modus-py 0.1.0a1__tar.gz

modus_py-0.1.0a1/.gitignore

@@ -0,0 +1,218 @@
+# 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

modus_py-0.1.0a1/LICENSE

@@ -0,0 +1,28 @@
+Copyright (c) 2026, Chloe Elvin
+
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

modus_py-0.1.0a1/PKG-INFO

@@ -0,0 +1,110 @@
+Metadata-Version: 2.4
+Name: modus-py
+Version: 0.1.0a1
+Summary: Schema-driven, unit-aware Polars transform engine.
+License: BSD-3-Clause
+License-File: LICENSE
+Requires-Python: >=3.12
+Requires-Dist: astropy<8.0.0,>=7.0.0
+Requires-Dist: polars<2.0.0,>=1.0.0
+Requires-Dist: pydantic<3.0.0,>=2.0.0
+Provides-Extra: dev
+Requires-Dist: pyright>=1.1; extra == 'dev'
+Requires-Dist: pytest-mock; extra == 'dev'
+Requires-Dist: pytest-ruff; extra == 'dev'
+Requires-Dist: pytest>=8; extra == 'dev'
+Requires-Dist: ruff>=0.15.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# modus
+
+Schema-driven, unit-aware Polars transform engine.
+
+modus pairs `ModusFrame` — a Polars DataFrame with per-column Astropy unit
+metadata — with `FrameTransform`, a builder-pattern engine for expressing
+timeseries transform pipelines (grouping, cleaning, deriving, filtering, and
+aggregating) declaratively, while keeping unit metadata accurate throughout.
+
+## Installation
+
+```
+pip install modus-py
+```
+
+## Quick start
+
+```python
+import astropy.units as u
+import polars
+import modus
+
+frame = modus.ModusFrame(
+    data=polars.DataFrame({"hoist_pressure1": [101.3, 98.7]}),
+    units={"hoist_pressure1": u.kPa},
+)
+
+velocity = frame.col("distance") / frame.col("time")  # UnitExpr; unit propagates
+frame = frame.with_columns(velocity=velocity)
+```
+
+```python
+from datetime import timedelta
+import modus
+
+result = (
+    modus.FrameTransform()
+    .add_grouper(modus.DataGap("chunk", gap_seconds=60))
+    .add_grouper(modus.EventSequence("body_up_event", source="dump_body_up_sts", value=1, within="chunk"))
+    .add_cleaner(modus.Interpolate("hoist_pressure1_kpa", within="chunk"))
+    .add_filter(modus.SuppressLeadingEvent("body_up_event", within_column="chunk"))
+    .add_filter(modus.SuppressTrailingEvent("body_up_event"))
+    .group_by("chunk", "body_up_event")
+    .add_aggregation(modus.Mean("hoist_pressure1_kpa", output_name="mean_hoist_pressure1_kpa"))
+    .add_aggregation(modus.Duration(output_name="body_up_duration_s"))
+    .apply(frame)
+)
+
+labelled = result.labelled      # ModusFrame -- timeseries with grouper columns added
+aggregated = result.aggregated  # ModusFrame -- one row per (chunk, body_up_event) group
+```
+
+## Custom units
+
+modus ships an extensible unit registry, in the same spirit as Astropy's own
+enabled-units model:
+
+```python
+import astropy.units as u
+import modus
+
+modus.units.registry.register("kgcm2", u.def_unit("kgcm2", 98.0665 * u.kPa))
+```
+
+## Custom derivations and aggregations
+
+Both extension points are plugin registries keyed by name, so a schema or
+manifest layer built on top of modus can construct bespoke operations from
+declarative configuration without importing analytic-specific Python:
+
+```python
+import modus
+
+@modus.DerivationRegistry.register("state_inference")
+class StateInferenceDerivation(modus.Derivation):
+    ...
+
+@modus.AggregationRegistry.register("weighted_percentile")
+class WeightedPercentile(modus.Aggregation):
+    ...
+```
+
+## Development
+
+```
+pip install -e .[dev]
+pytest
+```
+
+## Licence
+
+MIT — see [LICENSE](LICENSE).

