glaurlex 0.1.1__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,215 @@
1
+ # Byte-compiled / optimized / DLL files
2
+ __pycache__/
3
+ *.py[codz]
4
+ *$py.class
5
+
6
+ # C extensions
7
+ *.so
8
+
9
+ # Distribution / packaging
10
+ .Python
11
+ build/
12
+ develop-eggs/
13
+ dist/
14
+ downloads/
15
+ eggs/
16
+ .eggs/
17
+ lib/
18
+ lib64/
19
+ parts/
20
+ sdist/
21
+ var/
22
+ wheels/
23
+ share/python-wheels/
24
+ *.egg-info/
25
+ .installed.cfg
26
+ *.egg
27
+ MANIFEST
28
+
29
+ # PyInstaller
30
+ # Usually these files are written by a python script from a template
31
+ # before PyInstaller builds the exe, so as to inject date/other infos into it.
32
+ *.manifest
33
+ *.spec
34
+
35
+ # Installer logs
36
+ pip-log.txt
37
+ pip-delete-this-directory.txt
38
+
39
+ # Unit test / coverage reports
40
+ htmlcov/
41
+ .tox/
42
+ .nox/
43
+ .coverage
44
+ .coverage.*
45
+ .cache
46
+ nosetests.xml
47
+ coverage.xml
48
+ *.cover
49
+ *.py.cover
50
+ *.lcov
51
+ .hypothesis/
52
+ .pytest_cache/
53
+ cover/
54
+
55
+ # Translations
56
+ *.mo
57
+ *.pot
58
+
59
+ # Django stuff:
60
+ *.log
61
+ local_settings.py
62
+ db.sqlite3
63
+ db.sqlite3-journal
64
+
65
+ # Flask stuff:
66
+ instance/
67
+ .webassets-cache
68
+
69
+ # Scrapy stuff:
70
+ .scrapy
71
+
72
+ # Sphinx documentation
73
+ docs/_build/
74
+
75
+ # PyBuilder
76
+ .pybuilder/
77
+ target/
78
+
79
+ # Jupyter Notebook
80
+ .ipynb_checkpoints
81
+
82
+ # IPython
83
+ profile_default/
84
+ ipython_config.py
85
+
86
+ # pyenv
87
+ # For a library or package, you might want to ignore these files since the code is
88
+ # intended to run in multiple environments; otherwise, check them in:
89
+ # .python-version
90
+
91
+ # pipenv
92
+ # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
93
+ # However, in case of collaboration, if having platform-specific dependencies or dependencies
94
+ # having no cross-platform support, pipenv may install dependencies that don't work, or not
95
+ # install all needed dependencies.
96
+ # Pipfile.lock
97
+
98
+ # uv
99
+ # Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
100
+ # This is especially recommended for binary packages to ensure reproducibility, and is more
101
+ # commonly ignored for libraries.
102
+ # uv.lock
103
+
104
+ # poetry
105
+ # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
106
+ # This is especially recommended for binary packages to ensure reproducibility, and is more
107
+ # commonly ignored for libraries.
108
+ # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
109
+ # poetry.lock
110
+ # poetry.toml
111
+
112
+ # pdm
113
+ # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
114
+ # pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
115
+ # https://pdm-project.org/en/latest/usage/project/#working-with-version-control
116
+ # pdm.lock
117
+ # pdm.toml
118
+ .pdm-python
119
+ .pdm-build/
120
+
121
+ # pixi
122
+ # Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
123
+ # pixi.lock
124
+ # Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
125
+ # in the .venv directory. It is recommended not to include this directory in version control.
126
+ .pixi/*
127
+ !.pixi/config.toml
128
+
129
+ # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
130
+ __pypackages__/
131
+
132
+ # Celery stuff
133
+ celerybeat-schedule*
134
+ celerybeat.pid
135
+
136
+ # Redis
137
+ *.rdb
138
+ *.aof
139
+ *.pid
140
+
141
+ # RabbitMQ
142
+ mnesia/
143
+ rabbitmq/
144
+ rabbitmq-data/
145
+
146
+ # ActiveMQ
147
+ activemq-data/
148
+
149
+ # SageMath parsed files
150
+ *.sage.py
151
+
152
+ # Environments
153
+ .env
154
+ .envrc
155
+ .venv
156
+ env/
157
+ venv/
158
+ ENV/
159
+ env.bak/
160
+ venv.bak/
161
+
162
+ # Spyder project settings
163
+ .spyderproject
164
+ .spyproject
165
+
166
+ # Rope project settings
167
+ .ropeproject
168
+
169
+ # mkdocs/Zensical documentation
170
+ /site
171
+
172
+ # mypy
173
+ .mypy_cache/
174
+ .dmypy.json
175
+ dmypy.json
176
+
177
+ # Pyre type checker
178
+ .pyre/
179
+
180
+ # pytype static type analyzer
181
+ .pytype/
182
+
183
+ # Cython debug symbols
184
+ cython_debug/
185
+
186
+ # PyCharm
187
+ # JetBrains specific template is maintained in a separate JetBrains.gitignore that can
188
+ # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
189
+ # and can be added to the global gitignore or merged into this file. For a more nuclear
190
+ # option (not recommended) you can uncomment the following to ignore the entire idea folder.
191
+ # .idea/
192
+
193
+ # Visual Studio Code
194
+ # Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore that
195
+ # can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
196
+ # and can be added to the global gitignore or merged into this file. However, if you prefer, you
197
+ # could uncomment the following to ignore the entire vscode folder
198
+ # .vscode/
199
+ # Temporary file for partial code execution
200
+ tempCodeRunnerFile.py
201
+
202
+ # Ruff stuff:
203
+ .ruff_cache/
204
+
205
+ # PyPI configuration file
206
+ .pypirc
207
+
208
+ # Marimo
209
+ marimo/_static/
210
+ marimo/_lsp/
211
+ __marimo__/
212
+
213
+ # Streamlit
214
+ .streamlit/secrets.toml
215
+
@@ -0,0 +1,69 @@
1
+ # Changelog
2
+
3
+ ## 0.1.1 (2026-11-16)
4
+
5
+ First release published to PyPI as `glaurlex`. No API or numerical changes compared to 0.1.0.
