==================================================================
SpecHomo - Spectral homogenization of multispectral satellite data
==================================================================
* Free software: Apache-2.0
* **Documentation:** https://geomultisens.git-pages.gfz-potsdam.de/spechomo/doc/
* The **paper** corresponding to this software repository can be found here:
`Scheffler et al. 2020 <https://doi.org/10.1016/j.rse.2020.111723>`__ (cite as:
Scheffler D., Frantz D., Segl K. (2020). Spectral harmonization and red edge prediction of Landsat-8 to Sentinel-2
using land cover optimized multivariate regressors. Remote Sens. Environ. 241, 111723.
https://doi.org/10.1016/j.rse.2020.111723)
* Information on how to **cite the SpecHomo Python package** can be found in the
`CITATION <https://git.gfz-potsdam.de/geomultisens/spechomo/-/blob/main/CITATION>`__ file.
* Submit feedback by filing an issue `here <https://git.gfz-potsdam.de/geomultisens/spechomo/issues>`__
or join our chat here: |Gitter|
.. |Gitter| image:: https://badges.gitter.im/Join%20Chat.svg
:target: https://gitter.im/spechomo/community#
:alt: https://gitter.im/spechomo/community#
Status
------
.. image:: https://git.gfz-potsdam.de/geomultisens/spechomo/badges/main/pipeline.svg
:target: https://git.gfz-potsdam.de/geomultisens/spechomo/commits/main
.. image:: https://git.gfz-potsdam.de/geomultisens/spechomo/badges/main/coverage.svg
:target: https://geomultisens.git-pages.gfz-potsdam.de/spechomo/coverage/
.. image:: https://img.shields.io/static/v1?label=Documentation&message=GitLab%20Pages&color=orange
:target: https://geomultisens.git-pages.gfz-potsdam.de/spechomo/doc/
.. image:: https://img.shields.io/pypi/v/spechomo.svg
:target: https://pypi.python.org/pypi/spechomo
.. image:: https://img.shields.io/conda/vn/conda-forge/spechomo.svg
:target: https://anaconda.org/conda-forge/spechomo
.. image:: https://img.shields.io/pypi/l/spechomo.svg
:target: https://git.gfz-potsdam.de/geomultisens/spechomo/blob/main/LICENSE
.. image:: https://img.shields.io/pypi/pyversions/spechomo.svg
:target: https://img.shields.io/pypi/pyversions/spechomo.svg
.. image:: https://img.shields.io/pypi/dm/spechomo.svg
:target: https://pypi.python.org/pypi/spechomo
.. image:: https://zenodo.org/badge/241405333.svg
:target: https://zenodo.org/badge/latestdoi/241405333
See also the latest coverage_ report and the pytest_ HTML report.
Feature overview
----------------
SpecHomo is a **Python package for spectral homogenization of multispectral satellite data**, i.e., for the transformation
of the spectral information of one sensor into the spectral domain of another one. This simplifies workflows, increases
the reliability of subsequently derived multi-sensor products and may also enable the generation of new products that
are not possible with the initial spectral definition.
SpecHomo offers **different machine learning techniques** for the prediction of the target sensor spectral information. So
far, multivariate linear regression, multivariate quadratic regression and random forest regression are implemented. To
allow easy comparisons to the most simple homogenization approach, we also implemented linear spectral interpolation.
In contrast to previous spectral homogenization techniques, SpecHomo not only allows to apply a global (band-wise)
transformation with the same prediction coefficients for all gray values of a spectral band. It also **distinguishes**
**between individual spectral characteristics of different land-cover types** by using specifically trained prediction
coefficients for various spectral clusters. This increases the accuracy of the predicted spectral information.
Apart from that, SpecHomo can not only be used to homogenize already similar spectral definitions - it also **allows to**
**predict unilaterally missing bands** such as the red edge bands that are not present in Landsat-8 data.
**Prediction accuracies and effects to subsequent products** such as spectral indices or classifications have been
evaluated in the above mentioned paper at the example of Sentinel-2 spectral information predicted from Landsat-8.
