如何在 xgboost 中获得特征重要性? [英] How to get feature importance in xgboost?

问题描述

我正在使用 xgboost 构建模型，并尝试使用 get_fscore() 找出每个功能的重要性，但它返回 {}

I'm using xgboost to build a model, and try to find the importance of each feature using get_fscore(), but it returns {}

我的火车代码是:

dtrain = xgb.DMatrix(X, label=Y)
watchlist = [(dtrain, 'train')]
param = {'max_depth': 6, 'learning_rate': 0.03}
num_round = 200
bst = xgb.train(param, dtrain, num_round, watchlist)

那么我的火车有什么错误吗?如何在 xgboost 中获取特征重要性?

So is there any mistake in my train? How to get feature importance in xgboost?

推荐答案

在您的代码中，您可以以 dict 形式获取每个功能的功能重要性:

In your code you can get feature importance for each feature in dict form:

bst.get_score(importance_type='gain')

>>{'ftr_col1': 77.21064539577829,
   'ftr_col2': 10.28690566363971,
   'ftr_col3': 24.225014841466294,
   'ftr_col4': 11.234086283060112}

说明:train() API 的 get_score() 方法定义为:

Explanation: The train() API's method get_score() is defined as:

get_score(fmap='',importance_type='weight')

get_score(fmap='', importance_type='weight')

• fmap(str(可选))– 特征映射文件的名称.
• importance_type
  • ‘权重’ - 一个特征被用来在所有树上分割数据的次数.
  • ‘增益’ - 使用该特征的所有分割的平均增益.
  • ‘cover’ - 使用该特征的所有分割的平均覆盖率.
  • ‘total_gain’ - 使用该特征的所有分割的总增益.
  • ‘total_cover’ - 使用该特征的所有分割的总覆盖率.
  • fmap (str (optional)) – The name of feature map file.
  • importance_type
    • ‘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.

    https://xgboost.readthedocs.io/en/latest/python/python_api.html

    这篇关于如何在 xgboost 中获得特征重要性?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！