scikit-learn/sklearn/manifold/locally_linear.py could have a parameter for metric type · scikit-learn/scikit-learn#9868

2017-10-03T22:07:55.000Z

#### Description 0--> Local Linear Embedding uses distance metrics in the calculation of nearest neigbhors. it uses the NearestNeighbors class to do that. There doesnt seem to be a way to pass in the type of distance metric used. It uses a default of euclidean (or minkowski 2). It would be nice to pass in as a parameter different metrics to try, such as jaccard for categorical or whatever one would like. #### Steps/Code to Reproduce  #### Expected Results #### Actual Results #### Versions

(8 留言) (0 反應) (0 負責人)Python (66,084 star) (27,020 fork)batch import

Enhancementhelp wantedmodule:manifold

描述

Description

Local Linear Embedding uses distance metrics in the calculation of nearest neigbhors. it uses the NearestNeighbors class to do that. There doesnt seem to be a way to pass in the type of distance metric used. It uses a default of euclidean (or minkowski 2). It would be nice to pass in as a parameter different metrics to try, such as jaccard for categorical or whatever one would like.

Steps/Code to Reproduce

Expected Results

Actual Results

Versions

貢獻者指南

技術棧: python
領域: machine learningapi
議題類型: feature
難度: 3
預計時間: half day
活動狀態: stale
清晰度: clear
前置要求: scikit learn contribution guidePythonNearestNeighbors APIMetric parameter handling
新手友善度: 65
研究方向: Review the existing implementation in sklearn/manifold/locally linear.py to understand how NearestNeighbors is currently used. Examine how other estimators in scikit learn (e.g., KernelPCA) pass metric parameters and validate them. Implement the new parameter, ensuring it integrates with the existing grid search and documentation conventions.