From f2958ed8a069a8c16682f4f645b13a8bbe0e9015 Mon Sep 17 00:00:00 2001 From: Ken Brewer Date: Sun, 24 Mar 2024 23:26:37 +0000 Subject: [PATCH 1/2] feat(core): add models and class for pycytominer core --- poetry.lock | 260 +++++++++++++++++++++++++++++++++- pycytominer/core/__init__.py | 0 pycytominer/core/operation.py | 54 +++++++ pycytominer/core/profiles.py | 80 +++++++++++ pyproject.toml | 3 + 5 files changed, 391 insertions(+), 6 deletions(-) create mode 100644 pycytominer/core/__init__.py create mode 100644 pycytominer/core/operation.py create mode 100644 pycytominer/core/profiles.py diff --git a/poetry.lock b/poetry.lock index 28501460..67098f14 100644 --- a/poetry.lock +++ b/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand. +# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand. [[package]] name = "agate" @@ -232,6 +232,20 @@ files = [ {file = "alabaster-0.7.13.tar.gz", hash = "sha256:a27a4a084d5e690e16e01e03ad2b2e552c61a65469419b907243193de1a84ae2"}, ] +[[package]] +name = "annotated-types" +version = "0.6.0" +description = "Reusable constraint types to use with typing.Annotated" +optional = false +python-versions = ">=3.8" +files = [ + {file = "annotated_types-0.6.0-py3-none-any.whl", hash = "sha256:0641064de18ba7a25dee8f96403ebc39113d0cb953a01429249d5c7564666a43"}, + {file = "annotated_types-0.6.0.tar.gz", hash = "sha256:563339e807e53ffd9c267e99fc6d9ea23eb8443c08f112651963e24e22f84a5d"}, +] + +[package.dependencies] +typing-extensions = {version = ">=4.0.0", markers = "python_version < \"3.9\""} + [[package]] name = "anyascii" version = "0.3.2" @@ -1957,6 +1971,28 @@ files = [ {file = "multidict-6.0.5.tar.gz", hash = "sha256:f7e301075edaf50500f0b341543c41194d8df3ae5caf4702f2095f3ca73dd8da"}, ] +[[package]] +name = "multimethod" +version = "1.10" +description = "Multiple argument dispatching." +optional = false +python-versions = ">=3.8" +files = [ + {file = "multimethod-1.10-py3-none-any.whl", hash = "sha256:afd84da9c3d0445c84f827e4d63ad42d17c6d29b122427c6dee9032ac2d2a0d4"}, + {file = "multimethod-1.10.tar.gz", hash = "sha256:daa45af3fe257f73abb69673fd54ddeaf31df0eb7363ad6e1251b7c9b192d8c5"}, +] + +[[package]] +name = "mypy-extensions" +version = "1.0.0" +description = "Type system extensions for programs checked with the mypy type checker." +optional = false +python-versions = ">=3.5" +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"}, +] + [[package]] name = "nbclient" version = "0.9.0" @@ -2213,6 +2249,41 @@ sql-other = ["SQLAlchemy (>=1.4.16)"] test = ["hypothesis (>=6.34.2)", "pytest (>=7.3.2)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)"] xml = ["lxml (>=4.6.3)"] +[[package]] +name = "pandera" +version = "0.18.3" +description = "A light-weight and flexible data validation and testing tool for statistical data objects." +optional = false +python-versions = ">=3.7" +files = [ + {file = "pandera-0.18.3-py3-none-any.whl", hash = "sha256:376faf746db57517f7fd85f234fa193e34266e7bcd1781e5c5912befbc180b98"}, + {file = "pandera-0.18.3.tar.gz", hash = "sha256:47dd2e10ed7d2a2bc9cfd154b76b8bcd065a9bf1413d00de902d31c7afeec014"}, +] + +[package.dependencies] +multimethod = "<=1.10.0" +numpy = ">=1.19.0" +packaging = ">=20.0" +pandas = ">=1.2.0" +pydantic = "*" +typeguard = ">=3.0.2" +typing-inspect = ">=0.6.0" +wrapt = "*" + +[package.extras] +all = ["black", "dask", "fastapi", "frictionless (<=4.40.8)", "geopandas", "hypothesis (>=6.92.7)", "modin", "pandas-stubs", "pyspark (>=3.2.0)", "pyyaml (>=5.1)", "ray", "scipy", "shapely"] +dask = ["dask"] +fastapi = ["fastapi"] +geopandas = ["geopandas", "shapely"] +hypotheses = ["scipy"] +io = ["black", "frictionless (<=4.40.8)", "pyyaml (>=5.1)"] +modin = ["dask", "modin", "ray"] +modin-dask = ["dask", "modin"] +modin-ray = ["modin", "ray"] +mypy = ["pandas-stubs"] +pyspark = ["pyspark (>=3.2.0)"] +strategies = ["hypothesis (>=6.92.7)"] + [[package]] name = "pandocfilters" version = "1.5.1" @@ -2443,6 +2514,135 @@ files = [ {file = "pycparser-2.21.tar.gz", hash = "sha256:e644fdec12f7872f86c58ff790da456218b10f863970249516d60a5eaca77206"}, ] +[[package]] +name = "pydantic" +version = "2.6.4" +description = "Data validation using Python type hints" +optional = false +python-versions = ">=3.8" +files = [ + {file = "pydantic-2.6.4-py3-none-any.whl", hash = "sha256:cc46fce86607580867bdc3361ad462bab9c222ef042d3da86f2fb333e1d916c5"}, + {file = "pydantic-2.6.4.tar.gz", hash = "sha256:b1704e0847db01817624a6b86766967f552dd9dbf3afba4004409f908dcc84e6"}, +] + +[package.dependencies] +annotated-types = ">=0.4.0" +pydantic-core = "2.16.3" +typing-extensions = ">=4.6.1" + +[package.extras] +email = ["email-validator (>=2.0.0)"] + +[[package]] +name = "pydantic-core" +version = "2.16.3" +description = "" +optional = false +python-versions = ">=3.8" +files = [ + {file = "pydantic_core-2.16.3-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:75b81e678d1c1ede0785c7f46690621e4c6e63ccd9192af1f0bd9d504bbb6bf4"}, + {file = "pydantic_core-2.16.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9c865a7ee6f93783bd5d781af5a4c43dadc37053a5b42f7d18dc019f8c9d2bd1"}, + {file = "pydantic_core-2.16.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:162e498303d2b1c036b957a1278fa0899d02b2842f1ff901b6395104c5554a45"}, + {file = "pydantic_core-2.16.3-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2f583bd01bbfbff4eaee0868e6fc607efdfcc2b03c1c766b06a707abbc856187"}, + {file = "pydantic_core-2.16.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b926dd38db1519ed3043a4de50214e0d600d404099c3392f098a7f9d75029ff8"}, + {file = "pydantic_core-2.16.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:716b542728d4c742353448765aa7cdaa519a7b82f9564130e2b3f6766018c9ec"}, + {file = "pydantic_core-2.16.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fc4ad7f7ee1a13d9cb49d8198cd7d7e3aa93e425f371a68235f784e99741561f"}, + {file = "pydantic_core-2.16.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:bd87f48924f360e5d1c5f770d6155ce0e7d83f7b4e10c2f9ec001c73cf475c99"}, + {file = "pydantic_core-2.16.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:0df446663464884297c793874573549229f9eca73b59360878f382a0fc085979"}, + {file = "pydantic_core-2.16.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:4df8a199d9f6afc5ae9a65f8f95ee52cae389a8c6b20163762bde0426275b7db"}, + {file = "pydantic_core-2.16.3-cp310-none-win32.whl", hash = "sha256:456855f57b413f077dff513a5a28ed838dbbb15082ba00f80750377eed23d132"}, + {file = "pydantic_core-2.16.3-cp310-none-win_amd64.whl", hash = "sha256:732da3243e1b8d3eab8c6ae23ae6a58548849d2e4a4e03a1924c8ddf71a387cb"}, + {file = "pydantic_core-2.16.3-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:519ae0312616026bf4cedc0fe459e982734f3ca82ee8c7246c19b650b60a5ee4"}, + {file = "pydantic_core-2.16.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:b3992a322a5617ded0a9f23fd06dbc1e4bd7cf39bc4ccf344b10f80af58beacd"}, + {file = "pydantic_core-2.16.