duckpd 0.0.2__tar.gz

duckpd-0.0.2/.github/workflows/ci.yml

@@ -0,0 +1,27 @@
+name: CI
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: ["3.11", "3.12", "3.13", "3.14"]
+
+    steps:
+      - uses: actions/checkout@v5
+      - uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: true
+          python-version: ${{ matrix.python-version }}
+      - run: uv sync --frozen --group dev
+      - run: uv run pytest
+      - run: uv run ruff check .
+      - run: uv run ruff format --check .
+      - run: uv run pyright
+      - run: uv build

duckpd-0.0.2/.gitignore

@@ -0,0 +1,229 @@
+.venv/
+.pytest_cache/
+.ruff_cache/
+.coverage
+__pycache__/
+*.py[cod]
+build/
+dist/
+*.egg-info/
+*.duckdb.tmp/
+demo/data/
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+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/
+cover/
+
+# 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
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.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/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

duckpd-0.0.2/.pre-commit-config.yaml

@@ -0,0 +1,23 @@
+repos:
+  - repo: local
+    hooks:
+      - id: ruff
+        name: ruff
+        entry: uv run ruff check .
+        language: system
+        pass_filenames: false
+      - id: ruff-format
+        name: ruff-format
+        entry: uv run ruff format --check .
+        language: system
+        pass_filenames: false
+      - id: pyright
+        name: pyright
+        entry: uv run pyright
+        language: system
+        pass_filenames: false
+      - id: pytest
+        name: pytest
+        entry: uv run pytest
+        language: system
+        pass_filenames: false

duckpd-0.0.2/.python-version

@@ -0,0 +1 @@
+3.12

duckpd-0.0.2/CONTRIBUTING.md

@@ -0,0 +1,37 @@
+# Contributing
+
+DuckPD uses Python 3.11+, `uv`, pytest, Ruff, and Pyright.
+
+## Setup
+
+```bash
+uv sync --frozen --group dev
+uv run pre-commit install
+```
+
+## Checks
+
+Run focused tests while developing, then run the complete gate before opening a
+pull request:
+
+```bash
+make check
+make build
+```
+
+The equivalent commands, useful on systems without GNU Make, are:
+
+```bash
+uv run pytest
+uv run ruff check .
+uv run ruff format --check .
+uv run pyright
+uv build
+```
+
+Every public operation must remain lazy until an explicit execution boundary,
+update frame metadata, reject unsupported arguments before execution, and have
+differential tests against the supported pandas behavior.
+
+Do not add an automatic pandas fallback. Unsupported behavior should raise a
+specific exception.

duckpd-0.0.2/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 QuantBert
+
+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.

duckpd-0.0.2/Makefile

@@ -0,0 +1,49 @@
+.DEFAULT_GOAL := help
+
+.PHONY: help install test lint format format-check typecheck check build demos-smoke release-check clean publish
+
+help: ## Show available targets
+	@grep -E '^[a-z-]+:.*##' $(MAKEFILE_LIST) | awk -F ':.*## ' '{printf "  %-20s %s\n", $$1, $$2}'
+
+install: ## Sync the locked development environment
+	uv sync --frozen --group dev
+
+test: ## Run tests with the configured coverage requirements
+	uv run pytest
+
+lint: ## Run Ruff lint checks
+	uv run ruff check .
+
+format: ## Format the repository with Ruff
+	uv run ruff format .
+
+format-check: ## Verify Ruff formatting without changing files
+	uv run ruff format --check .
+
+typecheck: ## Run strict Pyright checks
+	uv run pyright
+
+check: lint format-check typecheck test ## Run the complete local quality gate
+
+build: ## Build the wheel and source distribution
+	rm -rf dist
+	uv build
+
+demos-smoke: ## Run the inexpensive executable demos
+	uv run python demo/basic_pipeline.py
+	uv run python demo/parquet_pipeline.py
+	uv run python demo/reduction_pipeline.py
+	uv run python demo/generate_market_data.py smoke
+
+release-check: check build ## Validate source and build release artifacts
+
+publish: test ## Run tests, bump patch version, build, and publish to PyPI
+	uv version --bump patch
+	rm -rf dist
+	uv build
+	uv publish
+
+clean: ## Remove caches, coverage data, and build artifacts
+	rm -rf .pytest_cache .ruff_cache .hypothesis htmlcov build dist
+	rm -f .coverage coverage.xml
+	find . -type d \( -path './.git' -o -path './.venv' \) -prune -o -type d -name __pycache__ -exec rm -rf {} +

