff --git a/tests/integration/test_ingest.py b/tests/integration/test_ingest.py index db82a29..0acdbdb 100644 --- a/tests/integration/test_ingest.py +++ b/tests/integration/test_ingest.py @@ -1,7 +1,8 @@ import csv import os import tempfile -from typing import Tuple, List +from pathlib import Path +from typing import List, Tuple from pyspark.sql import SparkSession @@ -9,23 +10,22 @@ def test_should_sanitize_column_names(spark_session: SparkSession) -> None: - given_ingest_folder, given_transform_folder = __create_ingest_and_transform_folders() - input_csv_path = given_ingest_folder + 'input.csv' + given_ingest_folder, given_transform_folder = ( + __create_ingest_and_transform_folders() + ) + input_csv_path = given_ingest_folder + "input.csv" csv_content = [ - ['first_field', 'field with space', ' fieldWithOuterSpaces '], - ['3', '4', '1'], - ['1', '5', '2'], + ["first_field", "field with space", " fieldWithOuterSpaces "], + ["3", "4", "1"], + ["1", "5", "2"], ] __write_csv_file(input_csv_path, csv_content) ingest.run(spark_session, input_csv_path, given_transform_folder) actual = spark_session.read.parquet(given_transform_folder) expected = spark_session.createDataFrame( - [ - ['3', '4', '1'], - ['1', '5', '2'] - ], - ['first_field', 'field_with_space', '_fieldWithOuterSpaces_'] + [["3", "4", "1"], ["1", "5", "2"]], + ["first_field", "field_with_space", "_fieldWithOuterSpaces_"], ) assert expected.collect() == actual.collect() @@ -39,7 +39,6 @@ def __create_ingest_and_transform_folders() -> Tuple[str, str]: def __write_csv_file(file_path: str, content: List[List[str]]) -> None: - with open(file_path, 'w') as csv_file: + with Path(file_path).open(mode="w") as csv_file: input_csv_writer = csv.writer(csv_file) input_csv_writer.writerows(content) - csv_file.close() diff --git a/tests/integration/test_validate_spark_environment.py b/tests/integration/test_validate_spark_environment.py index e53c2b0..62e02b2 100644 --- a/tests/integration/test_validate_spark_environment.py +++ b/tests/integration/test_validate_spark_environment.py @@ -7,28 +7,32 @@ def test_java_home_is_set() -> None: java_home = os.environ.get("JAVA_HOME") - assert java_home is not None, \ + assert java_home is not None, ( "Environment variable 'JAVA_HOME' is not set but is required by pySpark to work." + ) -def test_java_version_minimum_requirement(expected_major_version: int = 11) -> None: +def test_java_version_minimum_requirement(expected_major_version: int = 17) -> None: version_line = __extract_version_line(__java_version_output()) major_version = __parse_major_version(version_line) assert major_version >= expected_major_version, ( f"Major version {major_version} is not recent enough, " - f"we need at least version {expected_major_version}.") + f"we need at least version {expected_major_version}." + ) def __java_version_output() -> str: - java_version = subprocess.check_output(['java', '-version'], stderr=subprocess.STDOUT).decode( - "utf-8") + java_version = subprocess.check_output( # noqa: S603 + [f"{os.environ['JAVA_HOME']}/bin/java", "-version"], stderr=subprocess.STDOUT + ).decode("utf-8") print(f"\n`java -version` returned\n{java_version}") return java_version def __extract_version_line(java_version_output: str) -> str: - version_line = next((line for line in java_version_output.splitlines() if "version" in line), - None) + version_line = next( + (line for line in java_version_output.splitlines() if "version" in line), None + ) if not version_line: pytest.fail("Couldn't find version information in `java -version` output.") return version_line diff --git a/tests/integration/test_word_count.py b/tests/integration/test_word_count.py index 2e212f6..5a895be 100644 --- a/tests/integration/test_word_count.py +++ b/tests/integration/test_word_count.py @@ -1,6 +1,7 @@ import os import tempfile -from typing import Tuple, List +from pathlib import Path +from typing import List, Tuple import pytest from pyspark.sql import SparkSession @@ -12,7 +13,7 @@ def _get_file_paths(input_file_lines: List[str]) -> Tuple[str, str]: base_path = tempfile.mkdtemp() input_text_path = "%s%sinput.txt" % (base_path, os.path.sep) - with open(input_text_path, 'w') as input_file: + with Path(input_text_path).open(mode="w") as input_file: input_file.writelines(input_file_lines) output_path = "%s%soutput" % (base_path, os.path.sep) @@ -23,7 +24,7 @@ def _get_file_paths(input_file_lines: List[str]) -> Tuple[str, str]: def test_should_tokenize_words_and_count_them(spark_session: SparkSession) -> None: lines = [ "In my younger and more vulnerable years my father gave me some advice that I've been " - "turning over in my mind ever since. \"Whenever you feel like criticising any one,\"" + 'turning over in my mind ever since. "Whenever you feel like criticising any one,"' " he told me, \"just remember that all the people in this world haven't had the advantages" " that you've had.\"", "Most of the big shore places were closed now and there were hardly any lights except the " @@ -43,7 +44,7 @@ def test_should_tokenize_words_and_count_them(spark_session: SparkSession) -> No "Gatsby believed in the green light, the orgastic future that year by year recedes before " "us. It eluded us then, but that's no matter--tomorrow we will run faster, stretch out our " "arms farther.... And one fine morning----", - "So we beat on, boats against the current, borne back ceaselessly into the past. " + "So we beat on, boats against the current, borne back ceaselessly into the past. ", ] input_file_path, output_path = _get_file_paths(lines) diff --git a/tests/unit/test_ingest.py b/tests/unit/test_ingest.py index b9c98a2..fae6cf9 100644 --- a/tests/unit/test_ingest.py +++ b/tests/unit/test_ingest.py @@ -2,7 +2,7 @@ def test_should_sanitize_nothing() -> None: - no_whitespace_columns = ['foo'] + no_whitespace_columns = ["foo"] actual = ingest.sanitize_columns(no_whitespace_columns) expected = no_whitespace_columns @@ -11,18 +11,18 @@ def test_should_sanitize_nothing() -> None: def test_should_sanitize_whitespace_outside() -> None: - no_whitespace_columns = [' foo '] + no_whitespace_columns = [" foo "] actual = ingest.sanitize_columns(no_whitespace_columns) - expected = ['_foo_'] + expected = ["_foo_"] assert expected == actual def test_should_sanitize_whitespace_in_between() -> None: - no_whitespace_columns = ['foo bar'] + no_whitespace_columns = ["foo bar"] actual = ingest.sanitize_columns(no_whitespace_columns) - expected = ['foo_bar'] + expected = ["foo_bar"] assert expected == actual