sqlframe 1.1.3__tar.gz

sqlframe-1.1.3/.github/CODEOWNERS

@@ -0,0 +1 @@
+*       @eakmanrq

sqlframe-1.1.3/.github/workflows/main.workflow.yaml

@@ -0,0 +1,42 @@
+name: SQLFrame
+on:
+  push:
+    branches:
+    - main
+    paths:
+      - 'sqlframe/**'
+      - 'tests/**'
+      - 'Makefile'
+      - 'setup.py'
+  pull_request:
+    types:
+    - synchronize
+    - opened
+    paths:
+    - 'sqlframe/**'
+    - 'tests/**'
+    - 'Makefile'
+    - 'setup.py'
+jobs:
+  run-tests:
+    runs-on: ubuntu-latest
+    env:
+      PYTEST_XDIST_AUTO_NUM_WORKERS: 4
+    strategy:
+      matrix:
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+    - name: Install Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: make install-dev
+    - name: Run Style
+      run: make style
+    - name: Setup Postgres
+      uses: ikalnytskyi/action-setup-postgres@v6
+    - name: Run tests
+      run: make local-test

sqlframe-1.1.3/.github/workflows/publish.workflow.yaml

@@ -0,0 +1,27 @@
+name: Publish
+on:
+  push:
+    tags:
+      - 'v[0-9]+.[0-9]+.[0-9]+'
+permissions:
+  contents: write
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    env:
+      TWINE_USERNAME: ${{ secrets.TWINE_USERNAME }}
+      TWINE_PASSWORD: ${{ secrets.TWINE_PASSWORD }}
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+    - name: Publish
+      run: make publish
+    - name: Create release
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        tag: ${{ github.ref_name }}
+      run: |
+        gh release create "$tag" \
+            --repo="$GITHUB_REPOSITORY" \
+            --title="SQLFrame ${tag#v}" \
+            --generate-notes

sqlframe-1.1.3/.gitignore

@@ -0,0 +1,145 @@
+# 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/
+pip-wheel-metadata/
+share/python-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/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# 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/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# PyCharm
+.idea/
+
+# Visual Studio Code
+.vscode
+
+.DS_STORE
+metastore_db
+spark_warehouse
+
+# Version file
+sqlframe/_version.py
+
+# Emacs files
+*~

sqlframe-1.1.3/.pre-commit-config.yaml

@@ -0,0 +1,33 @@
+repos:
+  - repo: local
+    hooks:
+      - id: ruff
+        name: ruff
+        description: "Run 'ruff' for extremely fast Python linting"
+        entry: ruff check
+            --force-exclude 
+            --fix
+            --select I
+            --ignore E721
+            --ignore E741
+        language: python
+        types_or: [python, pyi]
+        require_serial: true
+        additional_dependencies: []
+        files: ^(sqlframe/|tests/|setup.py)
+      - id: ruff-format
+        name: ruff-format
+        description: "Run 'ruff format' for extremely fast Python formatting"
+        entry: ruff format
+          --force-exclude
+          --line-length 100
+        language: python
+        types_or: [python, pyi]
+        require_serial: true
+      - id: mypy
+        name: mypy
+        entry: mypy sqlframe tests
+        language: system
+        types: [ python ]
+        files: ^(sqlframe/|tests/)
+        pass_filenames: false

sqlframe-1.1.3/.readthedocs.yaml

@@ -0,0 +1,13 @@
+version: 2
+
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.8"
+
+mkdocs:
+  configuration: mkdocs.yml
+
+python:
+   install:
+   - requirements: docs/requirements.txt

sqlframe-1.1.3/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Ryan Eakman
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

sqlframe-1.1.3/Makefile

@@ -0,0 +1,37 @@
+install-dev:
+	pip install -e ".[dev,docs,duckdb,postgres,redshift,bigquery,snowflake,spark]"
+
+install-pre-commit:
+	pre-commit install
+
+slow-test:
+	pytest -n auto tests
+
+fast-test:
+	pytest -n auto -m "fast"
+
+local-test:
+	pytest -n auto -m "fast or local"
+
+bigquery-test:
+	pytest -n auto -m "bigquery"
+
+duckdb-test:
+	pytest -n auto -m "duckdb"
+
+style:
+	pre-commit run --all-files
+
+docs-serve:
+	mkdocs serve
+
+stubs:
+	stubgen sqlframe/bigquery/functions.py --output ./ --inspect-mode
+	stubgen sqlframe/duckdb/functions.py --output ./ --inspect-mode
+	stubgen sqlframe/postgres/functions.py --output ./ --inspect-mode
+
+package:
+	pip3 install wheel && python3 setup.py sdist bdist_wheel
+
+publish: package
+	pip3 install twine && python3 -m twine upload dist/*