modus_py-0.1.0a1/README.md

@@ -0,0 +1,92 @@
+# modus
+
+Schema-driven, unit-aware Polars transform engine.
+
+modus pairs `ModusFrame` — a Polars DataFrame with per-column Astropy unit
+metadata — with `FrameTransform`, a builder-pattern engine for expressing
+timeseries transform pipelines (grouping, cleaning, deriving, filtering, and
+aggregating) declaratively, while keeping unit metadata accurate throughout.
+
+## Installation
+
+```
+pip install modus-py
+```
+
+## Quick start
+
+```python
+import astropy.units as u
+import polars
+import modus
+
+frame = modus.ModusFrame(
+    data=polars.DataFrame({"hoist_pressure1": [101.3, 98.7]}),
+    units={"hoist_pressure1": u.kPa},
+)
+
+velocity = frame.col("distance") / frame.col("time")  # UnitExpr; unit propagates
+frame = frame.with_columns(velocity=velocity)
+```
+
+```python
+from datetime import timedelta
+import modus
+
+result = (
+    modus.FrameTransform()
+    .add_grouper(modus.DataGap("chunk", gap_seconds=60))
+    .add_grouper(modus.EventSequence("body_up_event", source="dump_body_up_sts", value=1, within="chunk"))
+    .add_cleaner(modus.Interpolate("hoist_pressure1_kpa", within="chunk"))
+    .add_filter(modus.SuppressLeadingEvent("body_up_event", within_column="chunk"))
+    .add_filter(modus.SuppressTrailingEvent("body_up_event"))
+    .group_by("chunk", "body_up_event")
+    .add_aggregation(modus.Mean("hoist_pressure1_kpa", output_name="mean_hoist_pressure1_kpa"))
+    .add_aggregation(modus.Duration(output_name="body_up_duration_s"))
+    .apply(frame)
+)
+
+labelled = result.labelled      # ModusFrame -- timeseries with grouper columns added
+aggregated = result.aggregated  # ModusFrame -- one row per (chunk, body_up_event) group
+```
+
+## Custom units
+
+modus ships an extensible unit registry, in the same spirit as Astropy's own
+enabled-units model:
+
+```python
+import astropy.units as u
+import modus
+
+modus.units.registry.register("kgcm2", u.def_unit("kgcm2", 98.0665 * u.kPa))
+```
+
+## Custom derivations and aggregations
+
+Both extension points are plugin registries keyed by name, so a schema or
+manifest layer built on top of modus can construct bespoke operations from
+declarative configuration without importing analytic-specific Python:
+
+```python
+import modus
+
+@modus.DerivationRegistry.register("state_inference")
+class StateInferenceDerivation(modus.Derivation):
+    ...
+
+@modus.AggregationRegistry.register("weighted_percentile")
+class WeightedPercentile(modus.Aggregation):
+    ...
+```
+
+## Development
+
+```
+pip install -e .[dev]
+pytest
+```
+
+## Licence
+
+MIT — see [LICENSE](LICENSE).

