def main():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description=
'Build and test models based on dim reductions and provided spectra')
parser.add_argument('--spectra_path',
type=str,
default='.',
metavar='PATH',
help='Spectra path to work from, if not '
'.'
'')
parser.add_argument('--method',
type=str,
default='ICA',
metavar='METHOD',
help='Dim reduction method to load data for')
parser.add_argument(
'--file_path',
type=str,
default=None,
metavar='FILE_PATH',
help='COMPLETE path from which to load a dim reduction')
args = parser.parse_args()
data_model = None
scaler = None
if args.file_path is not None:
data_model, scaler = ize.unpickle_model(filename=args.file_path)
else:
data_model, scaler = ize.unpickle_model(path=args.spectra_path,
method=args.method)
components = ize.get_components(args.method, data_model)
offset = 0
for i, comp_i in enumerate(components):
if i > 0:
offset += np.max(np.abs(comp_i[comp_i < 0])) * 1.2
plt.plot(stack.skyexp_wlen_out, comp_i + offset)
offset += np.max(comp_i[comp_i > 0]) * 1.2
plt.show()
plt.close()
def main():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="Build and test models based on dim reductions and provided spectra",
)
parser.add_argument(
"--spectra_path", type=str, default=".", metavar="PATH", help="Spectra path to work from, if not " "." ""
)
parser.add_argument(
"--method", type=str, default="ICA", metavar="METHOD", help="Dim reduction method to load data for"
)
parser.add_argument(
"--file_path",
type=str,
default=None,
metavar="FILE_PATH",
help="COMPLETE path from which to load a dim reduction",
)
args = parser.parse_args()
data_model = None
scaler = None
if args.file_path is not None:
data_model, scaler = ize.unpickle_model(filename=args.file_path)
else:
data_model, scaler = ize.unpickle_model(path=args.spectra_path, method=args.method)
components = ize.get_components(args.method, data_model)
offset = 0
for i, comp_i in enumerate(components):
if i > 0:
offset += np.max(np.abs(comp_i[comp_i < 0])) * 1.2
plt.plot(stack.skyexp_wlen_out, comp_i + offset)
offset += np.max(comp_i[comp_i > 0]) * 1.2
plt.show()
plt.close()
def animate_sky_spectra_for_coord(obs_time_start, obs_time_end, point_coord, lunar_metadata_file,
solar_metadata_file, sunspot_metadata_file, model_path, dm_path, dm_method):
metadata_tups, dates, lunar_data, solar_data, sunspot_data = get_sky_for_coord(obs_time_start,
obs_time_end, point_coord, lunar_metadata_file, solar_metadata_file, sunspot_metadata_file)
model = rfs.load_model(model_path)
dm, ss, model_args = iz.unpickle_model(path=dm_path, method=dm_method)
inv_spec = []
labels = []
for i, metadata in enumerate(metadata_tups):
#print(metadata)
np_metadata = np.array(metadata)
pred = model.predict(np_metadata.reshape(1, -1))
inv_spec.append(iz.inverse_transform(pred, dm, ss, dm_method, model_args)[0, :])
labels.append(dates[i] + "(ALT,AZ): (" + str(metadata[3]) + ", " + str(metadata[2]) + ")")
return inv_spec, labels
def main():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description='Build and test models based on dim reductions and provided spectra'
)
subparsers = parser.add_subparsers(dest='subparser_name')
parser.add_argument(
'--metadata_path', type=str, default='.', metavar='PATH',
help='Metadata path to work from, if not ''.'''
)
parser.add_argument(
'--spectra_path', type=str, default='.', metavar='PATH',
help='Spectra path to work from, if not ''.'''