Algorithm details may also be found there.
Satellite data (surface reflectance) acquired by **following sensors may be used** as source or target sensor:
* Landsat-5 TM
* Landsat-7 ETM+
* Landsat-8 OLI
* Sentinel-2A MSI
* Sentinel-2B MSI
* RapidEye-5 MSI
* SPOT-4
* SPOT-5
SpecHomo features **classifiers for homogenization** that we trained in the context of the GeoMultiSens project (see the
credits section) and for our evaluations related with the above mentioned paper. The initial spectral information for
classifier training has been derived from hyperspectral airborne data, spectrally convolved to different sensors. You
may also train your own homogenization classifiers specifically optimized to your area of interest. SpecHomo provides
the needed functionality for that.
For further details on how to use SpecHomo check out the
`documentation <https://geomultisens.git-pages.gfz-potsdam.de/spechomo/doc/>`__!
Credits
-------
The spechomo package was developed within the context of the GeoMultiSens project funded
by the German Federal Ministry of Education and Research (project grant code: 01 IS 14 010 A-C).
This package was created with Cookiecutter_ and the `audreyr/cookiecutter-pypackage`_ project template.
.. _Cookiecutter: https://github.com/audreyr/cookiecutter
.. _`audreyr/cookiecutter-pypackage`: https://github.com/audreyr/cookiecutter-pypackage
.. _coverage: https://geomultisens.git-pages.gfz-potsdam.de/spechomo/coverage/
.. _pytest: https://geomultisens.git-pages.gfz-potsdam.de/spechomo/test_reports/report.html
=======
History
=======
0.10.3 (2023-08-11)
-------------------
* !21: Fixed some warnings during package build process and 'make docs'.
0.10.2 (2021-12-16)
-------------------
* Replaced deprecated numpy data types.
0.10.1 (2021-12-15)
-------------------
* Migrated test calls from nosetests to pytest (!20).
0.10.0 (2021-09-27)
-------------------
* Solved matplotlib DeprecationWarning.
* 'make lint' now directly prints the log output.
* Revised RSImage_ClusterPredictor.predict() to improve speed
(reduced processing time to 70-50% of the previous version).
* Added weights attribute to prediction result.
* RSImage_ClusterPredictor.predict now logs the fractions of nodata, global and optimized regressors.
* Added 'progress' keyword to SpectralHomogenizer and RSImage_ClusterPredictor. Improved log output.
* Fixed TypeError in case the input image for the prediction has no nodata pixels and no in- and output nodata
value is given.
* Fixed type error in case non-kNN regressors are used for prediction.
* Fixed Exception in case a ClassifierCollection does not have the requested key (LBA).
* Revised test_spechomo_install CI job (now uses mamba).
* Added sphinx plugin requirements to environment_spechomo.yml.
* Updated minimal versions of py_tools_ds and geoarray to 0.18.0 and 0.15.0. Added minimal version 0.5.0 of pyrsr.
* Switched to Apache 2.0 license.
* The CI runner now uses Mambaforge. Revised CI jobs accordingly.
0.9.3 (2020-12-15)
------------------
* Fixed incorrect handling of classification map nodata value in SpectralHomogenizer (default is now -9999).
* Updated minimal version of specclassify to 0.2.8. This fixes issue #8 (Homogenization using kNN classifiers uses
faulty weights in case SpectralHomogenizer.predict_by_machine_learner() is called with global_clf_threshold=None.).
* Changed minimum and maximum values used for normalization of spectral distance measures. SAM values are now
normalized between 0 and 15 degrees SA and all other measures use the 90% percentile as maximum value.
This fixes issue #9 (Harmonization weights are affected by extreme values in the computed spectral distances between
spectrum and available regressors.).
0.9.2 (2020-12-15)
------------------
* Cluster classifiers can now be saved as JSON files (relates to issue #5).
