uncoverml.scripts package

Submodules

uncoverml.scripts.cluster_cli module

Run the uncoverml pipeline for clustering, supervised learning and prediction.

Usage: uncoverml [OPTIONS] COMMAND [ARGS]...

Options:
  -v, --verbosity [DEBUG|INFO|WARNING|ERROR]
                                  Level of logging
  --help                          Show this message and exit.

Commands:
  cluster
  covdiag
  gammasensor
  gridsearch
  learn
  modelfix
  predict
  resample
  shiftmap
  subsample
  targetsearch
  tiff2kmz
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.metrics.scorer module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.metrics. Anything that cannot be imported from sklearn.metrics is now part of the private API.
  warnings.warn(message, FutureWarning)
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.feature_selection.base module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.feature_selection. Anything that cannot be imported from sklearn.feature_selection is now part of the private API.
  warnings.warn(message, FutureWarning)
uncoverml.scripts.cluster_cli.main(config_file, subsample_fraction)
uncoverml.scripts.cluster_cli.semisupervised(config)
uncoverml.scripts.cluster_cli.unsupervised(config)

uncoverml.scripts.covdiag_cli module

uncoverml.scripts.covdiag_cli.diagnostic(filename)
uncoverml.scripts.covdiag_cli.main(path, csvfile, recursive)

Will output some basic diagnostic information for geotiffs. If a directory is provided, all geotiffs in the direcotry (and subdirectories if ‘-r’ option is used) will be processed. Providing a single filepath will only process that file.

To store the printed output in a txt file, use output redirection: ‘covdiag /path/to/file >> output.txt’.

uncoverml.scripts.covdiag_cli.printer(diag)

uncoverml.scripts.gammasensor_cli module

Run the Gamma sensor prediction/super-resolution pipeline.

System Message: ERROR/6 (/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/uncoverml/scripts/gammasensor_cli.py:docstring of uncoverml.scripts.gammasensor_cli.main, line 6)

Command 'gammasensor --help' failed: [Errno 2] No such file or directory: 'gammasensor': 'gammasensor'

uncoverml.scripts.gammasensor_cli.main(verbosity, geotiff, height, absorption, forward, outputdir, noise, impute)
uncoverml.scripts.gammasensor_cli.write_data(data, name, in_image, outputdir, forward)

uncoverml.scripts.gridsearch_cli module

Run the various machine learning parameter optimisation using scikit-learn GridSearchCv.

Available scorers:
Regression:

‘r2’, ‘expvar’, ‘smse’, ‘lins_ccc’

Classification:

‘accuracy’

Classification with probability:

‘log_loss’, ‘auc’

Not yet implemented:
Regression with variance (models w/ predict_dist):

‘mll’

Classification:

‘mean_confusion’, ‘mean_confusion_normalized’

If no scorers are provided, then the default score method of the model will be used.

Note that GridSearchCV is run with refit set to False. This is because the _best_estimator (best model found by GridSearchCV) is never used to predict anything, so fitting it is a waste.

If you ever do want to use refit, keep in mind that if you use mutliple scorers, refit needs to be set to the name of a scorer used to find the best parameters for refitting the model.

System Message: ERROR/6 (/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/uncoverml/scripts/gridsearch_cli.py:docstring of uncoverml.scripts.gridsearch_cli.main, line 32)

Command 'gridsearch --help' failed: [Errno 2] No such file or directory: 'gridsearch': 'gridsearch'

uncoverml.scripts.gridsearch_cli.main(pipeline_file, partitions, njobs)
uncoverml.scripts.gridsearch_cli.setup_pipeline(config)

uncoverml.scripts.learn_cli module

Run the uncoverml pipeline for clustering, supervised learning and prediction.

Usage: uncoverml [OPTIONS] COMMAND [ARGS]...

Options:
  -v, --verbosity [DEBUG|INFO|WARNING|ERROR]
                                  Level of logging
  --help                          Show this message and exit.

Commands:
  cluster
  covdiag
  gammasensor
  gridsearch
  learn
  modelfix
  predict
  resample
  shiftmap
  subsample
  targetsearch
  tiff2kmz
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.metrics.scorer module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.metrics. Anything that cannot be imported from sklearn.metrics is now part of the private API.
  warnings.warn(message, FutureWarning)
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.feature_selection.base module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.feature_selection. Anything that cannot be imported from sklearn.feature_selection is now part of the private API.
  warnings.warn(message, FutureWarning)
uncoverml.scripts.learn_cli.main(config_file, partitions)

uncoverml.scripts.modelfix_cli module

This command is used to hotfix models that were trained before the covariate transform fixes were applied.

Usage: uncoverml [OPTIONS] COMMAND [ARGS]...

Options:
  -v, --verbosity [DEBUG|INFO|WARNING|ERROR]
                                  Level of logging
  --help                          Show this message and exit.

Commands:
  cluster
  covdiag
  gammasensor
  gridsearch
  learn
  modelfix
  predict
  resample
  shiftmap
  subsample
  targetsearch
  tiff2kmz
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.metrics.scorer module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.metrics. Anything that cannot be imported from sklearn.metrics is now part of the private API.
  warnings.warn(message, FutureWarning)
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.feature_selection.base module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.feature_selection. Anything that cannot be imported from sklearn.feature_selection is now part of the private API.
  warnings.warn(message, FutureWarning)
uncoverml.scripts.modelfix_cli.main(config_file)

uncoverml.scripts.predict_cli module

Run the uncoverml pipeline for clustering, supervised learning and prediction.

