pydaltoolbox 0.1.0__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.
Files changed (49) hide show
  1. pydaltoolbox-0.1.0/.gitignore +223 -0
  2. pydaltoolbox-0.1.0/LICENSE +21 -0
  3. pydaltoolbox-0.1.0/PKG-INFO +154 -0
  4. pydaltoolbox-0.1.0/README.md +122 -0
  5. pydaltoolbox-0.1.0/pyproject.toml +54 -0
  6. pydaltoolbox-0.1.0/src/pydaltoolbox/__init__.py +141 -0
  7. pydaltoolbox-0.1.0/src/pydaltoolbox/adjust.py +75 -0
  8. pydaltoolbox-0.1.0/src/pydaltoolbox/autoenc.py +58 -0
  9. pydaltoolbox-0.1.0/src/pydaltoolbox/base.py +103 -0
  10. pydaltoolbox-0.1.0/src/pydaltoolbox/classification/__init__.py +28 -0
  11. pydaltoolbox-0.1.0/src/pydaltoolbox/classification/base.py +140 -0
  12. pydaltoolbox-0.1.0/src/pydaltoolbox/classification/baseline.py +24 -0
  13. pydaltoolbox-0.1.0/src/pydaltoolbox/classification/dtree.py +65 -0
  14. pydaltoolbox-0.1.0/src/pydaltoolbox/classification/ensemble.py +78 -0
  15. pydaltoolbox-0.1.0/src/pydaltoolbox/classification/knn.py +21 -0
  16. pydaltoolbox-0.1.0/src/pydaltoolbox/classification/linear.py +81 -0
  17. pydaltoolbox-0.1.0/src/pydaltoolbox/classification/naive_bayes.py +20 -0
  18. pydaltoolbox-0.1.0/src/pydaltoolbox/classification/neural.py +50 -0
  19. pydaltoolbox-0.1.0/src/pydaltoolbox/classification/svm.py +49 -0
  20. pydaltoolbox-0.1.0/src/pydaltoolbox/clustering/__init__.py +8 -0
  21. pydaltoolbox-0.1.0/src/pydaltoolbox/clustering/base.py +62 -0
  22. pydaltoolbox-0.1.0/src/pydaltoolbox/clustering/dbscan.py +55 -0
  23. pydaltoolbox-0.1.0/src/pydaltoolbox/clustering/gmm.py +53 -0
  24. pydaltoolbox-0.1.0/src/pydaltoolbox/clustering/hclust.py +67 -0
  25. pydaltoolbox-0.1.0/src/pydaltoolbox/clustering/kmeans.py +44 -0
  26. pydaltoolbox-0.1.0/src/pydaltoolbox/clustering/metrics.py +139 -0
  27. pydaltoolbox-0.1.0/src/pydaltoolbox/datasets.py +50 -0
  28. pydaltoolbox-0.1.0/src/pydaltoolbox/regression/__init__.py +19 -0
  29. pydaltoolbox-0.1.0/src/pydaltoolbox/regression/base.py +77 -0
  30. pydaltoolbox-0.1.0/src/pydaltoolbox/regression/dtree.py +28 -0
  31. pydaltoolbox-0.1.0/src/pydaltoolbox/regression/ensemble.py +31 -0
  32. pydaltoolbox-0.1.0/src/pydaltoolbox/regression/knn.py +19 -0
  33. pydaltoolbox-0.1.0/src/pydaltoolbox/regression/lm.py +18 -0
  34. pydaltoolbox-0.1.0/src/pydaltoolbox/regression/neural.py +50 -0
  35. pydaltoolbox-0.1.0/src/pydaltoolbox/regression/svm.py +42 -0
  36. pydaltoolbox-0.1.0/src/pydaltoolbox/sampling.py +113 -0
  37. pydaltoolbox-0.1.0/src/pydaltoolbox/transform/__init__.py +34 -0
  38. pydaltoolbox-0.1.0/src/pydaltoolbox/transform/balance.py +158 -0
  39. pydaltoolbox-0.1.0/src/pydaltoolbox/transform/clean.py +67 -0
  40. pydaltoolbox-0.1.0/src/pydaltoolbox/transform/curvature.py +58 -0
  41. pydaltoolbox-0.1.0/src/pydaltoolbox/transform/encode.py +48 -0
  42. pydaltoolbox-0.1.0/src/pydaltoolbox/transform/feature_selection.py +234 -0
  43. pydaltoolbox-0.1.0/src/pydaltoolbox/transform/normalize.py +89 -0
  44. pydaltoolbox-0.1.0/src/pydaltoolbox/transform/outliers.py +77 -0
