dataeval.core¶
Core stateless functions for performing dataset, metadata and model evaluation.
Submodules¶
Module for flag enums that control function behavior. |
Functions¶
|
Mutual information between factors (class label, metadata, label/image properties). |
|
Mutual information (MI) between factors (class label, metadata, label/image properties). |
|
An estimator for Multi-class Bayes error rate using KNN test statistic basis. |
|
An estimator for Multi-class Bayes error rate using FR with a minimum spanning tree (MST) test statistic basis. |
|
Compute specified statistics on a set of images. |
|
Uses hierarchical clustering on the flattened data and returns clustering |
|
Compute k nearest neighbors for each point in data (self-query, excluding self). |
|
For each sample in data_query, compute the k nearest neighbors in data_fit. |
|
Evaluate coverage using an adaptive radius calculation method. |
|
Evaluate coverage using a naive radius calculation method. |
|
Counts label disagreements between nearest neighbors in data. |
|
Counts the number of cross-label edges in the minimum spanning tree of data. |
|
Measures the feature-wise distance between two continuous distributions and computes a |
|
Calculate the chi-square statistic to assess the parity between expected and observed label distributions. |
|
Compute the minimum spanning tree of a dataset. |
|
Calculates accuracy from binary classification results. |
|
Calculates FPR (False Positive Rate) from binary classification results. |
|
Calculates precision from binary classification results. |
|
Calculates recall (True Positive Rate) from binary classification results. |
|
Calculate chi-square statistics to assess the linear relationship between multiple factors and class labels. |
|
Performs a perceptual hash on an image by resizing to a square NxN image |
|
Performs a fast non-cryptographic hash using the xxhash algorithm |