sqlframe-1.1.3/PKG-INFO

@@ -0,0 +1,138 @@
+Metadata-Version: 2.1
+Name: sqlframe
+Version: 1.1.3
+Summary: Taking the Spark out of PySpark by converting to SQL
+Home-page: https://github.com/eakmanrq/sqlframe
+Author: Ryan Eakman
+Author-email: eakmanrq@gmail.com
+License: MIT
+Platform: UNKNOWN
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: SQL
+Classifier: Programming Language :: Python :: 3 :: Only
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Provides-Extra: bigquery
+Provides-Extra: dev
+Provides-Extra: docs
+Provides-Extra: duckdb
+Provides-Extra: postgres
+Provides-Extra: redshift
+Provides-Extra: snowflake
+Provides-Extra: spark
+License-File: LICENSE
+
+<div align="center">
+  <img src="https://sqlframe.readthedocs.io/en/latest/docs/images/sqlframe_logo.png" alt="SQLFrame Logo" width="400"/>
+</div>
+
+SQLFrame implements the PySpark DataFrame API in order to enable running transformation pipelines directly on database engines - no Spark clusters or dependencies required.
+
+SQLFrame currently supports the following engines (many more in development):
+
+* [BigQuery](https://sqlframe.readthedocs.io/en/latest/bigquery/)
+* [DuckDB](https://sqlframe.readthedocs.io/en/latest/duckdb)
+* [Postgres](https://sqlframe.readthedocs.io/en/latest/postgres)
+
+SQLFrame also has a "Standalone" session that be used to generate SQL without any connection to a database engine.
+* [Standalone](https://sqlframe.readthedocs.io/en/latest/standalone)
+
+SQLFrame is great for:
+
+* Users who want to run PySpark DataFrame code without having to use a Spark cluster
+* Users who want a SQL representation of their DataFrame code for debugging or sharing with others
+* Users who want a DataFrame API that leverages the full power of their engine to do the processing 
+
+## Installation
+
+```bash
+# BigQuery
+pip install "sqlframe[bigquery]"
+# DuckDB
+pip install "sqlframe[duckdb]"
+# Postgres
+pip install "sqlframe[postgres]"
+# Standalone
+pip install sqlframe
+```
+
+See specific engine documentation for additional setup instructions.
+
+## Example Usage
+
+```python
+from sqlframe.bigquery import BigQuerySession
+from sqlframe.bigquery import functions as F
+from sqlframe.bigquery import Window
+
+session = BigQuerySession()
+table_path = "bigquery-public-data.samples.natality"
+# Top 5 years with the greatest year-over-year % change in new families with single child
+df = (
+    session.table(table_path)
+    .where(F.col("ever_born") == 1)
+    .groupBy("year")
+    .agg(F.count("*").alias("num_single_child_families"))
+    .withColumn(
+        "last_year_num_single_child_families", 
+        F.lag(F.col("num_single_child_families"), 1).over(Window.orderBy("year"))
+    )
+    .withColumn(
+        "percent_change", 
+        (F.col("num_single_child_families") - F.col("last_year_num_single_child_families")) 
+        / F.col("last_year_num_single_child_families")
+    )
+    .orderBy(F.abs(F.col("percent_change")).desc())
+    .select(
+        F.col("year").alias("year"),
+        F.format_number("num_single_child_families", 0).alias("new families single child"),
+        F.format_number(F.col("percent_change") * 100, 2).alias("percent change"),
+    )
+    .limit(5)
+)
+```
+```python
+>>> df.sql()
+WITH `t94228` AS (
+  SELECT
+    `natality`.`year` AS `year`,
+    COUNT(*) AS `num_single_child_families`
+  FROM `bigquery-public-data`.`samples`.`natality` AS `natality`
+  WHERE
+    `natality`.`ever_born` = 1
+  GROUP BY
+    `natality`.`year`
+), `t39093` AS (
+  SELECT
+    `t94228`.`year` AS `year`,
+    `t94228`.`num_single_child_families` AS `num_single_child_families`,
+    LAG(`t94228`.`num_single_child_families`, 1) OVER (ORDER BY `t94228`.`year`) AS `last_year_num_single_child_families`
+  FROM `t94228` AS `t94228`
+)
+SELECT
+  `t39093`.`year` AS `year`,
+  FORMAT('%\'.0f', ROUND(CAST(`t39093`.`num_single_child_families` AS FLOAT64), 0)) AS `new families single child`,
+  FORMAT('%\'.2f', ROUND(CAST((((`t39093`.`num_single_child_families` - `t39093`.`last_year_num_single_child_families`) / `t39093`.`last_year_num_single_child_families`) * 100) AS FLOAT64), 2)) AS `percent change`
+FROM `t39093` AS `t39093`
+ORDER BY
+  ABS(`percent_change`) DESC
+LIMIT 5
+```
+```python
+>>> df.show()
++------+---------------------------+----------------+
+| year | new families single child | percent change |
++------+---------------------------+----------------+
+| 1989 |         1,650,246         |     25.02      |
+| 1974 |          783,448          |     14.49      |
+| 1977 |         1,057,379         |     11.38      |
+| 1985 |         1,308,476         |     11.15      |
+| 1975 |          868,985          |     10.92      |
++------+---------------------------+----------------+
+```
+
+

