typedspark 0.0.0__tar.gz

typedspark-0.0.0/LICENSE.txt

@@ -0,0 +1,201 @@
+                                 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.

typedspark-0.0.0/PKG-INFO

@@ -0,0 +1,93 @@
+Metadata-Version: 2.1
+Name: typedspark
+Version: 0.0.0
+Summary: Column-wise type annotations for pyspark DataFrames
+Home-page: https://github.com/kaiko-ai/typedspark
+Author: Nanne Aben
+Author-email: nanne@kaiko.ai
+License: Apache-2.0
+Keywords: pyspark spark typing type checking annotations
+Classifier: Programming Language :: Python
+Classifier: Typing :: Typed
+Requires-Python: >=3.9.0
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+Requires-Dist: typing-extensions<=4.11.0
+Provides-Extra: pyspark
+Requires-Dist: pyspark; extra == "pyspark"
+
+# Typedspark: column-wise type annotations for pyspark DataFrames
+
+We love Spark! But in production code we're wary when we see:
+
+```python
+from pyspark.sql import DataFrame
+
+def foo(df: DataFrame) -> DataFrame:
+    # do stuff
+    return df
+```
+
+Because… How do we know which columns are supposed to be in ``df``?
+
+Using ``typedspark``, we can be more explicit about what these data should look like.
+
+```python
+from typedspark import Column, DataSet, Schema
+from pyspark.sql.types import LongType, StringType
+
+class Person(Schema):
+    id: Column[LongType]
+    name: Column[StringType]
+    age: Column[LongType]
+
+def foo(df: DataSet[Person]) -> DataSet[Person]:
+    # do stuff
+    return df
+```
+The advantages include:
+
+* Improved readibility of the code
+* Typechecking, both during runtime and linting
+* Auto-complete of column names
+* Easy refactoring of column names
+* Easier unit testing through the generation of empty ``DataSets`` based on their schemas
+* Improved documentation of tables
+
+## Documentation
+Please see our documentation on [readthedocs](https://typedspark.readthedocs.io/en/latest/index.html).
+
+## Installation
+
+You can install ``typedspark`` from [pypi](https://pypi.org/project/typedspark/) by running:
+
+```bash
+pip install typedspark
+```
+By default, ``typedspark`` does not list ``pyspark`` as a dependency, since many platforms (e.g. Databricks) come with ``pyspark`` preinstalled.  If you want to install ``typedspark`` with ``pyspark``, you can run:
+
+```bash
+pip install "typedspark[pyspark]"
+```
+
+## Demo videos
+
+### IDE demo
+
+https://github.com/kaiko-ai/typedspark/assets/47976799/e6f7fa9c-6d14-4f68-baba-fe3c22f75b67
+
+You can find the corresponding code [here](docs/videos/ide.ipynb).
+
+### Jupyter / Databricks notebooks demo
+
+https://github.com/kaiko-ai/typedspark/assets/47976799/39e157c3-6db0-436a-9e72-44b2062df808
+
+You can find the corresponding code [here](docs/videos/notebook.ipynb).
+
+## FAQ
+
+**I found a bug! What should I do?**</br>
+Great! Please make an issue and we'll look into it.
+
+**I have a great idea to improve typedspark! How can we make this work?**</br>
+Awesome, please make an issue and let us know!

typedspark-0.0.0/README.md

@@ -0,0 +1,75 @@
+# Typedspark: column-wise type annotations for pyspark DataFrames
+
+We love Spark! But in production code we're wary when we see:
+
+```python
+from pyspark.sql import DataFrame
+
+def foo(df: DataFrame) -> DataFrame:
+    # do stuff
+    return df
+```
+
+Because… How do we know which columns are supposed to be in ``df``?
+
+Using ``typedspark``, we can be more explicit about what these data should look like.
+
+```python
+from typedspark import Column, DataSet, Schema
+from pyspark.sql.types import LongType, StringType
+
+class Person(Schema):
+    id: Column[LongType]
+    name: Column[StringType]
+    age: Column[LongType]
+
+def foo(df: DataSet[Person]) -> DataSet[Person]:
+    # do stuff
+    return df
+```
+The advantages include:
+
+* Improved readibility of the code
+* Typechecking, both during runtime and linting
+* Auto-complete of column names
+* Easy refactoring of column names
+* Easier unit testing through the generation of empty ``DataSets`` based on their schemas
+* Improved documentation of tables
+
+## Documentation
+Please see our documentation on [readthedocs](https://typedspark.readthedocs.io/en/latest/index.html).
+
+## Installation
+
+You can install ``typedspark`` from [pypi](https://pypi.org/project/typedspark/) by running:
+
+```bash
+pip install typedspark
+```
+By default, ``typedspark`` does not list ``pyspark`` as a dependency, since many platforms (e.g. Databricks) come with ``pyspark`` preinstalled.  If you want to install ``typedspark`` with ``pyspark``, you can run:
+
+```bash
+pip install "typedspark[pyspark]"
+```
+
+## Demo videos
+
+### IDE demo
+
+https://github.com/kaiko-ai/typedspark/assets/47976799/e6f7fa9c-6d14-4f68-baba-fe3c22f75b67
+
+You can find the corresponding code [here](docs/videos/ide.ipynb).
+
+### Jupyter / Databricks notebooks demo
+
+https://github.com/kaiko-ai/typedspark/assets/47976799/39e157c3-6db0-436a-9e72-44b2062df808
+
+You can find the corresponding code [here](docs/videos/notebook.ipynb).
+
+## FAQ
+
+**I found a bug! What should I do?**</br>
+Great! Please make an issue and we'll look into it.
+
+**I have a great idea to improve typedspark! How can we make this work?**</br>
+Awesome, please make an issue and let us know!