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8d62da299c6ecb04df729e4b5c52dc0d53f4f8430b4492b93aa8de1f541c4aac"}, + {file = "pydantic_core-2.16.3-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2acca2be4bb2f2147ada8cac612f8a98fc09f41c89f87add7256ad27332c2fda"}, + {file = "pydantic_core-2.16.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1b662180108c55dfbf1280d865b2d116633d436cfc0bba82323554873967b340"}, + {file = "pydantic_core-2.16.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e7c6ed0dc9d8e65f24f5824291550139fe6f37fac03788d4580da0d33bc00c97"}, + {file = "pydantic_core-2.16.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a6b1bb0827f56654b4437955555dc3aeeebeddc47c2d7ed575477f082622c49e"}, + {file = "pydantic_core-2.16.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e56f8186d6210ac7ece503193ec84104da7ceb98f68ce18c07282fcc2452e76f"}, + {file = "pydantic_core-2.16.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:936e5db01dd49476fa8f4383c259b8b1303d5dd5fb34c97de194560698cc2c5e"}, + {file = "pydantic_core-2.16.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:33809aebac276089b78db106ee692bdc9044710e26f24a9a2eaa35a0f9fa70ba"}, + {file = "pydantic_core-2.16.3-cp311-none-win32.whl", hash = "sha256:ded1c35f15c9dea16ead9bffcde9bb5c7c031bff076355dc58dcb1cb436c4721"}, + {file = "pydantic_core-2.16.3-cp311-none-win_amd64.whl", hash = "sha256:d89ca19cdd0dd5f31606a9329e309d4fcbb3df860960acec32630297d61820df"}, + {file = "pydantic_core-2.16.3-cp311-none-win_arm64.whl", hash = "sha256:6162f8d2dc27ba21027f261e4fa26f8bcb3cf9784b7f9499466a311ac284b5b9"}, + {file = "pydantic_core-2.16.3-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:0f56ae86b60ea987ae8bcd6654a887238fd53d1384f9b222ac457070b7ac4cff"}, + {file = "pydantic_core-2.16.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:c9bd22a2a639e26171068f8ebb5400ce2c1bc7d17959f60a3b753ae13c632975"}, + {file = "pydantic_core-2.16.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4204e773b4b408062960e65468d5346bdfe139247ee5f1ca2a378983e11388a2"}, + {file = "pydantic_core-2.16.3-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f651dd19363c632f4abe3480a7c87a9773be27cfe1341aef06e8759599454120"}, + {file = "pydantic_core-2.16.3-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:aaf09e615a0bf98d406657e0008e4a8701b11481840be7d31755dc9f97c44053"}, + {file = "pydantic_core-2.16.3-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8e47755d8152c1ab5b55928ab422a76e2e7b22b5ed8e90a7d584268dd49e9c6b"}, + {file = "pydantic_core-2.16.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:500960cb3a0543a724a81ba859da816e8cf01b0e6aaeedf2c3775d12ee49cade"}, + {file = "pydantic_core-2.16.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:cf6204fe865da605285c34cf1172879d0314ff267b1c35ff59de7154f35fdc2e"}, + {file = "pydantic_core-2.16.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:d33dd21f572545649f90c38c227cc8631268ba25c460b5569abebdd0ec5974ca"}, + {file = "pydantic_core-2.16.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:49d5d58abd4b83fb8ce763be7794d09b2f50f10aa65c0f0c1696c677edeb7cbf"}, + {file = "pydantic_core-2.16.3-cp312-none-win32.whl", hash = "sha256:f53aace168a2a10582e570b7736cc5bef12cae9cf21775e3eafac597e8551fbe"}, + {file = "pydantic_core-2.16.3-cp312-none-win_amd64.whl", hash = "sha256:0d32576b1de5a30d9a97f300cc6a3f4694c428d956adbc7e6e2f9cad279e45ed"}, + {file = "pydantic_core-2.16.3-cp312-none-win_arm64.whl", hash = "sha256:ec08be75bb268473677edb83ba71e7e74b43c008e4a7b1907c6d57e940bf34b6"}, + {file = "pydantic_core-2.16.3-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:b1f6f5938d63c6139860f044e2538baeee6f0b251a1816e7adb6cbce106a1f01"}, + {file = "pydantic_core-2.16.