)
parser.add_argument(
'--method', type=str, default='ICA', metavar='METHOD',
help='Dim reduction method to load data for'
)
parser.add_argument(
'--n_jobs', type=int, default=1, metavar='N_JOBS',
help='N_JOBS'
)
parser.add_argument(
'--model', type=str, choices=['ET', 'RF', 'GP', 'KNN', 'SVR'], default='ET',
help='Which model type to use: ET (Extra Trees), RF (Random Forest), GP (Gaussian Process), KNN, or SVR (Support Vector Regression)'
)
parser.add_argument(
'--load_model', action='store_true',
help='Whether or not to load the model from --model_path'
)
parser.add_argument(
'--model_path', type=str, default='model.pkl', metavar='MODEL_PATH',
help='COMPLETE path from which to load a model'
)
parser.add_argument(
'--metadata_flags', type=str, default='', metavar='METADATA_FLAGS',
help='Flags specifying observational metadata pre-processing, e.g. LUNAR_MAG which takes the '\
'magnitude and linearizes it (ignoring that it is an area magnitude)'
)
parser.add_argument(
'--compacted_path', type=str, default=None, metavar='COMPATED_PATH',
help='Path to find compacted/arrayized data; setting this will cause --path, --pattern to be ignored'
)
parser_compare = subparsers.add_parser('compare')
parser_compare.add_argument(
'--folds', type=int, default=3, metavar='TEST_FOLDS',
help='Do k-fold cross validation with specified number of folds. Defaults to 3.'
)
parser_compare.add_argument(
'--iters', type=int, default=50, metavar='HYPER_FIT_ITERS',
help='Number of iterations when fitting hyper-params'
)
parser_compare.add_argument(
'--outputfbk', action='store_true',
help='If set, outputs \'grid_scores_\' data from RandomizedSearchCV'
)
parser_compare.add_argument(
'--save_best', action='store_true',
help='Whether or not to save the (last/best) model built for e.g. --hyper_fit'
)
parser_compare.add_argument(
'--scorer', type=str, choices=['R2', 'MAE', 'MSE', 'LL', 'EXP_VAR', 'MAPED', 'MSEMV'], default='R2',
help='Which scoring method to use to determine ranking of model instances.'
)
parser_compare.add_argument(
'--use_spectra', action='store_true',
help='Whether scoring is done against the DM components or the predicted spectra'
)
parser_compare.add_argument(
'--ivar_cutoff', type=float, default=0.001, metavar='IVAR_CUTOFF',
help='data with inverse variace below cutoff is masked as if ivar==0'
)
parser_compare.add_argument(
'--plot_final_errors', action='store_true',
help='If set, will plot the errors from the final/best model, for the whole dataset, from ' + \
'the best model re-trained on CV folds used for testing.' + \
'Plots all errors on top of each other with low-ish alpha, to give a kind of visual ' + \
'density map of errors.'
)
args = parser.parse_args()
obs_metadata = trim_observation_metadata(load_observation_metadata(args.metadata_path, flags=args.metadata_flags))
sources, components, exposures, wavelengths = ICAize.deserialize_data(args.spectra_path, args.method)
source_model, ss, model_args = ICAize.unpickle_model(args.spectra_path, args.method)
comb_flux_arr, comb_exposure_arr, comb_wavelengths = None, None, None
if args.use_spectra:
comb_flux_arr, comb_exposure_arr, comb_ivar_arr, comb_masks, comb_wavelengths = ICAize.load_data(args)
filter_arr = np.in1d(comb_exposure_arr, exposures)
comb_flux_arr = comb_flux_arr[filter_arr]
comb_exposure_arr = comb_exposure_arr[filter_arr]
sorted_inds = np.argsort(comb_exposure_arr)
comb_flux_arr = comb_flux_arr[sorted_inds]
comb_exposure_arr = comb_exposure_arr[sorted_inds]
del comb_ivar_arr
del comb_masks
reduced_obs_metadata = obs_metadata[np.in1d(obs_metadata['EXP_ID'], exposures)]
reduced_obs_metadata.sort('EXP_ID')
sorted_inds = np.argsort(exposures)
reduced_obs_metadata.remove_column('EXP_ID')
md_len = len(reduced_obs_metadata)
var_count = len(reduced_obs_metadata.columns)
X_arr = np.array(reduced_obs_metadata).view('f8').reshape((md_len,-1))
