def test_classify_image_joblib():
# use our test config file with algo set to joblib
config = 'test_config_files/config_test_joblib.ini'
# create mineral classifier instance
mc = mineral.MineralClassification(
config_file=config, library_file_name=test.libraryFilenames[0])
# for each of the test images
for image_file_name in test_classifyImage_testFilenames:
# classify the test image
classified_file_name = image_file_name[:-4] + "_class_test.hdr"
mc.classify_image(image_file_name, classified_file_name)
actual = spectral.open_image(classified_file_name)
# classified image for comparison
expected = spectral.open_image(image_file_name[:-4] + "_class.hdr")
# validate metadata
assert actual.metadata.get(
u'description') == 'COAL ' + pycoal.version + ' mineral ' \
'classified image.'
assert expected.metadata.get(u'file type') == actual.metadata.get(
u'file type')
assert expected.metadata.get(u'map info') == actual.metadata.get(
u'map info')
assert expected.metadata.get(u'class names') == actual.metadata.get(
u'class names')
assert expected.metadata.get(u'classes') == actual.metadata.get(
u'classes')
# verify that every pixel has the same classification
assert numpy.array_equal(expected.asarray(), actual.asarray())
# create mineral classifier instance with image loading enabled
mc = mineral.MineralClassification(
config_filename=config,
library_file_name=test.libraryFilenames[0],
in_memory=True)
# for each of the test images
for image_file_name in test_classifyImage_testFilenames:
# classify the test image
classified_file_name = image_file_name[:-4] + "_class_test.hdr"
mc.classify_image(image_file_name, classified_file_name)
actual = spectral.open_image(classified_file_name)
# classified image for comparison
expected = spectral.open_image(image_file_name[:-4] + "_class.hdr")
# verify that every pixel has the same classification
assert numpy.array_equal(expected.asarray(), actual.asarray())
def test_classify_image():
# create mineral classifier instance
mc = mineral.MineralClassification(library_file_name=libraryFilenames[0])
# for each of the test images
for image_file_name in test_classifyImage_testFilenames:
# classify the test image
classified_file_name = image_file_name[:-4] + "_class_test.hdr"
mc.classify_image(image_file_name, classified_file_name)
actual = spectral.open_image(classified_file_name)
# classified image for comparison
expected = spectral.open_image(image_file_name[:-4] + "_class.hdr")
# validate metadata
assert actual.metadata.get(
u'description'
) == 'COAL ' + pycoal.version + ' mineral classified image.'
assert expected.metadata.get(u'file type') == actual.metadata.get(
u'file type')
assert expected.metadata.get(u'map info') == actual.metadata.get(
u'map info')
assert expected.metadata.get(u'class names') == actual.metadata.get(
u'class names')
assert expected.metadata.get(u'classes') == actual.metadata.get(
u'classes')
# verify that every pixel has the same classification
assert numpy.array_equal(expected.asarray(), actual.asarray())
def test_classify_image_threshold():
# create mineral classification instance with threshold
mc = mineral.MineralClassification(library_file_name=libraryFilenames[0],
threshold=0.75)
# classify image
mc.classify_image(test_classifyImage_threshold_subset_imageFilename, \
test_classifyImage_threshold_subset_testFilename)
actual = spectral.open_image(
test_classifyImage_threshold_subset_testFilename)
# compare expected to actual classifications
expected = spectral.open_image(
test_classifyImage_threshold_subset_classifiedFilename)
for x in range(actual.shape[0]):
for y in range(actual.shape[1]):
actual_class_id = actual[x, y, 0]
actual_class_name = actual.metadata.get(
'class names')[actual_class_id]
expected_class_id = expected[x, y, 0]
expected_class_name = expected.metadata.get(
'class names')[expected_class_id]
assert actual_class_name == expected_class_name \
or actual_class_name == 'No data'
def run_mineral(input_filename=constants.INPUT_FILENAME,
library_filename=constants.LIBRARY_FILENAME):
""" Run mineral classification.
