Repository: CedricFR/dataenforce Branch: master Commit: 5dfc5f725d6a Files: 7 Total size: 24.7 KB Directory structure: gitextract_fed2iyuc/ ├── .gitignore ├── LICENSE ├── README.md ├── dataenforce/ │ └── __init__.py ├── setup.py └── tests/ ├── test_dataset.py └── test_validate.py ================================================ FILE CONTENTS ================================================ ================================================ FILE: .gitignore ================================================ # Byte-compiled / optimized / DLL files __pycache__/ *.py[cod] *$py.class # C extensions *.so # Distribution / packaging .Python build/ develop-eggs/ dist/ downloads/ eggs/ .eggs/ lib/ lib64/ parts/ sdist/ var/ wheels/ *.egg-info/ .installed.cfg *.egg MANIFEST # PyInstaller # Usually these files are written by a python script from a template # before PyInstaller builds the exe, so as to inject date/other infos into it. *.manifest *.spec # Installer logs pip-log.txt pip-delete-this-directory.txt # Unit test / coverage reports htmlcov/ .tox/ .coverage .coverage.* .cache nosetests.xml coverage.xml *.cover .hypothesis/ .pytest_cache/ # Translations *.mo *.pot # Django stuff: *.log local_settings.py db.sqlite3 # Flask stuff: instance/ .webassets-cache # Scrapy stuff: .scrapy # Sphinx documentation docs/_build/ # PyBuilder target/ # Jupyter Notebook .ipynb_checkpoints # pyenv .python-version # celery beat schedule file celerybeat-schedule # SageMath parsed files *.sage.py # Environments .env .venv env/ venv/ ENV/ env.bak/ venv.bak/ # Spyder project settings .spyderproject .spyproject # Rope project settings .ropeproject # mkdocs documentation /site # mypy .mypy_cache/ ================================================ FILE: LICENSE ================================================ Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document. "Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License. "Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity. "You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License. "Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types. "Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below). "Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof. "Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution." "Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work. 2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form. 3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed. 4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions: (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and (b) You must cause any modified files to carry prominent notices stating that You changed the files; and (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License. 5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions. 6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file. 7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License. 8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages. 9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability. END OF TERMS AND CONDITIONS APPENDIX: How to apply the Apache License to your work. To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets "[]" replaced with your own identifying information. (Don't include the brackets!) The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same "printed page" as the copyright notice for easier identification within third-party archives. Copyright [yyyy] [name of copyright owner] Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. ================================================ FILE: README.md ================================================ # Overview `dataenforce` is a Python package used to enforce column names & types of pandas DataFrames using Python 3 type hinting. It is a common issue in Data Analysis to pass dataframes into functions without a clear idea of which columns are included or not, and as columns are added to or removed from input data, code can break in unexpected ways. With `dataenforce`, you can provide a clear interface to your functions and ensure that the input dataframes will have the right format when your code is used. # How to install Install with pip: ``` pip install dataenforce ``` You can also pip install it from the sources, or just import the `dataenforce` folder. # How to use There are two parts in `dataenforce`: the type-hinting part, and the validation. You can use type-hinting with the provided class to indicate what shape the input dataframes should have, and the validation decorator to additionally ensure the format is respected in every function call. ## Type-hinting: `Dataset` The `Dataset` type indicates that we expect a `pandas.DataFrame` ### Column name checking ```py from dataenforce import Dataset def process_data(data: Dataset["id", "name", "location"]) pass ``` The code above specifies that `data` must be a DataFrame with exactly the 3 mentioned columns. If you want to only specify a subset of columns which is required, you