sqlframe-1.1.3/README.md

@@ -0,0 +1,108 @@
+<div align="center">
+  <img src="https://sqlframe.readthedocs.io/en/latest/docs/images/sqlframe_logo.png" alt="SQLFrame Logo" width="400"/>
+</div>
+
+SQLFrame implements the PySpark DataFrame API in order to enable running transformation pipelines directly on database engines - no Spark clusters or dependencies required.
+
+SQLFrame currently supports the following engines (many more in development):
+
+* [BigQuery](https://sqlframe.readthedocs.io/en/latest/bigquery/)
+* [DuckDB](https://sqlframe.readthedocs.io/en/latest/duckdb)
+* [Postgres](https://sqlframe.readthedocs.io/en/latest/postgres)
+
+SQLFrame also has a "Standalone" session that be used to generate SQL without any connection to a database engine.
+* [Standalone](https://sqlframe.readthedocs.io/en/latest/standalone)
+
+SQLFrame is great for:
+
+* Users who want to run PySpark DataFrame code without having to use a Spark cluster
+* Users who want a SQL representation of their DataFrame code for debugging or sharing with others
+* Users who want a DataFrame API that leverages the full power of their engine to do the processing 
+
+## Installation
+
+```bash
+# BigQuery
+pip install "sqlframe[bigquery]"
+# DuckDB
+pip install "sqlframe[duckdb]"
+# Postgres
+pip install "sqlframe[postgres]"
+# Standalone
+pip install sqlframe
+```
+
+See specific engine documentation for additional setup instructions.
+
+## Example Usage
+
+```python
+from sqlframe.bigquery import BigQuerySession
+from sqlframe.bigquery import functions as F
+from sqlframe.bigquery import Window
+
+session = BigQuerySession()
+table_path = "bigquery-public-data.samples.natality"
+# Top 5 years with the greatest year-over-year % change in new families with single child
+df = (
+    session.table(table_path)
+    .where(F.col("ever_born") == 1)
+    .groupBy("year")
+    .agg(F.count("*").alias("num_single_child_families"))
+    .withColumn(
+        "last_year_num_single_child_families", 
+        F.lag(F.col("num_single_child_families"), 1).over(Window.orderBy("year"))
+    )
+    .withColumn(
+        "percent_change", 
+        (F.col("num_single_child_families") - F.col("last_year_num_single_child_families")) 
+        / F.col("last_year_num_single_child_families")
+    )
+    .orderBy(F.abs(F.col("percent_change")).desc())
+    .select(
+        F.col("year").alias("year"),
+        F.format_number("num_single_child_families", 0).alias("new families single child"),
+        F.format_number(F.col("percent_change") * 100, 2).alias("percent change"),
+    )
+    .limit(5)
+)
+```
+```python
+>>> df.sql()
+WITH `t94228` AS (
+  SELECT
+    `natality`.`year` AS `year`,
+    COUNT(*) AS `num_single_child_families`
+  FROM `bigquery-public-data`.`samples`.`natality` AS `natality`
+  WHERE
+    `natality`.`ever_born` = 1
+  GROUP BY
+    `natality`.`year`
+), `t39093` AS (
+  SELECT
+    `t94228`.`year` AS `year`,
+    `t94228`.`num_single_child_families` AS `num_single_child_families`,
+    LAG(`t94228`.`num_single_child_families`, 1) OVER (ORDER BY `t94228`.`year`) AS `last_year_num_single_child_families`
+  FROM `t94228` AS `t94228`
+)
+SELECT
+  `t39093`.`year` AS `year`,
+  FORMAT('%\'.0f', ROUND(CAST(`t39093`.`num_single_child_families` AS FLOAT64), 0)) AS `new families single child`,
+  FORMAT('%\'.2f', ROUND(CAST((((`t39093`.`num_single_child_families` - `t39093`.`last_year_num_single_child_families`) / `t39093`.`last_year_num_single_child_families`) * 100) AS FLOAT64), 2)) AS `percent change`
+FROM `t39093` AS `t39093`
+ORDER BY
+  ABS(`percent_change`) DESC
+LIMIT 5
+```
+```python
+>>> df.show()
++------+---------------------------+----------------+
+| year | new families single child | percent change |
++------+---------------------------+----------------+
+| 1989 |         1,650,246         |     25.02      |
+| 1974 |          783,448          |     14.49      |
+| 1977 |         1,057,379         |     11.38      |
+| 1985 |         1,308,476         |     11.15      |
+| 1975 |          868,985          |     10.92      |
++------+---------------------------+----------------+
+```