# Generative Topographic Mapping and Analysis Toolkit
## Introduction
The Generative Topographic Mapping and Analysis Toolkit is a Python package designed for high-dimensional data analysis using Generative Topographic Mapping (GTM). This toolkit facilitates the visualization of high-dimensional datasets in lower-dimensional spaces, supports both forward and inverse mappings, and offers comprehensive tools for model fitting, dimensionality reduction, error analysis, and hyperparameter optimization. It is particularly useful for researchers and practitioners in machine learning, data science, and bioinformatics.
## Features
- GTM model fitting for dimensionality reduction and data visualization.
- k-nearest neighbor normalized error (k3n-error) calculation for error analysis.
- Cross-validation based hyperparameter optimization for GTM models.
- Support for both forward analysis (regression) and inverse analysis.
- Visualization tools for low-dimensional embeddings of high-dimensional data.
## Installation
To install the GTMAnalysisToolkit, run the following command in your terminal:
```bash
pip install GTMAnalysisToolkit
```
Ensure you have Python 3.x installed on your system. This package depends on numpy, scipy, matplotlib, and sklearn, which will be automatically installed during the GTMAnalysisToolkit installation.
## Quick Start
Here's a quick example to get you started with using the GTMAnalysisToolkit:
```Python
import matplotlib.figure as figure
import matplotlib.pyplot as plt
from GTMAnalysisToolkit import GTM
from sklearn.datasets import load_iris
# settings
shape_of_map = [10, 10]
shape_of_rbf_centers = [5, 5]
variance_of_rbfs = 4
lambda_in_em_algorithm = 0.001
number_of_iterations = 300
display_flag = 1
# load an iris dataset
iris = load_iris()
# input_dataset = pd.DataFrame(iris.data, columns=iris.feature_names)
input_dataset = iris.data
color = iris.target
# autoscaling
input_dataset = (input_dataset - input_dataset.mean(axis=0)) / input_dataset.std(axis=0, ddof=1)
# construct GTM model
model = GTM(shape_of_map, shape_of_rbf_centers, variance_of_rbfs, lambda_in_em_algorithm, number_of_iterations,
display_flag)
model.fit(input_dataset)
if model.success_flag:
# calculate of responsibilities
responsibilities = model.responsibility(input_dataset)
# plot the mean of responsibilities
means = responsibilities.dot(model.map_grids)
plt.figure(figsize=figure.figaspect(1))
plt.scatter(means[:, 0], means[:, 1], c=color)
plt.ylim(-1.1, 1.1)
plt.xlim(-1.1, 1.1)
plt.xlabel("z1 (mean)")
plt.ylabel("z2 (mean)")
plt.show()
# plot the mode of responsibilities
modes = model.map_grids[responsibilities.argmax(axis=1), :]
plt.figure(figsize=figure.figaspect(1))
plt.scatter(modes[:, 0], modes[:, 1], c=color)
plt.ylim(-1.1, 1.1)
plt.xlim(-1.1, 1.1)
plt.xlabel("z1 (mode)")
plt.ylabel("z2 (mode)")
plt.show()
```
## License
This project is licensed under the GNU General Public License version 3 (GPL-3.0) - see the LICENSE file for details.
## Contributing
We welcome contributions to the GTMAnalysisToolkit! If you have suggestions or want to contribute code, please feel free to open an issue or pull request on our GitHub repository.
## Contact
For questions or support, please contact Eng. Alberto Biscalchin at biscalchin.mau.se@gmail.com
Raw data
{
"_id": null,
"home_page": "",
"name": "GTMAnalysisToolkit",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "generative topographic mapping,dimensionality reduction,data visualization,machine learning,high-dimensional data analysis",
"author": "Eng. Alberto Biscalchin",
"author_email": "<biscalchin.mau.se@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/9f/88/87264ee16bb07b636e06ae8ebe952aae2e950a0529445e25c3a8b211387c/GTMAnalysisToolkit-1.0.2.tar.gz",
"platform": null,
"description": "# Generative Topographic Mapping and Analysis Toolkit\r\n## Introduction\r\n\r\nThe Generative Topographic Mapping and Analysis Toolkit is a Python package designed for high-dimensional data analysis using Generative Topographic Mapping (GTM). This toolkit facilitates the visualization of high-dimensional datasets in lower-dimensional spaces, supports both forward and inverse mappings, and offers comprehensive tools for model fitting, dimensionality reduction, error analysis, and hyperparameter optimization. It is particularly useful for researchers and practitioners in machine learning, data science, and bioinformatics.\r\n\r\n## Features\r\n\r\n- GTM model fitting for dimensionality reduction and data visualization.\r\n- k-nearest neighbor normalized error (k3n-error) calculation for error analysis.