categoricalInformationValue
Calculates the value of (P(tag = 1) - P(tag = 0))(log(P(tag = 1)) - log(P(tag = 0)))
for each category.
categoricalInformationValue(category1, category2, ..., tag)
The result indicates how a discrete (categorical) feature [category1, category2, ...]
contribute to a learning model which predicting the value of tag
.
当前内容版权归 ClickHouse 或其关联方所有,如需对内容或内容相关联开源项目进行关注与资助,请访问 ClickHouse .