def test_commission_real_change(sim_real_change):
""" Test commission test's ability to avoid merging real changes
This test is run with a relatively large p value (very likely to reject H0
and retain changes)
"""
record = commission_test(sim_real_change, 0.10)
assert len(record) == len(sim_real_change.record)
def test_commission_real_change(sim_real_change):
""" Test commission test's ability to avoid merging real changes
This test is run with a relatively large p value (very likely to reject H0
and retain changes)
"""
record = commission_test(sim_real_change, 0.10)
assert len(record) == len(sim_real_change.record)
def test_commission_nochange(sim_nochange):
""" In no change situation, we should get back exactly what we gave in
"""
record = commission_test(sim_nochange, 0.10)
assert len(record) == 1
np.testing.assert_array_equal(record, sim_nochange.record)
def test_commission_no_real_change_2(sim_no_real_change_2):
""" Test commission test's ability to resolve two spurious changes
"""
record = commission_test(sim_no_real_change_2, 0.01)
assert len(record) == 1
assert record[0]['break'] == 0
def line(ctx, config, job_number, total_jobs,
resume, check_cache, do_not_run, verbose_yatsm):
if verbose_yatsm:
logger_algo.setLevel(logging.DEBUG)
# Parse config
cfg = parse_config_file(config)
if ('phenology' in cfg and cfg['phenology'].get('enable')) and not pheno:
click.secho('Could not import yatsm.phenology but phenology metrics '
'are requested', fg='red')
click.secho('Error: %s' % pheno_exception, fg='red')
raise click.Abort()
# Make sure output directory exists and is writable
output_dir = cfg['dataset']['output']
try:
os.makedirs(output_dir)
except OSError as e:
# File exists
if e.errno == 17:
pass
elif e.errno == 13:
click.secho('Cannot create output directory %s' % output_dir,
fg='red')
raise click.Abort()
if not os.access(output_dir, os.W_OK):
click.secho('Cannot write to output directory %s' % output_dir,
fg='red')
raise click.Abort()
# Test existence of cache directory
read_cache, write_cache = test_cache(cfg['dataset'])
logger.info('Job {i} of {n} - using config file {f}'.format(i=job_number,
n=total_jobs,
f=config))
df = csvfile_to_dataframe(cfg['dataset']['input_file'],
cfg['dataset']['date_format'])
df['image_ID'] = get_image_IDs(df['filename'])
# Get attributes of one of the images
nrow, ncol, nband, dtype = get_image_attribute(df['filename'][0])
# Calculate the lines this job ID works on
job_lines = distribute_jobs(job_number, total_jobs, nrow)
logger.debug('Responsible for lines: {l}'.format(l=job_lines))
# Calculate X feature input
dates = np.asarray(df['date'])
kws = {'x': dates}
kws.update(df.to_dict())
X = patsy.dmatrix(cfg['YATSM']['design_matrix'], kws)
cfg['YATSM']['design'] = X.design_info.column_name_indexes
# Form YATSM class arguments
fit_indices = np.arange(cfg['dataset']['n_bands'])
if cfg['dataset']['mask_band'] is not None:
fit_indices = fit_indices[:-1]
if cfg['YATSM']['reverse']:
X = np.flipud(X)
# Create output metadata to save
md = {
'YATSM': cfg['YATSM'],
cfg['YATSM']['algorithm']: cfg[cfg['YATSM']['algorithm']]
}
if cfg['phenology']['enable']:
md.update({'phenology': cfg['phenology']})
# Begin process
start_time_all = time.time()
for line in job_lines:
out = get_output_name(cfg['dataset'], line)
if resume:
try:
np.load(out)
except:
pass
else:
logger.debug('Already processed line %s' % line)
continue
logger.debug('Running line %s' % line)
start_time = time.time()
Y = read_line(line, df['filename'], df['image_ID'], cfg['dataset'],
ncol, nband, dtype,
read_cache=read_cache, write_cache=write_cache,
validate_cache=False)
