def test_create_tornado_targets(self):
"""Ensures correct output from create_tornado_targets."""
this_storm_to_tornadoes_table = target_val_utils.create_tornado_targets(
storm_to_tornadoes_table=copy.deepcopy(STORM_TO_TORNADOES_TABLE),
min_lead_time_sec=MIN_LEAD_TIME_SEC,
max_lead_time_sec=MAX_LEAD_TIME_SEC,
min_link_distance_metres=MIN_LINK_DISTANCE_METRES,
max_link_distance_metres=MAX_LINK_DISTANCE_METRES)
these_target_values = this_storm_to_tornadoes_table[TARGET_NAME].values
self.assertTrue(numpy.array_equal(these_target_values, TARGET_VALUES))
def test_create_tornado_targets_genesis(self):
"""Ensures correct output from create_tornado_targets.
In this case, target value is based on tornadogenesis only, not
occurrence.
"""
this_storm_to_tornadoes_table = target_val_utils.create_tornado_targets(
storm_to_tornadoes_table=copy.deepcopy(STORM_TO_TORNADOES_TABLE),
min_lead_time_sec=MIN_LEAD_TIME_SEC,
max_lead_time_sec=MAX_LEAD_TIME_SEC,
min_link_distance_metres=MIN_LINK_DISTANCE_METRES,
max_link_distance_metres=MAX_LINK_DISTANCE_METRES,
genesis_only=True)
self.assertTrue(
numpy.array_equal(
this_storm_to_tornadoes_table[MAIN_TORNADOGENESIS_TARGET_NAME].
values, MAIN_TORNADOGENESIS_TARGET_VALUES))
def _run(top_linkage_dir_name, spc_date_string, min_lead_times_sec,
max_lead_times_sec, min_link_distances_metres,
max_link_distances_metres, event_type_string,
wind_speed_percentile_level, wind_speed_cutoffs_kt,
top_output_dir_name):
"""Computes target value for ea storm object, lead-time window, and buffer.
This is effectively the main method.
:param top_linkage_dir_name: See documentation at top of file.
:param spc_date_string: Same.
:param min_lead_times_sec: Same.
:param max_lead_times_sec: Same.
:param min_link_distances_metres: Same.
:param max_link_distances_metres: Same.
:param event_type_string: Same.
:param wind_speed_percentile_level: Same.
:param wind_speed_cutoffs_kt: Same.
:param top_output_dir_name: Same.
"""
num_lead_time_windows = len(min_lead_times_sec)
error_checking.assert_is_numpy_array(
max_lead_times_sec,
exact_dimensions=numpy.array([num_lead_time_windows])
)
num_distance_buffers = len(min_link_distances_metres)
error_checking.assert_is_numpy_array(
max_link_distances_metres,
exact_dimensions=numpy.array([num_distance_buffers])
)
linkage_file_name = linkage.find_linkage_file(
top_directory_name=top_linkage_dir_name,
event_type_string=event_type_string, spc_date_string=spc_date_string)
print 'Reading data from: "{0:s}"...'.format(linkage_file_name)
storm_to_events_table = linkage.read_linkage_file(linkage_file_name)
if event_type_string == linkage.WIND_EVENT_STRING:
list_of_cutoff_arrays_kt = general_utils.split_array_by_nan(
wind_speed_cutoffs_kt)
num_cutoff_sets = len(wind_speed_cutoffs_kt)
else:
list_of_cutoff_arrays_kt = None
num_cutoff_sets = 1
target_names = []
for i in range(num_lead_time_windows):
for j in range(num_distance_buffers):
for k in range(num_cutoff_sets):
if event_type_string == linkage.WIND_EVENT_STRING:
this_target_name = target_val_utils.target_params_to_name(
min_lead_time_sec=min_lead_times_sec[i],
max_lead_time_sec=max_lead_times_sec[i],
min_link_distance_metres=min_link_distances_metres[j],
max_link_distance_metres=max_link_distances_metres[j],
wind_speed_percentile_level=wind_speed_percentile_level,
wind_speed_cutoffs_kt=list_of_cutoff_arrays_kt[k])
