pharmadata 0.1.0__tar.gz

pharmadata-0.1.0/LICENSE

@@ -0,0 +1,177 @@
+
+                                 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

pharmadata-0.1.0/NOTICE

@@ -0,0 +1,139 @@
+This product bundles software and data that originate from other projects.
+The Apache License, Version 2.0 applies to this product as a whole; the
+notices below identify what is third-party and under what terms it may be
+redistributed.
+
+--------------------------------------------------------------------------------
+1. Upstream R packages (code, data and documentation)
+--------------------------------------------------------------------------------
+
+Derived from:
+
+  * pharmaverseadam - "ADaM Test Data for the 'Pharmaverse' Family of
+    Packages", taken from an upstream development version
+    https://github.com/pharmaverse/pharmaverseadam
+    shipped as the pharmadata.pharmaverseadam collection
+  * pharmaversesdtm - "SDTM Test Data for the 'Pharmaverse' Family of
+    Packages", taken from an upstream development version
+    https://github.com/pharmaverse/pharmaversesdtm
+    shipped as the pharmadata.pharmaversesdtm collection
+
+Both upstream packages are also published on CRAN. This product has its own
+version (0.1.0) that does not identify an upstream release; data-raw/export
+scripts read the upstream sources, so running them against your own checkout
+reproduces these inputs without the shipped parquet files.
+
+Both are licensed under the Apache License, Version 2.0 or later (their
+DESCRIPTION files declare `License: Apache License (>= 2)` and
+`License: Apache License (>= 2.0)` respectively), and their copyright
+holders - the entries with role "cph" in the Authors@R field of their
+DESCRIPTION files - are:
+
+  Copyright Cytel Inc.
+  Copyright F. Hoffmann-La Roche AG
+  Copyright GlaxoSmithKline LLC
+
+The ADaM datasets come from the admiral template scripts
+(https://github.com/pharmaverse/admiral, Apache-2.0) applied to the SDTM
+datasets above. Their labels, types, mandatory flags and roles come from
+`pharmaverseadam/inst/extdata/adams-specs.json`, drawn from the CDISC ADaM
+Implementation Guide.
+
+Changes made by this product (per Apache-2.0 Section4(b)):
+
+  * `.rda` -> Parquet conversion, plus per-dataset metadata tables
+    exported alongside (the pharmaverseadam and pharmaversesdtm collections);
+  * bytes that are invalid UTF-8 in the upstream `.rda` (for example the
+    0x92 right single quotation mark in the `ts` dataset) are re-decoded as
+    CP1252, and an empty character is exported as a Parquet null - the missing
+    value it stands for. No other value is edited;
+  * column labels and roles are additionally embedded in the Parquet files as
+    Arrow field metadata, and a merged `_meta.json` plus generated IDE stubs and
+    MkDocs documentation are added.
+
+--------------------------------------------------------------------------------
+2. The CDISC pilot submission packages, redistributed directly
+--------------------------------------------------------------------------------
+
+The pharmadata.cdiscpilotadam and pharmadata.cdiscpilotsdtm collections are
+built from two archives published by the PHUSE Scripts repository:
+
+  * data/adam/cdiscpilot_update1.zip
+  * data/sdtm/cdiscpilot_update2.zip
+    https://github.com/phuse-org/phuse-scripts
+
+They are the CDISC SDTM/ADaM Pilot Project's own submission packages as updated
+by the PHUSE Test Data Factory working group (the repository's
+`data/sdtm/README.md` names those updates). The PHUSE Scripts repository is
+licensed under the MIT (Expat) licence, names no copyright holder, and is in its
+`LICENSE.md`. The data inside the archives is CDISC's; section 3 records the
+terms it carries.
+
+Changes made by this product (per Apache-2.0 Section4(b)):
+
+  * SAS transport files (`.xpt`) -> Parquet conversion, and the per-dataset
+    metadata tables are exported alongside (the cdiscpilotadam and cdiscpilotsdtm
+    collections, sharing a common helper);
+  * a blank character is exported as a Parquet null, the missing value it stands
+    for: the SAS transport format has no missing character value, so a text
+    variable a record does not use is written there as an empty string;
+  * the dataset label, the structure, the mandatory flags and the roles are read
+    from the Define-XML 2.0 each archive ships, and the column labels from the
+    transport files' own variable labels with the Define-XML as fallback;
+  * those labels and roles are additionally embedded in the Parquet files as
+    Arrow field metadata, and a merged `_meta.json` plus generated IDE stubs and
+    MkDocs documentation are added.
+
+No other data value is edited: the conversion is a container change, and the
+metadata published beside the data is the one the submission package itself
+records.
+
+--------------------------------------------------------------------------------
+3. The CDISC pilot project data at the root of the chain
+--------------------------------------------------------------------------------
+
+Both routes above lead back to the CDISC SDTM/ADaM Pilot Project, whose files are
+published at
+
+  https://github.com/cdisc-org/sdtm-adam-pilot-project
+
+and that repository states a Terms of Use for the data, of which the following
+conditions travel with any redistribution:
+
+  * attribution back to CDISC is required, and users must not be misled about
+    the origin of the data;
+  * the data may not be sublicensed or distributed for a fee;
+  * the data may not be used to compete with CDISC, or in any manner that
+    violates a law or regulation;
+  * the data is provided "AS IS", without warranties of any kind, and CDISC
+    disclaims the currency, accuracy, relevance and completeness of it.
+
+This product is distributed free of charge, attributes CDISC as the source of the
+underlying data, and makes no claim that the data is fit for any regulatory or
+analytical purpose: it is synthetic test data for exercising software.
+
+Note that the pilot project's Terms of Use also ask that the data not be
+"disassembled, reverse engineered, decompiled, modified, or altered". The
+upstream pharmaverse packages already rework it, and this product's Parquet
+conversion is a format change that reads a blank character as the missing value
+it stands for. If a stricter reading of that clause matters to your use case, the
+regeneration programs in `data-raw/` rebuild the same datasets from the upstream
+sources without shipping Parquet files.
+
+--------------------------------------------------------------------------------
+4. CDISC standards documentation
+--------------------------------------------------------------------------------
+
+CDISC standards and Implementation Guides are copyrighted by CDISC, which grants
+open public use of its published standards (https://www.cdisc.org/). This product
+reproduces the variable names, labels, mandatory flags and roles recorded in the
+upstream specs and Define-XML files; it does not reproduce the Implementation
+Guide documents themselves.
+
+--------------------------------------------------------------------------------
+5. No endorsement
+--------------------------------------------------------------------------------
+
+Cytel, F. Hoffmann-La Roche AG, GlaxoSmithKline LLC, CDISC, PHUSE and the
+pharmaverse initiative are not affiliated with this product and do not endorse it.
+The datasets carry no real subject data: they are simulated test data.

