combatlearn 0.2.2__tar.gz → 1.1.0__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 (16) hide show
  1. {combatlearn-0.2.2/combatlearn.egg-info → combatlearn-1.1.0}/PKG-INFO +36 -8
  2. combatlearn-0.2.2/PKG-INFO → combatlearn-1.1.0/README.md +25 -30
  3. combatlearn-1.1.0/combatlearn/__init__.py +5 -0
  4. {combatlearn-0.2.2 → combatlearn-1.1.0}/combatlearn/combat.py +780 -40
  5. combatlearn-0.2.2/README.md → combatlearn-1.1.0/combatlearn.egg-info/PKG-INFO +58 -6
  6. {combatlearn-0.2.2 → combatlearn-1.1.0}/combatlearn.egg-info/SOURCES.txt +1 -0
  7. combatlearn-1.1.0/combatlearn.egg-info/requires.txt +19 -0
  8. {combatlearn-0.2.2 → combatlearn-1.1.0}/pyproject.toml +20 -12
  9. combatlearn-0.2.2/combatlearn.egg-info/requires.txt → combatlearn-1.1.0/requirements.txt +1 -2
  10. combatlearn-1.1.0/tests/test_combat.py +489 -0
  11. combatlearn-0.2.2/combatlearn/__init__.py +0 -4
  12. combatlearn-0.2.2/tests/test_combat.py +0 -150
  13. {combatlearn-0.2.2 → combatlearn-1.1.0}/LICENSE +0 -0
  14. {combatlearn-0.2.2 → combatlearn-1.1.0}/combatlearn.egg-info/dependency_links.txt +0 -0
  15. {combatlearn-0.2.2 → combatlearn-1.1.0}/combatlearn.egg-info/top_level.txt +0 -0
  16. {combatlearn-0.2.2 → combatlearn-1.1.0}/setup.cfg +0 -0
{combatlearn-0.2.2/combatlearn.egg-info → combatlearn-1.1.0}/PKG-INFO RENAMED
@@ -1,9 +1,9 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: combatlearn
3
- Version: 0.2.2
3
+ Version: 1.1.0
4
4
  Summary: Batch-effect harmonization for machine learning frameworks.
5
5
  Author-email: Ettore Rocchi <ettoreroc@gmail.com>
6
- License-Expression: MIT
6
+ License: MIT
7
7
  Keywords: machine-learning,harmonization,combat,preprocessing
8
8
  Classifier: Development Status :: 3 - Alpha
9
9
  Classifier: Intended Audience :: Science/Research
@@ -19,13 +19,23 @@ Requires-Dist: matplotlib>=3.4
19
19
  Requires-Dist: plotly>=5.0
20
20
  Requires-Dist: nbformat>=4.2
21
21
  Requires-Dist: umap-learn>=0.5
22
- Requires-Dist: pytest>=7
22
+ Provides-Extra: dev
23
+ Requires-Dist: pytest>=7; extra == "dev"
24
+ Requires-Dist: pytest-cov>=4.0; extra == "dev"
25
+ Requires-Dist: ruff>=0.1; extra == "dev"
26
+ Requires-Dist: mypy>=1.0; extra == "dev"
27
+ Provides-Extra: docs
28
+ Requires-Dist: mkdocs>=1.5.0; extra == "docs"
29
+ Requires-Dist: mkdocs-material>=9.0.0; extra == "docs"
30
+ Requires-Dist: mkdocstrings[python]>=0.24.0; extra == "docs"
31
+ Requires-Dist: pymdown-extensions>=10.0; extra == "docs"
23
32
  Dynamic: license-file
24
33
 
