Discrete Feature Analysis

• Machine Learning Platform for AI console

  Parameter	Description
  Feature Columns	The columns to represent the features of data in training samples.
  Label Column	The label column.
  Sparse Matrix	If data in an input table is in the sparse format, features must be in the key-value pair format.

• PAI command

  PAI
  -name enum_feature_selection
  -project algo_public
  -DinputTableName=enumfeautreselection_input
  -DlabelColName=label
  -DfeatureColNames=col0,col1
  -DenableSparse=false
  -DoutputCntTableName=enumfeautreselection_output_cntTable
  -DoutputValueTableName=enumfeautreselection_output_valuetable
  -DoutputEnumValueTableName=enumfeautreselection_output_enumvaluetable;

  Parameter	Required	Description	Default value
  inputTableName	Yes	The name of the input table.	No default value
  inputTablePartitions	No	The partitions selected from the input table for training. The following formats are supported: Partition_name=value name1=value1/name2=value2: multi-level partitions Note Separate multiple partitions with commas (,).	Full table
  featureColNames	No	The names of the feature columns selected from the input table for training.	No default value
  labelColName	No	The name of the label column in the input table.	No default value
  enableSparse	No	Specifies whether to configure input data in the sparse format. Valid values: {true,false}.	false
  kvFeatureColNames	No	The names of the feature columns that are in the key-value pair format.	Full table
  kvDelimiter	No	The delimiter used to separate keys and values if data in an input table is in the sparse format.	Colon (:)
  itemDelimiter	No	The delimiter used to separate key-value pairs if data in an input table is in the sparse format.	Comma (,)
  outputCntTableName	No	The output distribution table that contains the enumerated values of discrete features.	N/A
  outputValueTableName	No	The output table that contains gini and entropy values of discrete features.	N/A
  outputEnumValueTableName	No	The output table that contains enumerated gini and entropy values of discrete features.	N/A
  lifecycle	No	The lifecycle of the table.	No default value
  coreNum	No	The number of cores. The parameter value must be a positive integer.	Automatically allocated
  memSizePerCore	No	The memory size of each core, in MB. Valid values: 1 to 65536.	Automatically allocated

drop table if exists enum_feature_selection_test_input;
create table enum_feature_selection_test_input
as
select
    *
from
(
    select
        '00' as col_string,
        1 as col_bigint,
        0.0 as col_double
    from dual
    union all
        select
            cast(null as string) as col_string,
            0 as col_bigint,
            0.0 as col_double
        from dual
    union all
        select
            '01' as col_string,
            0 as col_bigint,
            1.0 as col_double
        from dual
    union all
        select
            '01' as col_string,
            1 as col_bigint,
            cast(null as double) as col_double
        from dual
    union all
        select
            '01' as col_string,
            1 as col_bigint,
            1.0 as col_double
        from dual
    union all
        select
            '00' as col_string,
            0 as col_bigint,
            0.0 as col_double
        from dual
) tmp;

+------------+------------+------------+
| col_string | col_bigint | col_double |
+------------+------------+------------+
| 01         | 1          | 1.0        |
| 01         | 0          | 1.0        |
| 01         | 1          | NULL       |
| NULL       | 0          | 0.0        |
| 00         | 1          | 0.0        |
| 00         | 0          | 0.0        |
+------------+------------+------------+