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:2a1ef6a36fdbf71538142ed604ad19b82f67b05749512e47f247a6ddd06afdc7"}, + {file = "pydantic_core-2.16.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:704d35ecc7e9c31d48926150afada60401c55efa3b46cd1ded5a01bdffaf1d48"}, + {file = "pydantic_core-2.16.3-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d937653a696465677ed583124b94a4b2d79f5e30b2c46115a68e482c6a591c8a"}, + {file = "pydantic_core-2.16.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c9803edf8e29bd825f43481f19c37f50d2b01899448273b3a7758441b512acf8"}, + {file = "pydantic_core-2.16.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:72282ad4892a9fb2da25defeac8c2e84352c108705c972db82ab121d15f14e6d"}, + {file = "pydantic_core-2.16.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7f752826b5b8361193df55afcdf8ca6a57d0232653494ba473630a83ba50d8c9"}, + {file = "pydantic_core-2.16.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:4384a8f68ddb31a0b0c3deae88765f5868a1b9148939c3f4121233314ad5532c"}, + {file = "pydantic_core-2.16.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:a4b2bf78342c40b3dc830880106f54328928ff03e357935ad26c7128bbd66ce8"}, + {file = "pydantic_core-2.16.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:13dcc4802961b5f843a9385fc821a0b0135e8c07fc3d9949fd49627c1a5e6ae5"}, + {file = "pydantic_core-2.16.3-cp38-none-win32.whl", hash = "sha256:e3e70c94a0c3841e6aa831edab1619ad5c511199be94d0c11ba75fe06efe107a"}, + {file = "pydantic_core-2.16.3-cp38-none-win_amd64.whl", hash = "sha256:ecdf6bf5f578615f2e985a5e1f6572e23aa632c4bd1dc67f8f406d445ac115ed"}, + {file = "pydantic_core-2.16.3-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:bda1ee3e08252b8d41fa5537413ffdddd58fa73107171a126d3b9ff001b9b820"}, + {file = "pydantic_core-2.16.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:21b888c973e4f26b7a96491c0965a8a312e13be108022ee510248fe379a5fa23"}, + {file = "pydantic_core-2.16.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:be0ec334369316fa73448cc8c982c01e5d2a81c95969d58b8f6e272884df0074"}, + {file = "pydantic_core-2.16.3-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:b5b6079cc452a7c53dd378c6f881ac528246b3ac9aae0f8eef98498a75657805"}, + {file = "pydantic_core-2.16.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7ee8d5f878dccb6d499ba4d30d757111847b6849ae07acdd1205fffa1fc1253c"}, + {file = "pydantic_core-2.16.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7233d65d9d651242a68801159763d09e9ec96e8a158dbf118dc090cd77a104c9"}, + {file = "pydantic_core-2.16.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c6119dc90483a5cb50a1306adb8d52c66e447da88ea44f323e0ae1a5fcb14256"}, + {file = "pydantic_core-2.16.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:578114bc803a4c1ff9946d977c221e4376620a46cf78da267d946397dc9514a8"}, + {file = "pydantic_core-2.16.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:d8f99b147ff3fcf6b3cc60cb0c39ea443884d5559a30b1481e92495f2310ff2b"}, + {file = "pydantic_core-2.16.