can use an ellipsis: ```py def process_data(data: Dataset["id", "name", "location", ...]) pass ``` ### dtype checking ```py def process_data(data: Dataset["id": int, "name": object, "latitude": float, "longitude": float]) pass ``` The code above specifies the column names which must be there, with associated types. A combination of only names & with types is possible: `Dataset["id": int, "name"]`. ### Reusing dataframe formats As you're likely to use the same column subsets several times in your code, you can define them to reuse & combine them later: ```py DName = Dataset["id", "name"] DLocation = Dataset["id", "latitude", "longitude"] # Expects columns id, name def process1(data: DName): pass # Expects columns id, name, latitude, longitude, timestamp def process2(data: Dataset[DName, DLocation, "timestamp"]) pass ``` ## Enforcing: `@validate` The `@validate` decorator ensures that input `Dataset`s have the right format when the function is called, otherwise raises `TypeError`. ```py from dataenforce import Dataset, validate import pandas as pd @validate def process_data(data: Dataset["id", "name"]): pass process_data(pd.DataFrame(dict(id=[1,2], name=["Alice", "Bob"]))) # Works process_data(pd.DataFrame(dict(id=[1,2]))) # Raises a TypeError, column name missing ``` # How to test `dataenforce` uses `pytest` as a testing library. If you have `pytest` installed, just run `PYTHONPATH="." pytest` in the command line while being in the root folder. # Notes * You can use `dataenforce` to type-hint the return value of a function, but it is not currently possible to `validate` it (it is not included in the checks) * You can't use `@validate` on a function where you use non-base class type-hints as strings (like `def f() -> "MyClass"`). Issue related to PEP 563 * This work is at experimental state. It is not production-ready. Please raise issues & send pull requests if you find/solve some bugs * `dataenforce` is released under the Apache License 2.0, meaning you can freely use the library and redistribute it, provided Copyright is kept * Dependencies: Pandas & Numpy * Tested with Python 3.6, 3.7, 3.8 ================================================ FILE: dataenforce/__init__.py ================================================ # Copyright 2018 Cedric Canovas # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. import inspect from functools import wraps import pandas as pd from typing import _TypingEmpty, _tp_cache, Generic, get_type_hints import numpy as np try: from typing import GenericMeta # Python 3.6 except ImportError: # Python 3.7 class GenericMeta(type): pass def validate(f): signature = inspect.signature(f) hints = get_type_hints(f) @wraps(f) def wrapper(*args, **kwargs): bound = signature.bind(*args, **kwargs) for argument_name, value in bound.arguments.items(): if argument_name in hints and isinstance(hints[argument_name], DatasetMeta): hint = hints[argument_name] if not isinstance(value, pd.DataFrame): raise TypeError("%s is not a pandas Dataframe" % value) columns = set(value.columns) if hint.only_specified and not columns == hint.columns: raise TypeError("%s columns do not match required column set %s" % (argument_name, hint.columns)) if not hint.only_specified and not hint.columns.issubset(columns): raise TypeError("%s is missing some columns from %s" % (argument_name, hint.columns)) if hint.dtypes: dtypes = dict(value.dtypes) for colname, dt in hint.dtypes.items(): if not np.issubdtype(dtypes[colname], np.dtype(dt)): raise TypeError("%s is not a subtype of %s for column %s" % (dtypes[colname], dt, colname)) return f(*args, **kwargs) return wrapper def _get_columns_dtypes(p): columns = set() dtypes = {} if isinstance(p, str): columns.add(p) elif isinstance(p, slice): columns.add(p.start) if not inspect.isclass(p.stop): raise TypeError("Column type hints must be classes, error with %s" % repr(p.stop)) dtypes[p.start] = p.stop elif isinstance(p, (list, set)): for el in p: subcolumns, subdtypes = _get_columns_dtypes(el) columns |= subcolumns dtypes.update(subdtypes) elif isinstance(p, DatasetMeta): columns |= p.columns dtypes.update(p.dtypes) else: raise TypeError("Dataset[col1, col2, ...]: each col must be a string, list or set.") return columns, dtypes class DatasetMeta(GenericMeta): """Metaclass for Dataset (internal).""" def __new__(metacls, name, bases, namespace, **kargs): return super().__new__(metacls, name, bases, namespace) @_tp_cache def __getitem__(self, parameters): if hasattr(self, '__origin__') and (self.__origin__ is not None or self._gorg is not Dataset): return super().__getitem__(parameters) if parameters == (): return super().__getitem__((_TypingEmpty,)) if not isinstance(parameters, tuple): parameters = (parameters,) parameters = list(parameters) only_specified = True if parameters[-1] is ...: only_specified = False parameters.pop() columns, dtypes = _get_columns_dtypes(parameters) meta = DatasetMeta(self.__name__, self.