25
34
  # **combatlearn**
26
35
 
27
36
  [![Python versions](https://img.shields.io/badge/python-%3E%3D3.10-blue?logo=python)](https://www.python.org/)
28
37
  [![Test](https://github.com/EttoreRocchi/combatlearn/actions/workflows/test.yaml/badge.svg)](https://github.com/EttoreRocchi/combatlearn/actions/workflows/test.yaml)
38
+ [![Documentation](https://readthedocs.org/projects/combatlearn/badge/?version=latest)](https://combatlearn.readthedocs.io)
29
39
  [![PyPI Downloads](https://static.pepy.tech/badge/combatlearn)](https://pepy.tech/projects/combatlearn)
30
40
  [![PyPI Version](https://img.shields.io/pypi/v/combatlearn?cacheSeconds=300)](https://pypi.org/project/combatlearn/)
31
41
  [![License](https://img.shields.io/github/license/EttoreRocchi/combatlearn)](https://github.com/EttoreRocchi/combatlearn/blob/main/LICENSE)
@@ -47,8 +57,21 @@ Dynamic: license-file
47
57
  pip install combatlearn
48
58
  ```
49
59
 
60
+ ## Documentation
61
+
62
+ **Full documentation is available at [combatlearn.readthedocs.io](https://combatlearn.readthedocs.io)**
63
+
64
+ The documentation includes:
65
+ - [Installation Guide](https://combatlearn.readthedocs.io/en/latest/installation/)
66
+ - [Quick Start Tutorial](https://combatlearn.readthedocs.io/en/latest/quickstart/)
67
+ - [User Guide](https://combatlearn.readthedocs.io/en/latest/user-guide/overview/)
68
+ - [API Reference](https://combatlearn.readthedocs.io/en/latest/api/)
69
+ - [Examples](https://combatlearn.readthedocs.io/en/latest/examples/basic-usage/)
70
+
50
71
  ## Quick start
51
72
 
73
+ For more details, see the [Quick Start Tutorial](https://combatlearn.readthedocs.io/en/latest/quickstart/).
74
+
52
75
  ```python
53
76
  import pandas as pd
54
77
  from sklearn.pipeline import Pipeline
@@ -97,7 +120,7 @@ For a full example of how to use **combatlearn** see the [notebook demo](https:/
97
120
 
98
121
  ## `ComBat` parameters
99
122
 
100
- The following section provides a detailed explanation of all parameters available in the scikit-learn-compatible `ComBat` class.
123
+ The following section provides a detailed explanation of all parameters available in the scikit-learn-compatible `ComBat` class. For complete API documentation, see the [API Reference](https://combatlearn.readthedocs.io/en/latest/api/).
101
124
 
102
125
  ### Main Parameters
103
126
 
@@ -119,11 +142,17 @@ The following section provides a detailed explanation of all parameters availabl
119
142
  | `eps` | float | `1e-8` | Small jitter value added to variances to prevent divide-by-zero errors during standardization. |
120
143
 
121
144
 
122
- ### Batch Effect Correction Visualization
145
+ ### Batch Effect Correction Visualization
123
146
 
124
147
  The `plot_transformation` method allows to visualize the **ComBat** transformation effect using dimensionality reduction, showing the before/after comparison of data transformed by `ComBat` using PCA, t-SNE, or UMAP to reduce dimensions for visualization.
125
148
 
126
- For further details see the [notebook demo](https://github.com/EttoreRocchi/combatlearn/blob/main/docs/demo/combatlearn_demo.ipynb).
149
+ For further details see the [Visualization Guide](https://combatlearn.readthedocs.io/en/latest/user-guide/visualization/) and the [notebook demo](https://github.com/EttoreRocchi/combatlearn/blob/main/docs/demo/combatlearn_demo.ipynb).
150
+
151
+ ### Batch Effect Metrics
152
+
153
+ The `compute_batch_metrics` method provides quantitative assessment of batch correction quality. It computes metrics including Silhouette coefficient, Davies-Bouldin index, kBET, LISI, and variance ratio for batch effect quantification, as well as k-NN preservation and distance correlation for structure preservation.
154
+
155
+ For further details see the [Metrics Guide](https://combatlearn.readthedocs.io/en/latest/user-guide/metrics/) and the [notebook demo](https://github.com/EttoreRocchi/combatlearn/blob/main/docs/demo/combatlearn_demo.ipynb).
127
156
 
128
157
  ## Contributing
129
158
 
@@ -146,8 +175,7 @@ We gratefully acknowledge:
146
175
 
147
176
  ## Citation
148
177
 
149
- If **combatlearn** is useful in your research, please cite the original
150
- papers:
178
+ If **combatlearn** is useful in your research, please cite the original papers:
151
179
 