duckpd-0.0.2/PKG-INFO

@@ -0,0 +1,139 @@
+Metadata-Version: 2.5
+Name: duckpd
+Version: 0.0.2
+Summary: A lazy pandas-shaped DataFrame powered by DuckDB
+Project-URL: Homepage, https://github.com/quantbert/duckpd
+Project-URL: Repository, https://github.com/quantbert/duckpd
+Project-URL: Issues, https://github.com/quantbert/duckpd/issues
+Project-URL: Changelog, https://github.com/quantbert/duckpd/blob/main/docs/CHANGELOG.md
+Author: QuantBert
+License: MIT License
+        
+        Copyright (c) 2026 QuantBert
+        
+        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.
+License-File: LICENSE
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Database
+Classifier: Topic :: Scientific/Engineering
+Classifier: Typing :: Typed
+Requires-Python: >=3.11
+Requires-Dist: duckdb<1.6,>=1.5
+Requires-Dist: pandas<3.1,>=3.0
+Requires-Dist: pyarrow>=18
+Description-Content-Type: text/markdown
+
+# duckpd
+
+DuckPD is an experimental lazy DataFrame library with a pandas-shaped frontend
+and DuckDB as its execution engine.
+
+> [!WARNING]
+> **DuckPD is a work in progress and is not yet recommended for
+> production-critical workloads.** The API and supported pandas semantics may
+> change between `0.x` releases, and many pandas operations are intentionally
+> unsupported. Validate results and resource behavior for each intended
+> workload before adopting it.
+
+DuckPD intentionally supports a small, explicit subset of pandas rather than
+silently falling back to materializing a complete pandas DataFrame. See the
+[release policy](docs/RELEASES.md) for the pre-`1.0` stability policy.
+
+## Current capabilities
+
+- Lazy pandas, Arrow, Parquet, DuckDB table, and read-only SQL sources.
+- Column selection, boolean filtering, arithmetic expressions, `assign`,
+  `sort_values`, and `limit`.
+- Eager DataFrame and Series `count`, `size`, `sum`, `mean`, `min`, and `max`
+	reductions over numeric and boolean data, including `skipna`, `min_count`,
+	and DataFrame `numeric_only` support.
+- Explicit lazy indexes with `set_index()`/`reset_index()` and source
+	`index=`/`order_by=` declarations.
+- Explicit pandas collection, bounded `head`, Arrow tables and record batches,
+  physical plan inspection, and direct Parquet writes.
+- Session-level memory, spill-directory, temporary-size, and thread settings.
+- Rejection of ambiguous cross-frame alignment and mutating SQL.
+
+## Example
+
+```python
+import duckpd as pd
+
+orders = pd.read_parquet("orders/*.parquet")
+
+result = (
+    orders[orders["status"] == "paid"]
+    .assign(net=lambda frame: frame["amount"] - frame["refund_amount"])
+    .sort_values("net", ascending=False)[["order_id", "net"]]
+    .limit(100)
+)
+
+print(result.explain())
+preview = result.head(10)
+result.write_parquet("largest-paid-orders.parquet")
+pandas_result = result.collect()
+```
+
+Transformations above are lazy. `explain()`, `head()`, `collect()`, Arrow output,
+and file output are explicit execution boundaries. `limit()` stays lazy while
+`head()` returns a bounded pandas preview.
+
+## Demos
+
+Small runnable programs are available in [demo/](demo/README.md):
+
+```bash
+uv run python demo/basic_pipeline.py
+uv run python demo/parquet_pipeline.py
+uv run python demo/reduction_pipeline.py
+uv run python demo/generate_market_data.py
+uv run python demo/market_data_demo.py
+```
+
+See the [benchmark results](docs/BENCHMARK.md) for performance and memory
+comparisons between DuckPD and pandas across 100 MB, 1 GB, and 5 GB datasets.
+
+## Development
+
+```bash
+uv sync --frozen --group dev
+make check
+make build
+```
+
+GNU Make is optional. The equivalent commands are:
+
+```bash
+uv run pytest
+uv run ruff check .
+uv run ruff format --check .
+uv run pyright
+uv build
+```
+
+See the [documentation index](docs/README.md) for the implementation roadmap,
+architecture decisions, benchmarks, research, and changelog.

