def compute_indicator(args):
# extract the arguments
lon_index_start = args[0]
lat_index = args[1]
# turn the shared arrays into numpy arrays
input_data = np.ctypeslib.as_array(input_shared_array)
input_data = input_data.reshape(input_data_shape)
gamma_data = np.ctypeslib.as_array(output_gamma_array)
gamma_data = gamma_data.reshape(output_data_shape)
pearson_data = np.ctypeslib.as_array(output_pearson_array)
pearson_data = pearson_data.reshape(output_data_shape)
for lon_index in range(lons_per_chunk):
# only process non-empty grid cells, i.e. input_data array contains at least some non-NaN values
if (isinstance(input_data[:, lon_index, lat_index], np.ma.MaskedArray) and input_data[:, lon_index, lat_index].mask.all()) \
or np.isnan(input_data[:, lon_index, lat_index]).all() or (input_data[:, lon_index, lat_index] <= 0).all():
# logger.info('No input_data at lon/lat: {0}/{1}'.format(lon_index_start + lon_index, lat_index))
pass
else: # we have some valid values to work with
logger.info('Processing longitude/latitude: {}/{}'.format(lon_index_start + lon_index, lat_index))
for scale_index, month_scale in enumerate(month_scales):
# perform a fitting to gamma
gamma_data[scale_index, :, lon_index, lat_index] = indices.spi_gamma(input_data[:, lon_index, lat_index],
month_scale,
valid_min,
valid_max)
# perform a fitting to gamma
pearson_data[scale_index, :, lon_index, lat_index] = indices.spi_pearson(input_data[:, lon_index, lat_index],
month_scale,
valid_min,
valid_max,
data_start_year,
data_end_year,
calibration_start_year,
calibration_end_year)
# slice out the period of record for the x/y point
precip_data = precip_dataset.variables[precip_var_name][:, x, y]
# only process non-empty grid cells, i.e. the data array contains at least some non-NaN values
if (isinstance(precip_data, np.ma.MaskedArray)) and precip_data.mask.all():
continue
else: # we have some valid values to work with
for month_scale_index, month_scale_var_name in enumerate(sorted(datasets.keys())):
# perform the SPI computation (fit to the Pearson distribution) and assign the values into the dataset
datasets[month_scale_var_name].variables[month_scale_var_name][
:, x, y
] = indices.spi_pearson(
precip_data,
month_scales[month_scale_index],
valid_min,
valid_max,
data_start_date.year,
data_end_date.year,
calibration_start_year,
calibration_end_year,
)
except Exception, e:
logger.error("Failed to complete", exc_info=True)
raise
# loop over the grid cells
for x in range(precip_dataset.variables[x_dim_name].size):
for y in range(precip_dataset.variables[y_dim_name].size):
logger.info('Processing x/y {}/{}'.format(x, y))
# slice out the period of record for the x/y point
precip_data = precip_dataset.variables[precip_var_name][:, x, y]
# only process non-empty grid cells, i.e. data array contains at least some non-NaN values
if (isinstance(precip_data, np.ma.MaskedArray)) and precip_data.mask.all():
continue
else: # we have some valid values to work with
# perform the SPI computation (fit to the Gamma distribution) and assign the values into the dataset
output_dataset.variables[variable_name][:, x, y] = indices.spi_pearson(precip_data,
month_scale,
valid_min,
valid_max,
data_start_date.year,
data_end_date.year,
calibration_start_year,
calibration_end_year)
except Exception, e:
logger.error('Failed to complete', exc_info=True)
raise
def compute_worker(args):
# extract the arguments
lat_index = args[0]
# turn the shared array into a numpy array
data = np.ctypeslib.as_array(shared_array)
data = data.reshape(data_shape)
# data now expected to be in shape: (indicators, distributions, month_scales, times, lats)
#
# with indicator (spi: 0, spei: 1)
# distribution (gamma: 0, pearson: 1)
# month_scales (0, month_scales)
#
# with data[0, 0, 0] indicating the longitude slice with shape: (times, lats) with values for precipitation
# with data[1, 0, 0] indicating the longitude slice with shape: (times, lats) with values for temperature
# only process non-empty grid cells, i.e. data array contains at least some non-NaN values
if (isinstance(data[0, 0, 0, :, lat_index], np.ma.MaskedArray) and data[0, 0, 0, :, lat_index].mask.all()) \
or np.isnan(data[0, 0, 0, :, lat_index]).all() or (data[0, 0, 0, :, lat_index] <= 0).all():
pass
else: # we have some valid values to work with
logger.info('Processing latitude: {}'.format(lat_index))
for month_index, month_scale in enumerate(month_scales):
# only process month scales after 0 since month_scale = 0 is reserved for the input data
if month_index > 0:
# loop over all specified indicators
for indicator in indicators:
# loop over all specified distributions
for distribution in distributions:
if indicator == 'spi':
if distribution == 'gamma':
# perform a fitting to gamma
data[0, 0, month_index, :, lat_index] = indices.spi_gamma(data[0, 0, 0, :, lat_index],
month_scale,
valid_min,
valid_max)
elif distribution == 'pearson':
# perform a fitting to Pearson type III
data[0, 1, month_index, :, lat_index] = indices.spi_pearson(data[0, 0, 0, :, lat_index],
month_scale,
valid_min,
valid_max,
data_start_year,
data_end_year,
calibration_start_year,
calibration_end_year)
elif indicator == 'spei':
if distribution == 'gamma':
# perform a fitting to gamma
data[1, 0, month_index, :, lat_index] = indices.spei_gamma(data[0, 0, 0, :, lat_index],
data[0, 0, 1, :, lat_index],
data_start_year,
lats_array[lat_index],
month_scale,
valid_min,
valid_max)
elif distribution == 'pearson':
# perform a fitting to Pearson type III
data[1, 1, month_index, :, lat_index] = indices.spei_pearson(data[0, 0, 0, :, lat_index],
data[0, 0, 1, :, lat_index],
month_scale,
lats_array[lat_index],
valid_min,
valid_max,
data_start_year,
data_end_year,
calibration_start_year,
calibration_end_year)
else:
raise ValueError('Invalid distribution specified: {}'.format(distribution))
else:
raise ValueError('Invalid indicator specified: {}'.format(indicator))