* Added attributes 'spechomo_version' and 'spechomo_versionalias' to ClusterLearner.
0.9.1 (2020-12-11)
------------------
* Added URL checker and corresponding CI job.
* Removed travis related files.
* Replaced hard-coded links in documentation by cross-linking directives.
0.9.0 (2020-11-02)
------------------
* Replaced deprecated 'source activate' by 'conda activate.'
* Updated installation instructions.
* Revised requirements.
* Added doc, test, lint and dev requirements to optional requirements in setup.py.
* Updated LR and QR classifiers.
* Added sklearn import to avoid static TLS ImportError.
* Improved code style of SpectralHomogenizer.interpolate_cube() and SpectralHomogenizer.predict().
* Bugfix for also predicting spectral information for pixels that contain nodata in any band
(causes faulty predictions).
* Bugfix for only choosing 25 spectra in classifier creation in case the maximum angle threshold is automatically
set to 0 because there are many well matching spectra.
* Added minimal version of geoarray.
0.8.2 (2020-10-12)
------------------
* Use SPDX license identifier and set all files to GLP3+ to be consistent with license headers in the source files.
0.8.1 (2020-10-08)
------------------
* Added latest QR classifiers.
0.8.0 (2020-10-07)
------------------
* SpecHomo is now on conda-forge! Updated the installation instructions accordingly.
0.7.0 (2020-10-01)
------------------
* Re-trained LR classifiers.
* Updated classifiers within test data.
* Classifiers are no longer stored in the repository (resources directory) but are automatically downloaded on demand
at the first run (added corresponding code).
* Fixed TemporaryDirectory bug in Test_Utils.test_export_classifiers_as_JSON().
* Re-enabled CI job 'deploy_pypi'.
0.6.10 (2020-09-25)
-------------------
* Fixed an AssertionError within ClusterClassifier_Generator.create_classifiers() caused by nodata pixels in the target
sensor reference cube that were not dropped before creating the classifier.
0.6.9 (2020-09-25)
------------------
* Moved matplotlib imports function/class level to avoid static TLS ImportError.
0.6.8 (2020-09-25)
------------------
* Moved scipy imports function/class level to avoid static TLS ImportError.
* environment_spechomo.yml now uses Python 3.7+.
* scikit-learn is now pinned to 0.23.2+ due to classifier recreation.
0.6.7 (2020-09-24)
------------------
* Fixed a DeprecationWarning in case of scikit-learn>=0.23.
* Dumped regressors now use the second highest dill protocol in order to have some downwards compatibility.
0.6.6 (2020-09-24)
------------------
* Moved imports of scikit-learn to function/class level to avoid static TLS ImportError.
0.6.5 (2020-09-15)
------------------
* Replaced deprecated HTTP links.
0.6.4 (2020-04-09)
------------------
* Fixed test_spechomo_install CI job.
0.6.3 (2020-04-09)
------------------
* Fixed create_github_release CI job.
0.6.2 (2020-04-09)
------------------
* Releases in the GitHub-Mirror-Repository are now created automatically
(added create_release_from_gitlab_ci.sh and create_github_release CI job).
* Added GitHub issue template.
0.6.1 (2020-04-07)
------------------
* Revised CITATION file and .zenodo.json.
0.6.0 (2020-04-04)
------------------
* Added functionality to export existing .dill classifiers to JSON format to make them also usable in different
programming environments.
* The documentation now contains links to the published version of the research paper corresponding to SpecHomo.
* Changed Zenodo title and description.
* Fixed fallback algorithm in SpectralHomogenizer.predict_by_machine_learner() and added corresponding tests.
* SpectralHomogenizer.interpolate_cube() now returns a GeoArray instead of a numpy array.
0.5.0 (2020-02-20)
------------------
* Removed pyresample dependency (not needed anymore).
* Updated README.rst and setup.py.
* Pinned geopandas to below version 0.6.3 to fix an incompatibility with pyproj.
* Updated CI runner setup scripts and CI jobs.