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:4ac6b4ce1e7283d715c4b729d8f9dab9627586dafce81d9eaa009dd7f25dd972"}, + {file = "pydantic_core-2.16.3-cp39-none-win32.whl", hash = "sha256:e7774b570e61cb998490c5235740d475413a1f6de823169b4cf94e2fe9e9f6b2"}, + {file = "pydantic_core-2.16.3-cp39-none-win_amd64.whl", hash = "sha256:9091632a25b8b87b9a605ec0e61f241c456e9248bfdcf7abdf344fdb169c81cf"}, + {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:36fa178aacbc277bc6b62a2c3da95226520da4f4e9e206fdf076484363895d2c"}, + {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:dcca5d2bf65c6fb591fff92da03f94cd4f315972f97c21975398bd4bd046854a"}, + {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2a72fb9963cba4cd5793854fd12f4cfee731e86df140f59ff52a49b3552db241"}, + {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b60cc1a081f80a2105a59385b92d82278b15d80ebb3adb200542ae165cd7d183"}, + {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:cbcc558401de90a746d02ef330c528f2e668c83350f045833543cd57ecead1ad"}, + {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:fee427241c2d9fb7192b658190f9f5fd6dfe41e02f3c1489d2ec1e6a5ab1e04a"}, + {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:f4cb85f693044e0f71f394ff76c98ddc1bc0953e48c061725e540396d5c8a2e1"}, + {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:b29eeb887aa931c2fcef5aa515d9d176d25006794610c264ddc114c053bf96fe"}, + {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:a425479ee40ff021f8216c9d07a6a3b54b31c8267c6e17aa88b70d7ebd0e5e5b"}, + {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:5c5cbc703168d1b7a838668998308018a2718c2130595e8e190220238addc96f"}, + {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:99b6add4c0b39a513d323d3b93bc173dac663c27b99860dd5bf491b240d26137"}, + {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75f76ee558751746d6a38f89d60b6228fa174e5172d143886af0f85aa306fd89"}, + {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:00ee1c97b5364b84cb0bd82e9bbf645d5e2871fb8c58059d158412fee2d33d8a"}, + {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:287073c66748f624be4cef893ef9174e3eb88fe0b8a78dc22e88eca4bc357ca6"}, + {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:ed25e1835c00a332cb10c683cd39da96a719ab1dfc08427d476bce41b92531fc"}, + {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:86b3d0033580bd6bbe07590152007275bd7af95f98eaa5bd36f3da219dcd93da"}, + {file = "pydantic_core-2.16.3.tar.gz", hash = "sha256:1cac689f80a3abab2d3c0048b29eea5751114054f032a941a32de4c852c59cad"}, +] + +[package.dependencies] +typing-extensions = ">=4.6.0,<4.7.0 || >4.7.0" + +[[package]] +name = "pydantic-settings" +version = "2.2.1" +description = "Settings management using Pydantic" +optional = false +python-versions = ">=3.8" +files = [ + {file = "pydantic_settings-2.2.1-py3-none-any.whl", hash = "sha256:0235391d26db4d2190cb9b31051c4b46882d28a51533f97440867f012d4da091"}, + {file = "pydantic_settings-2.2.1.tar.gz", hash = "sha256:00b9f6a5e95553590434c0fa01ead0b216c3e10bc54ae02e37f359948643c5ed"}, +] + +[package.dependencies] +pydantic = ">=2.3.0" +python-dotenv = ">=0.21.0" + +[package.extras] +toml = ["tomli (>=2.0.1)"] +yaml = ["pyyaml (>=6.0.1)"] + [[package]] name = "pygments" version = "2.17.2" @@ -2512,6 +2712,20 @@ files = [ [package.dependencies] six = ">=1.5" +[[package]] +name = "python-dotenv" +version = "1.0.1" +description = "Read key-value pairs from a .env file and set them as environment variables" +optional = false +python-versions = ">=3.8" +files = [ + {file = "python-dotenv-1.0.1.tar.gz", hash = "sha256:e324ee90a023d808f1959c46bcbc04446a10ced277783dc6ee09987c37ec10ca"}, + {file = "python_dotenv-1.0.1-py3-none-any.whl", hash = "sha256:f7b63ef50f1b690dddf550d03497b66d609393b40b564ed0d674909a68ebf16a"}, +] + +[package.extras] +cli = ["click (>=5.0)"] + [[package]] name = "python-slugify" version = "8.0.4" @@ -3519,17 +3733,51 @@ files = [ docs = ["myst-parser", "pydata-sphinx-theme", "sphinx"] test = ["argcomplete (>=3.0.3)", "mypy (>=1.7.0)", "pre-commit", "pytest (>=7.0,<7.5)", "pytest-mock", "pytest-mypy-testing"] +[[package]] +name = "typeguard" +version = "4.2.1" +description = "Run-time type checker for Python" +optional = false +python-versions = ">=3.8" +files = [ + {file = "typeguard-4.2.1-py3-none-any.whl", hash = "sha256:7da3bd46e61f03e0852f8d251dcbdc2a336aa495d7daff01e092b55327796eb8"}, + {file = "typeguard-4.2.1.tar.gz", hash = "sha256:c556a1b95948230510070ca53fa0341fb0964611bd05d598d87fb52115d65fee"}, +] + +[package.dependencies] +importlib-metadata = {version = ">=3.6", markers = "python_version < \"3.10\""} +typing-extensions = {version = ">=4.10.0", markers = "python_version < \"3.13\""} + +[package.extras] +doc = ["Sphinx (>=7)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)"] +test = ["coverage[toml] (>=7)", "mypy (>=1.2.0)", "pytest (>=7)"] + [[package]] name = "typing-extensions" -version = "4.9.0" +version = "4.10.0" description = "Backported and Experimental Type Hints for Python 3.8+" optional = false python-versions = ">=3.8" files = [ - {file = "typing_extensions-4.9.0-py3-none-any.whl", hash = "sha256:af72aea155e91adfc61c3ae9e0e342dbc0cba726d6cba4b6c72c1f34e47291cd"}, - {file = "typing_extensions-4.9.0.tar.gz", hash = "sha256:23478f88c37f27d76ac8aee6c905017a143b0b1b886c3c9f66bc2fd94f9f5783"}, + {file = "typing_extensions-4.10.0-py3-none-any.whl", hash = "sha256:69b1a937c3a517342112fb4c6df7e72fc39a38e7891a5730ed4985b5214b5475"}, + {file = "typing_extensions-4.10.0.tar.gz", hash = "sha256:b0abd7c89e8fb96f98db18d86106ff1d90ab692004eb746cf6eda2682f91b3cb"}, ] +[[package]] +name = "typing-inspect" +version = "0.9.0" +description = "Runtime inspection utilities for typing module." +optional = false +python-versions = "*" +files = [ + {file = "typing_inspect-0.9.0-py3-none-any.whl", hash = "sha256:9ee6fc59062311ef8547596ab6b955e1b8aa46242d854bfc78f4f6b0eff35f9f"}, + {file = "typing_inspect-0.9.0.tar.gz", hash = "sha256:b23fc42ff6f6ef6954e4852c1fb512cdd18dbea03134f91f856a95ccc9461f78"}, +] + +[package.dependencies] +mypy-extensions = ">=0.3.0" +typing-extensions = ">=3.7.4" + [[package]] name = "tzdata" version = "2024.1" @@ -3711,7 +3959,7 @@ tests = ["PasteDeploy", "WSGIProxy2", "coverage", "pyquery", "pytest", "pytest-c name = "wrapt" version = "1.16.0" description = "Module for decorators, wrappers and monkey patching." -optional = true +optional = false python-versions = ">=3.6" files = [ {file = "wrapt-1.16.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ffa565331890b90056c01db69c0fe634a776f8019c143a5ae265f9c6bc4bd6d4"}, @@ -3927,4 +4175,4 @@ collate = ["cytominer-database"] [metadata] lock-version = "2.0" python-versions = ">=3.8,<4.0" -content-hash = "1fe82d749bc8512a4d80ef67538bd7ba986cb99d86d4d733e5563fb0812c76c5" +content-hash = "a119005411e42df0edc4741ccbc484dae0769ef64cbd5453a5355de361844492" diff --git a/pycytominer/core/__init__.py b/pycytominer/core/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/pycytominer/core/operation.py b/pycytominer/core/operation.py new file mode 100644 index 00000000..56ecc0af --- /dev/null +++ b/pycytominer/core/operation.py @@ -0,0 +1,54 @@ +"""This module contains the Operation class which is a base class for other file/dataframe operations in pycytominer.""" + +from typing import TypeVar + +import pandas as pd +from pandera.typing import DataFrame +from pydantic import BaseModel, Field, FilePath, NewPath + +from .profiles import Profiles + +Operation = TypeVar("Operation", bound="Operation") +DataframeOperation = TypeVar("DataframeOperation", bound="DataframeOperation") +FileOperation = TypeVar("FileOperation", bound="FileOperation") + + +class Operation(BaseModel): + """Base class for other file/dataframe operations in pycytominer.""" + + profiles: Profiles = Field( + ..., title="Profiles", description="Profiles data model." + ) + + +class DataframeOperation(Operation): + """Base class for dataframe operations in pycytominer.""" + + df: DataFrame = Field( + ..., + title="Dataframe", + description="A dataframe containing profiles data including metadata and features", + examples=[ + pd.DataFrame( + { + "Metadata_Plate": ["plate1", "plate1", "plate2"], + "Metadata_Well": ["A01", "A02", "B01"], + "Metadata_Treatment": ["control", "control", "control"], + "Feature_A": [1, 2, 3], + "Feature_B": [4, 5, 6], + "Feature_C": [7, 8, 9], + } + ) + ], + ) + + +class FileOperation(DataframeOperation): + """Base class for file operations in pycytominer.""" + + input_path: FilePath = Field( + ..., title="Input path", description="Path to the input file" + ) + output_path: NewPath = Field( + ..., title="Output path", description="Path to the output file" + ) diff --git a/pycytominer/core/profiles.py b/pycytominer/core/profiles.py new file mode 100644 index 00000000..3024e5c8 --- /dev/null +++ b/pycytominer/core/profiles.py @@ -0,0 +1,80 @@ +from typing import Optional + +from pandera.typing import DataFrame, Index +from pandera import DataFrameSchema +from pydantic import BaseModel, Field + + +class Profiles(BaseModel): + """Profiles data model. + + This model is used to store profiles data including metadata and features. + + Attributes: + - df: DataFrame: Profiles dataframe + - metadata_columns: Optional[Index]: Columns that contain metadata information + - features_columns: Optional[Index]: Columns that contain feature information + - strata_columns: Optional[Index]: Columns that contain strata information + """ + + df: DataFrame = Field( + ..., + title="Profiles dataframe", + description="A dataframe containing profiles data including metadata and features", + examples=[], + ) + columns: Optional[Index] = Field( + title="Columns", + description="Full list of columns in the profiles dataframe", + examples=[ + [ + "Metadata_Plate", + "Metadata_Well", + "Metadata_Treatment", + "Feature_A", + "Feature_B", + "Feature_C", + ] + ], + ) + strata_columns: Optional[Index] = Field( + title="Strata columns", + description="Columns that contain strata information (must be a subset of metadata columns)", + examples=[ + ["Metadata_Plate", "Metadata_Well"], + Index(["PlateBarcode", "WellPosition"]), + ], + ) + metadata_columns: Optional[Index] = Field( + title="Metadata columns", + description="Columns that contain metadata information", + examples=[["Metadata_Plate", "Metadata_Well", "Metadata_Treatment"]], + ) + features_columns: Optional[Index] = Field( + title="Feature columns", + description="Columns that contain feature information", + ) + schema: Optional[DataFrameSchema] = Field( + title="Profiles schema", + description="A Pandera schema for the profiles dataframe", + ) + + +class SingleCellProfiles(Profiles): + """Single cell profiles data model.""" + + +class AggregatedProfiles(Profiles): + """Aggregate profiles data model.""" + + +class AnnotatedProfiles(Profiles): + """Annotated profiles data model.""" + + +class NormalizedProfiles(Profiles): + """Normalized profiles data model.""" + + +class ConsensusProfiles(Profiles): + """Consensus profiles data model.""" diff --git