MNT Deprecate metrics.pairwise.paired_*_distances and paired_distances public functions #27129
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -23,7 +23,7 @@ | |
| ) | ||
| from ..metrics import DistanceMetric | ||
| from ..metrics._dist_metrics import METRIC_MAPPING64 | ||
| from ..metrics.pairwise import _VALID_METRICS, _paired_distances | ||
| from ..utils import check_array | ||
| from ..utils._fast_dict import IntFloatDict | ||
| from ..utils._param_validation import ( | ||
|
|
@@ -588,7 +588,7 @@ def linkage_tree( | |
| else: | ||
| # FIXME We compute all the distances, while we could have only computed | ||
| # the "interesting" distances | ||
| distances = _paired_distances( | ||
| X[connectivity.row], X[connectivity.col], metric=affinity | ||
| ) | ||
| connectivity.data = distances | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -32,7 +32,7 @@ | |
| from sklearn.metrics import DistanceMetric | ||
| from sklearn.metrics.cluster import adjusted_rand_score, normalized_mutual_info_score | ||
| from sklearn.metrics.pairwise import ( | ||
| _PAIRED_DISTANCES, | ||
| cosine_distances, | ||
| manhattan_distances, | ||
| pairwise_distances, | ||
|
|
@@ -237,7 +237,7 @@ def test_agglomerative_clustering(global_random_seed, lil_container): | |
| clustering.fit(X) | ||
|
|
||
| # Test using another metric than euclidean works with linkage complete | ||
| for metric in _PAIRED_DISTANCES.keys(): | ||
| # Compare our (structured) implementation to scipy | ||
| clustering = AgglomerativeClustering( | ||
| n_clusters=10, | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
|
|
@@ -36,6 +36,7 @@ | |||||
| StrOptions, | ||||||
| validate_params, | ||||||
| ) | ||||||
| from ..utils.deprecation import deprecated | ||||||
| from ..utils.extmath import row_norms, safe_sparse_dot | ||||||
| from ..utils.fixes import parse_version, sp_base_version | ||||||
| from ..utils.parallel import Parallel, delayed | ||||||
|
|
@@ -1129,6 +1130,11 @@ def cosine_distances(X, Y=None): | |||||
| return S | ||||||
|
|
||||||
|
|
||||||
| # TODO(1.6): Remove in 1.6 | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
| @deprecated( | ||||||
| "The public function `sklearn.pairwise.paired_euclidean_distances` has been " | ||||||
| "deprecated in 1.4 and will be removed in 1.6." | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
| ) | ||||||
| # Paired distances | ||||||
| @validate_params( | ||||||
| {"X": ["array-like", "sparse matrix"], "Y": ["array-like", "sparse matrix"]}, | ||||||
|
|
@@ -1139,6 +1145,29 @@ def paired_euclidean_distances(X, Y): | |||||
|
|
||||||
| Read more in the :ref:`User Guide <metrics>`. | ||||||
|
|
||||||
| Parameters | ||||||
| ---------- | ||||||
| X : {array-like, sparse matrix} of shape (n_samples, n_features) | ||||||
| Input array/matrix X. | ||||||
|
|
||||||
| Y : {array-like, sparse matrix} of shape (n_samples, n_features) | ||||||
| Input array/matrix Y. | ||||||
|
|
||||||
| Returns | ||||||
| ------- | ||||||
| distances : ndarray of shape (n_samples,) | ||||||
| Output array/matrix containing the calculated paired euclidean | ||||||
| distances. | ||||||
| """ | ||||||
|
|
||||||
| return _paired_euclidean_distances(X, Y) | ||||||
|
|
||||||
|
|
||||||
| def _paired_euclidean_distances(X, Y): | ||||||
| """Compute the paired euclidean distances between X and Y. | ||||||
|
|
||||||
| Read more in the :ref:`User Guide <metrics>`. | ||||||
|
|
||||||
| Parameters | ||||||
| ---------- | ||||||
| X : {array-like, sparse matrix} of shape (n_samples, n_features) | ||||||
|
|
@@ -1157,6 +1186,11 @@ def paired_euclidean_distances(X, Y): | |||||
| return row_norms(X - Y) | ||||||
|
|