:param input_filename: Input file to be processed
:param library_filename: Spectral Library filename
"""
logging.info(
"Starting mineral classification with input file '%s' and spectral "
"library '%s'." % (
input_filename, library_filename))
# path to save RGB image
rgb_filename = constants.INPUT_NAME + "_rgb.hdr"
# path to save mineral classified image
classified_filename = constants.INPUT_NAME + "_class.hdr"
# path to save classification scores image
scores_filename = constants.INPUT_NAME + "_scores.hdr"
# create a new mineral classification instance (defaults to SAM algorithm)
mineral_classification = mineral.MineralClassification(
library_file_name=library_filename, scores_file_name=scores_filename,
subset_rows=constants.MINERAL_SUBSET_ROWS,
subset_cols=constants.MINERAL_SUBSET_COLS,
config_file="../pycoal/config.ini")
# generate a georeferenced visible-light image
mineral_classification.to_rgb(input_filename, rgb_filename)
# generate a mineral classified image
mineral_classification.classify_image(input_filename, classified_filename)
def run_mineral(input_filename, library_filename):
logging.info(
"Starting mineral classification with input file '%s' and spectral "
"library '%s'." % (
input_filename, library_filename))
# path to save RGB image
rgb_filename = constants.INPUT_NAME + "_rgb.hdr"
# path to save mineral classified image
classified_filename = constants.INPUT_NAME + "_class.hdr"
# path to save classification scores image
scores_filename = constants.INPUT_NAME + "_scores.hdr"
# list containing the names of all considered classification classes
class_names = ["Schwertmannite", "non-Schwertmannite"]
# create a new mineral classification instance
mineral_classification = mineral.MineralClassification(
algorithm=mineral.avngDNN, model_file_name=model_filename,
class_names=class_names, scores_file_name=scores_filename)
# generate a georeferenced visible-light image
mineral_classification.to_rgb(input_filename, rgb_filename)
# generate a mineral classified image
mineral_classification.classify_image(input_filename, classified_filename)
def test_config_file_wrong_impl():
# create mineral classifier instance, should raise keyerror
# in __init__ due to no SAM_p function in globals array
config = 'test_config_files/config_test_wrong_impl.ini'
with assert_raises(KeyError):
_mc = mineral.MineralClassification(
library_file_name=test.libraryFilenames[0], config_file=config)
def test_classify_image_subset():
# create mineral classification instance with mining subset
mc = mineral.MineralClassification(library_file_name=libraryFilenames[0], class_names=mining.proxy_class_names_usgsv6)
# classify image
mc.classify_image(test_classifyImage_threshold_subset_imageFilename, \
test_classifyImage_threshold_subset_testFilename)
actual = spectral.open_image(test_classifyImage_threshold_subset_testFilename)
# inspect the classifications
for x in range(actual.shape[0]):
for y in range(actual.shape[1]):
actual_class_id = actual[x,y,0]
actual_class_name = actual.metadata.get('class names')[actual_class_id]
assert actual_class_name in mining.proxy_class_names_usgsv6 \
or actual_class_name == 'No data'
def test_classify_image_in_memory():
# create mineral classifier instance with image loading enabled
mc = mineral.MineralClassification(library_file_name=libraryFilenames[0], in_memory=True)
# for each of the test images
for image_file_name in test_classifyImage_testFilenames:
# classify the test image
classified_file_name = image_file_name[:-4] + "_class_test.hdr"
mc.classify_image(image_file_name, classified_file_name)
actual = spectral.open_image(classified_file_name)
# classified image for comparison
expected = spectral.open_image(image_file_name[:-4] + "_class.hdr")
# verify that every pixel has the same classification
assert numpy.array_equal(expected.asarray(), actual.asarray())
def test_classify_image_subset():
# create mineral classification instance with mining subset
mc = mineral.MineralClassification(
library_file_name=test.libraryFilenames[0],
class_names=mining.PROXY_CLASS_NAMES_USGSV6,
config_file="test_config_files/config_test_joblib.ini")
# classify image
mc.classify_image(test_classifyImage_threshold_subset_imageFilename,
test_classifyImage_threshold_subset_testFilename)
actual = spectral.open_image(
test_classifyImage_threshold_subset_testFilename)
# inspect the classifications
for x in range(actual.shape[0]):
for y in range(actual.shape[1]):
actual_class_id = actual[x, y, 0]
actual_class_name = actual.metadata.get(
'class names')[actual_class_id]
assert actual_class_name in mining.PROXY_CLASS_NAMES_USGSV6 or \
actual_class_name == 'No data'