taxonomic-entity-augmentation 1.0.2__tar.gz

taxonomic_entity_augmentation-1.0.2/LICENSE

@@ -0,0 +1,182 @@
+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.

taxonomic_entity_augmentation-1.0.2/NOTICE

@@ -0,0 +1,8 @@
+bio-tea
+Copyright 2026 tznurmin
+
+This package includes a modified UniProt organism list derived from speclist.txt.
+The vendored organism list is distributed under the Creative Commons Attribution
+4.0 License (CC BY 4.0). See src/bio_tea/data/attribution.txt.
+
+Downloaded TEA_curated_data material is external and separately licensed.

taxonomic_entity_augmentation-1.0.2/PKG-INFO

@@ -0,0 +1,30 @@
+Metadata-Version: 2.4
+Name: taxonomic-entity-augmentation
+Version: 1.0.2
+Summary: Taxonomic Entity Augmentation
+Author: tznurmin
+License-Expression: Apache-2.0
+Project-URL: Repository, https://github.com/tznurmin/bio-tea
+Project-URL: Issues, https://github.com/tznurmin/bio-tea/issues
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: PyYAML>=6.0
+Dynamic: license-file
+
+# Taxonomic Entity Augmentation (TEA)
+
+Taxonomic Entity Augmentation for biological texts.
+
+Install:
+
+```bash
+python -m pip install taxonomic-entity-augmentation
+```
+
+Use:
+
+```python
+from bio_tea import TEA
+```

taxonomic_entity_augmentation-1.0.2/README.md

@@ -0,0 +1,15 @@
+# Taxonomic Entity Augmentation (TEA)
+
+Taxonomic Entity Augmentation for biological texts.
+
+Install:
+
+```bash
+python -m pip install taxonomic-entity-augmentation
+```
+
+Use:
+
+```python
+from bio_tea import TEA
+```

taxonomic_entity_augmentation-1.0.2/pyproject.toml

@@ -0,0 +1,43 @@
+[build-system]
+requires = ["setuptools>=77.0.3"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "taxonomic-entity-augmentation"
+version = "1.0.2"
+authors = [{ name = "tznurmin" }]
+description = "Taxonomic Entity Augmentation"
+readme = "README.md"
+requires-python = ">=3.9"
+license = "Apache-2.0"
+license-files = ["LICENSE", "NOTICE"]
+dependencies = [
+  "PyYAML>=6.0",
+]
+
+[project.urls]
+Repository = "https://github.com/tznurmin/bio-tea"
+Issues = "https://github.com/tznurmin/bio-tea/issues"
+
+[project.scripts]
+bio-tea-inspect = "bio_tea.datasets.cli:inspect_main"
+bio-tea-sample = "bio_tea.datasets.cli:sample_main"
+bio-tea-validate = "bio_tea.datasets.cli:validate_main"
+bio-tea-stats = "bio_tea.datasets.cli:stats_main"
+bio-tea-qa = "bio_tea.datasets.cli:qa_main"
+bio-tea-manifest-compare = "bio_tea.datasets.cli:manifest_compare_main"
+
+[tool.setuptools]
+include-package-data = true
+package-dir = { "" = "src" }
+packages = [
+  "bio_tea",
+  "bio_tea.data",
+  "bio_tea.augment",
+  "bio_tea.resources",
+  "bio_tea.transforms",
+  "bio_tea.datasets",
+]
+
+[tool.setuptools.package-data]
+"bio_tea.data" = ["species.txt", "attribution.txt"]

taxonomic_entity_augmentation-1.0.2/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

taxonomic_entity_augmentation-1.0.2/src/bio_tea/__init__.py

@@ -0,0 +1,20 @@
+# Copyright 2026 tznurmin
+#
+# 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.
+"""Top-level TEA package API."""
+
+from .core import TEA
+
+__version__ = "1.0.2"
+
+__all__ = ["TEA", "__version__"]

