"""``HTMLDataset`` saves a plotly figure to an HTML file using an underlying
filesystem (e.g.: local, S3, GCS).
"""
from __future__ import annotations
from copy import deepcopy
from pathlib import PurePosixPath
from typing import Any, NoReturn
import fsspec
from kedro.io.core import (
AbstractVersionedDataset,
DatasetError,
Version,
get_filepath_str,
get_protocol_and_path,
)
from plotly import graph_objects as go
[docs]
class HTMLDataset(AbstractVersionedDataset[go.Figure, go.Figure | go.FigureWidget]):
"""``HTMLDataset`` saves a plotly figure to an HTML file using an
underlying filesystem (e.g.: local, S3, GCS).
Example usage for the
`YAML API <https://kedro.readthedocs.io/en/stable/data/\
data_catalog_yaml_examples.html>`_:
.. code-block:: yaml
scatter_plot:
type: plotly.HTMLDataset
filepath: data/08_reporting/scatter_plot.html
save_args:
auto_open: False
Example usage for the
`Python API <https://kedro.readthedocs.io/en/stable/data/\
advanced_data_catalog_usage.html>`_:
.. code-block:: pycon
>>> from kedro_datasets.plotly import HTMLDataset
>>> import plotly.express as px
>>>
>>> fig = px.bar(x=["a", "b", "c"], y=[1, 3, 2])
>>> dataset = HTMLDataset(filepath=tmp_path / "test.html")
>>> dataset.save(fig)
"""
DEFAULT_SAVE_ARGS: dict[str, Any] = {}
DEFAULT_FS_ARGS: dict[str, Any] = {
"open_args_save": {"mode": "w", "encoding": "utf-8"}
}
[docs]
def __init__( # noqa: PLR0913
self,
*,
filepath: str,
save_args: dict[str, Any] | None = None,
version: Version | None = None,
credentials: dict[str, Any] | None = None,
fs_args: dict[str, Any] | None = None,
metadata: dict[str, Any] | None = None,
) -> None:
"""Creates a new instance of ``HTMLDataset`` pointing to a concrete HTML file
on a specific filesystem.
Args:
filepath: Filepath in POSIX format to an HTML file prefixed with a protocol like `s3://`.
If prefix is not provided `file` protocol (local filesystem) will be used.
The prefix should be any protocol supported by ``fsspec``.
Note: `http(s)` doesn't support versioning.
save_args: Plotly options for saving HTML files.
Here you can find all available arguments:
https://plotly.com/python-api-reference/generated/plotly.io.write_html.html#plotly.io.write_html
All defaults are preserved.
version: If specified, should be an instance of
``kedro.io.core.Version``. If its ``load`` attribute is
None, the latest version will be loaded. If its ``save``
attribute is None, save version will be autogenerated.
credentials: Credentials required to get access to the underlying filesystem.
E.g. for ``GCSFileSystem`` it should look like `{'token': None}`.
fs_args: Extra arguments to pass into underlying filesystem class constructor
(e.g. `{"project": "my-project"}` for ``GCSFileSystem``), as well as
to pass to the filesystem's `open` method through nested keys
`open_args_load` and `open_args_save`.
Here you can find all available arguments for `open`:
https://filesystem-spec.readthedocs.io/en/latest/api.html#fsspec.spec.AbstractFileSystem.open
All defaults are preserved, except `mode`, which is set to `w` when
saving.
metadata: Any arbitrary metadata.
This is ignored by Kedro, but may be consumed by users or external plugins.
"""
_fs_args = deepcopy(fs_args) or {}
_fs_open_args_save = _fs_args.pop("open_args_save", {})
_credentials = deepcopy(credentials) or {}
protocol, path = get_protocol_and_path(filepath, version)
if protocol == "file":
_fs_args.setdefault("auto_mkdir", True)
self._protocol = protocol
self._fs = fsspec.filesystem(self._protocol, **_credentials, **_fs_args)
self.metadata = metadata
super().__init__(
filepath=PurePosixPath(path),
version=version,
exists_function=self._fs.exists,
glob_function=self._fs.glob,
)
# Handle default save and fs arguments
self._save_args = {**self.DEFAULT_SAVE_ARGS, **(save_args or {})}
self._fs_open_args_save = {
**self.DEFAULT_FS_ARGS.get("open_args_save", {}),
**(_fs_open_args_save or {}),
}
def _describe(self) -> dict[str, Any]:
return {
"filepath": self._filepath,
"protocol": self._protocol,
"save_args": self._save_args,
"version": self._version,
}
[docs]
def load(self) -> NoReturn:
raise DatasetError(f"Loading not supported for '{self.__class__.__name__}'")
[docs]
def save(self, data: go.Figure) -> None:
save_path = get_filepath_str(self._get_save_path(), self._protocol)
with self._fs.open(save_path, **self._fs_open_args_save) as fs_file:
data.write_html(fs_file, **self._save_args)
self._invalidate_cache()
def _exists(self) -> bool:
load_path = get_filepath_str(self._get_load_path(), self._protocol)
return self._fs.exists(load_path)
def _release(self) -> None:
super()._release()
self._invalidate_cache()
def _invalidate_cache(self) -> None:
filepath = get_filepath_str(self._filepath, self._protocol)
self._fs.invalidate_cache(filepath)