152
180
  - Johnson WE, Li C, Rabinovic A. Adjusting batch effects in microarray expression data using empirical Bayes methods. _Biostatistics_. 2007 Jan;8(1):118-27. doi: [10.1093/biostatistics/kxj037](https://doi.org/10.1093/biostatistics/kxj037)
153
181
 
combatlearn-0.2.2/PKG-INFO → combatlearn-1.1.0/README.md RENAMED
@@ -1,31 +1,8 @@
1
- Metadata-Version: 2.4
2
- Name: combatlearn
3
- Version: 0.2.2
4
- Summary: Batch-effect harmonization for machine learning frameworks.
5
- Author-email: Ettore Rocchi <ettoreroc@gmail.com>
6
- License-Expression: MIT
7
- Keywords: machine-learning,harmonization,combat,preprocessing
8
- Classifier: Development Status :: 3 - Alpha
9
- Classifier: Intended Audience :: Science/Research
10
- Classifier: Operating System :: OS Independent
11
- Classifier: Programming Language :: Python :: 3
12
- Requires-Python: >=3.10
13
- Description-Content-Type: text/markdown
14
- License-File: LICENSE
15
- Requires-Dist: pandas>=1.3
16
- Requires-Dist: numpy>=1.21
17
- Requires-Dist: scikit-learn>=1.2
18
- Requires-Dist: matplotlib>=3.4
19
- Requires-Dist: plotly>=5.0
20
- Requires-Dist: nbformat>=4.2
21
- Requires-Dist: umap-learn>=0.5
22
- Requires-Dist: pytest>=7
23
- Dynamic: license-file
24
-
25
1
  # **combatlearn**
26
2
 
27
3
  [![Python versions](https://img.shields.io/badge/python-%3E%3D3.10-blue?logo=python)](https://www.python.org/)
28
4
  [![Test](https://github.com/EttoreRocchi/combatlearn/actions/workflows/test.yaml/badge.svg)](https://github.com/EttoreRocchi/combatlearn/actions/workflows/test.yaml)
5
+ [![Documentation](https://readthedocs.org/projects/combatlearn/badge/?version=latest)](https://combatlearn.readthedocs.io)
29
6
  [![PyPI Downloads](https://static.pepy.tech/badge/combatlearn)](https://pepy.tech/projects/combatlearn)
30
7
  [![PyPI Version](https://img.shields.io/pypi/v/combatlearn?cacheSeconds=300)](https://pypi.org/project/combatlearn/)
31
8
  [![License](https://img.shields.io/github/license/EttoreRocchi/combatlearn)](https://github.com/EttoreRocchi/combatlearn/blob/main/LICENSE)
@@ -47,8 +24,21 @@ Dynamic: license-file
47
24
  pip install combatlearn
48
25
  ```
49
26
 
27
+ ## Documentation
28
+
29
+ **Full documentation is available at [combatlearn.readthedocs.io](https://combatlearn.readthedocs.io)**
30
+
31
+ The documentation includes:
32
+ - [Installation Guide](https://combatlearn.readthedocs.io/en/latest/installation/)
33
+ - [Quick Start Tutorial](https://combatlearn.readthedocs.io/en/latest/quickstart/)
34
+ - [User Guide](https://combatlearn.readthedocs.io/en/latest/user-guide/overview/)
35
+ - [API Reference](https://combatlearn.readthedocs.io/en/latest/api/)
36
+ - [Examples](https://combatlearn.readthedocs.io/en/latest/examples/basic-usage/)
37
+
50
38
  ## Quick start
51
39
 
40
+ For more details, see the [Quick Start Tutorial](https://combatlearn.readthedocs.io/en/latest/quickstart/).
41
+
52
42
  ```python
53
43
  import pandas as pd
54
44
  from sklearn.pipeline import Pipeline
@@ -97,7 +87,7 @@ For a full example of how to use **combatlearn** see the [notebook demo](https:/
97
87
 
98
88
  ## `ComBat` parameters
99
89
 
100
- The following section provides a detailed explanation of all parameters available in the scikit-learn-compatible `ComBat` class.
90
+ The following section provides a detailed explanation of all parameters available in the scikit-learn-compatible `ComBat` class. For complete API documentation, see the [API Reference](https://combatlearn.readthedocs.io/en/latest/api/).
101
91
 
