def test_fluxes_to_heating_rate(self):
"""Ensures correct output from fluxes_to_heating_rate."""
this_example_dict = example_utils.fluxes_to_heating_rate(
copy.deepcopy(EXAMPLE_DICT_FLUXES_ONLY))
self.assertTrue(
_compare_example_dicts(this_example_dict,
EXAMPLE_DICT_WITH_HEATING_RATE))
def _fluxes_to_heating_rate(down_fluxes_w_m02, up_fluxes_w_m02, pressures_pa):
"""Converts upwelling and downwelling fluxes to heating rate at each level.
This is a light wrapper for `example_utils.fluxes_to_heating_rate`.
L = number of levels in grid
:param down_fluxes_w_m02: length-L numpy array of downwelling fluxes (Watts
per square metre).
:param up_fluxes_w_m02 : length-L numpy array of upwelling fluxes (Watts
per square metre).
:param pressures_pa: length-L numpy array of pressures (Pascals).
:return: heating_rates_k_day01: length-L numpy array of heating rates
(Kelvins per day).
"""
target_matrix = numpy.vstack((down_fluxes_w_m02, up_fluxes_w_m02))
target_matrix = numpy.expand_dims(numpy.transpose(target_matrix), axis=0)
predictor_matrix = numpy.expand_dims(pressures_pa, axis=-1)
predictor_matrix = numpy.expand_dims(predictor_matrix, axis=0)
dummy_example_dict = {
example_utils.VECTOR_TARGET_NAMES_KEY: [
example_utils.SHORTWAVE_DOWN_FLUX_NAME,
example_utils.SHORTWAVE_UP_FLUX_NAME
],
example_utils.VECTOR_TARGET_VALS_KEY:
target_matrix,
example_utils.VECTOR_PREDICTOR_NAMES_KEY:
[example_utils.PRESSURE_NAME],
example_utils.VECTOR_PREDICTOR_VALS_KEY:
predictor_matrix
}
dummy_example_dict = example_utils.fluxes_to_heating_rate(
dummy_example_dict)
return example_utils.get_field_from_dict(
example_dict=dummy_example_dict,
field_name=example_utils.SHORTWAVE_HEATING_RATE_NAME)[0, :]
def _get_predicted_heating_rates(prediction_example_dict,
pressure_matrix_pascals, model_metadata_dict):
"""Computes predicted heating rates from predicted flux-increment profiles.
:param prediction_example_dict: Dictionary with predictions. For a list of
keys, see doc for `example_io.read_file`.
:param pressure_matrix_pascals: See doc for `_get_unnormalized_pressure`.
:param model_metadata_dict: Same.
:return: prediction_example_dict: Same but with heating rates.
"""
num_examples = pressure_matrix_pascals.shape[0]
generator_option_dict = copy.deepcopy(
model_metadata_dict[neural_net.TRAINING_OPTIONS_KEY])
this_dict = {
example_utils.VECTOR_PREDICTOR_NAMES_KEY:
[example_utils.PRESSURE_NAME],
example_utils.VECTOR_PREDICTOR_VALS_KEY:
numpy.expand_dims(pressure_matrix_pascals, axis=-1),
example_utils.SCALAR_PREDICTOR_NAMES_KEY: [],
example_utils.SCALAR_PREDICTOR_VALS_KEY:
numpy.full((num_examples, 0), 0.),
example_utils.VALID_TIMES_KEY:
numpy.full(num_examples, 0, dtype=int)
}
prediction_example_dict.update(this_dict)
prediction_example_dict = (
example_utils.fluxes_increments_to_actual(prediction_example_dict))
prediction_example_dict = example_utils.fluxes_to_heating_rate(
prediction_example_dict)
target_names = (generator_option_dict[neural_net.VECTOR_TARGET_NAMES_KEY] +
generator_option_dict[neural_net.SCALAR_TARGET_NAMES_KEY])
return example_utils.subset_by_field(example_dict=prediction_example_dict,
field_names=target_names)
def _fluxes_to_heating_rate(vector_target_matrix, vector_prediction_matrix,
model_metadata_dict, prediction_file_name,
example_dir_name):
"""If necessary, converts fluxes to heating rates.