__bases__, {}) meta.only_specified = only_specified meta.columns = columns meta.dtypes = dtypes return meta class Dataset(pd.DataFrame, extra=Generic, metaclass=DatasetMeta): """Defines type Dataset to serve as column name & type enforcement for pandas DataFrames""" __slots__ = () def __new__(cls, *args, **kwds): if not hasattr(cls, '_gorg') or cls._gorg is Dataset: raise TypeError("Type Dataset cannot be instantiated; " "use pandas.DataFrame() instead") return _generic_new(pd.DataFrame, cls, *args, **kwds) ================================================ FILE: setup.py ================================================ import setuptools with open("README.md", "r") as fh: long_description = fh.read().replace("```py", "```") setuptools.setup( name="dataenforce", version="0.1.2", author="Cedric Canovas", author_email="dev@canovas.me", description="Enforce column names & data types of pandas DataFrames", long_description=long_description, long_description_content_type="text/markdown", url="https://github.com/CedricFR/dataenforce", packages=setuptools.find_packages(), classifiers=[ "Programming Language :: Python :: 3", "Operating System :: OS Independent", "License :: OSI Approved :: Apache Software License" ], ) ================================================ FILE: tests/test_dataset.py ================================================ import pytest from dataenforce import Dataset def test_empty(): DEmpty = Dataset[...] assert DEmpty.columns == set() assert DEmpty.dtypes == {} assert DEmpty.only_specified == False def test_columns(): DName = Dataset["id", "name"] assert DName.columns == {"id", "name"} assert DName.dtypes == {} assert DName.only_specified == True def test_ellipsis(): DName = Dataset["id", "name", ...] assert DName.columns == {"id", "name"} assert DName.dtypes == {} assert DName.only_specified == False def test_dtypes(): DName = Dataset["id": int, "name": object, "location"] assert DName.columns == {"id", "name", "location"} assert DName.dtypes == {'id': int, 'name': object} assert DName.only_specified == True def test_nested(): DName = Dataset["id": int, "name": object] DLocation = Dataset["id": int, "longitude": float, "latitude": float] DNameLoc = Dataset[DName, DLocation] assert DNameLoc.columns == {"id", "name", "longitude", "latitude"} assert DNameLoc.dtypes == {'id': int, 'name': object, "longitude": float, "latitude": float} assert DNameLoc.only_specified == True DNameLocEtc = Dataset[DNameLoc, "description": object, ...] assert DNameLocEtc.columns == {"id", "name", "longitude", "latitude", "description"} assert DNameLocEtc.dtypes == {'id': int, 'name': object, "longitude": float, "latitude": float, "description": object} assert DNameLocEtc.only_specified == False def test_init(): with pytest.raises(TypeError): Dataset() ================================================ FILE: tests/test_validate.py ================================================ import pytest from dataenforce import Dataset, validate import pandas as pd import numpy as np from datetime import datetime def test_validate_columns(): df1 = pd.DataFrame(dict(a=[1,2,3])) df2 = pd.DataFrame(dict(a=[1,2,3], b=[4,5,6])) df3 = pd.DataFrame(dict(a=[1,2,3], b=[4,5,6], c=[7,8,9])) @validate def process(data: Dataset["a", "b"]): pass process(df2) with pytest.raises(TypeError): process(df1) with pytest.raises(TypeError): process(df3) def test_validate_combination(): df1 = pd.DataFrame(dict(a=[1,2,3])) df2 = pd.DataFrame(dict(a=[1,2,3], b=[4,5,6])) @validate def process(data1: Dataset["a"], data2: Dataset["a", "b"]): pass process(df1, df2) def test_validate_ellipsis(): df1 = pd.DataFrame(dict(a=[1,2,3])) df2 = pd.DataFrame(dict(a=[1,2,3], b=[4,5,6])) df3 = pd.DataFrame(dict(a=[1,2,3], b=[4,5,6], c=[7,8,9])) @validate def process(data: Dataset["a", "b", ...]): pass process(df2) process(df3) with pytest.raises(TypeError): process(df1) def test_validate_empty(): df = pd.DataFrame(dict(a=[1,2,3])) @validate def process(data: Dataset[...]): pass process(df) with pytest.raises(TypeError): process(False) def test_validate_dtypes(): df = pd.DataFrame(dict(a=[1,2,3], b=[4.1,5.1,6.1], c=["a", "b", "c"], d=[datetime.now().replace(hour=x) for x in [7,8,9]])) @validate def process1(data: Dataset["a": int, "b": np.float, "c": object, "d": np.datetime64]): pass @validate def process2(data: Dataset["a": float, "b", ...]): pass @validate def process3(data: Dataset["a": np.datetime64, ...]): pass process1(df) with pytest.raises(TypeError): process2(df) with pytest.raises(TypeError): process3(df) def test_validate_other_types(): df = pd.DataFrame(dict(a=[1,2,3])) @validate def process(data: Dataset["a"], other: int): pass process(df, 3) def test_return_type(): df = pd.DataFrame(dict(a=[1,2,3])) class Klass: pass @validate def process(data: Dataset["a"]) -> int: return 2 @validate def process2(data: Dataset["a"]) -> Klass: return Klass() #@validate #def process3(data: Dataset["a"]) -> "Klass": # return Klass() process(df) process2(df) #process3(df) # -> This scenario fails, issue with eval in get_type_hints (read PEP 563)