ctdGAN 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 (9) hide show
  1. ctdGAN-0.1.0/PKG-INFO +24 -0
  2. ctdGAN-0.1.0/README.md +8 -0
  3. ctdGAN-0.1.0/ctdGAN.egg-info/PKG-INFO +24 -0
  4. ctdGAN-0.1.0/ctdGAN.egg-info/SOURCES.txt +7 -0
  5. ctdGAN-0.1.0/ctdGAN.egg-info/dependency_links.txt +1 -0
  6. ctdGAN-0.1.0/ctdGAN.egg-info/requires.txt +10 -0
  7. ctdGAN-0.1.0/ctdGAN.egg-info/top_level.txt +1 -0
  8. ctdGAN-0.1.0/setup.cfg +4 -0
  9. ctdGAN-0.1.0/setup.py +43 -0
ctdGAN-0.1.0/PKG-INFO ADDED
@@ -0,0 +1,24 @@
1
+ Metadata-Version: 2.1
2
+ Name: ctdGAN
3
+ Version: 0.1.0
4
+ Summary: A Generative Adversarial Network for synthesizing artificial tabular data.
5
+ Home-page: https://github.com/lakritidis/ctdGAN
6
+ Author: Leonidas Akritidis
7
+ Author-email: lakritidis@ihu.gr
8
+ Maintainer: Leonidas Akritidis
9
+ Maintainer-email: lakritidis@ihu.gr
10
+ License: Apache
11
+ Keywords: ctdGAN,GAN,Generative Adversarial Network,imbalanced data,tabular data,deep learning
12
+ Description-Content-Type: text/markdown
13
+ Requires-Dist: numpy
14
+ Requires-Dist: pandas
15
+ Requires-Dist: matplotlib
16
+ Requires-Dist: seaborn
17
+ Requires-Dist: sdv
18
+ Requires-Dist: tqdm
19
+ Requires-Dist: joblib
20
+ Requires-Dist: torch>=2.0.0
21
+ Requires-Dist: scikit-learn>=1.4.0
22
+ Requires-Dist: rdt<2.0,>=1.3.0
23
+
24
+ <p>ctdGAN is a Conditional Generative Adversarial Network for alleviating class imbalance in tabular datasets. The model is based on an initial space partitioning step that assigns cluster labels to the input samples. These labels are used to synthesize samples via a probabilistic sampling mechanism. ctdGAN optimizes a loss function that is sensitive to both cluster and class mis-predictions, rendering the modelcapable of generating samples in subspaces that resemble those of the original data distribution.</p><p><b>Licence:</b> Apache License, 2.0 (Apache-2.0)</p><p><b>Dependencies:</b>NumPy, pandas, Matplotlib, seaborn, joblib, Reversible Data Transforms(RDT), scikit-learn, pytorch, Synthetic Data Vault</p><p><b>GitHub repository:</b> <a href="https://github.com/lakritidis/ctdGAN">https://github.com/lakritidis/ctdGAN</a></p>
ctdGAN-0.1.0/README.md ADDED
@@ -0,0 +1,8 @@
1
+ # ctdGAN
2
+ A Generative Adversarial Network for synthesizing artificial tabular data
3
+
4
+ ctdGAN is a Conditional Generative Adversarial Network for alleviating class imbalance in tabular datasets. The model is based on an initial space partitioning step that assigns cluster labels to the input samples.
5
+ These labels are used to synthesize samples via a probabilistic sampling mechanism. ctdGAN optimizes a loss function that is sensitive to both cluster and class mis-predictions, rendering the model capable of
6
+ generating samples in subspaces that resemble those of the original data distribution.
7
+
8
+ **Licence:** Apache License, 2.0 (Apache-2.0)
ctdGAN-0.1.0/ctdGAN.egg-info/PKG-INFO ADDED
@@ -0,0 +1,24 @@
1
+ Metadata-Version: 2.1
2
+ Name: ctdGAN
3
+ Version: 0.1.0
4
+ Summary: A Generative Adversarial Network for synthesizing artificial tabular data.