* Updated LR and QR classifiers.
0.4.0 (2019-10-07)
------------------
* Added Sphinx documentation.
* Improved usability by adding functions to explore available spectral tansformations.
0.3.0 (2019-09-25)
------------------
* All tests are working properly now.
* Added license texts.
* Revised global classifiers.
* Added harmonization using weighted averaging.
0.2.0 (2019-07-22)
------------------
* A lot of algorithm improvements. Refer to the commits for details.
0.1.0 (2019-03-26)
------------------
* First version working separately from geomultisens.
Raw data
{
"_id": null,
"home_page": "https://git.gfz-potsdam.de/geomultisens/spechomo",
"name": "spechomo",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "spechomo,spectral homogenization,sensor fusion,remote sensing",
"author": "Daniel Scheffler",
"author_email": "daniel.scheffler@gfz-potsdam.de",
"download_url": "https://files.pythonhosted.org/packages/ad/47/75cc195a6f11d9e9cdff8c270644421a007a1b3ac12c450435648c7b8a98/spechomo-0.10.3.tar.gz",
"platform": null,
"description": "==================================================================\nSpecHomo - Spectral homogenization of multispectral satellite data\n==================================================================\n\n* Free software: Apache-2.0\n* **Documentation:** https://geomultisens.git-pages.gfz-potsdam.de/spechomo/doc/\n* The **paper** corresponding to this software repository can be found here:\n `Scheffler et al. 2020 <https://doi.org/10.1016/j.rse.2020.111723>`__ (cite as:\n Scheffler D., Frantz D., Segl K. (2020). Spectral harmonization and red edge prediction of Landsat-8 to Sentinel-2\n using land cover optimized multivariate regressors. Remote Sens. Environ. 241, 111723.\n https://doi.org/10.1016/j.rse.2020.111723)\n* Information on how to **cite the SpecHomo Python package** can be found in the\n `CITATION <https://git.gfz-potsdam.de/geomultisens/spechomo/-/blob/main/CITATION>`__ file.\n* Submit feedback by filing an issue `here <https://git.gfz-potsdam.de/geomultisens/spechomo/issues>`__\n or join our chat here: |Gitter|\n\n.. |Gitter| image:: https://badges.gitter.im/Join%20Chat.svg\n :target: https://gitter.im/spechomo/community#\n :alt: https://gitter.im/spechomo/community#\n\nStatus\n------\n\n.. image:: https://git.gfz-potsdam.de/geomultisens/spechomo/badges/main/pipeline.svg\n :target: https://git.gfz-potsdam.de/geomultisens/spechomo/commits/main\n.. image:: https://git.gfz-potsdam.de/geomultisens/spechomo/badges/main/coverage.svg\n :target: https://geomultisens.git-pages.gfz-potsdam.de/spechomo/coverage/\n.. image:: https://img.shields.io/static/v1?label=Documentation&message=GitLab%20Pages&color=orange\n :target: https://geomultisens.git-pages.gfz-potsdam.de/spechomo/doc/\n.. image:: https://img.shields.io/pypi/v/spechomo.svg\n :target: https://pypi.python.org/pypi/spechomo\n.. image:: https://img.shields.io/conda/vn/conda-forge/spechomo.svg\n :target: https://anaconda.org/conda-forge/spechomo\n.. image:: https://img.shields.io/pypi/l/spechomo.svg\n :target: https://git.gfz-potsdam.de/geomultisens/spechomo/blob/main/LICENSE\n.. image:: https://img.shields.io/pypi/pyversions/spechomo.svg\n :target: https://img.shields.io/pypi/pyversions/spechomo.svg\n.. image:: https://img.shields.io/pypi/dm/spechomo.svg\n :target: https://pypi.python.org/pypi/spechomo\n.. image:: https://zenodo.org/badge/241405333.svg\n :target: https://zenodo.org/badge/latestdoi/241405333\n\nSee also the latest coverage_ report and the pytest_ HTML report.\n\n\nFeature overview\n----------------\n\nSpecHomo is a **Python package for spectral homogenization of multispectral satellite data**, i.e., for the transformation\nof the spectral information of one sensor into the spectral domain of another one. This simplifies workflows, increases\nthe reliability of subsequently derived multi-sensor products and may also enable the generation of new products that\nare not possible with the initial spectral definition.