src.prepare_data#

Module Contents#

Classes#

_open

Class containing the dataset-specific code for opening each available dataset

Functions#

maybe_generate_CAFE_grid_files()

Generate files containing CAFE grids

prepare_dataset(config, save_dir[, save])

Prepare a dataset according to a provided config file

main(config, config_dir, save_dir)

Spin up a dask cluster and process and save raw data according to a provided config file

Attributes#

PROJECT_DIR

DATA_DIR

log_fmt

src.prepare_data.PROJECT_DIR#
src.prepare_data.DATA_DIR#
class src.prepare_data._open#

Class containing the dataset-specific code for opening each available dataset

static JRA55(variables, realm, preprocess)#

Open JRA55 variables from specified realm

static HadISST(variables, realm, preprocess)#

Open HadISST variables from specified realm

static EN422(variables, _, preprocess)#

Open EN.4.2.2 variables

static GPCP(variables, _, preprocess)#

Open GPCP v2.3 variables

static AGCD(variables, _, preprocess)#

Open AGCD variables

static CAFEf6(variables, realm, preprocess)#

Open CAFE-f6 variables from specified realm applying preprocess prior to concanenating forecasts

static CAFEf5(variables, realm, preprocess)#

Open CAFE-f5 variables from specified realm, including appending first 10 members of CAFE-f6 for 2020 forecast

static CAFE60v1(variables, realm, preprocess)#

Open CAFE60v1 variables from specified realm

static CAFE_hist(variables, realm, preprocess)#

Open CAFE historical run variables from specified realm

static _cmip6_dcppA_hindcast(model, variant_id, grid, variables, realm, years, members, version)#

Open CMIP6 dcppA-hindcast variables from specified monthly realm

static CanESM5(variables, realm, preprocess)#

Open CanESM5 dcppA-hindcast variables from specified monthly realm

static EC_Earth3(variables, realm, preprocess)#

Open EC-Earth3 dcppA-hindcast variables from specified monthly realm

static HadGEM3(variables, realm, preprocess)#

Open HadGEM3-GC31-MM dcppA-hindcast variables from specified monthly realm

static _cmip6(model, experiment, variant_id, grid, variables, realm, members, version)#

Open CMIP6 variables from specified realm

Can specify version=’latest’ but this is slower as it has to search each directory for the latest version

static CanESM5_hist(variables, realm, preprocess)#

Open CanESM5 historical variables from specified realm

static CanESM5_ctrl(variables, realm, preprocess)#

Open CanESM5 piControl variables from specified realm

static EC_Earth3_hist(variables, realm, preprocess)#

Open EC-Earth3 historical variables from specified realm

static EC_Earth3_ctrl(variables, realm, preprocess)#

Open EC-Earth3 piControl variables from specified realm

src.prepare_data.maybe_generate_CAFE_grid_files()#

Generate files containing CAFE grids

src.prepare_data.prepare_dataset(config, save_dir, save=True)#

Prepare a dataset according to a provided config file

Parameters
configstr

The name of the config file

save_dirstr

The directory to save to

saveboolean, optional

If True (default), save the prepared dataset(s) in zarr format to save_dir. If False, return an xarray Dataset containing the prepared data. The latter is useful for debugging

src.prepare_data.main(config, config_dir, save_dir)#

Spin up a dask cluster and process and save raw data according to a provided config file

Parameters
configstr

The name of the config file

config_dirstr

The directory containing the config file

save_dirstr

The directory to save to

src.prepare_data.log_fmt = %(asctime)s - %(name)s - %(levelname)s - %(message)s#