typedspark-0.0.0/pyproject.toml

@@ -0,0 +1,41 @@
+[tool.black]
+line-length = 100
+
+[tool.isort]
+profile = "black"
+line_length = 100
+
+[tool.pylint]
+ignore-paths = ['^tests/.+.py$', 'setup.py', '^docs/.+.py$']
+
+[tool.pylint."messages control"]
+disable = "all"
+enable = [
+    "empty-docstring",
+    "missing-module-docstring",
+    "missing-class-docstring",
+    "missing-function-docstring",
+    "unidiomatic-typecheck",
+    "no-else-return",
+    "consider-using-dict-comprehension",
+    "dangerous-default-value",
+    "unspecified-encoding",
+    "unnecessary-pass",
+    "redefined-outer-name",
+    "invalid-name",
+    "unused-argument",
+    "redefined-builtin",
+    "simplifiable-if-expression",
+    "logging-fstring-interpolation",
+    "inconsistent-return-statements",
+    "consider-using-set-comprehension"
+]
+
+[tool.coverage.run]
+source = ["typedspark/"]
+
+[tool.mypy]
+exclude = ['^docs\/.+\.py$']
+
+[tool.bandit]
+exclude_dirs = ["tests"]

typedspark-0.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

typedspark-0.0.0/setup.py

@@ -0,0 +1,34 @@
+from setuptools import find_packages, setup
+
+
+def get_requirements():
+    with open("requirements.txt") as f:
+        return f.read().splitlines()
+
+
+def get_long_description():
+    with open("README.md", encoding="utf-8") as f:
+        return f.read()
+
+
+setup(
+    name="typedspark",
+    url="https://github.com/kaiko-ai/typedspark",
+    license="Apache-2.0",
+    author="Nanne Aben",
+    author_email="nanne@kaiko.ai",
+    description="Column-wise type annotations for pyspark DataFrames",
+    keywords="pyspark spark typing type checking annotations",
+    long_description=get_long_description(),
+    long_description_content_type="text/markdown",
+    packages=find_packages(include=["typedspark", "typedspark.*"]),
+    install_requires=get_requirements(),
+    python_requires=">=3.9.0",
+    classifiers=["Programming Language :: Python", "Typing :: Typed"],
+    version_config=True,
+    setup_requires=["setuptools-git-versioning"],
+    package_data={"typedspark": ["py.typed"]},
+    extras_require={
+        "pyspark": ["pyspark"],
+    },
+)

typedspark-0.0.0/typedspark/__init__.py

@@ -0,0 +1,54 @@
+"""Typedspark: column-wise type annotations for pyspark DataFrames."""
+
+from typedspark._core.column import Column
+from typedspark._core.column_meta import ColumnMeta
+from typedspark._core.dataset import DataSet, DataSetImplements
+from typedspark._core.datatypes import (
+    ArrayType,
+    DayTimeIntervalType,
+    DecimalType,
+    MapType,
+    StructType,
+)
+from typedspark._core.literaltype import IntervalType
+from typedspark._schema.schema import MetaSchema, Schema
+from typedspark._transforms.structtype_column import structtype_column
+from typedspark._transforms.transform_to_schema import transform_to_schema
+from typedspark._utils.create_dataset import (
+    create_empty_dataset,
+    create_partially_filled_dataset,
+    create_structtype_row,
+)
+from typedspark._utils.databases import Catalogs, Database, Databases
+from typedspark._utils.load_table import create_schema, load_table
+from typedspark._utils.register_schema_to_dataset import (
+    register_schema_to_dataset,
+    register_schema_to_dataset_with_alias,
+)
+
+__all__ = [
+    "ArrayType",
+    "Catalogs",
+    "Column",
+    "ColumnMeta",
+    "Database",
+    "Databases",
+    "DataSet",
+    "DayTimeIntervalType",
+    "DecimalType",
+    "IntervalType",
+    "MapType",
+    "MetaSchema",
+    "DataSetImplements",
+    "Schema",
+    "StructType",
+    "create_empty_dataset",
+    "create_partially_filled_dataset",
+    "create_structtype_row",
+    "create_schema",
+    "load_table",
+    "register_schema_to_dataset",
+    "register_schema_to_dataset_with_alias",
+    "structtype_column",
+    "transform_to_schema",
+]