||||||
|
|
||||||
| # TODO(1.6): Remove in 1.6 | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
| @deprecated( | ||||||
| "The public function `sklearn.pairwise.paired_manhattan_distances` has been " | ||||||
| "deprecated in 1.4 and will be removed in 1.6." | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
| ) | ||||||
| @validate_params( | ||||||
| {"X": ["array-like", "sparse matrix"], "Y": ["array-like", "sparse matrix"]}, | ||||||
| prefer_skip_nested_validation=True, | ||||||
|
|
@@ -1192,6 +1226,31 @@ def paired_manhattan_distances(X, Y): | |||||
| >>> paired_manhattan_distances(X, Y) | ||||||
| array([1., 2., 1.]) | ||||||
| """ | ||||||
| return _paired_manhattan_distances(X, Y) | ||||||
|
|
||||||
|
|
||||||
| def _paired_manhattan_distances(X, Y): | ||||||
| """Compute the paired L1 distances between X and Y. | ||||||
|
|
||||||
| Distances are calculated between (X[0], Y[0]), (X[1], Y[1]), ..., | ||||||
| (X[n_samples], Y[n_samples]). | ||||||
|
|
||||||
| Read more in the :ref:`User Guide <metrics>`. | ||||||
|
|
||||||
| Parameters | ||||||
| ---------- | ||||||
| X : {array-like, sparse matrix} of shape (n_samples, n_features) | ||||||
| An array-like where each row is a sample and each column is a feature. | ||||||
|
|
||||||
| Y : {array-like, sparse matrix} of shape (n_samples, n_features) | ||||||
| An array-like where each row is a sample and each column is a feature. | ||||||
|
|
||||||
| Returns | ||||||
| ------- | ||||||
| distances : ndarray of shape (n_samples,) | ||||||
| L1 paired distances between the row vectors of `X` | ||||||
| and the row vectors of `Y`. | ||||||
| """ | ||||||
| X, Y = check_paired_arrays(X, Y) | ||||||
| diff = X - Y | ||||||
| if issparse(diff): | ||||||
|
|
@@ -1201,6 +1260,11 @@ def paired_manhattan_distances(X, Y): | |||||
| return np.abs(diff).sum(axis=-1) | ||||||
|
|
||||||
|
|
||||||
| # TODO*1.6: Remove in 1.6 | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
| @deprecated( | ||||||
| "The public function `sklearn.pairwise.paired_cosine_distances` has been " | ||||||
| "deprecated in 1.4 and will be removed in 1.6." | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
| ) | ||||||
| @validate_params( | ||||||
| {"X": ["array-like", "sparse matrix"], "Y": ["array-like", "sparse matrix"]}, | ||||||
| prefer_skip_nested_validation=True, | ||||||
|
|
@@ -1211,6 +1275,35 @@ def paired_cosine_distances(X, Y): | |||||
|
|
||||||
| Read more in the :ref:`User Guide <metrics>`. | ||||||
|
|
||||||
| Parameters | ||||||
| ---------- | ||||||
| X : {array-like, sparse matrix} of shape (n_samples, n_features) | ||||||
| An array where each row is a sample and each column is a feature. | ||||||
|
|
||||||
| Y : {array-like, sparse matrix} of shape (n_samples, n_features) | ||||||
| An array where each row is a sample and each column is a feature. | ||||||
|
|
||||||
| Returns | ||||||
| ------- | ||||||
| distances : ndarray of shape (n_samples,) | ||||||
| Returns the distances between the row vectors of `X` | ||||||
| and the row vectors of `Y`, where `distances[i]` is the | ||||||
| distance between `X[i]` and `Y[i]`. | ||||||
|
|
||||||
| Notes | ||||||
| ----- | ||||||
| The cosine distance is equivalent to the half the squared | ||||||
| euclidean distance if each sample is normalized to unit norm. | ||||||
| """ | ||||||
| return _paired_cosine_distances(X, Y) | ||||||
|
|
||||||
|
|
||||||
| def _paired_cosine_distances(X, Y): | ||||||
| """ | ||||||
| Compute the paired cosine distances between X and Y. | ||||||
|
|
||||||
| Read more in the :ref:`User Guide <metrics>`. | ||||||
|
|
||||||
| Parameters | ||||||
| ---------- | ||||||
