Utilities¶

Coordinate Utilities¶

A collection of utilities to manipulate and check coordinate systems dictionaries.

`handshake_dim`	Simple check to see if coordinate system has a dimension in a particular index
`handshake_coords`	Simple check to see if the required dimensions have the same coordinate system
`handshake_size`	Simple check to see if a coordinate system of a given dimension is a required size
`map_coords`	A basic interpolation util to map between coordinate systems with common dimensions.
`split_coords`	A utility function to split a dimension from a (x,coords) pair and convert it into a list of tensors, a CoordSystem, and the dimension that extract from coords.

LatLonInterpolation Bilinear interpolation between arbitrary grids.

ObsGridMapping Maps point observations to and from a 2-D model grid.

`timearray_to_datetime`	Simple converter from numpy datetime64 array into a list of datetimes.
`to_time_array`	A general converter for various time iterables into a numpy datetime64 array

`Checkpoint`	Catalog of restart checkpoints for a named inference run.
`CheckpointSession`	Active checkpoint row or new checkpoint session.
`CheckpointState`	Bound checkpoint state proxy returned by `bind_checkpoint_state`.
`NullCheckpoint`	No-op checkpoint used when checkpointing is disabled.

bind_checkpoint_state Bind a dataclass instance to checkpoint state metadata.

`datasource_to_file`	Utility function that can be used for building a local data store needed for an inference request.
`fetch_data`	Utility function to fetch data arrays from particular sources and load data on the target device.
`prep_data_array`	Prepares a data array from a data source for inference workflows by converting the data array to a torch tensor and the coordinate system to an OrderedDict.

Package A generic file system abstraction with local caching, uses Fsspec WholeFileCacheFileSystem to manage files.

batch_func Batch utility decorator which can be added to prognostic and diagnostic models to help enable support for automatic batching of data.