lens-eval 0.1.0__tar.gz

lens_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 2026 Foudil Chebbour
+
+   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.

lens_eval-0.1.0/PKG-INFO

@@ -0,0 +1,44 @@
+Metadata-Version: 2.4
+Name: lens-eval
+Version: 0.1.0
+Summary: Interpretable multi-dimension text quality metric with combiner
+Author-email: Foudil Chebbour <foudil.chebbour@gmail.com>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/foudil09/lens-eval
+Keywords: nlp,evaluation,lens,interpretable
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.23
+Requires-Dist: scipy>=1.10
+Requires-Dist: scikit-learn>=1.2
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-cov>=5.0; extra == "dev"
+Provides-Extra: encoders
+Requires-Dist: torch>=2.0; extra == "encoders"
+Requires-Dist: transformers>=4.30; extra == "encoders"
+Requires-Dist: sentence-transformers>=2.2; extra == "encoders"
+Provides-Extra: statsmodels
+Requires-Dist: statsmodels>=0.14; extra == "statsmodels"
+Provides-Extra: ebm
+Requires-Dist: interpret>=0.5; extra == "ebm"
+Provides-Extra: gbm
+Requires-Dist: lightgbm>=4.0; extra == "gbm"
+Provides-Extra: report
+Requires-Dist: jinja2>=3.1; extra == "report"
+Provides-Extra: cli
+Provides-Extra: all
+Requires-Dist: torch>=2.0; extra == "all"
+Requires-Dist: transformers>=4.30; extra == "all"
+Requires-Dist: sentence-transformers>=2.2; extra == "all"
+Requires-Dist: statsmodels>=0.14; extra == "all"
+Requires-Dist: interpret>=0.5; extra == "all"
+Requires-Dist: lightgbm>=4.0; extra == "all"
+Requires-Dist: jinja2>=3.1; extra == "all"
+Dynamic: license-file

lens_eval-0.1.0/lens_eval/__init__.py

@@ -0,0 +1,55 @@
+"""lens-eval: interpretable multi-dimension text quality scoring.
+
+Public entrypoints:
+
+    from lens_eval import LENS
+    from lens_eval import semantic_score, nli_score, naturalness_score, emotion_score
+    from lens_eval import configure   # device, paths, naturalness mode/centroid
+
+See README.md for usage.
+"""
+
+from __future__ import annotations
+
+__version__ = "0.1.0"
+
+from .encoders import (
+    DIMENSIONS,
+    configure,
+    emotion_score,
+    featurize,
+    free,
+    naturalness_score,
+    nli_score,
+    semantic_score,
+)
+from .errors import (
+    AmbiguousTaskError,
+    CombinerBackendMissing,
+    DegenerateTargetError,
+    EncoderVersionMismatchError,
+    InsufficientDataError,
+    LensEvalError,
+    ReferenceModeError,
+)
+from .lens import LENS
+
+__all__ = [
+    "LENS",
+    "DIMENSIONS",
+    "configure",
+    "featurize",
+    "free",
+    "semantic_score",
+    "nli_score",
+    "naturalness_score",
+    "emotion_score",
+    "LensEvalError",
+    "InsufficientDataError",
+    "DegenerateTargetError",
+    "AmbiguousTaskError",
+    "ReferenceModeError",
+    "EncoderVersionMismatchError",
+    "CombinerBackendMissing",
+    "__version__",
+]