  45. pydaltoolbox-0.1.0/src/pydaltoolbox/transform/pca.py +74 -0
  46. pydaltoolbox-0.1.0/src/pydaltoolbox/tune/__init__.py +6 -0
  47. pydaltoolbox-0.1.0/src/pydaltoolbox/tune/base.py +60 -0
  48. pydaltoolbox-0.1.0/src/pydaltoolbox/tune/clustering.py +29 -0
  49. pydaltoolbox-0.1.0/src/pydaltoolbox/tune/supervised.py +72 -0
@@ -0,0 +1,223 @@
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
+ # Conda environments
163
+ conda-meta/
164
+
165
+ # Spyder project settings
166
+ .spyderproject
167
+ .spyproject
168
+
169
+ # Rope project settings
170
+ .ropeproject
171
+
172
+ # mkdocs/Zensical documentation
173
+ /site
174
+
175
+ # mypy
176
+ .mypy_cache/
177
+ .dmypy.json
178
+ dmypy.json
179
+
180
+ # Pyre type checker
181
+ .pyre/
182
+
183
+ # pytype static type analyzer
184
+ .pytype/
185
+
186
+ # Cython debug symbols
187
+ cython_debug/
188
+
189
+ # PyCharm
190
+ # JetBrains specific template is maintained in a separate JetBrains.gitignore that can
191
+ # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
192
+ # and can be added to the global gitignore or merged into this file. For a more nuclear
193
+ # option (not recommended) you can uncomment the following to ignore the entire idea folder.
194
+ # .idea/
195
+
196
+ # Abstra
197
+ # Abstra is an AI-powered process automation framework.
198
+ # Ignore directories containing user credentials, local state, and settings.
199
+ # Learn more at https://abstra.io/docs
200
+ .abstra/
201
+
202
+ # Visual Studio Code
203
+ # Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore that
204
+ # can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
205
+ # and can be added to the global gitignore or merged into this file. However, if you prefer, you
206
+ # could uncomment the following to ignore the entire vscode folder
207
+ # .vscode/
208
+ # Temporary file for partial code execution
209
+ tempCodeRunnerFile.py
210
+
211
+ # Ruff stuff:
212
+ .ruff_cache/
213
+
214
+ # PyPI configuration file
215
+ .pypirc
216
+
217
+ # Marimo
218
+ marimo/_static/
219
+ marimo/_lsp/
220
+ __marimo__/
221
+
222
+ # Streamlit
223
+ .streamlit/secrets.toml
@@ -0,0 +1,21 @@
1
+ MIT License
2
+
3
+ Copyright (c) 2026 Data Analytics Lab
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining a copy
6
+ of this software and associated documentation files (the "Software"), to deal
7
+ in the Software without restriction, including without limitation the rights
8
+ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9
+ copies of the Software, and to permit persons to whom the Software is
10
+ furnished to do so, subject to the following conditions:
11
+
12
+ The above copyright notice and this permission notice shall be included in all
13
+ copies or substantial portions of the Software.
14
+
15
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18
+ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20
+ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21
+ SOFTWARE.
