问题描述
我想知道XGBClassifier对它所做的每个预测有多自信.是否有可能具有这样的价值?还是predict_proba已经间接地建立了模型的可信度?
I'd like to know how confident an XGBClassifier is for each prediction it makes. Is it possible to have such a value? Or is the predict_proba already indirectly the confidence of the model?
推荐答案
您的直觉确实是正确的:predict_proba返回每个示例属于给定类的概率；来自 docs :
Your intuition is indeed correct: predict_proba returns the probability of each example being of a given class; from the docs:
预测每个数据示例属于给定类的概率.
Predict the probability of each data example being of a given class.
实际上，该概率反过来通常在惯例中被解释为预测的置信度.
This probability in turn is routinely interpreted in practice as the confidence of the prediction.
也就是说，这是一种特殊的，实用的解释，与p值或任何其他统计严谨度无关.一般来说，对于AFAIK而言，没有(或类似的)机器学习技术可采用的此类措施.
That said, this is an ad-hoc, practical interpretation, and it has nothing to do with p-values or any other measure of statistical rigour; generally speaking and AFAIK, there are no such measures available for this (and similar) machine learning techniques.
更笼统地说，您可能想知道p值本身已迅速在统计学家中失宠；一些快速链接:
On a more general level, you may be interested to know that p-values themselves have been quickly falling out of grace among statisticians; some quick links:
-
ASA关于p值的声明:上下文，过程和目的(美国统计学家)
统计学家问题警告错误使用 P 值(自然)
p值的问题不仅仅是带有p值(Andrew Gelman @ American Statistician)
The problems with p-values are not just with p-values (Andrew Gelman @ American Statistician)
p值存在问题(指向数据科学博客文章)
The problem with p-values (Towards Data Science blog post)
这篇关于如何获取XGBClassifier的预测p值?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！