dataeval.outputs.PixelStatsOutput¶

class dataeval.outputs.PixelStatsOutput¶

Output class for pixelstats() stats metric.

mean¶

Mean of the pixel values of the images

Type:¶

NDArray[np.float16]

std¶

Standard deviation of the pixel values of the images

Type:¶

NDArray[np.float16]

var¶

Variance of the pixel values of the images

Type:¶

NDArray[np.float16]

missing¶

Percentage of the images with missing pixels

Type:¶

NDArray[np.float16]

zeros¶

Percentage of the images with zero value pixels

Type:¶

NDArray[np.float16]

skew¶

Skew of the pixel values of the images

Type:¶

NDArray[np.float16]

kurtosis¶

Kurtosis of the pixel values of the images

Type:¶

NDArray[np.float16]

entropy¶

Entropy of the pixel values of the images

Type:¶

NDArray[np.float16]

histogram¶

Histogram of the pixel values of the images across 256 bins scaled between 0 and 1

Type:¶

NDArray[np.uint32]

data()¶

The output data as a dictionary.

Return type:¶

dict[str, Any]

factors(filter=None, exclude_constant=False)¶

Returns all 1-dimensional data as a dictionary of numpy arrays.

Parameters:¶

filter : str, Sequence[str] or None, default None:¶

If provided, only returns keys that match the filter.

exclude_constant : bool, default False¶

If True, exclude arrays that contain only a single unique value.

Return type:¶

Mapping[str, NDArray[Any]]

get_channel_mask(channel_index, channel_count=None)¶

Boolean mask for results filtered to specified channel index and optionally the count of the channels per image.

Parameters:¶

channel_index : int | Iterable[int] | None¶

Index or indices of channel(s) to filter for

channel_count : int | Iterable[int] | None¶

Optional count(s) of channels to filter for

Return type:¶

collections.abc.Sequence[bool]

meta()¶

Metadata about the execution of the function or method for the Output class.

Return type:¶

ExecutionMetadata

plot(log, channel_limit=None, channel_index=None)¶

Plots the statistics as a set of histograms.

Parameters:¶

log : bool¶

If True, plots the histograms on a logarithmic scale.

channel_limit : int or None¶

The maximum number of channels to plot. If None, all channels are plotted.

channel_index : int, Iterable[int] or None¶

The index or indices of the channels to plot. If None, all channels are plotted.

Return type:¶

matplotlib.Figure

to_dataframe()¶

Returns the processed factors a polars dataframe of shape (factors, samples)

Return type:¶

polars.DataFrame