typedspark-0.0.0/typedspark/_core/column.py

@@ -0,0 +1,97 @@
+"""Module containing classes and functions related to TypedSpark Columns."""
+
+from logging import warn
+from typing import Generic, Optional, TypeVar, Union, get_args, get_origin
+
+from pyspark.sql import Column as SparkColumn
+from pyspark.sql import DataFrame, SparkSession
+from pyspark.sql.functions import col
+from pyspark.sql.types import DataType
+
+from typedspark._core.datatypes import StructType
+
+T = TypeVar("T", bound=DataType)
+
+
+class EmptyColumn(SparkColumn):
+    """Column object to be instantiated when there is no active Spark session."""
+
+    def __init__(self, *args, **kwargs) -> None:  # pragma: no cover
+        pass
+
+
+class Column(SparkColumn, Generic[T]):
+    """Represents a ``Column`` in a ``Schema``. Can be used as:
+
+    .. code-block:: python
+
+        class A(Schema):
+            a: Column[IntegerType]
+            b: Column[StringType]
+    """
+
+    def __new__(
+        cls,
+        name: str,
+        dataframe: Optional[DataFrame] = None,
+        curid: Optional[int] = None,
+        dtype: Optional[T] = None,
+        parent: Union[DataFrame, "Column", None] = None,
+        alias: Optional[str] = None,
+    ):
+        """``__new__()`` instantiates the object (prior to ``__init__()``).
+
+        Here, we simply take the provided ``name``, create a pyspark
+        ``Column`` object and cast it to a typedspark ``Column`` object.
+        This allows us to bypass the pypsark ``Column`` constuctor in
+        ``__init__()``, which requires parameters that may be difficult
+        to access.
+        """
+        # pylint: disable=unused-argument
+
+        if dataframe is not None and parent is None:
+            parent = dataframe
+            warn("The use of Column(dataframe=...) is deprecated, use Column(parent=...) instead.")
+
+        column: SparkColumn
+        if SparkSession.getActiveSession() is None:
+            column = EmptyColumn()  # pragma: no cover
+        elif alias is not None:
+            column = col(f"{alias}.{name}")
+        elif parent is not None:
+            column = parent[name]
+        else:
+            column = col(name)
+
+        column.__class__ = Column
+        return column
+
+    def __init__(
+        self,
+        name: str,
+        dataframe: Optional[DataFrame] = None,
+        curid: Optional[int] = None,
+        dtype: Optional[T] = None,
+        parent: Union[DataFrame, "Column", None] = None,
+        alias: Optional[str] = None,
+    ):
+        # pylint: disable=unused-argument
+        self.str = name
+        self._dtype = dtype if dtype is not None else DataType
+        self._curid = curid
+
+    def __hash__(self) -> int:
+        return hash((self.str, self._curid))
+
+    @property
+    def dtype(self) -> T:
+        """Get the datatype of the column, e.g. Column[IntegerType] -> IntegerType."""
+        dtype = self._dtype
+
+        if get_origin(dtype) == StructType:
+            return StructType(
+                schema=get_args(dtype)[0],
+                parent=self,
+            )  # type: ignore
+
+        return dtype()  # type: ignore

typedspark-0.0.0/typedspark/_core/column_meta.py

@@ -0,0 +1,26 @@
+"""Metadata for ``Column`` objects that can be accessed during runtime."""
+
+from dataclasses import dataclass
+from typing import Dict, Optional
+
+
+@dataclass
+class ColumnMeta:
+    """Contains the metadata for a ``Column``. Used as:
+
+    .. code-block:: python
+
+        class A(Schema):
+            a: Annotated[
+                Column[IntegerType],
+                ColumnMeta(
+                    comment="This is a comment",
+                )
+            ]
+    """
+
+    comment: Optional[str] = None
+
+    def get_metadata(self) -> Optional[Dict[str, str]]:
+        """Returns the metadata of this column."""
+        return {"comment": self.comment} if self.comment else None