Y_arr = sources[sorted_inds]
if args.load_model:
predictive_model = load_model(args.model_path)
else:
predictive_model = get_model(args.model)
if args.subparser_name == 'compare':
pdist = get_param_distribution_for_model(args.model, args.iters)
scorer = None
if args.scorer == 'R2':
scorer = make_scorer(R2)
elif args.scorer == 'MAE':
if args.use_spectra:
p_MAE_ = partial(MAE, Y_full=Y_arr, flux_arr=comb_flux_arr,
source_model=source_model, ss=ss,
source_model_args=model_args, method=args.method)
scorer = make_scorer(p_MAE_, greater_is_better=False)
else:
scorer = make_scorer(MAE, greater_is_better=False)
elif args.scorer == 'MSE':
if args.use_spectra:
p_MSE_ = partial(MSE, Y_full=Y_arr, flux_arr=comb_flux_arr,
source_model=source_model, ss=ss,
source_model_args=model_args, method=args.method)
scorer = make_scorer(p_MSE_, greater_is_better=False)
else:
scorer = make_scorer(MSE, greater_is_better=False)
elif args.scorer == 'MSEMV':
if args.use_spectra:
p_MSEMV_ = partial(MSEMV, Y_full=Y_arr, flux_arr=comb_flux_arr,
source_model=source_model, ss=ss,
source_model_args=model_args, method=args.method)
scorer = make_scorer(p_MSEMV_, greater_is_better=False)
else:
scorer = make_scorer(MSEMV, greater_is_better=False)
elif args.scorer == 'EXP_VAR':
if args.use_spectra:
p_EXP_VAR_ = partial(EXP_VAR, Y_full=Y_arr, flux_arr=comb_flux_arr,
source_model=source_model, ss=ss,
source_model_args=model_args, method=args.method)
scorer = make_scorer(p_EXP_VAR_)
else:
scorer = make_scorer(EXP_VAR)
elif args.scorer == 'MAPED':
if args.use_spectra:
p_MAPED_ = partial(MAPED, Y_full=Y_arr, flux_arr=comb_flux_arr,
source_model=source_model, ss=ss,
source_model_args=model_args, method=args.method)
scorer = make_scorer(p_MAPED_, greater_is_better=False)
else:
scorer = make_scorer(MAPED, greater_is_better=False)
elif args.scorer == 'LL':
scorer = None
folder = ShuffleSplit(exposures.shape[0], n_iter=args.folds, test_size=1.0/args.folds,
random_state=12345)
if args.model == 'GP':
predictive_model.random_start = args.folds
rcv = GridSearchCV(predictive_model, param_grid=pdist,
error_score=0, cv=3, n_jobs=args.n_jobs,
scoring=scorer)
#random_state=RANDOM_STATE,
#n_iter=args.iters,
else:
rcv = RandomizedSearchCV(predictive_model, param_distributions=pdist,
n_iter=args.iters, cv=folder, n_jobs=args.n_jobs,
scoring=scorer)
# This is going to fit X (metdata) to Y (DM'ed sources). But there are
# really two tests here: how well hyperparams fit/predict the sources
# and how well they fit/predict the actual source spectra. Until I know
# better, I 'm going to need to build a way to test both.
rcv.fit(X_arr, Y_arr)
print(rcv.best_score_)
print(rcv.best_params_)
print(rcv.best_estimator_)
if args.outputfbk:
print("=+"*10 + "=")
for val in rcv.grid_scores_:
print(val)
print("=+"*10 + "=")
if args.save_best:
save_model(rcv.best_estimator_, args.model_path)
if args.plot_final_errors:
for train_inds, test_inds in folder:
rcv.best_estimator_.fit(X_arr[train_inds], Y_arr[train_inds])
predicted = rcv.best_estimator_.predict(X_arr[test_inds])
back_trans_flux = ICAize.inverse_transform(predicted, source_model, ss, args.method, model_args)
diffs = np.abs(comb_flux_arr[test_inds] - back_trans_flux)
#Is there not 'trick' to getting matplotlib to do this without a loop?
for i in range(diffs.shape[0]):
plt.plot(comb_wavelengths, diffs[i, :], 'b-', alpha=0.01)
plt.show()
def main():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description=
'Build and test models based on dim reductions and provided spectra')
subparsers = parser.add_subparsers(dest='subparser_name')
parser.add_argument('--metadata_path',
type=str,
default='.',
metavar='PATH',
help='Metadata path to work from, if not '
'.'
'')
parser.add_argument('--spectra_path',
type=str,
default='.',
metavar='PATH',
help='Spectra path to work from, if not '
'.'
