recsys-eval 0.1.0__tar.gz

recsys_eval-0.1.0/.gitignore

@@ -0,0 +1,16 @@
+__pycache__/
+*.py[cod]
+.venv/
+venv/
+dist/
+build/
+*.egg-info/
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.hypothesis/
+.coverage
+htmlcov/
+.DS_Store
+.idea/
+.vscode/

recsys_eval-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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.

recsys_eval-0.1.0/PKG-INFO

@@ -0,0 +1,124 @@
+Metadata-Version: 2.4
+Name: recsys-eval
+Version: 0.1.0
+Summary: Offline evaluation and promotion gating for recommender systems.
+Project-URL: Source, https://github.com/ZynclaveTech/recsys
+Project-URL: Issues, https://github.com/ZynclaveTech/recsys/issues
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: evaluation,mlops,ndcg,ranking-metrics,recommender-systems
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+
+# recsys-eval
+
+Offline evaluation and promotion gating for recommender systems.
+
+> **Status: alpha.** Feature-complete for v0.1 — metrics, fixture, ranker
+> protocol, scoring, preflight checks, and promotion gate. The API may still
+> move before 1.0.
+
+Built around one claim: the useful question is usually not *"how good is this
+model"* but *"is this candidate worse than the one already in production"*.
+Those need different machinery, and conflating them is how teams end up with a
+dashboard full of numbers nobody can act on.
+
+## The whole loop
+
+```python
+from recsys_eval import Fixture, Interaction, RelevancePolicy, preflight
+from recsys_eval.gate import GatePolicy, run_gate
+
+fixture = Fixture.from_interactions(
+    events,  # your logs, as Interaction(...)
+    candidates=serving_index,  # your pool, passed explicitly
+    holdout_start=cutoff,
+    holdout_end=cutoff + timedelta(days=7),
+    policy=RelevancePolicy(positive_kinds=frozenset({"like", "share", "save"})),
+)
+
+preflight(build_fixture, candidate, incumbent)  # prove the harness works
+
+verdict = run_gate(
+    candidate,
+    incumbent,
+    fixture,
+    policy=GatePolicy(gated_metrics=["ndcg@10", "recall@50"]),
+    recorder=save_audit_row,
+)
+if verdict.promoted:
+    deploy(candidate)
+```
+
+Implementing a ranker is two methods:
+
+```python
+class MyRanker:
+    def prepare(self, candidates): ...  # build an index, once
+    def rank(self, user, k, exclude): ...  # return bare ids, best first
+```
+
+A runnable end-to-end version lives in `examples/quickstart.py`.
+
+## Install
+
+```bash
+pip install recsys-eval
+```
+
+No dependencies. The metrics are pure stdlib; the fixture and gate layers talk
+to your data through protocols rather than through pandas, numpy, or an ORM.
+
+## Metrics
+
+```python
+from recsys_eval import ndcg_at_k, recall_at_k, catalog_coverage
+
+# Graded relevance: say that a share is worth more than a like, and NDCG
+# will reward ranking shares higher.
+ndcg_at_k(["post_a", "post_b"], {"post_a": 3.0, "post_b": 1.0}, k=10)
+
+# Relevant items your candidate index never even offered stay in the
+# denominator, so a shrinking index shows up as a falling score.
+recall_at_k(["post_a"], {"post_a", "post_c"}, k=10)  # 0.5, not 1.0
+
+# Read this beside NDCG. A ranker can raise NDCG by collapsing onto
+# universally-popular items, and every per-user metric is blind to that.
+catalog_coverage(rankings, catalog_size=50_000, k=10)
+```
+
+| Function | Relevance | Sensitive to rank |
+|---|---|---|
+| `ndcg_at_k` | graded | yes |
+| `recall_at_k` | binary | no |
+| `precision_at_k` | binary | no |
+| `average_precision_at_k` | binary | yes |
+| `reciprocal_rank_at_k` | binary | yes |
+| `hit_rate_at_k` | binary | no |
+| `catalog_coverage` | — | no |
+
+All are **per-user** quantities. MAP@k, MRR@k and NDCG@k are their
+macro-averages — naming them honestly keeps the aggregation choice visible at
+the call site, where it belongs.
+
+Every function returns `0.0` — never `NaN`, never raising — on degenerate
+input, so a user with no usable labels cannot poison a macro-average.
+
+## What these numbers are not
+
+They are not a measure of absolute recommendation quality. In any real system
+the candidate pool is truncated, which structurally caps Recall below 1.0 no
+matter how good the model is.
+
+**Do not quote them as system quality. Do compare them run over run, candidate
+against incumbent.**
+
+## License
+
+Apache-2.0

