ducta 0.1.0__tar.gz

ducta-0.1.0/LICENSE

@@ -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.

ducta-0.1.0/PKG-INFO

@@ -0,0 +1,358 @@
+Metadata-Version: 2.4
+Name: ducta
+Version: 0.1.0
+Summary: A unified data-pipeline framework for batch, streaming, ML, and hybrid workflows.
+License: Apache-2.0
+License-File: LICENSE
+Keywords: data-pipeline,etl,spark,streaming,orchestration,workflow,data-quality,mlops
+Author: Faustino Lopez Ramos
+Author-email: faustinolopezramos@gmail.com
+Maintainer: Faustino Lopez Ramos
+Maintainer-email: faustinolopezramos@gmail.com
+Requires-Python: >=3.10,<3.14
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Environment :: Web Environment
+Classifier: Framework :: FastAPI
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
+Classifier: Topic :: System :: Distributed Computing
+Provides-Extra: all
+Provides-Extra: api
+Provides-Extra: database
+Provides-Extra: databricks
+Provides-Extra: mlops
+Provides-Extra: monitoring
+Provides-Extra: spark
+Requires-Dist: GitPython (>=3.1.0,<4.0.0) ; extra == "api" or extra == "all"
+Requires-Dist: PyYAML (>=6.0,<7.0)
+Requires-Dist: aiosqlite (>=0.20.0,<0.21.0) ; extra == "api" or extra == "database" or extra == "all"
+Requires-Dist: alembic (>=1.14.0,<2.0.0) ; extra == "api" or extra == "database" or extra == "all"
+Requires-Dist: asyncpg (>=0.30.0,<0.31.0) ; extra == "api" or extra == "database" or extra == "all"
+Requires-Dist: bcrypt (>=4.0.0,<5.0.0) ; extra == "api" or extra == "all"
+Requires-Dist: databricks-connect (>=14.0.0,<15.0.0) ; extra == "databricks"
+Requires-Dist: fastapi (>=0.104.0,<1.0.0) ; extra == "api" or extra == "all"
+Requires-Dist: loguru (>=0.7.0,<0.8.0)
+Requires-Dist: mlflow (>=2.10.0,<3.0.0) ; extra == "mlops" or extra == "all"
+Requires-Dist: msgpack (>=1.0.0,<2.0.0) ; extra == "api" or extra == "all"
+Requires-Dist: numpy (>=1.24.0,<2.0.0) ; extra == "mlops" or extra == "all"
+Requires-Dist: pandas (>=2.0.0,<3.0.0)
+Requires-Dist: prometheus-client (>=0.17.0,<0.18.0) ; extra == "monitoring" or extra == "all"
+Requires-Dist: psycopg2-binary (>=2.9.0,<3.0.0) ; extra == "api" or extra == "database" or extra == "all"
+Requires-Dist: pyarrow (>=15.0.0,<20.0.0) ; extra == "spark" or extra == "all"
+Requires-Dist: pydantic (>=2.0.0,<3.0.0)
+Requires-Dist: pydantic-settings (>=2.0.0,<3.0.0)
+Requires-Dist: pyspark (>=3.5.0,<4.0.0) ; extra == "spark" or extra == "all"
+Requires-Dist: python-dotenv (>=1.0.0,<2.0.0)
+Requires-Dist: python-jose[cryptography] (>=3.3.0,<4.0.0) ; extra == "api" or extra == "all"
+Requires-Dist: redis (>=5.0.0,<6.0.0) ; extra == "api" or extra == "all"
+Requires-Dist: rich (>=13.0.0,<14.0.0)
+Requires-Dist: scikit-learn (>=1.3.0,<2.0.0) ; extra == "mlops" or extra == "all"
+Requires-Dist: scipy (>=1.11.0,<2.0.0) ; extra == "mlops" or extra == "all"
+Requires-Dist: setuptools (>=68.0.0) ; (python_version >= "3.12") and (extra == "spark" or extra == "all")
+Requires-Dist: sqlalchemy[asyncio] (>=2.0.0,<3.0.0) ; extra == "api" or extra == "database" or extra == "all"
+Requires-Dist: sqlglot (>=23.0.0,<31.0.0)
+Requires-Dist: tomli (>=1.2.0,<2.0.0) ; python_version < "3.11"
+Requires-Dist: tomli-w (>=1.0.0,<2.0.0)
+Requires-Dist: typing-extensions (>=4.3.0,<5.0.0)
+Requires-Dist: uvicorn[standard] (>=0.23.0,<0.24.0) ; extra == "api" or extra == "all"
+Requires-Dist: watchdog (>=4.0.0,<5.0.0) ; extra == "api" or extra == "all"
+Project-URL: Changelog, https://github.com/faustinolopezramos/ducta/blob/main/CHANGELOG.md
+Project-URL: Documentation, https://github.com/faustinolopezramos/ducta/tree/main/docs
+Project-URL: Homepage, https://github.com/faustinolopezramos/ducta
+Project-URL: Issues, https://github.com/faustinolopezramos/ducta/issues
+Project-URL: Repository, https://github.com/faustinolopezramos/ducta
+Project-URL: Source, https://github.com/faustinolopezramos/ducta
+Description-Content-Type: text/markdown
+
+<div align="center">
+
+# Ducta
+
+**Build, run, and trust data pipelines — batch, streaming, and machine learning — from simple configuration.**
+
+[![Python](https://img.shields.io/badge/python-3.10%20|%203.11%20|%203.12%20|%203.13-blue)](https://www.python.org/)
+[![License: Apache 2.0](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE)
+[![Status: Alpha](https://img.shields.io/badge/status-alpha-orange)](CHANGELOG.md)
+
+</div>
+
+Ducta lets you describe a data pipeline in a few config files, write your
+transformations as ordinary Python functions, and run them with one command —
+locally or on the cloud. Data-quality checks, experiment tracking, and a
+tamper-evident record of every run come built in, so you can trust the results.