| X : {array-like, sparse matrix} of shape (n_samples, n_features) | ||||||
|
|
@@ -1235,6 +1328,8 @@ def paired_cosine_distances(X, Y): | |||||
| return 0.5 * row_norms(normalize(X) - normalize(Y), squared=True) | ||||||
|
|
||||||
|
|
||||||
| # TODO(1.6): Remove PAIRED_DISTANCES dictionary since pairwise_*_distance public | ||||||
| # functions are deprecated in 1.6 | ||||||
| PAIRED_DISTANCES = { | ||||||
| "cosine": paired_cosine_distances, | ||||||
| "euclidean": paired_euclidean_distances, | ||||||
|
|
@@ -1244,7 +1339,21 @@ def paired_cosine_distances(X, Y): | |||||
| "cityblock": paired_manhattan_distances, | ||||||
| } | ||||||
|
|
||||||
| _PAIRED_DISTANCES = { | ||||||
| "cosine": _paired_cosine_distances, | ||||||
| "euclidean": _paired_euclidean_distances, | ||||||
| "l2": _paired_euclidean_distances, | ||||||
| "l1": _paired_manhattan_distances, | ||||||
| "manhattan": _paired_manhattan_distances, | ||||||
| "cityblock": _paired_manhattan_distances, | ||||||
| } | ||||||
|
|
||||||
|
|
||||||
| # TODO(1.6): Remove in 1.6 | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
| @deprecated( | ||||||
| "The public function `sklearn.pairwise.paired_distances` has been " | ||||||
| "deprecated in 1.4 and will be removed in 1.6." | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
| ) | ||||||
| @validate_params( | ||||||
| { | ||||||
| "X": ["array-like"], | ||||||
|
|
@@ -1301,9 +1410,52 @@ def paired_distances(X, Y, *, metric="euclidean", **kwds): | |||||
| >>> paired_distances(X, Y) | ||||||
| array([0., 1.]) | ||||||
| """ | ||||||
| return _paired_distances(X, Y, metric=metric, **kwds) | ||||||
|
|
||||||
|
|
||||||
| def _paired_distances(X, Y, *, metric="euclidean", **kwds): | ||||||
| """ | ||||||
| Compute the paired distances between X and Y. | ||||||
|
|
||||||
| Compute the distances between (X[0], Y[0]), (X[1], Y[1]), etc... | ||||||
|
|
||||||
| Read more in the :ref:`User Guide <metrics>`. | ||||||
|
|
||||||
| Parameters | ||||||
| ---------- | ||||||
| X : ndarray of shape (n_samples, n_features) | ||||||
| Array 1 for distance computation. | ||||||
|
|
||||||
| Y : ndarray of shape (n_samples, n_features) | ||||||
| Array 2 for distance computation. | ||||||
|
|
||||||
| metric : str or callable, default="euclidean" | ||||||
| The metric to use when calculating distance between instances in a | ||||||
| feature array. If metric is a string, it must be one of the options | ||||||
| specified in PAIRED_DISTANCES, including "euclidean", | ||||||
| "manhattan", or "cosine". | ||||||
| Alternatively, if metric is a callable function, it is called on each | ||||||
| pair of instances (rows) and the resulting value recorded. The callable | ||||||
| should take two arrays from `X` as input and return a value indicating | ||||||
| the distance between them. | ||||||
|
|
||||||
| **kwds : dict | ||||||
| Unused parameters. | ||||||
|
|
||||||
| Returns | ||||||
| ------- | ||||||
| distances : ndarray of shape (n_samples,) | ||||||
| Returns the distances between the row vectors of `X` | ||||||
| and the row vectors of `Y`. | ||||||
|
|
||||||
| See Also | ||||||
| -------- | ||||||
| sklearn.metrics.pairwise_distances : Computes the distance between every pair of | ||||||
| samples. | ||||||
| """ | ||||||
|
|
||||||
| if metric in _PAIRED_DISTANCES: | ||||||
| func = _PAIRED_DISTANCES[metric] | ||||||
| return func(X, Y) | ||||||
| elif callable(metric): | ||||||
| # Check the matrix first (it is usually done by the metric) | ||||||
|
|
||||||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can these be moved to
scikit-learn/doc/modules/classes.rst
Lines 1903 to 1904 in 93f6ce9