target_names.append(this_target_name)
print 'Computing values for "{0:s}"...'.format(
target_names[-1])
storm_to_events_table = (
target_val_utils.create_wind_classification_targets(
storm_to_winds_table=storm_to_events_table,
min_lead_time_sec=min_lead_times_sec[i],
max_lead_time_sec=max_lead_times_sec[i],
min_link_distance_metres=min_link_distances_metres[
j],
max_link_distance_metres=max_link_distances_metres[
j],
percentile_level=wind_speed_percentile_level,
class_cutoffs_kt=list_of_cutoff_arrays_kt[k])
)
else:
this_target_name = target_val_utils.target_params_to_name(
min_lead_time_sec=min_lead_times_sec[i],
max_lead_time_sec=max_lead_times_sec[i],
min_link_distance_metres=min_link_distances_metres[j],
max_link_distance_metres=max_link_distances_metres[j])
target_names.append(this_target_name)
print 'Computing values for "{0:s}"...'.format(
target_names[-1])
storm_to_events_table = (
target_val_utils.create_tornado_targets(
storm_to_tornadoes_table=storm_to_events_table,
min_lead_time_sec=min_lead_times_sec[i],
max_lead_time_sec=max_lead_times_sec[i],
min_link_distance_metres=min_link_distances_metres[
j],
max_link_distance_metres=max_link_distances_metres[
j]
)
)
target_file_name = target_val_utils.find_target_file(
top_directory_name=top_output_dir_name,
event_type_string=event_type_string, spc_date_string=spc_date_string,
raise_error_if_missing=False)
print 'Writing target values to: "{0:s}"...'.format(target_file_name)
target_val_utils.write_target_values(
storm_to_events_table=storm_to_events_table, target_names=target_names,
netcdf_file_name=target_file_name)
def _compute_targets_one_day(storm_to_events_table, spc_date_string,
min_lead_times_sec, max_lead_times_sec,
min_link_distances_metres,
max_link_distances_metres, event_type_string,
wind_speed_percentile_level,
wind_speed_cutoffs_kt, top_output_dir_name):
"""Computes target values for one SPC date.
:param storm_to_events_table: pandas DataFrame returned by
`linkage.read_linkage_file`.
:param spc_date_string: SPC date (format "yyyymmdd").
:param min_lead_times_sec: See documentation at top of file.
:param max_lead_times_sec: Same.
:param min_link_distances_metres: Same.
:param max_link_distances_metres: Same.
:param event_type_string: Same.
:param wind_speed_percentile_level: Same.
:param wind_speed_cutoffs_kt: Same.
:param top_output_dir_name: Same.
"""
num_lead_time_windows = len(min_lead_times_sec)
num_distance_buffers = len(min_link_distances_metres)
if event_type_string == linkage.WIND_EVENT_STRING:
list_of_cutoff_arrays_kt = general_utils.split_array_by_nan(
wind_speed_cutoffs_kt)
num_cutoff_sets = len(wind_speed_cutoffs_kt)
else:
list_of_cutoff_arrays_kt = None
num_cutoff_sets = 1
target_names = []
for i in range(num_lead_time_windows):
for j in range(num_distance_buffers):
for k in range(num_cutoff_sets):
if event_type_string == linkage.WIND_EVENT_STRING:
this_target_name = target_val_utils.target_params_to_name(
min_lead_time_sec=min_lead_times_sec[i],
max_lead_time_sec=max_lead_times_sec[i],
min_link_distance_metres=min_link_distances_metres[j],
max_link_distance_metres=max_link_distances_metres[j],
wind_speed_percentile_level=wind_speed_percentile_level,
wind_speed_cutoffs_kt=list_of_cutoff_arrays_kt[k])
target_names.append(this_target_name)
print(('Computing labels for "{0:s}" on SPC date {1:s}...'