'')
parser.add_argument('--method',
type=str,
default='ICA',
metavar='METHOD',
help='Dim reduction method to load data for')
parser.add_argument('--n_jobs',
type=int,
default=1,
metavar='N_JOBS',
help='N_JOBS')
parser.add_argument(
'--model',
type=str,
choices=['ET', 'RF', 'GP', 'KNN', 'SVR'],
default='ET',
help=
'Which model type to use: ET (Extra Trees), RF (Random Forest), GP (Gaussian Process), KNN, or SVR (Support Vector Regression)'
)
parser.add_argument(
'--load_model',
action='store_true',
help='Whether or not to load the model from --model_path')
parser.add_argument('--model_path',
type=str,
default='model.pkl',
metavar='MODEL_PATH',
help='COMPLETE path from which to load a model')
parser.add_argument(
'--metadata_flags', type=str, default='', metavar='METADATA_FLAGS',
help='Flags specifying observational metadata pre-processing, e.g. LUNAR_MAG which takes the '\
'magnitude and linearizes it (ignoring that it is an area magnitude)'
)
parser.add_argument(
'--compacted_path',
type=str,
default=None,
metavar='COMPATED_PATH',
help=
'Path to find compacted/arrayized data; setting this will cause --path, --pattern to be ignored'
)
parser_compare = subparsers.add_parser('compare')
parser_compare.add_argument(
'--folds',
type=int,
default=3,
metavar='TEST_FOLDS',
help=
'Do k-fold cross validation with specified number of folds. Defaults to 3.'
)
parser_compare.add_argument(
'--iters',
type=int,
default=50,
metavar='HYPER_FIT_ITERS',
help='Number of iterations when fitting hyper-params')
parser_compare.add_argument(
'--outputfbk',
action='store_true',
help='If set, outputs \'grid_scores_\' data from RandomizedSearchCV')
parser_compare.add_argument(
'--save_best',
action='store_true',
help=
'Whether or not to save the (last/best) model built for e.g. --hyper_fit'
)
parser_compare.add_argument(
'--scorer',
type=str,
choices=['R2', 'MAE', 'MSE', 'LL', 'EXP_VAR', 'MAPED', 'MSEMV'],
default='R2',
help=
'Which scoring method to use to determine ranking of model instances.')
parser_compare.add_argument(
'--use_spectra',
action='store_true',
help=
'Whether scoring is done against the DM components or the predicted spectra'
)
parser_compare.add_argument(
'--ivar_cutoff',
type=float,
default=0.001,
metavar='IVAR_CUTOFF',
help='data with inverse variace below cutoff is masked as if ivar==0')
parser_compare.add_argument(
'--plot_final_errors', action='store_true',
help='If set, will plot the errors from the final/best model, for the whole dataset, from ' + \
'the best model re-trained on CV folds used for testing.' + \
'Plots all errors on top of each other with low-ish alpha, to give a kind of visual ' + \
'density map of errors.'
)
args = parser.parse_args()
obs_metadata = trim_observation_metadata(
load_observation_metadata(args.metadata_path,
flags=args.metadata_flags))
sources, components, exposures, wavelengths = ICAize.deserialize_data(
args.spectra_path, args.method)
source_model, ss, model_args = ICAize.unpickle_model(
args.spectra_path, args.method)
comb_flux_arr, comb_exposure_arr, comb_wavelengths = None, None, None
if args.use_spectra:
comb_flux_arr, comb_exposure_arr, comb_ivar_arr, comb_masks, comb_wavelengths = ICAize.load_data(
args)
filter_arr = np.in1d(comb_exposure_arr, exposures)
comb_flux_arr = comb_flux_arr[filter_arr]
comb_exposure_arr = comb_exposure_arr[filter_arr]
sorted_inds = np.argsort(comb_exposure_arr)
comb_flux_arr = comb_flux_arr[sorted_inds]
comb_exposure_arr = comb_exposure_arr[sorted_inds]
del comb_ivar_arr
del comb_masks
reduced_obs_metadata = obs_metadata[np.in1d(obs_metadata['EXP_ID'],
exposures)]
reduced_obs_metadata.sort('EXP_ID')