if do_not_run:
continue
if cfg['YATSM']['reverse']:
Y = np.fliplr(Y)
output = []
for col in np.arange(Y.shape[-1]):
_Y = Y.take(col, axis=2)
# Mask
idx_mask = cfg['dataset']['mask_band'] - 1
valid = cyprep.get_valid_mask(
_Y,
cfg['dataset']['min_values'],
cfg['dataset']['max_values']).astype(bool)
valid *= np.in1d(_Y.take(idx_mask, axis=0),
cfg['dataset']['mask_values'],
invert=True).astype(np.bool)
_Y = np.delete(_Y, idx_mask, axis=0)[:, valid]
_X = X[valid, :]
_dates = dates[valid]
# Run model
cls = cfg['YATSM']['algorithm_cls']
algo_cfg = cfg[cfg['YATSM']['algorithm']]
yatsm = cls(lm=cfg['YATSM']['prediction_object'],
**algo_cfg.get('init', {}))
yatsm.px = col
yatsm.py = line
try:
yatsm.fit(_X, _Y, _dates, **algo_cfg.get('fit', {}))
except TSLengthException:
continue
if yatsm.record is None or len(yatsm.record) == 0:
continue
# Postprocess
if cfg['YATSM'].get('commission_alpha'):
yatsm.record = postprocess.commission_test(
yatsm, cfg['YATSM']['commission_alpha'])
for prefix, lm in zip(cfg['YATSM']['refit']['prefix'],
cfg['YATSM']['refit']['prediction_object']):
yatsm.record = postprocess.refit_record(yatsm, prefix, lm,
keep_regularized=True)
if cfg['phenology']['enable']:
pcfg = cfg['phenology']
ltm = pheno.LongTermMeanPhenology(**pcfg.get('init', {}))
yatsm.record = ltm.fit(yatsm, **pcfg.get('fit', {}))
output.extend(yatsm.record)
logger.debug(' Saving YATSM output to %s' % out)
np.savez(out,
record=np.array(output),
version=__version__,
metadata=md)
run_time = time.time() - start_time
logger.debug('Line %s took %ss to run' % (line, run_time))
logger.info('Completed {n} lines in {m} minutes'.format(
n=len(job_lines),
m=round((time.time() - start_time_all) / 60.0, 2)))
def test_commission_nochange(sim_nochange):
""" In no change situation, we should get back exactly what we gave in
"""
record = commission_test(sim_nochange, 0.10)
assert len(record) == 1
np.testing.assert_array_equal(record, sim_nochange.record)
def test_commission_no_real_change_2(sim_no_real_change_2):
""" Test commission test's ability to resolve two spurious changes
"""
record = commission_test(sim_no_real_change_2, 0.01)
assert len(record) == 1
assert record[0]['break'] == 0
def _fetch_results_live(self):
""" Run YATSM and get results """
logger.debug('Calculating YATSM results on the fly')
# Setup design matrix, Y, and dates
self.X = patsy.dmatrix(
self.controls['design'].value, {
'x': self.series[0].images['ordinal'],
'sensor': self.series[0].sensor,
'pr': self.series[0].pathrow
})
self._design_info = self.X.design_info.column_name_indexes
self.Y = self.series[0].data.astype(np.int16)
self.dates = np.asarray(self.series[0].images['ordinal'])
mask = self.Y[self.config['mask_band'].value[0] - 1, :]
Y_data = np.delete(self.Y,
self.config['mask_band'].value[0] - 1,
axis=0)
# Mask out masked values
clear = np.in1d(mask, self.mask_values, invert=True)
valid = get_valid_mask(Y_data, self.config['min_values'].value,
self.config['max_values'].value).astype(np.bool)
clear *= valid
# Setup parameters
estimator = sklearn.linear_model.Lasso(alpha=20)
reg = self.controls['regression_type'].value
if hasattr(yatsm.regression, 'packaged'):
if reg in yatsm.regression.packaged.packaged_regressions:
reg_fn = yatsm.regression.packaged.find_packaged_regressor(reg)
try:
estimator = jl.load(reg_fn)
except:
logger.error('Cannot load regressor: %s' % reg)
else:
logger.debug('Loaded regressor %s from %s' % (reg, reg_fn))
else:
logger.error('Cannot use unknown regression %s' % reg)
else:
logger.warning(
'Using failsafe Lasso(lambda=20) from scikit-learn. '
'Upgrade to yatsm>=0.5.1 to access more regressors.')