\n\nSpecHomo offers **different machine learning techniques** for the prediction of the target sensor spectral information. So\nfar, multivariate linear regression, multivariate quadratic regression and random forest regression are implemented. To\nallow easy comparisons to the most simple homogenization approach, we also implemented linear spectral interpolation.\n\nIn contrast to previous spectral homogenization techniques, SpecHomo not only allows to apply a global (band-wise)\ntransformation with the same prediction coefficients for all gray values of a spectral band. It also **distinguishes**\n**between individual spectral characteristics of different land-cover types** by using specifically trained prediction\ncoefficients for various spectral clusters. This increases the accuracy of the predicted spectral information.\nApart from that, SpecHomo can not only be used to homogenize already similar spectral definitions - it also **allows to**\n**predict unilaterally missing bands** such as the red edge bands that are not present in Landsat-8 data.\n\n**Prediction accuracies and effects to subsequent products** such as spectral indices or classifications have been\nevaluated in the above mentioned paper at the example of Sentinel-2 spectral information predicted from Landsat-8.\nAlgorithm details may also be found there.\n\nSatellite data (surface reflectance) acquired by **following sensors may be used** as source or target sensor:\n\n* Landsat-5 TM\n* Landsat-7 ETM+\n* Landsat-8 OLI\n* Sentinel-2A MSI\n* Sentinel-2B MSI\n* RapidEye-5 MSI\n* SPOT-4\n* SPOT-5\n\nSpecHomo features **classifiers for homogenization** that we trained in the context of the GeoMultiSens project (see the\ncredits section) and for our evaluations related with the above mentioned paper. The initial spectral information for\nclassifier training has been derived from hyperspectral airborne data, spectrally convolved to different sensors. You\nmay also train your own homogenization classifiers specifically optimized to your area of interest. SpecHomo provides\nthe needed functionality for that.\n\nFor further details on how to use SpecHomo check out the\n`documentation <https://geomultisens.git-pages.gfz-potsdam.de/spechomo/doc/>`__!\n\nCredits\n-------\n\nThe spechomo package was developed within the context of the GeoMultiSens project funded\nby the German Federal Ministry of Education and Research (project grant code: 01 IS 14 010 A-C).\n\nThis package was created with Cookiecutter_ and the `audreyr/cookiecutter-pypackage`_ project template.\n\n.. _Cookiecutter: https://github.com/audreyr/cookiecutter\n.. _`audreyr/cookiecutter-pypackage`: https://github.com/audreyr/cookiecutter-pypackage\n.. _coverage: https://geomultisens.git-pages.gfz-potsdam.de/spechomo/coverage/\n.. _pytest: https://geomultisens.git-pages.gfz-potsdam.de/spechomo/test_reports/report.html\n\n\n=======\nHistory\n=======\n\n0.10.3 (2023-08-11)\n-------------------\n\n* !21: Fixed some warnings during package build process and 'make docs'.\n\n\n0.10.2 (2021-12-16)\n-------------------\n\n* Replaced deprecated numpy data types.\n\n\n0.10.1 (2021-12-15)\n-------------------\n\n* Migrated test calls from nosetests to pytest (!20).\n\n\n0.10.0 (2021-09-27)\n-------------------\n\n* Solved matplotlib DeprecationWarning.\n* 'make lint' now directly prints the log output.\n* Revised RSImage_ClusterPredictor.predict() to improve speed\n (reduced processing time to 70-50% of the previous version).\n* Added weights attribute to prediction result.