@@ -0,0 +1,154 @@
1
+ Metadata-Version: 2.5
2
+ Name: pydaltoolbox
3
+ Version: 0.1.0
4
+ Summary: Leveraging Experiment Lines for Data Analytics (Python port of the R daltoolbox framework)
5
+ Project-URL: Homepage, https://github.com/cefet-rj-dal/pydaltoolbox
6
+ Project-URL: Repository, https://github.com/cefet-rj-dal/pydaltoolbox
7
+ Project-URL: Bug Tracker, https://github.com/cefet-rj-dal/pydaltoolbox/issues
8
+ Author-email: Eduardo Ogasawara <eogasawara@ieee.org>
9
+ License: MIT
10
+ License-File: LICENSE
11
+ Keywords: data analytics,experiment line,machine learning,pipeline,scikit-learn
12
+ Classifier: Development Status :: 3 - Alpha
13
+ Classifier: Intended Audience :: Science/Research
14
+ Classifier: License :: OSI Approved :: MIT License
15
+ Classifier: Programming Language :: Python :: 3
16
+ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
17
+ Requires-Python: >=3.9
18
+ Requires-Dist: numpy>=1.23
19
+ Requires-Dist: pandas>=1.5
20
+ Requires-Dist: scikit-learn>=1.2
21
+ Provides-Extra: dev
22
+ Requires-Dist: build; extra == 'dev'
23
+ Requires-Dist: pytest>=7; extra == 'dev'
24
+ Requires-Dist: ruff>=0.1; extra == 'dev'
25
+ Requires-Dist: twine; extra == 'dev'
26
+ Provides-Extra: docs
27
+ Requires-Dist: ipykernel>=6; extra == 'docs'
28
+ Requires-Dist: jupytext>=1.16; extra == 'docs'
29
+ Requires-Dist: nbclient>=0.9; extra == 'docs'
30
+ Requires-Dist: nbconvert>=7; extra == 'docs'
31
+ Description-Content-Type: text/markdown
32
+
33
+ # pydaltoolbox
34
+
35
+ Python port of the R [DAL Toolbox](https://github.com/cefet-rj-dal/daltoolbox) —
36
+ *leveraging Experiment Lines for Data Analytics*.
37
+
38
+ pydaltoolbox organizes data analytics workflows (preprocessing, modeling,
39
+ evaluation, tuning, extensibility) around a consistent **Experiment Line** style
40
+ API. Its value is **not** reimplementing classic algorithms — it reuses
41
+ scikit-learn, numpy and pandas — but a **rigid, extensible interface** that wraps
42
+ them with a uniform `fit` / `action` / `evaluate` contract. Building a new method
43
+ means subclassing a base and implementing two or three methods; sampling,
44
+ evaluation and tuning come for free.
45
+
46
+ It is the foundation of the DAL Python family that will also include `pytspredit`
47
+ (time series prediction) and `pyharbinger` (time series event detection).
48
+
49
+ ---
50
+
51
+ ## Installation
52
+
53
+ > The package is in early development. A stable PyPI release is planned.
54
+
55
+ Once published, the stable version will be available on PyPI:
56
+
57
+ ```bash
58
+ pip install pydaltoolbox
59
+ ```
60
+
61
+ The development version is available on GitHub:
62
+
63
+ ```bash
64
+ pip install git+https://github.com/cefet-rj-dal/pydaltoolbox.git
65
+ ```
66
+
67
+ For a local, editable clone (for contributing or running the examples):
68
+
69
+ ```bash
70
+ git clone https://github.com/cefet-rj-dal/pydaltoolbox.git
71
+ cd pydaltoolbox
72
+ pip install -e ".[dev]"
73
+ pytest
74
+ ```
75
+
76
+ ---
77
+
78
+ ## First experiment
79
+
80
+ ```python
81
+ import pydaltoolbox as dal
82
+
83
+ iris = dal.datasets.iris()
84
+ slevels = list(iris["Species"].cat.categories)
85
+
86
+ split = dal.SampleRandom(seed=42).train_test(iris)
87
+ train, test = split["train"], split["test"]
88
+
89
+ model = dal.ClaDtree("Species", slevels, random_state=42).fit(train)
90
+
91
+ pred = model.predict(test.drop(columns="Species")) # pass only the features
92
+ ev = model.evaluate(test["Species"], pred)
93
+ print(ev["metrics"])
94
+ ```
95
+
96
+ ---
97
+
98
+ ## Documentation
99
+
100
+ - [Processed examples](examples/) — notebooks executed end to end, with real output
101
+ embedded (the "processed documentation", analogous to the R package's `examples/`).