lens_eval-0.1.0/lens_eval/_validate.py

@@ -0,0 +1,85 @@
+"""Centralized structural validation for fit-time inputs.
+
+Both ``LENS.fit`` and the CLI route their inputs through this module so a
+missing ``groups`` array, an ambiguous task channel, or a malformed pairs
+matrix surfaces the *same* typed exception with the *same* error message
+regardless of where the call originated. The gateway is intentionally
+narrow — it does shape and channel checks only, no semantic validation.
+That belongs in the combiner layer.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Optional, Sequence, Tuple
+
+import numpy as np
+
+from .errors import AmbiguousTaskError
+
+
+TASK_CHANNELS = ("scores", "pairs", "ranks")
+TASK_TO_NAME = {"scores": "regression", "pairs": "pairwise", "ranks": "ranking"}
+
+
+def validate_task_channels(
+    *,
+    scores: Optional[Any] = None,
+    pairs:  Optional[Any] = None,
+    ranks:  Optional[Any] = None,
+    groups: Optional[Any] = None,
+) -> Tuple[str, str]:
+    """Resolve the task channel and validate channel-specific structure.
+
+    Returns ``(channel_name, task)`` where:
+      * ``channel_name`` is one of ``"scores" | "pairs" | "ranks"``.
+      * ``task``         is the inferred ``LENS`` task —
+                         ``"regression" | "pairwise" | "ranking"``.
+
+    Raises ``AmbiguousTaskError`` if zero or multiple channels are supplied.
+    Raises ``ValueError`` for shape / dtype / coverage issues with the chosen
+    channel (e.g. pairs must be ``(M, 2)``, ranking requires ``groups``).
+
+    Used by both ``LENS.fit`` and the CLI so the user-visible failure modes
+    are identical across entry points.
+    """
+    provided = [k for k, v in (("scores", scores), ("pairs", pairs), ("ranks", ranks))
+                if v is not None]
+    if len(provided) != 1:
+        # Zero ⇒ nothing to fit on. Two+ ⇒ which to optimise? Both are bad.
+        raise AmbiguousTaskError(
+            f"fit() / CLI needs exactly one of (scores, pairs, ranks); got {provided!r}"
+        )
+    channel = provided[0]
+    task = TASK_TO_NAME[channel]
+
+    if channel == "pairs":
+        arr = np.asarray(pairs)
+        if arr.ndim != 2 or arr.shape[1] != 2:
+            raise ValueError(
+                f"`pairs` must have shape (M, 2) of (winner_idx, loser_idx); got {arr.shape}"
+            )
+        if arr.size and not np.issubdtype(arr.dtype, np.integer):
+            # Allow float-typed indices that round to int, but reject strings /
+            # floats with fractional parts — those are user-error.
+            if not np.allclose(arr, np.round(arr)):
+                raise ValueError("`pairs` indices must be integer-valued.")
+    elif channel == "ranks":
+        # Ranking is the only channel that needs an auxiliary grouping array —
+        # lambdarank needs to know which rows belong to the same query. Without
+        # groups every row is treated as its own group, which silently
+        # collapses to "fit a regressor on rank labels" rather than learning
+        # within-query orderings. Reject upfront.
+        if groups is None:
+            raise ValueError(
+                "task='ranking' requires `groups` so lambdarank can isolate "
+                "within-query orderings — pass a per-row group-id array."
+            )
+        ranks_arr = np.asarray(ranks)
+        groups_arr = np.asarray(groups)
+        if ranks_arr.shape[0] != groups_arr.shape[0]:
+            raise ValueError(
+                f"`ranks` ({ranks_arr.shape[0]}) and `groups` ({groups_arr.shape[0]}) "
+                f"must align row-wise."
+            )
+
+    return channel, task