\n* RSImage_ClusterPredictor.predict now logs the fractions of nodata, global and optimized regressors.\n* Added 'progress' keyword to SpectralHomogenizer and RSImage_ClusterPredictor. Improved log output.\n* Fixed TypeError in case the input image for the prediction has no nodata pixels and no in- and output nodata\n value is given.\n* Fixed type error in case non-kNN regressors are used for prediction.\n* Fixed Exception in case a ClassifierCollection does not have the requested key (LBA).\n* Revised test_spechomo_install CI job (now uses mamba).\n* Added sphinx plugin requirements to environment_spechomo.yml.\n* Updated minimal versions of py_tools_ds and geoarray to 0.18.0 and 0.15.0. Added minimal version 0.5.0 of pyrsr.\n* Switched to Apache 2.0 license.\n* The CI runner now uses Mambaforge. Revised CI jobs accordingly.\n\n\n0.9.3 (2020-12-15)\n------------------\n\n* Fixed incorrect handling of classification map nodata value in SpectralHomogenizer (default is now -9999).\n* Updated minimal version of specclassify to 0.2.8. This fixes issue #8 (Homogenization using kNN classifiers uses\n faulty weights in case SpectralHomogenizer.predict_by_machine_learner() is called with global_clf_threshold=None.).\n* Changed minimum and maximum values used for normalization of spectral distance measures. SAM values are now\n normalized between 0 and 15 degrees SA and all other measures use the 90% percentile as maximum value.\n This fixes issue #9 (Harmonization weights are affected by extreme values in the computed spectral distances between\n spectrum and available regressors.).\n\n\n0.9.2 (2020-12-15)\n------------------\n\n* Cluster classifiers can now be saved as JSON files (relates to issue #5).\n* Added attributes 'spechomo_version' and 'spechomo_versionalias' to ClusterLearner.\n\n\n0.9.1 (2020-12-11)\n------------------\n\n* Added URL checker and corresponding CI job.\n* Removed travis related files.\n* Replaced hard-coded links in documentation by cross-linking directives.\n\n\n0.9.0 (2020-11-02)\n------------------\n\n* Replaced deprecated 'source activate' by 'conda activate.'\n* Updated installation instructions.\n* Revised requirements.\n* Added doc, test, lint and dev requirements to optional requirements in setup.py.\n* Updated LR and QR classifiers.\n* Added sklearn import to avoid static TLS ImportError.\n* Improved code style of SpectralHomogenizer.interpolate_cube() and SpectralHomogenizer.predict().\n* Bugfix for also predicting spectral information for pixels that contain nodata in any band\n (causes faulty predictions).\n* Bugfix for only choosing 25 spectra in classifier creation in case the maximum angle threshold is automatically\n set to 0 because there are many well matching spectra.\n* Added minimal version of geoarray.\n\n\n0.8.2 (2020-10-12)\n------------------\n\n* Use SPDX license identifier and set all files to GLP3+ to be consistent with license headers in the source files.\n\n\n0.8.1 (2020-10-08)\n------------------\n\n* Added latest QR classifiers.\n\n\n0.8.0 (2020-10-07)\n------------------\n\n* SpecHomo is now on conda-forge! Updated the installation instructions accordingly.\n\n\n0.7.0 (2020-10-01)\n------------------\n\n* Re-trained LR classifiers.\n* Updated classifiers within test data.\n* Classifiers are no longer stored in the repository (resources directory) but are automatically downloaded on demand\n at the first run (added corresponding code).\n* Fixed TemporaryDirectory bug in Test_Utils.test_export_classifiers_as_JSON().\n* Re-enabled CI job 'deploy_pypi'.\n\n\n0.6.10 (2020-09-25)\n-------------------\n\n* Fixed an AssertionError within ClusterClassifier_Generator.create_classifiers() caused by nodata pixels in the target\n sensor reference cube that were not dropped before creating the classifier.