pharmadata-0.1.0/PKG-INFO

@@ -0,0 +1,71 @@
+Metadata-Version: 2.4
+Name: pharmadata
+Version: 0.1.0
+Summary: CDISC SDTM and ADaM test datasets in Python for clinical programming
+Keywords: cdisc,adam,sdtm,clinical-trials,test-data,pyarrow,polars
+License-Expression: Apache-2.0
+License-File: LICENSE
+License-File: NOTICE
+Classifier: Development Status :: 3 - Alpha
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Developers
+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 :: Scientific/Engineering
+Classifier: Typing :: Typed
+Requires-Dist: pyarrow>=15
+Requires-Dist: polars>=1.31
+Requires-Dist: tzdata>=2024.1
+Requires-Dist: pandas>=3.0 ; extra == 'pandas'
+Requires-Python: >=3.11
+Project-URL: Homepage, https://github.com/ynsec37/pharmadata
+Project-URL: Repository, https://github.com/ynsec37/pharmadata
+Project-URL: Documentation, https://ynsec37.github.io/pharmadata/
+Project-URL: Issues, https://github.com/ynsec37/pharmadata/issues
+Project-URL: Changelog, https://github.com/ynsec37/pharmadata/blob/main/docs/changelog.md
+Provides-Extra: pandas
+Description-Content-Type: text/markdown
+
+<div align="center">
+
+<em>CDISC SDTM and ADaM Test Datasets in Python for Clinical Programming</em>
+
+[![CI](https://github.com/ynsec37/pharmadata/actions/workflows/ci.yml/badge.svg)](https://github.com/ynsec37/pharmadata/actions/workflows/ci.yml)
+[![Coverage](https://codecov.io/gh/ynsec37/pharmadata/branch/main/graph/badge.svg)](https://codecov.io/gh/ynsec37/pharmadata)
+[![PyPI](https://img.shields.io/pypi/v/pharmadata.svg)](https://pypi.org/project/pharmadata/)
+
+</div>
+
+## Installation
+
+```bash
+pip install pharmadata
+```
+
+## Quick start
+
+```python
+from pharmadata import pharmaverseadam as adam
+
+adsl = adam.adsl
+adsl_meta = adam.adsl_meta
+
+# Other datasets
+from pharmadata import pharmaversesdtm, cdiscpilotadam, cdiscpilotsdtm
+```
+
+Default output is polars, `set_output_pandas()` switches to pandas.
+
+## Credits
+
+Data from the following projects. They are gratefully acknowledged for making the data available.
+
+- [pharmaverseadam](https://github.com/pharmaverse/pharmaverseadam)
+- [pharmaversesdtm](https://github.com/pharmaverse/pharmaversesdtm)
+- [phuse-org/phuse-scripts](https://github.com/phuse-org/phuse-scripts)
+
+See [NOTICE](NOTICE)

