ValueToKeyMappingEstimator 类
定义
程序集:Microsoft.ML.Data.dll
包:Microsoft.ML v1.5.5
包:Microsoft.ML v1.0.0
包:Microsoft.ML v1.1.0
包:Microsoft.ML v1.2.0
包:Microsoft.ML v1.3.1
包:Microsoft.ML v1.4.0
IEstimator 的 ValueToKeyMappingTransformer 。 将一组分类值转换 (例如,将美国省/市/自治区缩写) 为数字键值 (例如 1-50) 。
数字键可以直接由分类算法使用。
本文内容
public sealed class ValueToKeyMappingEstimator : Microsoft.ML.IEstimator
type ValueToKeyMappingEstimator = class
interface IEstimator
Public NotInheritable Class ValueToKeyMappingEstimator
Implements IEstimator(Of ValueToKeyMappingTransformer)
继承
ValueToKeyMappingEstimator
注解
Estimator Characteristics
此估计器是否需要查看数据来训练它的参数?
是
输入列数据类型
数值、布尔值、 文本、 system.web 和 key 类型的标量或向量。
输出列数据类型
键类型的标量或向量。
可导出到 ONNX
是
The ValueToKeyMappingEstimator maps the input values to keys using a
dictionary that is built during training. The dictionary mapping values to
keys is most commonly learnt from the unique values in input data,
but can be pre-defined.
The key value is the one-based index of the item in the dictionary.
If the key is not found in the dictionary, it is assigned the missing value
indicator.
If multiple columns are used, each column builds exactly one dictionary.
The dictionary data is stored as an annotation in the schema, to enable
the reverse mapping to occur using KeyToValueMappingEstimator
Check the See Also section for links to usage examples.
方法
扩展方法
适用于
另请参阅