recsys_eval-0.1.0/README.md

@@ -0,0 +1,106 @@
+# recsys-eval
+
+Offline evaluation and promotion gating for recommender systems.
+
+> **Status: alpha.** Feature-complete for v0.1 — metrics, fixture, ranker
+> protocol, scoring, preflight checks, and promotion gate. The API may still
+> move before 1.0.
+
+Built around one claim: the useful question is usually not *"how good is this
+model"* but *"is this candidate worse than the one already in production"*.
+Those need different machinery, and conflating them is how teams end up with a
+dashboard full of numbers nobody can act on.
+
+## The whole loop
+
+```python
+from recsys_eval import Fixture, Interaction, RelevancePolicy, preflight
+from recsys_eval.gate import GatePolicy, run_gate
+
+fixture = Fixture.from_interactions(
+    events,  # your logs, as Interaction(...)
+    candidates=serving_index,  # your pool, passed explicitly
+    holdout_start=cutoff,
+    holdout_end=cutoff + timedelta(days=7),
+    policy=RelevancePolicy(positive_kinds=frozenset({"like", "share", "save"})),
+)
+
+preflight(build_fixture, candidate, incumbent)  # prove the harness works
+
+verdict = run_gate(
+    candidate,
+    incumbent,
+    fixture,
+    policy=GatePolicy(gated_metrics=["ndcg@10", "recall@50"]),
+    recorder=save_audit_row,
+)
+if verdict.promoted:
+    deploy(candidate)
+```
+
+Implementing a ranker is two methods:
+
+```python
+class MyRanker:
+    def prepare(self, candidates): ...  # build an index, once
+    def rank(self, user, k, exclude): ...  # return bare ids, best first
+```
+
+A runnable end-to-end version lives in `examples/quickstart.py`.
+
+## Install
+
+```bash
+pip install recsys-eval
+```
+
+No dependencies. The metrics are pure stdlib; the fixture and gate layers talk
+to your data through protocols rather than through pandas, numpy, or an ORM.
+
+## Metrics
+
+```python
+from recsys_eval import ndcg_at_k, recall_at_k, catalog_coverage
+
+# Graded relevance: say that a share is worth more than a like, and NDCG
+# will reward ranking shares higher.
+ndcg_at_k(["post_a", "post_b"], {"post_a": 3.0, "post_b": 1.0}, k=10)
+
+# Relevant items your candidate index never even offered stay in the
+# denominator, so a shrinking index shows up as a falling score.
+recall_at_k(["post_a"], {"post_a", "post_c"}, k=10)  # 0.5, not 1.0
+
+# Read this beside NDCG. A ranker can raise NDCG by collapsing onto
+# universally-popular items, and every per-user metric is blind to that.
+catalog_coverage(rankings, catalog_size=50_000, k=10)
+```
+
+| Function | Relevance | Sensitive to rank |
+|---|---|---|
+| `ndcg_at_k` | graded | yes |
+| `recall_at_k` | binary | no |
+| `precision_at_k` | binary | no |
+| `average_precision_at_k` | binary | yes |
+| `reciprocal_rank_at_k` | binary | yes |
+| `hit_rate_at_k` | binary | no |
+| `catalog_coverage` | — | no |
+
+All are **per-user** quantities. MAP@k, MRR@k and NDCG@k are their
+macro-averages — naming them honestly keeps the aggregation choice visible at
+the call site, where it belongs.
+
+Every function returns `0.0` — never `NaN`, never raising — on degenerate
+input, so a user with no usable labels cannot poison a macro-average.
+
+## What these numbers are not
+
+They are not a measure of absolute recommendation quality. In any real system
+the candidate pool is truncated, which structurally caps Recall below 1.0 no
+matter how good the model is.
+
+**Do not quote them as system quality. Do compare them run over run, candidate
+against incumbent.**
+
+## License
+
+Apache-2.0

