rompy.core.data.DataGrid#
- pydantic model rompy.core.data.DataGrid[source]#
Data object for gridded source data.
Generic data object for xarray datasets that with gridded spatial dimensions
Note
The fields filter_grid and filter_time trigger updates to the crop filter from the grid and time range objects passed to the get method. This is useful for data sources that are not defined on the same grid as the model grid or the same time range as the model run.
Show JSON schema
{ "title": "DataGrid", "description": "Data object for gridded source data.\n\nGeneric data object for xarray datasets that with gridded spatial dimensions\n\nNote\n----\nThe fields `filter_grid` and `filter_time` trigger updates to the crop filter from\nthe grid and time range objects passed to the get method. This is useful for data\nsources that are not defined on the same grid as the model grid or the same time\nrange as the model run.", "type": "object", "properties": { "model_type": { "const": "grid", "default": "grid", "description": "Model type discriminator", "title": "Model Type", "type": "string" }, "id": { "default": "data", "description": "Unique identifier for this data source", "title": "Id", "type": "string" }, "source": { "description": "Source reader, must return an xarray gridded dataset in the open method", "discriminator": { "mapping": { "csv": "#/$defs/SourceTimeseriesCSV", "datamesh": "#/$defs/SourceDatamesh", "file": "#/$defs/SourceFile", "intake": "#/$defs/SourceIntake", "wavespectra": "#/$defs/SourceWavespectra" }, "propertyName": "model_type" }, "oneOf": [ { "$ref": "#/$defs/SourceTimeseriesCSV" }, { "$ref": "#/$defs/SourceDatamesh" }, { "$ref": "#/$defs/SourceFile" }, { "$ref": "#/$defs/SourceIntake" }, { "$ref": "#/$defs/SourceWavespectra" } ], "title": "Source" }, "link": { "default": false, "description": "Whether to create a symbolic link instead of copying the file", "title": "Link", "type": "boolean" }, "filter": { "anyOf": [ { "$ref": "#/$defs/Filter" }, { "type": "null" } ], "description": "Optional filter specification to apply to the dataset" }, "variables": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": [], "description": "Subset of variables to extract from the dataset", "title": "Variables" }, "coords": { "anyOf": [ { "$ref": "#/$defs/DatasetCoords" }, { "type": "null" } ], "default": { "t": "time", "x": "longitude", "y": "latitude", "z": "depth", "s": "site" }, "description": "Names of the coordinates in the dataset" }, "crop_data": { "default": true, "description": "Update crop filters from Grid and Time objects if passed to get method", "title": "Crop Data", "type": "boolean" }, "buffer": { "default": 0.0, "description": "Space to buffer the grid bounding box if `filter_grid` is True", "title": "Buffer", "type": "number" }, "time_buffer": { "default": [ 0, 0 ], "description": "Number of source data timesteps to buffer the time range if `filter_time` is True", "items": { "type": "integer" }, "title": "Time Buffer", "type": "array" } }, "$defs": { "DatasetCoords": { "additionalProperties": false, "description": "Coordinates representation.", "properties": { "t": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "time", "description": "Name of the time coordinate", "title": "T" }, "x": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "longitude", "description": "Name of the x coordinate", "title": "X" }, "y": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "latitude", "description": "Name of the y coordinate", "title": "Y" }, "z": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "depth", "description": "Name of the z coordinate", "title": "Z" }, "s": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "site", "description": "Name of the site coordinate", "title": "S" } }, "title": "DatasetCoords", "type": "object" }, "Filter": { "additionalProperties": false, "properties": { "sort": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": {}, "title": "Sort" }, "subset": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": {}, "title": "Subset" }, "crop": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": {}, "title": "Crop" }, "timenorm": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": {}, "title": "Timenorm" }, "rename": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": {}, "title": "Rename" }, "derived": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": {}, "title": "Derived" } }, "title": "Filter", "type": "object" }, "SourceDatamesh": { "additionalProperties": false, "description": "Source dataset from Datamesh.