使用feature Importance進行特徵選擇
在前一篇機器學習之特徵選擇的文章中講到了樹模型中GBDT也可用來作爲基模型進行特徵選擇。今天在此基礎上進行拓展,介紹除決策樹外用的比較多的XGBoost、LightGBM。
DecisionTree
決策樹的feature_importances_屬性,返回的重要性是按照決策樹種被用來分割後帶來的增益(gain)總和進行返回。
The importance of a feature is computed as the (normalized) total reduction of the criterion brought by that feature. It is also known as the Gini importance.
關於信息增益(Gain)相關介紹可以決策樹簡介。
GradientBoosting和ExtraTrees與DecisionTree類似。
XGBoost
get_score(fmap='', importance_type='weight') Get feature importance of each feature. Importance type can be defined as: ‘weight’: the number of times a feature is used to split the data across all trees. ‘gain’: the average gain across all splits the feature is used in. ‘cover’: the average coverage across all splits the feature is used in. ‘total_gain’: the total gain across all splits the feature is used in. ‘total_cover’: the total coverage across all splits the feature is used in.
其中:
- weight:該特徵被選爲分裂特徵的次數。
- gain:該特徵的帶來平均增益(有多棵樹)。在tree中用到時的gain之和/在tree中用到的次數計數。gain = total_gain / weight
- cover:該特徵對每棵樹的覆蓋率。
- total_gain:在所有樹中,某特徵在每次分裂節點時帶來的總增益
- total_cover:在所有樹中,某特徵在每次分裂節點時處理(覆蓋)的所有樣例的數量。
參考鏈接: https://xgboost.readthedocs.io/en/latest/python/python_api.html#xgboost.Booster.get_score
LightGBM
feature_importance(importance_type='split', iteration=None) Get feature importances. importance_type (string, optional (default="split")) – How the importance is calculated. If “split”, result contains numbers of times the feature is used in a model. If “gain”, result contains total gains of splits which use the feature. iteration (int or None, optional (default=None)) – Limit number of iterations in the feature importance calculation. If None, if the best iteration exists, it is used; otherwise, all trees are used. If <= 0, all trees are used (no limits).
其中:
- split就是特徵在所有決策樹中被用來分割的總次數。
- gain就是特徵在所有決策樹種被用來分割後帶來的增益(gain)總和