duckpd-0.0.2/README.md

@@ -0,0 +1,90 @@
+# duckpd
+
+DuckPD is an experimental lazy DataFrame library with a pandas-shaped frontend
+and DuckDB as its execution engine.
+
+> [!WARNING]
+> **DuckPD is a work in progress and is not yet recommended for
+> production-critical workloads.** The API and supported pandas semantics may
+> change between `0.x` releases, and many pandas operations are intentionally
+> unsupported. Validate results and resource behavior for each intended
+> workload before adopting it.
+
+DuckPD intentionally supports a small, explicit subset of pandas rather than
+silently falling back to materializing a complete pandas DataFrame. See the
+[release policy](docs/RELEASES.md) for the pre-`1.0` stability policy.
+
+## Current capabilities
+
+- Lazy pandas, Arrow, Parquet, DuckDB table, and read-only SQL sources.
+- Column selection, boolean filtering, arithmetic expressions, `assign`,
+  `sort_values`, and `limit`.
+- Eager DataFrame and Series `count`, `size`, `sum`, `mean`, `min`, and `max`
+	reductions over numeric and boolean data, including `skipna`, `min_count`,
+	and DataFrame `numeric_only` support.
+- Explicit lazy indexes with `set_index()`/`reset_index()` and source
+	`index=`/`order_by=` declarations.
+- Explicit pandas collection, bounded `head`, Arrow tables and record batches,
+  physical plan inspection, and direct Parquet writes.
+- Session-level memory, spill-directory, temporary-size, and thread settings.
+- Rejection of ambiguous cross-frame alignment and mutating SQL.
+
+## Example
+
+```python
+import duckpd as pd
+
+orders = pd.read_parquet("orders/*.parquet")
+
+result = (
+    orders[orders["status"] == "paid"]
+    .assign(net=lambda frame: frame["amount"] - frame["refund_amount"])
+    .sort_values("net", ascending=False)[["order_id", "net"]]
+    .limit(100)
+)
+
+print(result.explain())
+preview = result.head(10)
+result.write_parquet("largest-paid-orders.parquet")
+pandas_result = result.collect()
+```
+
+Transformations above are lazy. `explain()`, `head()`, `collect()`, Arrow output,
+and file output are explicit execution boundaries. `limit()` stays lazy while
+`head()` returns a bounded pandas preview.
+
+## Demos
+
+Small runnable programs are available in [demo/](demo/README.md):
+
+```bash
+uv run python demo/basic_pipeline.py
+uv run python demo/parquet_pipeline.py
+uv run python demo/reduction_pipeline.py
+uv run python demo/generate_market_data.py
+uv run python demo/market_data_demo.py
+```
+
+See the [benchmark results](docs/BENCHMARK.md) for performance and memory
+comparisons between DuckPD and pandas across 100 MB, 1 GB, and 5 GB datasets.
+
+## Development
+
+```bash
+uv sync --frozen --group dev
+make check
+make build
+```
+
+GNU Make is optional. The equivalent commands are:
+
+```bash
+uv run pytest
+uv run ruff check .
+uv run ruff format --check .
+uv run pyright
+uv build
+```
+
+See the [documentation index](docs/README.md) for the implementation roadmap,
+architecture decisions, benchmarks, research, and changelog.