a/pyproject.toml b/pyproject.toml index 49b73e47..37a15999 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -58,6 +58,9 @@ fire = {version = ">=0.5.0", optional=true} # Extra dependencies for collate cytominer-database = {version = "0.3.4", optional=true} +pydantic = "^2.6.4" +pandera = "^0.18.3" +pydantic-settings = "^2.2.1" [tool.poetry.extras] cell-locations = ["fsspec", "s3fs", "boto3", "fire"] From 6ca5421ca175426b93feaa0316497f005e3c0483 Mon Sep 17 00:00:00 2001 From: Ken Brewer Date: Fri, 29 Mar 2024 23:40:36 +0000 Subject: [PATCH 2/2] feat: rename attributes in operations --- pycytominer/core/__init__.py | 7 +++++++ pycytominer/core/operation.py | 4 ++-- pycytominer/core/profiles.py | 19 ++++++++++--------- 3 files changed, 19 insertions(+), 11 deletions(-) diff --git a/pycytominer/core/__init__.py b/pycytominer/core/__init__.py index e69de29b..0bd43db2 100644 --- a/pycytominer/core/__init__.py +++ b/pycytominer/core/__init__.py @@ -0,0 +1,7 @@ +"""An experimental package for working with cytominer data in Python. + +pycytominer.core contains an object-oriented API for working with cell profiling data. +It is currently in development and should be considered experimental. +In the future, the functionality in this module may be used to refactor the existing +cytominer package. +""" diff --git a/pycytominer/core/operation.py b/pycytominer/core/operation.py index 56ecc0af..b1a18fb2 100644 --- a/pycytominer/core/operation.py +++ b/pycytominer/core/operation.py @@ -16,7 +16,7 @@ class Operation(BaseModel): """Base class for other file/dataframe operations in pycytominer.""" - profiles: Profiles = Field( + input_profiles: Profiles = Field( ..., title="Profiles", description="Profiles data model." ) @@ -24,7 +24,7 @@ class Operation(BaseModel): class DataframeOperation(Operation): """Base class for dataframe operations in pycytominer.""" - df: DataFrame = Field( + input_df: DataFrame = Field( ..., title="Dataframe", description="A dataframe containing profiles data including metadata and features", diff --git a/pycytominer/core/profiles.py b/pycytominer/core/profiles.py index 3024e5c8..9f4bd31a 100644 --- a/pycytominer/core/profiles.py +++ b/pycytominer/core/profiles.py @@ -14,7 +14,7 @@ class Profiles(BaseModel): - df: DataFrame: Profiles dataframe - metadata_columns: Optional[Index]: Columns that contain metadata information - features_columns: Optional[Index]: Columns that contain feature information - - strata_columns: Optional[Index]: Columns that contain strata information + - columns: Optional[Index]: Columns that contain strata information """ df: DataFrame = Field( @@ -37,14 +37,6 @@ class Profiles(BaseModel): ] ], ) - strata_columns: Optional[Index] = Field( - title="Strata columns", - description="Columns that contain strata information (must be a subset of metadata columns)", - examples=[ - ["Metadata_Plate", "Metadata_Well"], - Index(["PlateBarcode", "WellPosition"]), - ], - ) metadata_columns: Optional[Index] = Field( title="Metadata columns", description="Columns that contain metadata information", @@ -63,6 +55,15 @@ class Profiles(BaseModel): class SingleCellProfiles(Profiles): """Single cell profiles data model.""" + strata_columns: Optional[Index] = Field( + title="Strata columns", + description="Columns that contain strata information (must be a subset of metadata columns)", + examples=[ + ["Metadata_Plate", "Metadata_Well"], + Index(["PlateBarcode", "WellPosition"]), + ], + ) + class AggregatedProfiles(Profiles): """Aggregate profiles data model."""