taxonomic_entity_augmentation-1.0.2/src/bio_tea/augment/__init__.py

@@ -0,0 +1,21 @@
+# Copyright 2026 tznurmin
+#
+# 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.
+"""Augmentation helpers.
+
+This package contains lower-level routines used by TEA's augmentation pipeline.
+"""
+
+from .windowing import is_stop, extract_sentence, maximise
+
+__all__ = ["is_stop", "extract_sentence", "maximise"]

taxonomic_entity_augmentation-1.0.2/src/bio_tea/augment/labels.py

@@ -0,0 +1,48 @@
+# Copyright 2026 tznurmin
+#
+# 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.
+"""Label construction for TEA augmentation.
+
+Input curation data uses:
+- curation_data: dict[str, list[str]]
+- location strings in "start+len" token-index format
+"""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+
+
+def build_labels(tokens: list[str], curation_data: Mapping[str, list[str]], l2l: dict[str, str] | None = None) -> list[str]:
+    labels = ['O'] * len(tokens)
+
+    for t, locations in curation_data.items():
+        t0 = t.split('/')[0]
+        label = t0[0:4].upper()
+        if l2l is not None:
+            label = l2l.get(label, 'O')
+
+        if label == 'O':
+            continue
+
+        for loc in locations:
+            t_sta, t_len = loc.split('+')
+            t_sta_i = int(t_sta)
+            t_len_i = int(t_len)
+            for idx in range(t_sta_i, t_sta_i + t_len_i):
+                if idx == t_sta_i:
+                    labels[idx] = f"B-{label}"
+                else:
+                    labels[idx] = f"I-{label}"
+
+    return labels

taxonomic_entity_augmentation-1.0.2/src/bio_tea/augment/pipeline.py

@@ -0,0 +1,97 @@
+# Copyright 2026 tznurmin
+#
+# 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.
+"""Token-level entity augmentation pipeline."""
+
+from __future__ import annotations
+
+from collections.abc import Callable, Mapping
+
+from .labels import build_labels
+from .words import extract_span_phrases
+
+
+def augment_tokens(
+    tokens: list[str],
+    curation_data: Mapping[str, list[str]],
+    *,
+    maximise: Callable[[int, list[str]], tuple[int, int]],
+    switch: Callable[[str], str],
+    scramble: Callable[..., str],
+    num_tokens: Callable[[str], int],
+    max_final_len: int,
+    scramble_tags: list[str] | None = None,
+    l2l: dict[str, str] | None = None,
+) -> dict:
+    scramble_tags = scramble_tags or []
+
+    # Scramble wordlist must be deterministic; using a set directly makes output
+    # depend on hash iteration order.
+    words: set[str] = set()
+    results: dict = {
+        'original': {},
+        'scrambled': {},
+        'switched': {},
+        'all': {},
+    }
+
+    # Labels are constructed once over the full token sequence.
+    labels = build_labels(tokens, curation_data, l2l=l2l)
+
+    # Determine which phrases are eligible for scrambling.
+    for t, locations in curation_data.items():
+        t0 = t.split('/')[0]
+        if t0 in scramble_tags:
+            words.update(extract_span_phrases(tokens, {t0: locations}))
+
+        for loc in locations:
+            s0 = int(loc.split('+')[0])
+            s, e = maximise(s0, tokens)
+            results['original'][f"{s},{e}"] = ' '.join(tokens[s:e + 1])
+
+    results['labels'] = labels
+
+    # Deterministic ordering for scramble: longer phrases first avoids partial
+    # replacements when phrases overlap.
+    words_list = sorted(words, key=lambda s: (-len(s), s))
+
+    for pos, window_text in results['original'].items():
+        transformations = {
+            'switched': [switch],
+            'scrambled': [scramble],
+            'all': [switch, scramble],
+        }
+        extra_params = {scramble: [words_list]}
+
+        for out_key, tfs in transformations.items():
+            current = window_text
+
+            for idx, tf in enumerate(tfs):
+                base = current
+                tries = 5
+
+                while tries > 0:
+                    params = extra_params.get(tf, [])
+                    candidate = tf(base, *params)
+                    if num_tokens(candidate) <= max_final_len:
+                        current = candidate
+                        break
+                    tries -= 1
+
+                if tries == 0:
+                    break
+
+                if idx == len(tfs) - 1:
+                    results[out_key][pos] = current
+
+    return results