+
+> **Status:** Alpha (`0.1.0`). Things may change between releases — see the
+> [CHANGELOG](CHANGELOG.md).
+
+> **Using Ducta vs. contributing to it.** If you just want to *use* Ducta,
+> install the package from PyPI — `pip install ducta` (see [Install](#install)) —
+> and you never touch this source tree. **This repository is organized for
+> contributors** working on Ducta itself: its layout, tooling, and the
+> [Development setup](#development-setup) below are built around that. The
+> feature sections in between explain what Ducta does — useful context whichever
+> side you're on.
+
+---
+
+## Why Ducta
+
+- **One tool for every pipeline** — batch, streaming, and machine learning, the same way.
+- **You write plain Python** — Ducta runs your functions in the right order and handles the data plumbing.
+- **Runs anywhere** — your laptop (local Spark) or a cluster (Apache Spark / Databricks), no code changes.
+- **Quality you can enforce** — automatic checks on your data that can warn or stop a run before bad data spreads.
+- **Reproducible & auditable** — every run leaves a signed certificate of what ran, on which data, and with what result.
+- **Work how you like** — a command line, a REST API, or a visual web app.
+
+---
+
+## Install
+
+Requires **Python 3.10–3.13**. Once a release is published, the intended
+end-user install is:
+
+```bash
+pip install "ducta[spark]"        # running pipelines (start here)
+pip install "ducta[mlops]"        # + experiment tracking & model registry
+pip install "ducta[api]"          # + web app / REST API
+pip install "ducta[all]"          # everything above
+```
+
+> **Spark is required to run a pipeline.** Bare `pip install ducta` gives you the
+> library and the CLI, but every execution context builds a Spark session, so
+> commands that load a project (`ducta start`, `ducta config list-pipelines`, …)
+> need the `spark` extra. Install `ducta[spark]` unless you only want to import
+> Ducta as a library.
+
+> **`databricks` is a separate, mutually exclusive extra.** Use
+> `pip install "ducta[databricks]"` *instead of* `[spark]`, never alongside it:
+> `databricks-connect` ships its own `pyspark` package and overwrites the real
+> one, after which local execution fails. For that reason it is not part of
+> `[all]`.
+
+> **Contributing / working from source?** Don't use `pip` — set up the dev
+> environment with Poetry (or Docker) instead. See [Development setup](#development-setup).
+
+---
+
+## Get started in 5 minutes
+
+Scaffold a ready-to-run project and execute your first pipeline:
+
+```bash
+# 1. Create a project (Medallion layout: bronze → silver → gold)
+ducta template --template medallion_basic --project-name my_project --format yaml
+cd my_project
+
+# 2. See what pipelines it comes with
+ducta config list-pipelines
+
+# 3. Run one for a date range
+ducta start --env dev --pipeline <pipeline-name> \
+  --start-date 2026-01-01 --end-date 2026-01-31
+```
+
+Other starting points: `--template ml_ready`, `streaming_core`, or `hybrid`.
+Run `ducta --help` to see every command.
+
+---
+
+## Anatomy of a pipeline
+
+A Ducta project is **your transformation code** plus a few **config files** that
+wire everything together. Here is a complete, minimal pipeline.
+
+**1. Your transformation** — a normal Python function. Ducta passes in the input
+data (a Spark DataFrame) and the run's date range, and you return the result.
+
+```python
+# nodes.py
+def clean_sales(sales, start_date, end_date):
+    return sales.dropna()          # any DataFrame transformation
+```
+
+**2. Where the data comes from and goes** (`config/input.yaml`, `config/output.yaml`):
+
+```yaml
+# input.yaml
+raw_sales:
+  format: "csv"
+  filepath: "${input_path}/sales.csv"
+  options: { header: "true", inferSchema: "true" }
+```
+
+```yaml
+# output.yaml
+core.analytics.sales_clean:
+  format: "parquet"
+  write_mode: "overwrite"
+```
+
+**3. The step and the pipeline** (`config/nodes.yaml`, `config/pipelines.yaml`):
+
+```yaml
+# nodes.yaml — one entry per transformation
+clean_sales:
+  module: "nodes"                 # your nodes.py
+  function: "clean_sales"
+  input: ["raw_sales"]            # passed to your function, in order
+  output: ["core.analytics.sales_clean"]
+
+# pipelines.yaml — order your steps into a pipeline
+sales_daily:
+  type: batch
+  nodes: ["clean_sales"]
+```
+
+**4. Run it:**
+
+```bash
+ducta start --env dev --pipeline sales_daily \
+  --start-date 2026-01-01 --end-date 2026-01-31
+```
+
+Ducta reads `raw_sales`, runs `clean_sales`, checks the output, writes
+`sales_clean`, and records a run certificate — all from that config.
