dataeval 0.74.1__py3-none-any.whl → 0.75.0__py3-none-any.whl

dataeval/metrics/stats/labelstats.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-__all__ = ["LabelStatsOutput", "labelstats"]
+__all__ = []
 
 from collections import Counter, defaultdict
 from dataclasses import dataclass
@@ -86,13 +86,13 @@ def labelstats(
 
     >>> stats = labelstats(labels)
     >>> stats.label_counts_per_class
-    {'chicken': 3, 'cow': 8, 'horse': 9, 'pig': 7, 'sheep': 7}
+    {'chicken': 12, 'cow': 5, 'horse': 4, 'pig': 7, 'sheep': 4}
     >>> stats.label_counts_per_image
-    [3, 2, 3, 4, 1, 5, 4, 4, 4, 4]
+    [3, 3, 5, 3, 2, 5, 5, 2, 2, 2]
     >>> stats.image_counts_per_label
-    {'chicken': 2, 'cow': 6, 'horse': 7, 'pig': 5, 'sheep': 7}
+    {'chicken': 8, 'cow': 4, 'horse': 4, 'pig': 7, 'sheep': 4}
     >>> (stats.image_count, stats.class_count, stats.label_count)
-    (10, 5, 34)
+    (10, 5, 32)
     """
     label_counts = Counter()
     image_counts = Counter()

dataeval/metrics/stats/pixelstats.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-__all__ = ["PixelStatsOutput", "pixelstats"]
+__all__ = []
 
 from dataclasses import dataclass
 from typing import Any, Callable, Iterable
@@ -106,15 +106,10 @@ def pixelstats(
     --------
     Calculating the statistics on the images, whose shape is (C, H, W)
 
-    >>> results = pixelstats(images)
+    >>> results = pixelstats(stats_images)
     >>> print(results.mean)
-    [0.04828 0.562   0.06726 0.09937 0.1315  0.1636  0.1957  0.2278  0.26
-     0.292   0.3242  0.3562  0.3884  0.4204  0.4526  0.4846  0.5166  0.549
-     0.581   0.6133  0.6455  0.6772  0.7095  0.7417  0.774   0.8057  0.838
-     0.87    0.9023  0.934  ]
+    [0.2903 0.2108 0.397  0.596  0.743 ]
     >>> print(results.entropy)
-    [3.238  3.303  0.8125 1.028  0.8223 1.046  0.8247 1.041  0.8203 1.012
-     0.812  0.9883 0.795  0.9243 0.9243 0.795  0.9907 0.8125 1.028  0.8223
-     1.046  0.8247 1.041  0.8203 1.012  0.812  0.9883 0.795  0.9243 0.9243]
+    [4.99  2.371 1.179 2.406 0.668]
     """
     return run_stats(images, bboxes, per_channel, [PixelStatsProcessor])[0]

dataeval/metrics/stats/visualstats.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-__all__ = ["VisualStatsOutput", "visualstats"]
+__all__ = []
 
 from dataclasses import dataclass
 from typing import Any, Callable, Iterable
@@ -112,15 +112,10 @@ def visualstats(
     --------
     Calculating the :term:`statistics<Statistics>` on the images, whose shape is (C, H, W)
 
-    >>> results = visualstats(images)
+    >>> results = visualstats(stats_images)
     >>> print(results.brightness)
-    [0.02246 0.5557  0.06805 0.1014  0.1348  0.1681  0.2014  0.2347  0.268
-     0.3015  0.3347  0.3682  0.4014  0.4348  0.468   0.5015  0.5347  0.568
-     0.6016  0.635   0.668   0.701   0.735   0.768   0.8013  0.835   0.868
-     0.9014  0.9346  0.9683 ]
+    [0.1353 0.2085 0.4143 0.6084 0.8135]
     >>> print(results.contrast)
-    [2.041 1.332 1.293 1.279 1.272 1.268 1.265 1.263 1.261 1.26  1.259 1.258
-     1.258 1.257 1.257 1.256 1.256 1.255 1.255 1.255 1.255 1.254 1.254 1.254
-     1.254 1.254 1.254 1.253 1.253 1.253]
+    [2.04  1.331 1.261 1.279 1.253]
     """
     return run_stats(images, bboxes, per_channel, [VisualStatsProcessor])[0]