taxonomic_entity_augmentation-1.0.2/src/bio_tea/augment/windowing.py

@@ -0,0 +1,104 @@
+# Copyright 2026 tznurmin
+#
+# 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.
+"""Sentence windowing for TEA.
+
+This module operates on TEA's token stream and provides sentence-boundary and
+window-expansion helpers used by the augmentation pipeline.
+"""
+
+from __future__ import annotations
+
+from typing import Callable, Iterable, List, Sequence, Tuple
+
+
+def is_stop(word: str, non_stops: Iterable[str]) -> bool:
+    """Return True when the token is treated as a sentence boundary."""
+
+    if not word or word[-1] != ".":
+        return False
+
+    # Special-case: treat '].' as a stop even though it's short.
+    if word != "]." and (len(word) < 3 or word.lower() in set(map(str.lower, non_stops))):
+        return False
+
+    return True
+
+
+def extract_sentence(sp: int, tokens: Sequence[str], non_stops: Iterable[str]) -> Tuple[int, int]:
+    """Extract the sentence span (s, e) containing token index sp.
+
+    A "sentence" is a maximal contiguous run of tokens not interrupted by is_stop.
+    """
+
+    s = sp
+    e = sp
+
+    while e < len(tokens) - 1 and not is_stop(tokens[e], non_stops):
+        e += 1
+
+    while s > 0 and not is_stop(tokens[s - 1], non_stops):
+        s -= 1
+
+    return (s, e)
+
+
+def maximise(
+    loc: int,
+    tokens: Sequence[str],
+    maxlen: int,
+    token_counter: Callable[[str], int],
+    non_stops: Iterable[str],
+    rng,
+) -> Tuple[int, int]:
+    """Expand a token window by adding complete neighbouring sentences.
+
+    Expansion starts from the sentence containing the target span, attempts to
+    add left context first, then samples remaining left/right context while
+    preserving the token-budget constraint.
+    """
+
+    r_count = 0
+    f_count = 0
+    l_count = 0
+
+    s, e = extract_sentence(loc, tokens, non_stops)
+
+    s_done = s == 0
+    e_done = e == len(tokens) - 1
+
+    while not (s_done and e_done):
+        l_count += 1
+        if not s_done and (r_count < 2 or rng.randint(0, 1) == 0):
+            new_s, _ = extract_sentence(s - 1, tokens, non_stops)
+            if token_counter(" ".join(tokens[new_s : e + 1])) < maxlen:
+                r_count += 1
+                s = new_s
+                if s == 0:
+                    s_done = True
+            else:
+                s_done = True
+        else:
+            if e >= len(tokens) - 1:
+                e_done = True
+                continue
+            _, new_e = extract_sentence(e + 1, tokens, non_stops)
+            if token_counter(" ".join(tokens[s : new_e + 1])) < maxlen:
+                f_count += 1
+                e = new_e
+                if e == len(tokens) - 1:
+                    e_done = True
+            else:
+                e_done = True
+
+    return s, e

taxonomic_entity_augmentation-1.0.2/src/bio_tea/augment/words.py

@@ -0,0 +1,30 @@
+# Copyright 2026 tznurmin
+#
+# 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.
+"""Utilities for extracting word/phrase lists from curated spans."""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+
+
+def extract_span_phrases(tokens: list[str], curation_subset: Mapping[str, list[str]]) -> set[str]:
+    """Return set of ' '.join(tokens[start:start+len]) for each curated location."""
+    word_list: set[str] = set()
+    for _, locs in curation_subset.items():
+        for loc in locs:
+            s, e = loc.split('+')
+            s_i = int(s)
+            e_i = int(e)
+            word_list.add(' '.join(tokens[s_i:s_i + e_i]))
+    return word_list