102
92
  ### Main Parameters
103
93
 
@@ -119,11 +109,17 @@ The following section provides a detailed explanation of all parameters availabl
119
109
  | `eps` | float | `1e-8` | Small jitter value added to variances to prevent divide-by-zero errors during standardization. |
120
110
 
121
111
 
122
- ### Batch Effect Correction Visualization
112
+ ### Batch Effect Correction Visualization
123
113
 
124
114
  The `plot_transformation` method allows to visualize the **ComBat** transformation effect using dimensionality reduction, showing the before/after comparison of data transformed by `ComBat` using PCA, t-SNE, or UMAP to reduce dimensions for visualization.
125
115
 
126
- For further details see the [notebook demo](https://github.com/EttoreRocchi/combatlearn/blob/main/docs/demo/combatlearn_demo.ipynb).
116
+ For further details see the [Visualization Guide](https://combatlearn.readthedocs.io/en/latest/user-guide/visualization/) and the [notebook demo](https://github.com/EttoreRocchi/combatlearn/blob/main/docs/demo/combatlearn_demo.ipynb).
117
+
118
+ ### Batch Effect Metrics
119
+
120
+ The `compute_batch_metrics` method provides quantitative assessment of batch correction quality. It computes metrics including Silhouette coefficient, Davies-Bouldin index, kBET, LISI, and variance ratio for batch effect quantification, as well as k-NN preservation and distance correlation for structure preservation.
121
+
122
+ For further details see the [Metrics Guide](https://combatlearn.readthedocs.io/en/latest/user-guide/metrics/) and the [notebook demo](https://github.com/EttoreRocchi/combatlearn/blob/main/docs/demo/combatlearn_demo.ipynb).
127
123
 
128
124
  ## Contributing
129
125
 
@@ -146,11 +142,10 @@ We gratefully acknowledge:
146
142
 
147
143
  ## Citation
148
144
 
149
- If **combatlearn** is useful in your research, please cite the original
150
- papers:
145
+ If **combatlearn** is useful in your research, please cite the original papers:
151
146
 
152
147
  - Johnson WE, Li C, Rabinovic A. Adjusting batch effects in microarray expression data using empirical Bayes methods. _Biostatistics_. 2007 Jan;8(1):118-27. doi: [10.1093/biostatistics/kxj037](https://doi.org/10.1093/biostatistics/kxj037)
153
148
 
154
149
  - Fortin JP, Cullen N, Sheline YI, Taylor WD, Aselcioglu I, Cook PA, Adams P, Cooper C, Fava M, McGrath PJ, McInnis M, Phillips ML, Trivedi MH, Weissman MM, Shinohara RT. Harmonization of cortical thickness measurements across scanners and sites. _Neuroimage_. 2018 Feb 15;167:104-120. doi: [10.1016/j.neuroimage.2017.11.024](https://doi.org/10.1016/j.neuroimage.2017.11.024)
155
150
 
156
- - Chen AA, Beer JC, Tustison NJ, Cook PA, Shinohara RT, Shou H; Alzheimer's Disease Neuroimaging Initiative. Mitigating site effects in covariance for machine learning in neuroimaging data. _Hum Brain Mapp_. 2022 Mar;43(4):1179-1195. doi: [10.1002/hbm.25688](https://doi.org/10.1002/hbm.25688)
151
+ - Chen AA, Beer JC, Tustison NJ, Cook PA, Shinohara RT, Shou H; Alzheimer's Disease Neuroimaging Initiative. Mitigating site effects in covariance for machine learning in neuroimaging data. _Hum Brain Mapp_. 2022 Mar;43(4):1179-1195. doi: [10.1002/hbm.25688](https://doi.org/10.1002/hbm.25688)
combatlearn-1.1.0/combatlearn/__init__.py ADDED
@@ -0,0 +1,5 @@
1
+ from .combat import ComBat
2
+
3
+ __all__ = ["ComBat"]
4
+ __version__ = "1.1.0"
5
+ __author__ = "Ettore Rocchi"