dataeval 0.72.1__py3-none-any.whl → 0.73.0__py3-none-any.whl

dataeval/_internal/detectors/ood/aegmm.py

@@ -1,78 +0,0 @@
-"""
-Source code derived from Alibi-Detect 0.11.4
-https://github.com/SeldonIO/alibi-detect/tree/v0.11.4
-
-Original code Copyright (c) 2023 Seldon Technologies Ltd
-Licensed under Apache Software License (Apache 2.0)
-"""
-
-from __future__ import annotations
-
-from typing import Callable
-
-import tensorflow as tf
-import tf_keras as keras
-from numpy.typing import ArrayLike
-
-from dataeval._internal.detectors.ood.base import OODGMMBase, OODScoreOutput
-from dataeval._internal.interop import to_numpy
-from dataeval._internal.models.tensorflow.autoencoder import AEGMM
-from dataeval._internal.models.tensorflow.gmm import gmm_energy
-from dataeval._internal.models.tensorflow.losses import LossGMM
-from dataeval._internal.models.tensorflow.utils import predict_batch
-from dataeval._internal.output import set_metadata
-
-
-class OOD_AEGMM(OODGMMBase):
-    """
-    AE with Gaussian Mixture Model based outlier detector.
-
-    Parameters
-    ----------
-    model : AEGMM
-       An AEGMM model.
-    """
-
-    def __init__(self, model: AEGMM) -> None:
-        super().__init__(model)
-
-    def fit(
-        self,
-        x_ref: ArrayLike,
-        threshold_perc: float = 100.0,
-        loss_fn: Callable[..., tf.Tensor] | None = None,
-        optimizer: keras.optimizers.Optimizer = keras.optimizers.Adam,
-        epochs: int = 20,
-        batch_size: int = 64,
-        verbose: bool = True,
-    ) -> None:
-        if loss_fn is None:
-            loss_fn = LossGMM()
-        super().fit(x_ref, threshold_perc, loss_fn, optimizer, epochs, batch_size, verbose)
-
-    @set_metadata("dataeval.detectors")
-    def score(self, X: ArrayLike, batch_size: int = int(1e10)) -> OODScoreOutput:
-        """
-        Compute the :term:`out of distribution<Out-of-distribution (OOD)>` score for a given dataset.
-
-        Parameters
-        ----------
-        X : ArrayLike
-            Input data to score.
-        batch_size : int, default 1e10
-            Number of instances to process in each batch.
-            Use a smaller batch size if your dataset is large or if you encounter memory issues.
-
-        Returns
-        -------
-        OODScoreOutput
-            An object containing the instance-level OOD score.
-
-        Note
-        ----
-        This model does not produce a feature level score like the OOD_AE or OOD_VAE models.
-        """
-        self._validate(X := to_numpy(X))
-        _, z, _ = predict_batch(X, self.model, batch_size=batch_size)
-        energy, _ = gmm_energy(z, self.gmm_params, return_mean=False)
-        return OODScoreOutput(energy.numpy())  # type: ignore

dataeval/_internal/detectors/ood/vaegmm.py

@@ -1,89 +0,0 @@
-"""
-Source code derived from Alibi-Detect 0.11.4
-https://github.com/SeldonIO/alibi-detect/tree/v0.11.4
-
-Original code Copyright (c) 2023 Seldon Technologies Ltd
-Licensed under Apache Software License (Apache 2.0)
-"""
-
-from __future__ import annotations
-
-from typing import Callable
-
-import numpy as np
-import tensorflow as tf
-import tf_keras as keras
-from numpy.typing import ArrayLike
-
-from dataeval._internal.detectors.ood.base import OODGMMBase, OODScoreOutput
-from dataeval._internal.interop import to_numpy
-from dataeval._internal.models.tensorflow.autoencoder import VAEGMM
-from dataeval._internal.models.tensorflow.gmm import gmm_energy
-from dataeval._internal.models.tensorflow.losses import Elbo, LossGMM
-from dataeval._internal.models.tensorflow.utils import predict_batch
-from dataeval._internal.output import set_metadata
-
-
-class OOD_VAEGMM(OODGMMBase):
-    """
-    VAE with Gaussian Mixture Model based outlier detector.
-
-    Parameters
-    ----------
-    model : VAEGMM
-        A VAEGMM model.
-    samples
-        Number of samples sampled to evaluate each instance.
-    """
-
-    def __init__(self, model: VAEGMM, samples: int = 10) -> None:
-        super().__init__(model)
-        self.samples = samples
-
-    def fit(
-        self,
-        x_ref: ArrayLike,
-        threshold_perc: float = 100.0,
-        loss_fn: Callable[..., tf.Tensor] | None = None,
-        optimizer: keras.optimizers.Optimizer = keras.optimizers.Adam,
-        epochs: int = 20,
-        batch_size: int = 64,
-        verbose: bool = True,
-    ) -> None:
-        if loss_fn is None:
-            loss_fn = LossGMM(elbo=Elbo(0.05))
-        super().fit(x_ref, threshold_perc, loss_fn, optimizer, epochs, batch_size, verbose)
-
-    @set_metadata("dataeval.detectors")
-    def score(self, X: ArrayLike, batch_size: int = int(1e10)) -> OODScoreOutput:
-        """
-        Compute the out of distributuion<Out-of-distribution (OOD)>` score for a given dataset.
-
-        Parameters
-        ----------
-        X : ArrayLike
-            Input data to score.
-        batch_size : int, default 1e10
-            Number of instances to process in each batch.
-            Use a smaller batch size if your dataset is large or if you encounter memory issues.
-
-        Returns
-        -------
-        OODScoreOutput
-            An object containing the instance-level OOD score.
-
-        Note
-        ----
-        This model does not produce a feature level score like the OOD_AE or OOD_VAE models.
-        """
-        self._validate(X := to_numpy(X))
-
-        # draw samples from latent space
-        X_samples = np.repeat(X, self.samples, axis=0)
-        _, z, _ = predict_batch(X_samples, self.model, batch_size=batch_size)
-
-        # compute average energy for samples
-        energy, _ = gmm_energy(z, self.gmm_params, return_mean=False)
-        energy_samples = energy.numpy().reshape((-1, self.samples))  # type: ignore
-        iscore = np.mean(energy_samples, axis=-1)
-        return OODScoreOutput(iscore)

