scikit-learn(工程中用的相对较多的模型介绍):1.12. Multiclass and multilabel algorithms
分类:scikit-learn
在实际项目中,我们真的很少用到那些简单的模型,比如LR、kNN、NB等,虽然经典,但在工程中确实不实用。
今天我们关注在工程中用的相对较多的Multiclass and multilabel algorithms。
warning:scikit-learn的所有分类器都是可以domulticlass classification out-of-the-box(可直接使用),,所以没必要使用本节介绍的sklearn.multiclassmodule,这里只是讲些知识点。
Below is a summary of the classifiers supported by scikit-learn grouped by strategy; you don’t need the meta-estimators in this class if you’re using one of these unless you want custom multiclass behavior:
Inherently multiclass:Naive Bayes,,Decision Trees,,Nearest Neighbors, setting “multi_class=multinomial” in.One-Vs-One:.One-Vs-All: all linear models except.
Some estimators also support multioutput-multiclass classification tasksDecision Trees,,Nearest Neighbors.
三类问题:
Multiclass classificationmeans a classification task with more than two classes;但是一个sample只能属于其中一个类别(相当于一个多元分类)。
Multilabel classificationassigns to each sample a set of target labels.一个sample可以属于多个类别(相当于多个二元分类)。
Multioutput-multiclass classificationandmulti-task classificationmeans that a single estimator has to handle several joint classification tasks.(相当于多个多元分类:The set of labels can be different for each output variable. For instance a sample could be assigned “pear” for an output variable that takes possible values in a finite set of species such as “pear”, “apple”, “orange” and “green” for a second output variable that takes possible values in a finite set of colors such as “green”, “red”, “orange”, “yellow”…)。
版权声明:本文为博主原创文章,未经博主允许不得转载。
上一篇机器学习实践中应避免的七种常见错误下一篇scikit-learn(工程中用的相对较多的模型介绍):1.13. Feature selection
顶1踩0
没有一种不通过蔑视、忍受和奋斗就可以征服的命运。