pharmadata-0.1.0/README.md

@@ -0,0 +1,39 @@
+<div align="center">
+
+<em>CDISC SDTM and ADaM Test Datasets in Python for Clinical Programming</em>
+
+[![CI](https://github.com/ynsec37/pharmadata/actions/workflows/ci.yml/badge.svg)](https://github.com/ynsec37/pharmadata/actions/workflows/ci.yml)
+[![Coverage](https://codecov.io/gh/ynsec37/pharmadata/branch/main/graph/badge.svg)](https://codecov.io/gh/ynsec37/pharmadata)
+[![PyPI](https://img.shields.io/pypi/v/pharmadata.svg)](https://pypi.org/project/pharmadata/)
+
+</div>
+
+## Installation
+
+```bash
+pip install pharmadata
+```
+
+## Quick start
+
+```python
+from pharmadata import pharmaverseadam as adam
+
+adsl = adam.adsl
+adsl_meta = adam.adsl_meta
+
+# Other datasets
+from pharmadata import pharmaversesdtm, cdiscpilotadam, cdiscpilotsdtm
+```
+
+Default output is polars, `set_output_pandas()` switches to pandas.
+
+## Credits
+
+Data from the following projects. They are gratefully acknowledged for making the data available.
+
+- [pharmaverseadam](https://github.com/pharmaverse/pharmaverseadam)
+- [pharmaversesdtm](https://github.com/pharmaverse/pharmaversesdtm)
+- [phuse-org/phuse-scripts](https://github.com/phuse-org/phuse-scripts)
+
+See [NOTICE](NOTICE)

pharmadata-0.1.0/conftest.py

@@ -0,0 +1,64 @@
+"""Fixtures for every collected item: the tests/ suite and the src/ doctests.
+
+Sits at the root - the common ancestor of the two trees - so the docstring
+examples collected from src/ (``--doctest-modules``) run with the same fixtures
+as the tests.
+"""
+
+from collections.abc import Iterator, MutableMapping
+
+import pytest
+
+import pharmadata
+from pharmadata import (
+    cdiscpilotadam,
+    cdiscpilotsdtm,
+    pharmaverseadam,
+    pharmaversesdtm,
+    set_output_polars,
+)
+from pharmadata._core import collection, data, meta
+
+_FACADES = (cdiscpilotadam, cdiscpilotsdtm, pharmaverseadam, pharmaversesdtm)
+
+# Every @cache in _core: file-reading functions cache parsed parquet/JSON, so a
+# test patching the data source must start from a cold cache.
+_CACHED = (
+    data.data_dir,
+    data.raw_meta,
+    data.dataset_names,
+    data.load_dataset,
+    data.dataset_doc,
+    data.shape,
+    data._meta_tables_table,
+    data._meta_specs_table,
+    collection._load_polars,
+    collection._load_pandas,
+    meta.build,
+)
+
+
+@pytest.fixture(autouse=True)
+def _reset_output_format() -> Iterator[None]:
+    """Leave the output format on polars around every item, doctests included."""
+    set_output_polars()
+    yield
+    set_output_polars()
+
+
+@pytest.fixture(autouse=True)
+def _clear_caches() -> Iterator[None]:
+    """Drop every @cache so no test reads another test's parsed data or metadata."""
+    for fn in _CACHED:
+        fn.cache_clear()
+    yield
+    for fn in _CACHED:
+        fn.cache_clear()
+
+
+@pytest.fixture(autouse=True)
+def _doctest_namespace(doctest_namespace: MutableMapping[str, object]) -> None:
+    """Give the src/ docstring examples the package-level names they call."""
+    doctest_namespace["pharmadata"] = pharmadata
+    for facade in _FACADES:
+        doctest_namespace[facade.__name__.rsplit(".", 1)[-1]] = facade