dataeval/_internal/interop.py

@@ -1,49 +0,0 @@
-from __future__ import annotations
-
-from importlib import import_module
-from typing import Any, Iterable, Iterator
-
-import numpy as np
-from numpy.typing import ArrayLike, NDArray
-
-module_cache = {}
-
-
-def try_import(module_name):
-    if module_name in module_cache:
-        return module_cache[module_name]
-
-    try:
-        module = import_module(module_name)
-    except ImportError:  # pragma: no cover - covered by test_mindeps.py
-        module = None
-
-    module_cache[module_name] = module
-    return module
-
-
-def as_numpy(array: ArrayLike | None) -> NDArray[Any]:
-    return to_numpy(array, copy=False)
-
-
-def to_numpy(array: ArrayLike | None, copy: bool = True) -> NDArray[Any]:
-    if array is None:
-        return np.ndarray([])
-
-    if isinstance(array, np.ndarray):
-        return array.copy() if copy else array
-
-    tf = try_import("tensorflow")
-    if tf and tf.is_tensor(array):
-        return array.numpy().copy() if copy else array.numpy()  # type: ignore
-
-    torch = try_import("torch")
-    if torch and isinstance(array, torch.Tensor):
-        return array.detach().cpu().numpy().copy() if copy else array.detach().cpu().numpy()  # type: ignore
-
-    return np.array(array, copy=copy)
-
-
-def to_numpy_iter(iterable: Iterable[ArrayLike]) -> Iterator[NDArray[Any]]:
-    for array in iterable:
-        yield to_numpy(array)

dataeval/_internal/metrics/stats/hashstats.py

@@ -1,75 +0,0 @@
-from __future__ import annotations
-
-from dataclasses import dataclass
-from typing import Iterable
-
-from numpy.typing import ArrayLike
-
-from dataeval._internal.metrics.stats.base import BaseStatsOutput, StatsProcessor, run_stats
-from dataeval._internal.metrics.utils import pchash, xxhash
-from dataeval._internal.output import set_metadata
-
-
-@dataclass(frozen=True)
-class HashStatsOutput(BaseStatsOutput):
-    """
-    Output class for :func:`hashstats` stats metric
-
-    Attributes
-    ----------
-    xxhash : List[str]
-        xxHash hash of the images as a hex string
-    pchash : List[str]
-        :term:`Perception-based Hash` of the images as a hex string
-    """
-
-    xxhash: list[str]
-    pchash: list[str]
-
-
-class HashStatsProcessor(StatsProcessor[HashStatsOutput]):
-    output_class = HashStatsOutput
-    image_function_map = {
-        "xxhash": lambda x: xxhash(x.image),
-        "pchash": lambda x: pchash(x.image),
-    }
-
-
-@set_metadata("dataeval.metrics")
-def hashstats(
-    images: Iterable[ArrayLike],
-    bboxes: Iterable[ArrayLike] | None = None,
-) -> HashStatsOutput:
-    """
-    Calculates hashes for each image
-
-    This function computes hashes from the images including exact hashes and perception-based
-    hashes. These hash values can be used to determine if images are exact or near matches.
-
-    Parameters
-    ----------
-    images : ArrayLike
-        Images to hashing
-    bboxes : Iterable[ArrayLike] or None
-        Bounding boxes in `xyxy` format for each image
-
-    Returns
-    -------
-    HashStatsOutput
-        A dictionary-like object containing the computed hashes for each image.
-
-    See Also
-    --------
-    :term:`Duplicates`
-
-    Examples
-    --------
-    Calculating the :term:`statistics<Statistics>` on the images, whose shape is (C, H, W)
-
-    >>> results = hashstats(images)
-    >>> print(results.xxhash)
-    ['a72434443d6e7336', 'efc12c2f14581d79', '4a1e03483a27d674', '3a3ecedbcf814226']
-    >>> print(results.pchash)
-    ['8f25506af46a7c6a', '8000808000008080', '8e71f18e0ef18e0e', 'a956d6a956d6a928']
-    """
-    return run_stats(images, bboxes, False, [HashStatsProcessor])[0]