automl/auto-sklearn

FastICA: `n_components is too large: it will be set to _`

Open

#240 opened on 2017年2月24日

GitHub で見る
 (4 comments) (0 reactions) (0 assignees)Python (7,270 stars) (1,265 forks)batch import
Good first issueenhancement

説明

FastICA currently looks for n_components between 10 and 2000, with a default of 100. However, assuming there are more rows N than columns M, a data set can only support up to M independent components. The suggested range is therefore between 2 and M, with a default of round(M / 2).

Looking at the implementation, it appears information about the data set is not available in get_hyperparameter_search_space. As a workaround, the n_components property could be replaced by a n_components_rel property that indicates the amount of independent components relative to the total number of features M. When calling sklearn.decomposition.FastICA, you could then simply pass n_components=X.shape[1] * self.n_components_rel.

コントリビューターガイド

技術スタック
pythonscikit learn
領域
machine learning
Issue 種別
feature
難度新しい貢献者にとっての実装難度です。1 は非常に小さな変更、5 は専門的な作業です。
3
推定時間経験ある貢献者が調査、実装、テスト、pull request 準備にかけるおおよその時間範囲です。
half day
活動状況Issue が今どれだけ取り組みやすいかを示します。新しい、活発、古い、ブロック中、またはメンテナー入力待ちなどです。
stale
明確さ期待される変更、受け入れ条件、次の手順がどれだけ明確かを示します。
clear
前提条件
Pythonscikit learnauto sklearnFastICA concepts
初心者向け度初回貢献者にどれだけ取り組みやすいかを 1-100 で推定したスコアです。
70
調査方針
Examine the FastICA component implementation in auto sklearn, focusing on the `get hyperparameter search space` method. The issue suggests replacing `n components` with a relative property `n components rel` that derives from the number of features. Look for the existing hyperparameter definitions and modify them to accept a relative value, then adjust the call to `sklearn.decomposition.FastICA` accordingly. The discussion in the issue might provide further insights.
FastICA: `n_components is too large: it will be set to _` · automl/auto-sklearn#240 | Good First Issue