102
+ - [develop/planejamento.md](develop/planejamento.md) — the migration roadmap (phases, scope, status).
103
+ - [develop/deploy.md](develop/deploy.md) — step-by-step guide to publish the package to PyPI.
104
+
105
+ The example sources live under [notebooks/](notebooks/) (jupytext Markdown) and are
106
+ rendered into [examples/](examples/) by:
107
+
108
+ ```bash
109
+ pip install -e ".[docs]"
110
+ python tools/build_examples.py
111
+ ```
112
+
113
+ ---
114
+
115
+ ## Status
116
+
117
+ Alpha — the v1 foundation is complete. Implemented:
118
+
119
+ - **Core Experiment Line:** `DalBase`, `DalTransform`, `DalLearner`, `Predictor`,
120
+ `set_params`, and the `adjust_*` helpers.
121
+ - **Sampling:** `SampleRandom`, `SampleStratified` (`train_test`, `k_fold`),
122
+ `train_test_from_folds`.
123
+ - **Classification:** `Classification` base + `ClaDtree`, `ClaRpart`, `ClaKnn`,
124
+ `ClaNb`, `ClaRf`, `ClaBagging`, `ClaBoosting`, `ClaSvm`, `ClaMlp`, `ClaGlm`,
125
+ `ClaMultinom`, `ClaGlmnet`, `ClaMajority`.
126
+ - **Regression:** `Regression` base + `RegLm`, `RegDtree`, `RegKnn`, `RegRf`,
127
+ `RegSvm`, `RegMlp`.
128
+ - **Clustering:** `Clusterer` base + metrics + `ClusterKmeans`, `ClusterDbscan`,
129
+ `ClusterGmm`, `ClusterHclust`.
130
+ - **Transformations:** `MinMax`, `ZScore`, `NaRemoval`, `ImputationSimple`,
131
+ `OutliersBoxplot`, `OutliersGaussian`, `CategMapping`, `DtPca`, feature selection
132
+ (`Corr`, `Lasso`, `InfoGain`, `Stepwise`), balancing (`SampleBalance`,
133
+ `BalSubsampling`, `BalOversampling`), and curvature helpers.
134
+ - **Tuning:** `DalTune` base + `ClaTune`, `RegTune`, `CluTune`.
135
+ - **Autoencoder bases:** `AutoencBaseE`, `AutoencBaseEd` (identity, for extension).
136
+ - **Reference datasets:** `datasets.iris()`, `datasets.diabetes()`, `datasets.boston()`.
137
+
138
+ Wrappers are thin adapters over scikit-learn / numpy / pandas, each reproducing the R
139
+ backend's default behavior (e.g. SVM standardizes inputs like `e1071`, trees pre-prune
140
+ like `tree`/`rpart`). See [develop/planejamento.md](develop/planejamento.md) for the roadmap and what is
141
+ deferred to later versions (xgboost, k-medoids, fuzzy c-means, pattern mining, graphics).
142
+
143
+ ---
144
+
145
+ ## Related DAL projects
146
+
147
+ - [DAL Toolbox (R)](https://github.com/cefet-rj-dal/daltoolbox)
148
+ - [tspredit (R)](https://github.com/cefet-rj-dal/tspredit)
149
+ - [harbinger (R)](https://github.com/cefet-rj-dal/harbinger)
150
+ - [Data Analytics Lab](https://eic.cefet-rj.br/~dal/)
151
+
152
+ ## License
153
+
154
+ MIT
@@ -0,0 +1,122 @@
1
+ # pydaltoolbox
2
+
3
+ Python port of the R [DAL Toolbox](https://github.com/cefet-rj-dal/daltoolbox) —
4
+ *leveraging Experiment Lines for Data Analytics*.
5
+
6
+ pydaltoolbox organizes data analytics workflows (preprocessing, modeling,
7
+ evaluation, tuning, extensibility) around a consistent **Experiment Line** style
8
+ API. Its value is **not** reimplementing classic algorithms — it reuses
9
+ scikit-learn, numpy and pandas — but a **rigid, extensible interface** that wraps
10
+ them with a uniform `fit` / `action` / `evaluate` contract. Building a new method
11
+ means subclassing a base and implementing two or three methods; sampling,
12
+ evaluation and tuning come for free.