This method is a wrapper for `example_utils.fluxes_to_heating_rate`.
:param vector_target_matrix: See doc for `_fluxes_increments_to_actual`.
:param vector_prediction_matrix: Same.
:param model_metadata_dict: Same.
:param prediction_file_name: See documentation at top of file.
:param example_dir_name: Same.
:return: vector_target_matrix: See doc for `_fluxes_increments_to_actual`.
:return: vector_prediction_matrix: Same.
:return: model_metadata_dict: Same.
"""
generator_option_dict = model_metadata_dict[
neural_net.TRAINING_OPTIONS_KEY]
vector_target_names = (
generator_option_dict[neural_net.VECTOR_TARGET_NAMES_KEY])
need_heating_rate = (example_utils.SHORTWAVE_HEATING_RATE_NAME
not in vector_target_names)
have_fluxes = all([t in vector_target_names for t in FLUX_NAMES])
if not (need_heating_rate and have_fluxes
and example_dir_name is not None):
return (vector_target_matrix, vector_prediction_matrix,
model_metadata_dict)
num_examples = vector_target_matrix.shape[0]
this_example_dict = misc_utils.get_raw_examples(
example_file_name='',
num_examples=0,
example_dir_name=example_dir_name,
example_id_file_name=prediction_file_name)
this_example_dict = example_utils.subset_by_height(
example_dict=this_example_dict,
heights_m_agl=generator_option_dict[neural_net.HEIGHTS_KEY])
pressure_matrix_pascals = example_utils.get_field_from_dict(
example_dict=this_example_dict, field_name=example_utils.PRESSURE_NAME)
pressure_matrix_pascals = pressure_matrix_pascals[:num_examples, ...]
base_example_dict = {
example_utils.SCALAR_PREDICTOR_NAMES_KEY: [],
example_utils.SCALAR_PREDICTOR_VALS_KEY:
numpy.full((num_examples, 0), 0.),
example_utils.VECTOR_PREDICTOR_NAMES_KEY:
[example_utils.PRESSURE_NAME],
example_utils.VECTOR_PREDICTOR_VALS_KEY:
numpy.expand_dims(pressure_matrix_pascals, axis=-1),
example_utils.SCALAR_TARGET_NAMES_KEY: [],
example_utils.SCALAR_TARGET_VALS_KEY:
numpy.full((num_examples, 0), 0.),
example_utils.VECTOR_TARGET_NAMES_KEY:
generator_option_dict[neural_net.VECTOR_TARGET_NAMES_KEY],
example_utils.HEIGHTS_KEY:
generator_option_dict[neural_net.HEIGHTS_KEY],
example_utils.VALID_TIMES_KEY:
numpy.full(num_examples, 0, dtype=int)
}
target_example_dict = copy.deepcopy(base_example_dict)
target_example_dict[example_utils.VECTOR_TARGET_VALS_KEY] = (
vector_target_matrix)
target_example_dict = example_utils.fluxes_to_heating_rate(
target_example_dict)
vector_target_matrix = (
target_example_dict[example_utils.VECTOR_TARGET_VALS_KEY])
prediction_example_dict = copy.deepcopy(base_example_dict)
prediction_example_dict[example_utils.VECTOR_TARGET_VALS_KEY] = (
vector_prediction_matrix)
prediction_example_dict = example_utils.fluxes_to_heating_rate(
prediction_example_dict)
vector_prediction_matrix = (
prediction_example_dict[example_utils.VECTOR_TARGET_VALS_KEY])
generator_option_dict[neural_net.VECTOR_TARGET_NAMES_KEY] = (
target_example_dict[example_utils.VECTOR_TARGET_NAMES_KEY])
model_metadata_dict[neural_net.TRAINING_OPTIONS_KEY] = (
generator_option_dict)
return vector_target_matrix, vector_prediction_matrix, model_metadata_dict