lens_eval-0.1.0/lens_eval/cli.py

@@ -0,0 +1,215 @@
+"""`lens-eval` CLI — thin wrapper around the Python API.
+
+    lens-eval fit \
+        --texts hyp.txt --refs ref.txt --scores scores.csv \
+        --output ./my-lens --task auto --verbose
+
+    lens-eval score \
+        --model ./my-lens \
+        --texts new_hyp.txt --refs new_ref.txt \
+        --output predictions.csv
+
+    lens-eval report ./my-lens --html report.html
+
+All three accept ``--features path.csv`` to skip encoding entirely. The
+features CSV must have one column per dimension; column order follows the
+LENS ``dimensions_used_`` for ``score``, or the user-passed ``--dimensions``
+for ``fit``.
+"""
+
+from __future__ import annotations
+
+import argparse
+import csv
+import sys
+from pathlib import Path
+from typing import List, Optional
+
+import numpy as np
+
+
+def _read_lines(path: str | Path) -> List[str]:
+    p = Path(path)
+    text = p.read_text(encoding="utf-8")
+    if p.suffix.lower() == ".csv":
+        return [row[0] for row in csv.reader(text.splitlines()) if row]
+    return [ln for ln in text.splitlines() if ln]
+
+
+def _read_scalar_csv(path: str | Path) -> np.ndarray:
+    rows: List[float] = []
+    with open(path, newline="") as f:
+        for row in csv.reader(f):
+            if not row:
+                continue
+            try:
+                rows.append(float(row[0]))
+            except ValueError:
+                # Header row — skip silently.
+                continue
+    return np.asarray(rows, dtype=float)
+
+
+def _read_features_csv(path: str | Path) -> np.ndarray:
+    arr = []
+    with open(path, newline="") as f:
+        for row in csv.reader(f):
+            if not row:
+                continue
+            try:
+                arr.append([float(x) for x in row])
+            except ValueError:
+                continue
+    return np.asarray(arr, dtype=float)
+
+
+def _read_pairs_csv(path: str | Path) -> np.ndarray:
+    pairs = []
+    with open(path, newline="") as f:
+        for row in csv.reader(f):
+            if not row:
+                continue
+            try:
+                a, b = int(row[0]), int(row[1])
+            except (ValueError, IndexError):
+                continue
+            pairs.append((a, b))
+    if not pairs:
+        raise ValueError(f"no pair rows parsed from {path}")
+    return np.asarray(pairs, dtype=int)
+
+
+def _read_int_column_csv(path: str | Path) -> np.ndarray:
+    vals: List[int] = []
+    with open(path, newline="") as f:
+        for row in csv.reader(f):
+            if not row:
+                continue
+            try:
+                vals.append(int(row[0]))
+            except ValueError:
+                continue
+    if not vals:
+        raise ValueError(f"no integer rows parsed from {path}")
+    return np.asarray(vals, dtype=int)
+
+
+def _cmd_fit(args) -> int:
+    from . import encoders as enc
+    from ._validate import validate_task_channels
+    from .lens import LENS
+
+    if args.naturalness_mode:
+        enc.configure(naturalness_mode=args.naturalness_mode)
+
+    texts  = _read_lines(args.texts)           if args.texts    else None
+    refs   = _read_lines(args.refs)            if args.refs     else None
+    feats  = _read_features_csv(args.features) if args.features else None
+    y      = _read_scalar_csv(args.scores)     if args.scores   else None
+    pairs  = _read_pairs_csv(args.pairs)       if args.pairs    else None
+    ranks  = _read_int_column_csv(args.ranks)  if args.ranks    else None
+    groups = _read_int_column_csv(args.groups) if args.groups   else None
+
+    try:
+        channel, _ = validate_task_channels(
+            scores=y, pairs=pairs, ranks=ranks, groups=groups,
+        )
+    except Exception as exc:
+        print(f"error: {exc}", file=sys.stderr)
+        return 2
+
+    lens = LENS()
+    lens.fit(
+        texts=texts,
+        references=refs,
+        features=feats,
+        scores=y, pairs=pairs, ranks=ranks, groups=groups,
+        task=args.task,
+        target_type=args.target_type,
+        selection=args.selection,
+        verbose=args.verbose,
+    )
+    lens.save(args.output)
+    if args.html:
+        lens.report_html(args.html)
+    print(f"saved fitted LENS to {args.output} ({channel} channel)")
+    return 0
+
+
+def _cmd_score(args) -> int:
+    from .lens import LENS
+
+    lens = LENS.load(args.model)
+    texts = _read_lines(args.texts)            if args.texts    else None
+    refs  = _read_lines(args.refs)             if args.refs     else None
+    feats = _read_features_csv(args.features)  if args.features else None
+
+    if texts is None and feats is None:
+        print("error: provide --texts or --features", file=sys.stderr)
+        return 2
+
+    scores = lens.score(texts, references=refs, features=feats)
+
+    out = Path(args.output)
+    with open(out, "w", newline="") as f:
+        w = csv.writer(f)
+        w.writerow(["score"])
+        for s in scores:
+            w.writerow([float(s)])
+    print(f"wrote {len(scores)} scores to {out}")
+    return 0
+
+
+def _cmd_report(args) -> int:
+    from .lens import LENS
+
+    lens = LENS.load(args.model)
+    lens.report()
+    if args.html:
+        lens.report_html(args.html)
+        print(f"wrote HTML report to {args.html}")
+    return 0
+
+
+def main(argv: Optional[List[str]] = None) -> int:
+    p = argparse.ArgumentParser(prog="lens-eval", description="lens-eval CLI")
+    sub = p.add_subparsers(dest="command", required=True)
+
+    pf = sub.add_parser("fit", help="fit a LENS combiner")
+    pf.add_argument("--texts",    help="path to candidate texts (txt or csv)")
+    pf.add_argument("--refs",     help="path to references (txt or csv)")
+    pf.add_argument("--features", help="path to precomputed feature matrix CSV (D columns)")
+    pf.add_argument("--scores",   help="scalar targets CSV (1 column)")
+    pf.add_argument("--pairs",    help="pairwise CSV: 2 columns (winner_idx, loser_idx)")
+    pf.add_argument("--ranks",    help="ranking CSV: 1 column of integer ranks")
+    pf.add_argument("--groups",   help="ranking grouping CSV: 1 column of group ids — REQUIRED with --ranks")
+    pf.add_argument("--output",   required=True, help="where to save the fitted LENS directory")
+    pf.add_argument("--task",        default="auto", choices=("auto", "regression", "pairwise", "ranking"))
+    pf.add_argument("--target-type", default="auto",
+                    choices=("auto", "bounded", "ordinal", "binary", "continuous"))
+    pf.add_argument("--selection",   default="auto",
+                    choices=("auto", "fast", "exhaustive", "glm", "glm_interactions", "ebm", "gbm"))
+    pf.add_argument("--naturalness-mode", default="centroid", choices=("centroid", "reference"))
+    pf.add_argument("--html",    help="optional: also write an HTML report to this path")
+    pf.add_argument("--verbose", action="store_true")
+    pf.set_defaults(func=_cmd_fit)
+
+    ps = sub.add_parser("score", help="score new texts with a saved LENS")
+    ps.add_argument("--model",    required=True, help="path to a saved LENS directory")
+    ps.add_argument("--texts",    help="path to candidate texts (txt or csv)")
+    ps.add_argument("--refs",     help="path to references (txt or csv)")
+    ps.add_argument("--features", help="path to precomputed feature matrix CSV (D columns)")
+    ps.add_argument("--output",   required=True, help="output CSV path for predictions")
+    ps.set_defaults(func=_cmd_score)
+
+    pr = sub.add_parser("report", help="print/render the selection report from a saved LENS")
+    pr.add_argument("model", help="path to a saved LENS directory")
+    pr.add_argument("--html", help="optional: write an HTML report to this path too")
+    pr.set_defaults(func=_cmd_report)
+
+    args = p.parse_args(argv)
+    return int(args.func(args) or 0)
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())