sorted_inds = np.argsort(exposures)
reduced_obs_metadata.remove_column('EXP_ID')
md_len = len(reduced_obs_metadata)
var_count = len(reduced_obs_metadata.columns)
X_arr = np.array(reduced_obs_metadata).view('f8').reshape((md_len, -1))
Y_arr = sources[sorted_inds]
if args.load_model:
predictive_model = load_model(args.model_path)
else:
predictive_model = get_model(args.model)
if args.subparser_name == 'compare':
pdist = get_param_distribution_for_model(args.model, args.iters)
scorer = None
if args.scorer == 'R2':
scorer = make_scorer(R2)
elif args.scorer == 'MAE':
if args.use_spectra:
p_MAE_ = partial(MAE,
Y_full=Y_arr,
flux_arr=comb_flux_arr,
source_model=source_model,
ss=ss,
source_model_args=model_args,
method=args.method)
scorer = make_scorer(p_MAE_, greater_is_better=False)
else:
scorer = make_scorer(MAE, greater_is_better=False)
elif args.scorer == 'MSE':
if args.use_spectra:
p_MSE_ = partial(MSE,
Y_full=Y_arr,
flux_arr=comb_flux_arr,
source_model=source_model,
ss=ss,
source_model_args=model_args,
method=args.method)
scorer = make_scorer(p_MSE_, greater_is_better=False)
else:
scorer = make_scorer(MSE, greater_is_better=False)
elif args.scorer == 'MSEMV':
if args.use_spectra:
p_MSEMV_ = partial(MSEMV,
Y_full=Y_arr,
flux_arr=comb_flux_arr,
source_model=source_model,
ss=ss,
source_model_args=model_args,
method=args.method)
scorer = make_scorer(p_MSEMV_, greater_is_better=False)
else:
scorer = make_scorer(MSEMV, greater_is_better=False)
elif args.scorer == 'EXP_VAR':
if args.use_spectra:
p_EXP_VAR_ = partial(EXP_VAR,
Y_full=Y_arr,
flux_arr=comb_flux_arr,
source_model=source_model,
ss=ss,
source_model_args=model_args,
method=args.method)
scorer = make_scorer(p_EXP_VAR_)
else:
scorer = make_scorer(EXP_VAR)
elif args.scorer == 'MAPED':
if args.use_spectra:
p_MAPED_ = partial(MAPED,
Y_full=Y_arr,
flux_arr=comb_flux_arr,
source_model=source_model,
ss=ss,
source_model_args=model_args,
method=args.method)
scorer = make_scorer(p_MAPED_, greater_is_better=False)
else:
scorer = make_scorer(MAPED, greater_is_better=False)
elif args.scorer == 'LL':
scorer = None
folder = ShuffleSplit(exposures.shape[0],
n_iter=args.folds,
test_size=1.0 / args.folds,
random_state=12345)
if args.model == 'GP':
predictive_model.random_start = args.folds
rcv = GridSearchCV(predictive_model,
param_grid=pdist,
error_score=0,
cv=3,
n_jobs=args.n_jobs,
scoring=scorer)
#random_state=RANDOM_STATE,
#n_iter=args.iters,
else:
rcv = RandomizedSearchCV(predictive_model,
param_distributions=pdist,
n_iter=args.iters,
cv=folder,
n_jobs=args.n_jobs,
scoring=scorer)
# This is going to fit X (metdata) to Y (DM'ed sources). But there are
# really two tests here: how well hyperparams fit/predict the sources
# and how well they fit/predict the actual source spectra. Until I know
# better, I 'm going to need to build a way to test both.
rcv.fit(X_arr, Y_arr)
print(rcv.best_score_)
print(rcv.best_params_)
print(rcv.best_estimator_)
if args.outputfbk:
print("=+" * 10 + "=")
for val in rcv.grid_scores_:
print(val)
print("=+" * 10 + "=")
if args.save_best:
save_model(rcv.best_estimator_, args.model_path)
if args.plot_final_errors:
for train_inds, test_inds in folder:
rcv.best_estimator_.fit(X_arr[train_inds], Y_arr[train_inds])
predicted = rcv.best_estimator_.predict(X_arr[test_inds])
back_trans_flux = ICAize.inverse_transform(
predicted, source_model, ss, args.method, model_args)
diffs = np.abs(comb_flux_arr[test_inds] - back_trans_flux)
#Is there not 'trick' to getting matplotlib to do this without a loop?
for i in range(diffs.shape[0]):
plt.plot(comb_wavelengths, diffs[i, :], 'b-', alpha=0.01)
plt.show()