).format(this_target_name, spc_date_string))
storm_to_events_table = (
target_val_utils.create_wind_classification_targets(
storm_to_winds_table=storm_to_events_table,
min_lead_time_sec=min_lead_times_sec[i],
max_lead_time_sec=max_lead_times_sec[i],
min_link_distance_metres=min_link_distances_metres[
j],
max_link_distance_metres=max_link_distances_metres[
j],
percentile_level=wind_speed_percentile_level,
class_cutoffs_kt=list_of_cutoff_arrays_kt[k]))
else:
genesis_only = (event_type_string ==
linkage.TORNADOGENESIS_EVENT_STRING)
this_target_name = target_val_utils.target_params_to_name(
min_lead_time_sec=min_lead_times_sec[i],
max_lead_time_sec=max_lead_times_sec[i],
min_link_distance_metres=min_link_distances_metres[j],
max_link_distance_metres=max_link_distances_metres[j],
genesis_only=genesis_only)
target_names.append(this_target_name)
print(('Computing labels for "{0:s}" on SPC date {1:s}...'
).format(this_target_name, spc_date_string))
storm_to_events_table = (
target_val_utils.create_tornado_targets(
storm_to_tornadoes_table=storm_to_events_table,
min_lead_time_sec=min_lead_times_sec[i],
max_lead_time_sec=max_lead_times_sec[i],
min_link_distance_metres=min_link_distances_metres[
j],
max_link_distance_metres=max_link_distances_metres[
j],
genesis_only=genesis_only))
target_file_name = target_val_utils.find_target_file(
top_directory_name=top_output_dir_name,
event_type_string=event_type_string,
spc_date_string=spc_date_string,
raise_error_if_missing=False)
print('Writing target values to: "{0:s}"...'.format(target_file_name))
target_val_utils.write_target_values(
storm_to_events_table=storm_to_events_table,
target_names=target_names,
netcdf_file_name=target_file_name)
def _compute_tornado_targets_one_day(storm_to_tornadoes_table, spc_date_string,
min_lead_times_sec, max_lead_times_sec,
min_link_distances_metres,
max_link_distances_metres, genesis_only,
min_fujita_ratings, top_output_dir_name):
"""Computes tornado-related target values for one SPC date.
:param storm_to_tornadoes_table: pandas DataFrame returned by
`linkage.read_linkage_file`.
:param spc_date_string: SPC date (format "yyyymmdd").
:param min_lead_times_sec: See documentation at top of file.
:param max_lead_times_sec: Same.
:param min_link_distances_metres: Same.
:param max_link_distances_metres: Same.
:param genesis_only: Boolean flag. If True, will create labels for
tornadogenesis only. If False, will create labels for occurrence, which
includes pre-existing tornadoes (at forecast time).
:param min_fujita_ratings: Same.
:param top_output_dir_name: Same.
"""
num_time_windows = len(min_lead_times_sec)
num_distance_buffers = len(min_link_distances_metres)
num_strength_thresholds = len(min_fujita_ratings)
target_names = []
for i in range(num_time_windows):
for j in range(num_distance_buffers):
for k in range(num_strength_thresholds):
this_target_name = target_val_utils.target_params_to_name(
min_lead_time_sec=min_lead_times_sec[i],
max_lead_time_sec=max_lead_times_sec[i],
min_link_distance_metres=min_link_distances_metres[j],
max_link_distance_metres=max_link_distances_metres[j],
tornadogenesis_only=genesis_only,
min_fujita_rating=min_fujita_ratings[k])
target_names.append(this_target_name)
print(('Creating labels for "{0:s}" on SPC date "{1:s}"...'
).format(this_target_name, spc_date_string))
storm_to_tornadoes_table = (
target_val_utils.create_tornado_targets(
storm_to_tornadoes_table=storm_to_tornadoes_table,
min_lead_time_sec=min_lead_times_sec[i],
max_lead_time_sec=max_lead_times_sec[i],
min_link_distance_metres=min_link_distances_metres[j],
max_link_distance_metres=max_link_distances_metres[j],
genesis_only=genesis_only,
min_fujita_rating=min_fujita_ratings[k]))
print(SEPARATOR_STRING)
event_type_string = (linkage.TORNADOGENESIS_EVENT_STRING
if genesis_only else linkage.TORNADO_EVENT_STRING)
target_file_name = target_val_utils.find_target_file(
top_directory_name=top_output_dir_name,
event_type_string=event_type_string,
spc_date_string=spc_date_string,
raise_error_if_missing=False)
print('Writing target values to: "{0:s}"...'.format(target_file_name))
target_val_utils.write_target_values(
storm_to_events_table=storm_to_tornadoes_table,
target_names=target_names,
netcdf_file_name=target_file_name)