dataeval/output.py

@@ -65,7 +65,7 @@ R = TypeVar("R", bound=Output)
 
 
 def set_metadata(fn: Callable[P, R] | None = None, *, state: list[str] | None = None) -> Callable[P, R]:
-    """Decorator to stamp OutputMetadata classes with runtime metadata"""
+    """Decorator to stamp Output classes with runtime metadata"""
 
     if fn is None:
         return partial(set_metadata, state=state)  # type: ignore

dataeval/utils/__init__.py

@@ -1,18 +1,9 @@
 """
 The utility classes and functions are provided by DataEval to assist users
-in setting up architectures that are guaranteed to work with applicable DataEval
-metrics. Currently DataEval supports both :term:`TensorFlow` and PyTorch backends.
+in setting up data and architectures that are guaranteed to work with applicable
+DataEval metrics.
 """
 
-from dataeval import _IS_TORCH_AVAILABLE
-from dataeval.utils.metadata import merge_metadata
-from dataeval.utils.split_dataset import split_dataset
+__all__ = ["dataset", "metadata", "torch"]
 
-__all__ = ["split_dataset", "merge_metadata"]
-
-if _IS_TORCH_AVAILABLE:
-    from dataeval.utils import torch
-
-    __all__ += ["torch"]
-
-del _IS_TORCH_AVAILABLE
+from dataeval.utils import dataset, metadata, torch

dataeval/utils/dataset/__init__.py

@@ -0,0 +1,7 @@
+"""Provides utility functions for interacting with Computer Vision datasets."""
+
+__all__ = ["datasets", "read_dataset", "SplitDatasetOutput", "split_dataset"]
+
+from dataeval.utils.dataset import datasets
+from dataeval.utils.dataset.read import read_dataset
+from dataeval.utils.dataset.split import SplitDatasetOutput, split_dataset

dataeval/utils/{torch → dataset}/datasets.py

@@ -1,3 +1,5 @@
+"""Provides access to common Computer Vision datasets."""
+
 from __future__ import annotations
 
 __all__ = ["MNIST", "CIFAR10", "VOCDetection"]

dataeval/utils/dataset/read.py

@@ -0,0 +1,63 @@
+from __future__ import annotations
+
+__all__ = []
+
+from collections import defaultdict
+from typing import Any
+
+from torch.utils.data import Dataset
+
+
+def read_dataset(dataset: Dataset[Any]) -> list[list[Any]]:
+    """
+    Extract information from a dataset at each index into individual lists of each information position
+
+    Parameters
+    ----------
+    dataset : torch.utils.data.Dataset
+        Input dataset
+
+    Returns
+    -------
+    List[List[Any]]
+        All objects in individual lists based on return position from dataset
+
+    Warning
+    -------
+    No type checking is done between lists or data inside lists
+
+    See Also
+    --------
+    torch.utils.data.Dataset
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> data = np.ones((10, 1, 3, 3))
+    >>> labels = np.ones((10,))
+    >>> class ICDataset:
+    ...     def __init__(self, data, labels):
+    ...         self.data = data
+    ...         self.labels = labels
+    ...
+    ...     def __getitem__(self, idx):
+    ...         return self.data[idx], self.labels[idx]
+
+    >>> ds = ICDataset(data, labels)
+
+    >>> result = read_dataset(ds)
+    >>> len(result)  # images and labels
+    2
+    >>> np.asarray(result[0]).shape  # images
+    (10, 1, 3, 3)
+    >>> np.asarray(result[1]).shape  # labels
+    (10,)
+    """
+
+    ddict: dict[int, list[Any]] = defaultdict(list[Any])
+
+    for data in dataset:
+        for i, d in enumerate(data if isinstance(data, tuple) else (data,)):
+            ddict[i].append(d)
+
+    return list(ddict.values())