modus_py-0.1.0a1/pyproject.toml

@@ -0,0 +1,81 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "modus-py"
+version = "0.1.0a1"
+description = "Schema-driven, unit-aware Polars transform engine."
+readme = "README.md"
+requires-python = ">=3.12"
+license = { text = "BSD-3-Clause" }  # Updated to match your choice!
+
+dependencies = [
+    "astropy>=7.0.0,<8.0.0",
+    "polars>=1.0.0,<2.0.0",
+    "pydantic>=2.0.0,<3.0.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "ruff>=0.15.0",
+    "pytest>=8",
+    "pytest-ruff",
+    "pytest-mock",
+    "pyright>=1.1",
+]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/modus"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "--tb=short -q -vv --ruff --ruff-format"
+markers = [
+    "integration: integration tests",
+]
+
+[tool.pyright]
+pythonVersion = "3.12"
+pythonPlatform = "Linux"
+include = ["src"]
+strict = []
+typeCheckingMode = "basic"
+
+[tool.ruff]
+src = ["src"]
+target-version = "py312"
+line-length = 120
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "I", "UP", "B", "C4", "PT", "RUF", "ICN", "TID"]
+ignore = ["E501"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**/*.py" = ["S101"]   # assert statements are expected in tests
+
+[tool.ruff.lint.flake8-tidy-imports]
+# modus convention: local imports are always absolute
+# (`from modus.foo.bar import XYZ`) not (`from .foo import XYZ`).
+ban-relative-imports = "all"
+
+[tool.ruff.lint.isort]
+known-local-folder = ["modus", "tests"]
+section-order = ["future", "standard-library", "third-party", "local-folder"]
+lines-after-imports = 2
+
+[tool.ruff.lint.isort.import-heading]
+standard-library = "Standard Library"
+third-party = "Third Party"
+local-folder = "Local"
+
+[tool.ruff.lint.flake8-import-conventions]
+banned-from = ["typing", "collections.abc", "dataclasses", "abc"]
+
+[tool.ruff.lint.flake8-import-conventions.aliases]
+"astropy.units" = "u"
+
+[tool.ruff.lint.flake8-import-conventions.banned-aliases]
+pandas = ["pd"]
+numpy = ["np"]
+polars = ["pl"]