\r\n- Cross-validation based hyperparameter optimization for GTM models.\r\n- Support for both forward analysis (regression) and inverse analysis.\r\n- Visualization tools for low-dimensional embeddings of high-dimensional data.\r\n\r\n## Installation \r\n\r\nTo install the GTMAnalysisToolkit, run the following command in your terminal:\r\n```bash\r\npip install GTMAnalysisToolkit\r\n```\r\nEnsure you have Python 3.x installed on your system. This package depends on numpy, scipy, matplotlib, and sklearn, which will be automatically installed during the GTMAnalysisToolkit installation.\r\n\r\n## Quick Start\r\n\r\nHere's a quick example to get you started with using the GTMAnalysisToolkit:\r\n\r\n```Python\r\nimport matplotlib.figure as figure\r\nimport matplotlib.pyplot as plt\r\nfrom GTMAnalysisToolkit import GTM\r\nfrom sklearn.datasets import load_iris\r\n\r\n# settings\r\nshape_of_map = [10, 10]\r\nshape_of_rbf_centers = [5, 5]\r\nvariance_of_rbfs = 4\r\nlambda_in_em_algorithm = 0.001\r\nnumber_of_iterations = 300\r\ndisplay_flag = 1\r\n\r\n# load an iris dataset\r\niris = load_iris()\r\n# input_dataset = pd.DataFrame(iris.data, columns=iris.feature_names)\r\ninput_dataset = iris.data\r\ncolor = iris.target\r\n\r\n# autoscaling\r\ninput_dataset = (input_dataset - input_dataset.mean(axis=0)) / input_dataset.std(axis=0, ddof=1)\r\n\r\n# construct GTM model\r\nmodel = GTM(shape_of_map, shape_of_rbf_centers, variance_of_rbfs, lambda_in_em_algorithm, number_of_iterations,\r\n display_flag)\r\nmodel.fit(input_dataset)\r\n\r\nif model.success_flag:\r\n # calculate of responsibilities\r\n responsibilities = model.responsibility(input_dataset)\r\n\r\n # plot the mean of responsibilities\r\n means = responsibilities.dot(model.map_grids)\r\n plt.figure(figsize=figure.figaspect(1))\r\n plt.scatter(means[:, 0], means[:, 1], c=color)\r\n plt.ylim(-1.1, 1.1)\r\n plt.xlim(-1.1, 1.1)\r\n plt.xlabel(\"z1 (mean)\")\r\n plt.ylabel(\"z2 (mean)\")\r\n plt.show()\r\n\r\n # plot the mode of responsibilities\r\n modes = model.map_grids[responsibilities.argmax(axis=1), :]\r\n plt.figure(figsize=figure.figaspect(1))\r\n plt.scatter(modes[:, 0], modes[:, 1], c=color)\r\n plt.ylim(-1.1, 1.1)\r\n plt.xlim(-1.1, 1.1)\r\n plt.xlabel(\"z1 (mode)\")\r\n plt.ylabel(\"z2 (mode)\")\r\n plt.show()\r\n\r\n```\r\n\r\n## License\r\n\r\nThis project is licensed under the GNU General Public License version 3 (GPL-3.0) - see the LICENSE file for details.\r\n\r\n## Contributing\r\nWe welcome contributions to the GTMAnalysisToolkit! If you have suggestions or want to contribute code, please feel free to open an issue or pull request on our GitHub repository.\r\n\r\n## Contact\r\nFor questions or support, please contact Eng. Alberto Biscalchin at biscalchin.mau.se@gmail.com\r\n",
"bugtrack_url": null,
"license": "",
"summary": "Generative Topographic Mapping and Analysis Toolkit",
"version": "1.0.2",
"project_urls": null,
"split_keywords": [
"generative topographic mapping",
"dimensionality reduction",
"data visualization",
"machine learning",
"high-dimensional data analysis"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "42cc55966bd55bc5c852ddeb153a2a37ef842bb9ebc587e3c48c6b6731bf8c98",
"md5": "396aa97be6c712bc34f6cb1df010d4e8",
"sha256": "2f64b93a435da5ef12a1f3b0d55bfc8817efb5e8887bef1c5152c1905e377d88"
},
"downloads": -1,
"filename": "GTMAnalysisToolkit-1.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "396aa97be6c712bc34f6cb1df010d4e8",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 25254,
"upload_time": "2024-02-18T15:47:57",
"upload_time_iso_8601": "2024-02-18T15:47:57.522066Z",
"url": "https://files.pythonhosted.org/packages/42/cc/55966bd55bc5c852ddeb153a2a37ef842bb9ebc587e3c48c6b6731bf8c98/GTMAnalysisToolkit-1.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "9f8887264ee16bb07b636e06ae8ebe952aae2e950a0529445e25c3a8b211387c",
"md5": "4e130844590a179092a631e0b391c3e9",
"sha256": "2f723735c3ef9dd19a6e371cc2a1570635e6798735872ea35a0e5dbcd1916072"
},
"downloads": -1,
"filename": "GTMAnalysisToolkit-1.0.2.tar.gz",
"has_sig": false,
"md5_digest": "4e130844590a179092a631e0b391c3e9",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 25967,
"upload_time": "2024-02-18T15:47:58",
"upload_time_iso_8601": "2024-02-18T15:47:58.946101Z",
"url": "https://files.pythonhosted.org/packages/9f/88/87264ee16bb07b636e06ae8ebe952aae2e950a0529445e25c3a8b211387c/GTMAnalysisToolkit-1.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-18 15:47:58",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "gtmanalysistoolkit"
}
JSON