5
+ Home-page: https://github.com/lakritidis/ctdGAN
6
+ Author: Leonidas Akritidis
7
+ Author-email: lakritidis@ihu.gr
8
+ Maintainer: Leonidas Akritidis
9
+ Maintainer-email: lakritidis@ihu.gr
10
+ License: Apache
11
+ Keywords: ctdGAN,GAN,Generative Adversarial Network,imbalanced data,tabular data,deep learning
12
+ Description-Content-Type: text/markdown
13
+ Requires-Dist: numpy
14
+ Requires-Dist: pandas
15
+ Requires-Dist: matplotlib
16
+ Requires-Dist: seaborn
17
+ Requires-Dist: sdv
18
+ Requires-Dist: tqdm
19
+ Requires-Dist: joblib
20
+ Requires-Dist: torch>=2.0.0
21
+ Requires-Dist: scikit-learn>=1.4.0
22
+ Requires-Dist: rdt<2.0,>=1.3.0
23
+
24
+ <p>ctdGAN is a Conditional Generative Adversarial Network for alleviating class imbalance in tabular datasets. The model is based on an initial space partitioning step that assigns cluster labels to the input samples. These labels are used to synthesize samples via a probabilistic sampling mechanism. ctdGAN optimizes a loss function that is sensitive to both cluster and class mis-predictions, rendering the modelcapable of generating samples in subspaces that resemble those of the original data distribution.</p><p><b>Licence:</b> Apache License, 2.0 (Apache-2.0)</p><p><b>Dependencies:</b>NumPy, pandas, Matplotlib, seaborn, joblib, Reversible Data Transforms(RDT), scikit-learn, pytorch, Synthetic Data Vault</p><p><b>GitHub repository:</b> <a href="https://github.com/lakritidis/ctdGAN">https://github.com/lakritidis/ctdGAN</a></p>
ctdGAN-0.1.0/ctdGAN.egg-info/SOURCES.txt ADDED
@@ -0,0 +1,7 @@
1
+ README.md
2
+ setup.py
3
+ ctdGAN.egg-info/PKG-INFO
4
+ ctdGAN.egg-info/SOURCES.txt
5
+ ctdGAN.egg-info/dependency_links.txt
6
+ ctdGAN.egg-info/requires.txt
7
+ ctdGAN.egg-info/top_level.txt
ctdGAN-0.1.0/ctdGAN.egg-info/requires.txt ADDED
@@ -0,0 +1,10 @@
1
+ numpy
2
+ pandas
3
+ matplotlib
4
+ seaborn
5
+ sdv
6
+ tqdm
7
+ joblib
8
+ torch>=2.0.0
9
+ scikit-learn>=1.4.0
10
+ rdt<2.0,>=1.3.0
ctdGAN-0.1.0/ctdGAN.egg-info/top_level.txt ADDED
@@ -0,0 +1 @@
1
+
ctdGAN-0.1.0/setup.cfg ADDED
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+
ctdGAN-0.1.0/setup.py ADDED
@@ -0,0 +1,43 @@
1
+ from distutils.core import setup
2
+ from setuptools import find_packages
3
+
4
+ DESCRIPTION = 'A Generative Adversarial Network for synthesizing artificial tabular data.'
5
+
6
+ LONG_DESCRIPTION = '<p>ctdGAN is a Conditional Generative Adversarial Network for alleviating class imbalance in '\
7
+ 'tabular datasets. The model is based on an initial space partitioning step that assigns cluster labels to the '\
8
+ 'input samples. These labels are used to synthesize samples via a probabilistic sampling mechanism. ctdGAN '\
9
+ 'optimizes a loss function that is sensitive to both cluster and class mis-predictions, rendering the model'\
10
+ 'capable of generating samples in subspaces that resemble those of the original data distribution.</p>'\
11
+ '<p><b>Licence:</b> Apache License, 2.0 (Apache-2.0)</p>' \
12
+ '<p><b>Dependencies:</b>NumPy, pandas, Matplotlib, seaborn, joblib, ' \
13
+ 'Reversible Data Transforms(RDT), scikit-learn, pytorch, Synthetic Data Vault</p>'\
14
+ '<p><b>GitHub repository:</b> '\
15
+ '<a href="https://github.com/lakritidis/ctdGAN">https://github.com/lakritidis/ctdGAN</a></p>'
16
+
17
+ setup(
18
+ name='ctdGAN',
19
+ version='0.1.0',
20
+ description=DESCRIPTION,
21
+ long_description=LONG_DESCRIPTION,
22
+ long_description_content_type='text/markdown',
23
+ author="Leonidas Akritidis",
24
+ author_email="lakritidis@ihu.gr",
25
+ maintainer="Leonidas Akritidis",
26
+ maintainer_email="lakritidis@ihu.gr",
27
+ packages=find_packages(),
28
+ package_data={'': ['generators/*']},
29
+ url='https://github.com/lakritidis/ctdGAN',
30
+ install_requires=["numpy",
31
+ "pandas",
32
+ "matplotlib",
33
+ "seaborn",
34
+ "sdv",
35
+ "tqdm",
36
+ "joblib",
37
+ "torch>=2.0.0",
38
+ "scikit-learn>=1.4.0",
39
+ "rdt>=1.3.0,<2.0"],
40
+ license="Apache",
41
+ keywords=[
42
+ "ctdGAN", "GAN", "Generative Adversarial Network", "imbalanced data", "tabular data", "deep learning"]
43
+ )