6
+
7
+ ### Changed
8
+
9
+ - Package metadata (`[project.urls]`) and `README.md` installation instructions (`pip install glaurlex`) updated for PyPI.
10
+ - Release workflow publishes distributions to PyPI via trusted publishing.
11
+
12
+ ## 0.1.0 (2026-11-08)
13
+
14
+ First public release. The library is the computational core of the GLAURLex web application,
15
+ extracted into its own package. The entries below record what changed against that code.
16
+
17
+ ### Added
18
+
19
+ - `glaurlex.core.io`: Salamanca TXT parsing (`parse_salamanca`, `read_salamanca`,
20
+ `parse_stimulus_map`, `detect_topic_codes`, `decode_bytes`). The level map is a parameter
21
+ (`level_labels`) instead of being hard-coded.
22
+ - `graph.build_cooccurrence_graph`, `graph.partition_to_map`,
23
+ `graph_compare.pairwise_similarity_table`, `groups.select_informant_rows`,
24
+ `inference.qq_points`, `variables.split_variables`, `variables.is_numeric_like`.
25
+
26
+ ### Changed
27
+
28
+ - Every identifier, column, result key and message is in English; "topic" replaces "tema".
29
+ Main renames:
30
+
31
+ | Before | Now |
32
+ |---|---|
33
+ | `estadisticas_df(df, informantes_df)` | `type_statistics(df, informant_ids=None)` |
34
+ | columns `disponibilidad`, `aparición`, `freq_rel`, `freq_acum` | `availability`, `appearance`, `rel_freq`, `cum_freq` |
35
+ | `informant_metrics` keys `total_disp`, `mean_disp` | `total_availability`, `mean_availability` |
36
+ | `CODIGO_INFORMANTE`, `user_id` | `informant_id` (informants and topic frames) |
37
+ | Salamanca columns `EXPERIMENTO_ID`, `NIVEL_CODIGO`, `NIVEL` | `experiment_id`, `level_code`, `level` |
38
+ | Salamanca topic names `tema_<code>` | `topic_<code>` (`topic_prefix` parameter) |
39
+ | `process_salamanca`, `detect_theme_codes` | `parse_salamanca`, `detect_topic_codes` |
40
+ | `bigrams_for_tema` | `bigrams_for_topic` |
41
+ | `describe_series` keys `media`, `mediana`, `rango`, `varianza`, `asimetría`, `curtosis` | `mean`, `median`, `range`, `variance`, `skewness`, `kurtosis` |
42
+ | `PROFILE_METRICS` (dict of Spanish labels) `n_nodos`, `n_aristas`, `densidad`, `grado_prom`, `fuerza_prom`, `clustering_prom`, `diametro`, `long_camino_prom`, `componentes`, `frac_mayor_componente`, `asortatividad`, `n_comunidades`, `modularidad` | tuple of keys `n_nodes`, `n_edges`, `density`, `avg_degree`, `avg_strength`, `avg_clustering`, `diameter`, `avg_path_length`, `components`, `largest_component_fraction`, `assortativity`, `n_communities`, `modularity` |
43
+ | `ONLY_A`, `ONLY_B`, `BOTH` = `"solo A"`, `"solo B"`, `"ambos"` | `"only_a"`, `"only_b"`, `"both"` |
44
+ | permutation keys `observado`, `media_nula`, `sd_nula`, `nula`, `jaccard_nodos`, `jaccard_aristas` | `observed`, `null_mean`, `null_sd`, `null`, `jaccard_nodes`, `jaccard_edges` |
45
+
46
+ - Errors and notes in results are short codes (`insufficient_data`, `zero_path_length`, ...)
47
+ instead of sentences.
48
+ - `small_world_indices` returns a `SmallWorld` dataclass and raises `ValueError` on a directed,
49
+ disconnected or single-node graph.
50
+ - Long-running functions report progress only through `progress_cb(done, total)`; `status_cb` is
51
+ removed. `graph_stats` no longer takes `include_small_world`; call `small_world_indices`.
52
+ - `apply_group` raises `ValueError` on an unknown operator or a malformed `{"op": ...}` rule.
53
+
54
+ ### Fixed
55
+
56
+ - `apply_group` understands `{"op": "between", "min": a, "max": b}` and `{"op": ">", "value": v}`
57
+ rules and the `<` and `>` operators. Before, such rules were ignored, so groups that used them
58
+ silently contained every informant; they now filter.
59
+ - Rows with equal sort keys come out in the same order on every platform: `type_statistics` breaks
60
+ availability ties by `type`, `edge_weight_divergence` by edge, and `pairwise_similarity_table`
61
+ keeps pair order. Before, the order of tied rows, and with it their `cum_freq` in
62
+ `type_statistics`, could depend on the CPU.
63
+ - Post-hoc comparisons in `compare_groups` test the right pairs of levels when a level has fewer
64
+ than two observations.
65
+ - `decode_bytes` tries utf-8-sig, cp1252 and latin-1 in that order. Statistical encoding detection
66
+ misread Spanish cp1252 files (`niño` became `ni±o`).
67
+ - Per-informant availability is summed in sorted order, so informants with the same responses in a
68
+ different order tie exactly. This can change rank-test p-values (exact instead of asymptotic
69
+ Mann-Whitney).