kwargs = dict(
estimator=estimator,
test_indices=self.controls['test_indices'].value,
consecutive=self.controls['consecutive'].value,
threshold=self.controls['threshold'].value,
min_obs=self.controls['min_obs'].value,
min_rmse=(None if self.controls['enable_min_rmse'].value else
self.controls['min_rmse'].value),
screening_crit=self.controls['screen_crit'].value,
remove_noise=self.controls['remove_noise'].value,
dynamic_rmse=self.controls['dynamic_rmse'].value,
)
self.yatsm_model = CCDCesque(**version_kwargs(kwargs))
# Don't want to have DEBUG logging when we run YATSM
log_level = logger.level
logger.setLevel(logging.INFO)
if self.controls['reverse'].value:
self.yatsm_model.fit(np.flipud(self.X[clear, :]),
np.fliplr(Y_data[:, clear]),
self.dates[clear][::-1])
else:
self.yatsm_model.fit(self.X[clear, :], Y_data[:, clear],
self.dates[clear])
if self.controls['commit_test'].value:
self.yatsm_model.record = postprocess.commission_test(
self.yatsm_model, self.controls['commit_alpha'].value)
# if self.controls['robust_results'].value:
# self.coef_name = 'robust_coef'
# self.yatsm_model.record = postprocess.refit_record(
# self.yatsm_model, 'robust'
# else:
# self.coef_name = 'coef'
if self.config['calc_pheno'].value:
# TODO: parameterize band indices & scale factor
ltm = pheno.LongTermMeanPhenology()
self.yatsm_model.record = ltm.fit(self.yatsm_model)
# Restore log level
logger.setLevel(log_level)
def _fetch_results_live(self):
""" Run YATSM and get results """
logger.debug('Calculating YATSM results on the fly')
# Setup design matrix, Y, and dates
self.X = patsy.dmatrix(self.controls['design'].value,
{'x': self.series[0].images['ordinal'],
'sensor': self.series[0].sensor,
'pr': self.series[0].pathrow})
self._design_info = self.X.design_info.column_name_indexes
self.Y = self.series[0].data.astype(np.int16)
self.dates = np.asarray(self.series[0].images['ordinal'])
mask = self.Y[self.config['mask_band'].value[0] - 1, :]
Y_data = np.delete(self.Y, self.config['mask_band'].value[0] - 1,
axis=0)
# Mask out masked values
clear = np.in1d(mask, self.mask_values, invert=True)
valid = get_valid_mask(Y_data,
self.config['min_values'].value,
self.config['max_values'].value).astype(np.bool)
clear *= valid
# Setup parameters
estimator = sklearn.linear_model.Lasso(alpha=20)
reg = self.controls['regression_type'].value
if hasattr(yatsm.regression, 'packaged'):
if reg in yatsm.regression.packaged.packaged_regressions:
reg_fn = yatsm.regression.packaged.find_packaged_regressor(reg)
try:
estimator = jl.load(reg_fn)
except:
logger.error('Cannot load regressor: %s' % reg)
else:
logger.debug('Loaded regressor %s from %s' % (reg, reg_fn))
else:
logger.error('Cannot use unknown regression %s' % reg)
else:
logger.warning(
'Using failsafe Lasso(lambda=20) from scikit-learn. '
'Upgrade to yatsm>=0.5.1 to access more regressors.')
kwargs = dict(
estimator=estimator,
test_indices=self.controls['test_indices'].value,
consecutive=self.controls['consecutive'].value,
threshold=self.controls['threshold'].value,
min_obs=self.controls['min_obs'].value,
min_rmse=(None if self.controls['enable_min_rmse'].value else
self.controls['min_rmse'].value),
screening_crit=self.controls['screen_crit'].value,
remove_noise=self.controls['remove_noise'].value,
dynamic_rmse=self.controls['dynamic_rmse'].value,
)
self.yatsm_model = CCDCesque(**version_kwargs(kwargs))
# Don't want to have DEBUG logging when we run YATSM
log_level = logger.level
logger.setLevel(logging.INFO)
if self.controls['reverse'].value:
self.yatsm_model.fit(
np.flipud(self.X[clear, :]),
np.fliplr(Y_data[:, clear]),
self.dates[clear][::-1])
else:
self.yatsm_model.fit(
self.X[clear, :],
Y_data[:, clear],
self.dates[clear])
if self.controls['commit_test'].value:
self.yatsm_model.record = postprocess.commission_test(
self.yatsm_model, self.controls['commit_alpha'].value)
# if self.controls['robust_results'].value:
# self.coef_name = 'robust_coef'
# self.yatsm_model.record = postprocess.refit_record(
# self.yatsm_model, 'robust'
# else:
# self.coef_name = 'coef'
if self.config['calc_pheno'].value:
# TODO: parameterize band indices & scale factor
ltm = pheno.LongTermMeanPhenology()
self.yatsm_model.record = ltm.fit(self.yatsm_model)
# Restore log level
logger.setLevel(log_level)