\n\nDatamesh documentation: https://docs.oceanum.io/datamesh/index.html", "properties": { "model_type": { "const": "datamesh", "default": "datamesh", "description": "Model type discriminator", "title": "Model Type", "type": "string" }, "datasource": { "description": "The id of the datasource on Datamesh", "title": "Datasource", "type": "string" }, "token": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Datamesh API token, taken from the environment if not provided", "title": "Token" }, "kwargs": { "additionalProperties": true, "default": {}, "description": "Keyword arguments to pass to `oceanum.datamesh.Connector`", "title": "Kwargs", "type": "object" } }, "required": [ "datasource", "token" ], "title": "SourceDatamesh", "type": "object" }, "SourceFile": { "additionalProperties": false, "description": "Source dataset from file to open with xarray.open_dataset.", "properties": { "model_type": { "const": "file", "default": "file", "description": "Model type discriminator", "title": "Model Type", "type": "string" }, "uri": { "anyOf": [ { "type": "string" }, { "format": "path", "type": "string" } ], "description": "Path to the dataset", "title": "Uri" }, "kwargs": { "additionalProperties": true, "default": {}, "description": "Keyword arguments to pass to xarray.open_dataset", "title": "Kwargs", "type": "object" } }, "required": [ "uri" ], "title": "SourceFile", "type": "object" }, "SourceIntake": { "additionalProperties": false, "description": "Source dataset from intake catalog.\n\nnote\n----\nThe intake catalog can be prescribed either by the URI of an existing catalog file\nor by a YAML string defining the catalog. The YAML string can be obtained from\ncalling the `yaml()` method on an intake dataset instance.", "properties": { "model_type": { "const": "intake", "default": "intake", "description": "Model type discriminator", "title": "Model Type", "type": "string" }, "dataset_id": { "description": "The id of the dataset to read in the catalog", "title": "Dataset Id", "type": "string" }, "catalog_uri": { "anyOf": [ { "type": "string" }, { "format": "path", "type": "string" }, { "type": "null" } ], "default": null, "description": "The URI of the catalog to read from", "title": "Catalog Uri" }, "catalog_yaml": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The YAML string of the catalog to read from", "title": "Catalog Yaml" }, "kwargs": { "additionalProperties": true, "default": {}, "description": "Keyword arguments to define intake dataset parameters", "title": "Kwargs", "type": "object" } }, "required": [ "dataset_id" ], "title": "SourceIntake", "type": "object" }, "SourceTimeseriesCSV": { "additionalProperties": false, "description": "Timeseries source class from CSV file.\n\nThis class should return a timeseries from a CSV file. The dataset variables are\ndefined from the column headers, therefore the appropriate read_csv kwargs must be\npassed to allow defining the columns. The time index is defined from column name\nidentified by the tcol field.", "properties": { "model_type": { "const": "csv", "default": "csv", "description": "Model type discriminator", "title": "Model Type", "type": "string" }, "filename": { "anyOf": [ { "type": "string" }, { "format": "path", "type": "string" } ], "description": "Path to the csv file", "title": "Filename" }, "tcol": { "default": "time", "description": "Name of the column containing the time data", "title": "Tcol", "type": "string" }, "read_csv_kwargs": { "additionalProperties": true, "default": {}, "description": "Keyword arguments to pass to pandas.read_csv", "title": "Read Csv Kwargs", "type": "object" } }, "required": [ "filename" ], "title": "SourceTimeseriesCSV", "type": "object" }, "SourceWavespectra": { "additionalProperties": false, "description": "Wavespectra dataset from wavespectra reader.", "properties": { "model_type": { "const": "wavespectra", "default": "wavespectra", "description": "Model type discriminator", "title": "Model Type", "type": "string" }, "uri": { "anyOf": [ { "type": "string" }, { "format": "path", "type": "string" } ], "description": "Path to the dataset", "title": "Uri" }, "reader": { "description": "Name of the wavespectra reader to use, e.g., read_swan", "title": "Reader", "type": "string" }, "kwargs": { "additionalProperties": true, "default": {}, "description": "Keyword arguments to pass to the wavespectra reader", "title": "Kwargs", "type": "object" } }, "required": [ "uri", "reader" ], "title": "SourceWavespectra", "type": "object" } }, "additionalProperties": false, "required": [ "source" ] }
- Fields:
- field model_type: Literal['grid'] = 'grid'#
Model type discriminator
- field source: SourceTimeseriesCSV | SourceDatamesh | SourceFile | SourceIntake | SourceWavespectra [Required]#
Source reader, must return an xarray gridded dataset in the open method
- model_post_init(context: Any, /) None #
This function is meant to behave like a BaseModel method to initialise private attributes.
It takes context as an argument since that’s what pydantic-core passes when calling it.
- Parameters:
self – The BaseModel instance.
context – The context.