13
+
14
+ It is the foundation of the DAL Python family that will also include `pytspredit`
15
+ (time series prediction) and `pyharbinger` (time series event detection).
16
+
17
+ ---
18
+
19
+ ## Installation
20
+
21
+ > The package is in early development. A stable PyPI release is planned.
22
+
23
+ Once published, the stable version will be available on PyPI:
24
+
25
+ ```bash
26
+ pip install pydaltoolbox
27
+ ```
28
+
29
+ The development version is available on GitHub:
30
+
31
+ ```bash
32
+ pip install git+https://github.com/cefet-rj-dal/pydaltoolbox.git
33
+ ```
34
+
35
+ For a local, editable clone (for contributing or running the examples):
36
+
37
+ ```bash
38
+ git clone https://github.com/cefet-rj-dal/pydaltoolbox.git
39
+ cd pydaltoolbox
40
+ pip install -e ".[dev]"
41
+ pytest
42
+ ```
43
+
44
+ ---
45
+
46
+ ## First experiment
47
+
48
+ ```python
49
+ import pydaltoolbox as dal
50
+
51
+ iris = dal.datasets.iris()
52
+ slevels = list(iris["Species"].cat.categories)
53
+
54
+ split = dal.SampleRandom(seed=42).train_test(iris)
55
+ train, test = split["train"], split["test"]
56
+
57
+ model = dal.ClaDtree("Species", slevels, random_state=42).fit(train)
58
+
59
+ pred = model.predict(test.drop(columns="Species")) # pass only the features
60
+ ev = model.evaluate(test["Species"], pred)
61
+ print(ev["metrics"])
62
+ ```
63
+
64
+ ---
65
+
66
+ ## Documentation
67
+
68
+ - [Processed examples](examples/) — notebooks executed end to end, with real output
69
+ embedded (the "processed documentation", analogous to the R package's `examples/`).
70
+ - [develop/planejamento.md](develop/planejamento.md) — the migration roadmap (phases, scope, status).
71
+ - [develop/deploy.md](develop/deploy.md) — step-by-step guide to publish the package to PyPI.
72
+
73
+ The example sources live under [notebooks/](notebooks/) (jupytext Markdown) and are
74
+ rendered into [examples/](examples/) by:
75
+
76
+ ```bash
77
+ pip install -e ".[docs]"
78
+ python tools/build_examples.py
79
+ ```
80
+
81
+ ---
82
+
83
+ ## Status
84
+
85
+ Alpha — the v1 foundation is complete. Implemented:
86
+
87
+ - **Core Experiment Line:** `DalBase`, `DalTransform`, `DalLearner`, `Predictor`,
88
+ `set_params`, and the `adjust_*` helpers.
89
+ - **Sampling:** `SampleRandom`, `SampleStratified` (`train_test`, `k_fold`),
90
+ `train_test_from_folds`.
91
+ - **Classification:** `Classification` base + `ClaDtree`, `ClaRpart`, `ClaKnn`,
92
+ `ClaNb`, `ClaRf`, `ClaBagging`, `ClaBoosting`, `ClaSvm`, `ClaMlp`, `ClaGlm`,
93
+ `ClaMultinom`, `ClaGlmnet`, `ClaMajority`.
94
+ - **Regression:** `Regression` base + `RegLm`, `RegDtree`, `RegKnn`, `RegRf`,
95
+ `RegSvm`, `RegMlp`.
96
+ - **Clustering:** `Clusterer` base + metrics + `ClusterKmeans`, `ClusterDbscan`,
97
+ `ClusterGmm`, `ClusterHclust`.
98
+ - **Transformations:** `MinMax`, `ZScore`, `NaRemoval`, `ImputationSimple`,
99
+ `OutliersBoxplot`, `OutliersGaussian`, `CategMapping`, `DtPca`, feature selection
100
+ (`Corr`, `Lasso`, `InfoGain`, `Stepwise`), balancing (`SampleBalance`,
101
+ `BalSubsampling`, `BalOversampling`), and curvature helpers.