Usage: uncoverml [OPTIONS] COMMAND [ARGS]...

Options:
  -v, --verbosity [DEBUG|INFO|WARNING|ERROR]
                                  Level of logging
  --help                          Show this message and exit.

Commands:
  cluster
  covdiag
  gammasensor
  gridsearch
  learn
  modelfix
  predict
  resample
  shiftmap
  subsample
  targetsearch
  tiff2kmz
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.metrics.scorer module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.metrics. Anything that cannot be imported from sklearn.metrics is now part of the private API.
  warnings.warn(message, FutureWarning)
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.feature_selection.base module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.feature_selection. Anything that cannot be imported from sklearn.feature_selection is now part of the private API.
  warnings.warn(message, FutureWarning)
uncoverml.scripts.predict_cli.main(config_file, partitions, mask, retain)
uncoverml.scripts.predict_cli.write_prediction_metadata(model, config, out_filename='metadata.txt')

write the metadata for this prediction result, into a human-readable txt file. in order to make the ML results traceable and reproduceable (provenance) :return:

uncoverml.scripts.resample_cli module

uncoverml.scripts.resample_cli.main(config_file, validation=False, validation_points=100)

uncoverml.scripts.shiftmap_cli module

Run the uncoverml pipeline for clustering, supervised learning and prediction.

Usage: uncoverml [OPTIONS] COMMAND [ARGS]...

Options:
  -v, --verbosity [DEBUG|INFO|WARNING|ERROR]
                                  Level of logging
  --help                          Show this message and exit.

Commands:
  cluster
  covdiag
  gammasensor
  gridsearch
  learn
  modelfix
  predict
  resample
  shiftmap
  subsample
  targetsearch
  tiff2kmz
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.metrics.scorer module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.metrics. Anything that cannot be imported from sklearn.metrics is now part of the private API.
  warnings.warn(message, FutureWarning)
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.feature_selection.base module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.feature_selection. Anything that cannot be imported from sklearn.feature_selection is now part of the private API.
  warnings.warn(message, FutureWarning)
uncoverml.scripts.shiftmap_cli.main(config_file, partitions)

uncoverml.scripts.subsample_cli module

Subsample the targets from a shapefile to a new shapefile.

System Message: ERROR/6 (/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/uncoverml/scripts/subsample_cli.py:docstring of uncoverml.scripts.subsample_cli.main, line 6)

Command 'subsampletargets --help' failed: [Errno 2] No such file or directory: 'subsampletargets': 'subsampletargets'

uncoverml.scripts.subsample_cli.main(filename, outputdir, npoints)

uncoverml.scripts.targetsearch_cli module

Run the uncoverml pipeline for clustering, supervised learning and prediction.

Usage: uncoverml [OPTIONS] COMMAND [ARGS]...

Options:
  -v, --verbosity [DEBUG|INFO|WARNING|ERROR]
                                  Level of logging
  --help                          Show this message and exit.

Commands:
  cluster
  covdiag
  gammasensor
  gridsearch
  learn
  modelfix
  predict
  resample
  shiftmap
  subsample
  targetsearch
  tiff2kmz
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.metrics.scorer module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.metrics. Anything that cannot be imported from sklearn.metrics is now part of the private API.
  warnings.warn(message, FutureWarning)
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.feature_selection.base module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.feature_selection. Anything that cannot be imported from sklearn.feature_selection is now part of the private API.
  warnings.warn(message, FutureWarning)
uncoverml.scripts.targetsearch_cli.main(config_file, partitions)

uncoverml.scripts.tiff2kmz_cli module

Convert a Geotiff to a KMZ archive for display on Google and Cesium maps (e.g. National Map).

System Message: ERROR/6 (/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/uncoverml/scripts/tiff2kmz_cli.py:docstring of uncoverml.scripts.tiff2kmz_cli.main, line 7)

Command 'tiff2kmz --help' failed: [Errno 2] No such file or directory: 'tiff2kmz': 'tiff2kmz'

uncoverml.scripts.tiff2kmz_cli.main(tiff, outfile, overlayname)

Turn a geotiff into a KMZ that can be dragged onto an instance of Terria Map. This also constructs a JPEG of the Geotiff, as it is required for the KMZ.

Module contents

Run the uncoverml pipeline for clustering, supervised learning and prediction.

Usage: uncoverml [OPTIONS] COMMAND [ARGS]...

Options:
  -v, --verbosity [DEBUG|INFO|WARNING|ERROR]
                                  Level of logging
  --help                          Show this message and exit.

Commands:
  cluster
  covdiag
  gammasensor
  gridsearch
  learn
  modelfix
  predict
  resample
  shiftmap
  subsample
  targetsearch
  tiff2kmz
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.metrics.scorer module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.metrics. Anything that cannot be imported from sklearn.metrics is now part of the private API.
  warnings.warn(message, FutureWarning)
/home/circleci/uncover-ml/venv/lib/python3.7/site-packages/sklearn/utils/deprecation.py:144: FutureWarning: The sklearn.feature_selection.base module is  deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.feature_selection. Anything that cannot be imported from sklearn.feature_selection is now part of the private API.
  warnings.warn(message, FutureWarning)
uncoverml.scripts.total_gb()