modus_py-0.1.0a1/src/modus/__init__.py

@@ -0,0 +1,177 @@
+"""modus — schema-driven, unit-aware Polars transform engine.
+
+modus pairs a Polars `ModusFrame` (a DataFrame with per-column Astropy unit
+metadata) with `FrameTransform`, a builder-pattern engine for expressing
+timeseries transform pipelines — grouping, cleaning, deriving, filtering, and
+aggregating — declaratively, while keeping unit metadata accurate throughout.
+
+Quick start
+-----------
+>>> import astropy.units as u
+>>> import polars
+>>> import modus
+>>>
+>>> frame = modus.ModusFrame(
+...     data=polars.DataFrame({"hoist_pressure1": [101.3, 98.7]}),
+...     units={"hoist_pressure1": u.kPa},
+... )
+>>> velocity = frame.col("distance") / frame.col("time")  # UnitExpr; unit propagates
+>>> frame = frame.with_columns(velocity=velocity)
+
+Public surface
+--------------
+`ModusFrame`
+    Polars DataFrame paired with per-column Astropy unit metadata. Exposes
+    `~ModusFrame.col` to obtain unit-aware expressions and explicit
+    transformation methods (`~ModusFrame.with_columns`, `~ModusFrame.select`,
+    `~ModusFrame.filter`, `~ModusFrame.rename`, `~ModusFrame.drop`,
+    `~ModusFrame.sort`, `~ModusFrame.join`, `~ModusFrame.concat`) that
+    keep the unit dict accurate after each operation.
+
+`UnitExpr`
+    A `polars.Expr` paired with an `u.UnitBase`. Returned by
+    `ModusFrame.col`; supports arithmetic operator overloads (``+``, ``-``,
+    ``*``, ``/``) that propagate unit algebra alongside the Polars expression
+    tree.
+
+:data:`TIMESTAMP_COLUMN`
+    Module-level constant (``"ts"``) naming the canonical timestamp column
+    present in every timeseries `ModusFrame`.
+
+`ModusFrameBuilder`
+    Helper used to construct an `ModusFrame` from raw Polars data and unit
+    strings, parsed via `modus.units.registry`.
+
+`FrameTransform`
+    Schema-driven, unit-aware transform engine. Build up a pipeline with
+    groupers, cleaners, derivations, filters, and aggregations, then call
+    `~FrameTransform.apply` to execute it against an `ModusFrame`. Both a
+    labelled timeseries and a per-event aggregated summary are returned as a
+    `TransformResult`.
+
+`ModusError`, `FrameError`, `TransformError`
+    modus's exception hierarchy — see `modus.errors`.
+
+`modus.units.registry`
+    Shared, extensible unit registry (see `modus.units`). Register custom
+    unit strings against it, Astropy-style, before parsing them.
+
+Transform operations
+---------------------
+- Groupers: `DataGap`, `EventSequence`, `PatternSequence`
+- Cleaners: `FillForward`, `FillBackward`, `FillNull`, `Interpolate`
+- Derivations: `TimeDelta`, `Rate`, `LinearCombination`, `Formula`,
+  `ColumnExpression`, and the `Derivation` extension point with
+  `DerivationRegistry` for declarative construction by name
+- Filters: `SuppressLeadingEvent`, `SuppressTrailingEvent`,
+  `SuppressEventCrossingGrouper`
+- Aggregations: `Mean`, `Sum`, `Sem`, `Min`, `Max`, `MaxAbs`, `Std`, `First`,
+  `Last`, `Mode`, `NthValue`, `ValueSequence`, `Duration`, `Count`, and the
+  `Aggregation` extension point with `AggregationRegistry`
+- Group filters: `GroupCondition`, `GroupFilter`
+- Event views: `EventView`, `Budget`, `Rows`, `Seconds`
+"""
+
+# Local
+from modus import units
+from modus._builder import ModusFrameBuilder
+from modus.errors import FrameError, ModusError
+from modus.expr import UnitExpr
+from modus.frame import TIMESTAMP_COLUMN, ModusFrame
+from modus.transform import (
+    Aggregation,
+    AggregationRegistry,
+    Budget,
+    ColumnExpression,
+    Count,
+    DataGap,
+    Derivation,
+    DerivationRegistry,
+    Duration,
+    EventSequence,
+    EventView,
+    FillBackward,
+    FillForward,
+    FillNull,
+    First,
+    Formula,
+    FrameTransform,
+    GroupCondition,
+    GroupFilter,
+    Interpolate,
+    Last,
+    LinearCombination,
+    Max,
+    MaxAbs,
+    Mean,
+    Min,
+    Mode,
+    NthValue,
+    PatternSequence,
+    Rate,
+    Rows,
+    Seconds,
+    Sem,
+    Std,
+    Sum,
+    SuppressEventCrossingGrouper,
+    SuppressLeadingEvent,
+    SuppressTrailingEvent,
+    TimeDelta,
+    TransformError,
+    TransformResult,
+    ValueSequence,
+)
+
+
+__all__ = [
+    "TIMESTAMP_COLUMN",
+    "Aggregation",
+    "AggregationRegistry",
+    "Budget",
+    "ColumnExpression",
+    "Count",
+    "DataGap",
+    "Derivation",
+    "DerivationRegistry",
+    "Duration",
+    "EventSequence",
+    "EventView",
+    "FillBackward",
+    "FillForward",
+    "FillNull",
+    "First",
+    "Formula",
+    "FrameError",
+    "FrameTransform",
+    "GroupCondition",
+    "GroupFilter",
+    "Interpolate",
+    "Last",
+    "LinearCombination",
+    "Max",
+    "MaxAbs",
+    "Mean",
+    "Min",
+    "Mode",
+    "ModusError",
+    "ModusFrame",
+    "ModusFrameBuilder",
+    "NthValue",
+    "PatternSequence",
+    "Rate",
+    "Rows",
+    "Seconds",
+    "Sem",
+    "Std",
+    "Sum",
+    "SuppressEventCrossingGrouper",
+    "SuppressLeadingEvent",
+    "SuppressTrailingEvent",
+    "TimeDelta",
+    "TransformError",
+    "TransformResult",
+    "UnitExpr",
+    "ValueSequence",
+    "units",
+]