+
+---
+
+## Enforce data quality
+
+Add checks to any step. A **quality gate** decides whether a failure just warns
+or actually stops the run.
+
+```yaml
+# nodes.yaml
+clean_sales:
+  module: "nodes"
+  function: "clean_sales"
+  input: ["raw_sales"]
+  output: ["core.analytics.sales_clean"]
+  data_quality:
+    checks:
+      row_count: { min: 1000 }              # expect at least 1,000 rows
+      null_rate: { column: "id", max: 0.0 } # no missing ids
+      duplicates: { columns: ["id"] }       # ids must be unique
+    quality_gate:
+      max_errors: 0                          # any error blocks downstream steps
+```
+
+Built-in checks include row counts, null rates, ranges, duplicates, schema,
+freshness, and drift — and you can add your own.
+
+---
+
+## Use the web app
+
+Prefer a visual workspace? Launch the built-in server and open it in your browser:
+
+```bash
+ducta server start --port 8000
+# Web app & API docs:  http://localhost:8000
+```
+
+From there you can browse pipelines, edit configuration, launch runs, and watch
+logs stream live.
+
+---
+
+## Command cheatsheet
+
+| Command | What it does |
+|---------|--------------|
+| `ducta template --template medallion_basic --project-name NAME` | Scaffold a new project |
+| `ducta config list-pipelines` | List the pipelines in a project |
+| `ducta start --env dev --pipeline NAME` | Run a batch / ML pipeline |
+| `ducta stream run --pipeline NAME` | Start a streaming pipeline |
+| `ducta quality run --input data.parquet --config checks.yaml` | Check a data file's quality |
+| `ducta server start --port 8000` | Launch the web app + API |
+| `ducta certify verify --run-id RUN_ID` | Verify a run certificate (from `.ducta/runs/`) |
+| `ducta --help` | Full command reference |
+
+---
+
+## Development setup
+
+This repository is where Ducta is built — the following gets you a working copy
+to develop or contribute against. Two ways in:
+
+### Native — Poetry is the source of truth
+
+Requires **Python 3.10–3.13** (a JRE is only needed if you work on the Spark paths).
+
+```bash
+git clone <repo-url> && cd ducta
+poetry install --extras all           # all runtime extras + dev tools
+poetry run ducta --help
+poetry run pytest                     # run the test suite (tests/)
+```
+
+> Use `--extras all`, **not** `--all-extras`: the latter also installs the
+> `databricks` extra, whose `databricks-connect` overwrites `pyspark` and breaks
+> local Spark (and therefore most of the test suite).
+
+`pyproject.toml` + `poetry.lock` define every dependency — there is **no
+hand-maintained `requirements.txt`**. (The docs build keeps a minimal
+`docs/requirements.txt`, and the Docker image exports a locked constraints file
+at build time; both are generated from the lock, never edited by hand.) Docs
+dependencies are an optional group: `poetry install --with docs`.
+
+### Docker — the "works on any OS" fallback
+
+If the native toolchain misbehaves on your OS (Spark/JRE, native wheels, Python
+version), develop against a container instead. It runs the **full app — React
+UI + API on one port** (the same thing `ducta ui` does):
+
+```bash
+docker compose up --build
+# UI:  http://localhost:8000/        ·        API docs: /docs
+```
+
+Run any CLI command in that same reproducible environment:
+
+```bash
+docker compose run --rm ducta config list-pipelines
+docker compose run --rm ducta --help
+```
+
+### Frontend
+
+The visual workspace lives in `src/ducta/ui` (React + Vite). The API serves its
+compiled output, so build it once and `ducta ui` picks it up (the Docker image
+does this for you):
+
+```bash
+cd src/ducta/ui && npm ci && npm run build
+```
+
+See `src/ducta/ui/README.md` for live UI development.
+
+---
+
+## Documentation
+
+- [Getting started](docs/getting_started.rst)
+- [Installation](docs/installation.rst)
+- [Configuration reference](docs/configuration.rst)
+- [CLI usage](docs/cli_usage.rst)
+- [Databricks setup](docs/databricks_setup.rst)
+- [Best practices](docs/best_practices.rst)
+
+Building on top of Ducta or contributing? Each module has its own guide under
+`src/ducta/<module>/README.md`.
+
+---
+
+## License
+
+[Apache License 2.0](LICENSE). Copyright © Faustino Lopez Ramos.
+