102
+ - **Tuning:** `DalTune` base + `ClaTune`, `RegTune`, `CluTune`.
103
+ - **Autoencoder bases:** `AutoencBaseE`, `AutoencBaseEd` (identity, for extension).
104
+ - **Reference datasets:** `datasets.iris()`, `datasets.diabetes()`, `datasets.boston()`.
105
+
106
+ Wrappers are thin adapters over scikit-learn / numpy / pandas, each reproducing the R
107
+ backend's default behavior (e.g. SVM standardizes inputs like `e1071`, trees pre-prune
108
+ like `tree`/`rpart`). See [develop/planejamento.md](develop/planejamento.md) for the roadmap and what is
109
+ deferred to later versions (xgboost, k-medoids, fuzzy c-means, pattern mining, graphics).
110
+
111
+ ---
112
+
113
+ ## Related DAL projects
114
+
115
+ - [DAL Toolbox (R)](https://github.com/cefet-rj-dal/daltoolbox)
116
+ - [tspredit (R)](https://github.com/cefet-rj-dal/tspredit)
117
+ - [harbinger (R)](https://github.com/cefet-rj-dal/harbinger)
118
+ - [Data Analytics Lab](https://eic.cefet-rj.br/~dal/)
119
+
120
+ ## License
121
+
122
+ MIT
@@ -0,0 +1,54 @@
1
+ [build-system]
2
+ requires = ["hatchling"]
3
+ build-backend = "hatchling.build"
4
+
5
+ [project]
6
+ name = "pydaltoolbox"
7
+ version = "0.1.0"
8
+ description = "Leveraging Experiment Lines for Data Analytics (Python port of the R daltoolbox framework)"
9
+ readme = "README.md"
10
+ requires-python = ">=3.9"
11
+ license = { text = "MIT" }
12
+ authors = [
13
+ { name = "Eduardo Ogasawara", email = "eogasawara@ieee.org" },
14
+ ]
15
+ keywords = ["data analytics", "machine learning", "experiment line", "scikit-learn", "pipeline"]
16
+ classifiers = [
17
+ "Development Status :: 3 - Alpha",
18
+ "Intended Audience :: Science/Research",
19
+ "License :: OSI Approved :: MIT License",
20
+ "Programming Language :: Python :: 3",
21
+ "Topic :: Scientific/Engineering :: Artificial Intelligence",
22
+ ]
23
+ dependencies = [
24
+ "numpy>=1.23",
25
+ "pandas>=1.5",
26
+ "scikit-learn>=1.2",
27
+ ]
28
+
29
+ [project.optional-dependencies]
30
+ dev = ["pytest>=7", "ruff>=0.1", "build", "twine"]
31
+ docs = ["jupytext>=1.16", "nbconvert>=7", "nbclient>=0.9", "ipykernel>=6"]
32
+
33
+ [project.urls]
34
+ Homepage = "https://github.com/cefet-rj-dal/pydaltoolbox"
35
+ Repository = "https://github.com/cefet-rj-dal/pydaltoolbox"
36
+ "Bug Tracker" = "https://github.com/cefet-rj-dal/pydaltoolbox/issues"
37
+
38
+ [tool.hatch.build.targets.wheel]
39
+ packages = ["src/pydaltoolbox"]
40
+
41
+ # The published source distribution ships only the package and essential metadata.
42
+ # Development-only material (develop/, notebooks/, examples/, tests/, tools/) is kept
43
+ # out of what users install.
44
+ [tool.hatch.build.targets.sdist]
45
+ include = ["src/pydaltoolbox", "README.md", "LICENSE"]
46
+ exclude = ["develop", "notebooks", "examples", "tests", "tools"]
47
+
48
+ [tool.pytest.ini_options]
49
+ testpaths = ["tests"]
50
+ addopts = "-q"
51
+
52
+ [tool.ruff]
53
+ line-length = 100
54
+ target-version = "py39"