recsys_eval-0.1.0/pyproject.toml

@@ -0,0 +1,39 @@
+[project]
+name = "recsys-eval"
+version = "0.1.0"
+description = "Offline evaluation and promotion gating for recommender systems."
+readme = "README.md"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+keywords = [
+    "recommender-systems",
+    "evaluation",
+    "ndcg",
+    "ranking-metrics",
+    "mlops",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3 :: Only",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Typing :: Typed",
+]
+
+# Deliberately empty. The metrics are pure stdlib, and the fixture and gate
+# layers talk to your data through protocols rather than through pandas,
+# numpy, or an ORM. Adding a dependency here should require an argument.
+dependencies = []
+
+[project.urls]
+Source = "https://github.com/ZynclaveTech/recsys"
+Issues = "https://github.com/ZynclaveTech/recsys/issues"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/recsys_eval"]

recsys_eval-0.1.0/src/recsys_eval/__init__.py

@@ -0,0 +1,86 @@
+"""Offline evaluation and promotion gating for recommender systems.
+
+The package is built around one claim: the useful question is not "how good is
+this model" but "is this candidate worse than the one already in production".
+Those need different machinery, and conflating them is how teams end up with a
+dashboard full of numbers that nobody can act on.
+
+See :mod:`recsys_eval.metrics` for the metric definitions.
+"""
+
+from __future__ import annotations
+
+import importlib.metadata
+
+from recsys_eval.checks import (
+    CheckFailed,
+    assert_deterministic,
+    assert_discriminating,
+    assert_reproducible,
+    assert_within_unit_interval,
+    preflight,
+)
+from recsys_eval.fixture import Fixture
+from recsys_eval.gate import (
+    Decision,
+    GatePolicy,
+    GateResult,
+    decide,
+    run_gate,
+)
+from recsys_eval.metrics import (
+    average_precision_at_k,
+    catalog_coverage,
+    hit_rate_at_k,
+    ndcg_at_k,
+    precision_at_k,
+    recall_at_k,
+    reciprocal_rank_at_k,
+)
+from recsys_eval.protocols import Ranker
+from recsys_eval.scoring import (
+    DEFAULT_KS,
+    DEFAULT_METRICS,
+    METRIC_NAMES,
+    Scores,
+    score,
+)
+from recsys_eval.types import Aggregate, Interaction, RelevancePolicy
+
+# Read from installed metadata rather than repeated here. Two hand-maintained
+# copies of a version drift, and the release workflow checks the tag against
+# pyproject.toml only -- so a stale literal would ship silently and misreport
+# itself in every bug report that quotes it.
+__version__ = importlib.metadata.version("recsys-eval")
+
+__all__ = [
+    "DEFAULT_KS",
+    "DEFAULT_METRICS",
+    "METRIC_NAMES",
+    "Aggregate",
+    "CheckFailed",
+    "Decision",
+    "Fixture",
+    "GatePolicy",
+    "GateResult",
+    "Interaction",
+    "Ranker",
+    "RelevancePolicy",
+    "Scores",
+    "__version__",
+    "assert_deterministic",
+    "assert_discriminating",
+    "assert_reproducible",
+    "assert_within_unit_interval",
+    "average_precision_at_k",
+    "catalog_coverage",
+    "decide",
+    "hit_rate_at_k",
+    "ndcg_at_k",
+    "precision_at_k",
+    "preflight",
+    "recall_at_k",
+    "reciprocal_rank_at_k",
+    "run_gate",
+    "score",
+]