\n\n\n0.6.9 (2020-09-25)\n------------------\n\n* Moved matplotlib imports function/class level to avoid static TLS ImportError.\n\n\n0.6.8 (2020-09-25)\n------------------\n\n* Moved scipy imports function/class level to avoid static TLS ImportError.\n* environment_spechomo.yml now uses Python 3.7+.\n* scikit-learn is now pinned to 0.23.2+ due to classifier recreation.\n\n\n0.6.7 (2020-09-24)\n------------------\n\n* Fixed a DeprecationWarning in case of scikit-learn>=0.23.\n* Dumped regressors now use the second highest dill protocol in order to have some downwards compatibility.\n\n\n0.6.6 (2020-09-24)\n------------------\n\n* Moved imports of scikit-learn to function/class level to avoid static TLS ImportError.\n\n\n0.6.5 (2020-09-15)\n------------------\n\n* Replaced deprecated HTTP links.\n\n\n0.6.4 (2020-04-09)\n------------------\n\n* Fixed test_spechomo_install CI job.\n\n\n0.6.3 (2020-04-09)\n------------------\n\n* Fixed create_github_release CI job.\n\n\n0.6.2 (2020-04-09)\n------------------\n\n* Releases in the GitHub-Mirror-Repository are now created automatically\n (added create_release_from_gitlab_ci.sh and create_github_release CI job).\n* Added GitHub issue template.\n\n\n0.6.1 (2020-04-07)\n------------------\n\n* Revised CITATION file and .zenodo.json.\n\n\n0.6.0 (2020-04-04)\n------------------\n\n* Added functionality to export existing .dill classifiers to JSON format to make them also usable in different\n programming environments.\n* The documentation now contains links to the published version of the research paper corresponding to SpecHomo.\n* Changed Zenodo title and description.\n* Fixed fallback algorithm in SpectralHomogenizer.predict_by_machine_learner() and added corresponding tests.\n* SpectralHomogenizer.interpolate_cube() now returns a GeoArray instead of a numpy array.\n\n\n0.5.0 (2020-02-20)\n------------------\n\n* Removed pyresample dependency (not needed anymore).\n* Updated README.rst and setup.py.\n* Pinned geopandas to below version 0.6.3 to fix an incompatibility with pyproj.\n* Updated CI runner setup scripts and CI jobs.\n* Updated LR and QR classifiers.\n\n\n0.4.0 (2019-10-07)\n------------------\n\n* Added Sphinx documentation.\n* Improved usability by adding functions to explore available spectral tansformations.\n\n\n0.3.0 (2019-09-25)\n------------------\n\n* All tests are working properly now.\n* Added license texts.\n* Revised global classifiers.\n* Added harmonization using weighted averaging.\n\n\n0.2.0 (2019-07-22)\n------------------\n\n* A lot of algorithm improvements. Refer to the commits for details.\n\n\n0.1.0 (2019-03-26)\n------------------\n\n* First version working separately from geomultisens.\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Spectral homogenization of multispectral satellite data.",
"version": "0.10.3",
"project_urls": {
"Homepage": "https://git.gfz-potsdam.de/geomultisens/spechomo"
},
"split_keywords": [
"spechomo",
"spectral homogenization",
"sensor fusion",
"remote sensing"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "ad4775cc195a6f11d9e9cdff8c270644421a007a1b3ac12c450435648c7b8a98",
"md5": "141d9f81aac8a8777a5495477b47790e",
"sha256": "0c3f4139e293150923ffeff9b4a8109a2e73ed36d4d7d7467ddd21747b9d255c"
},
"downloads": -1,
"filename": "spechomo-0.10.3.tar.gz",
"has_sig": false,
"md5_digest": "141d9f81aac8a8777a5495477b47790e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 459868,
"upload_time": "2023-08-11T13:27:59",
"upload_time_iso_8601": "2023-08-11T13:27:59.037995Z",
"url": "https://files.pythonhosted.org/packages/ad/47/75cc195a6f11d9e9cdff8c270644421a007a1b3ac12c450435648c7b8a98/spechomo-0.10.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-08-11 13:27:59",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "spechomo"
}
JSON