| Package | Description |
|---|---|
| com.hankcs.hanlp.classification.classifiers | |
| com.hankcs.hanlp.classification.features |
| Modifier and Type | Method and Description |
|---|---|
protected BaseFeatureData |
NaiveBayesClassifier.selectFeatures(IDataSet dataSet)
统计特征并且执行特征选择,返回一个FeatureStats对象,用于计算模型中的概率
|
| Modifier and Type | Class and Description |
|---|---|
class |
DfFeatureData
包含倒排文档频次的特征数据
|
| Modifier and Type | Method and Description |
|---|---|
static BaseFeatureData |
ChiSquareFeatureExtractor.extractBasicFeatureData(IDataSet dataSet)
生成一个FeatureStats对象,包含一个分类中的所有词语,分类数,实例数。这些统计数据
将用于特征选择算法。
|
| Modifier and Type | Method and Description |
|---|---|
Map<Integer,Double> |
ChiSquareFeatureExtractor.chi_square(BaseFeatureData stats)
使用卡方非参数校验来执行特征选择
https://nlp.stanford.edu/IR-book/html/htmledition/feature-selectionchi2-feature-selection-1.html |
Copyright © 2014–2021 码农场. All rights reserved.