异常检测 - HBOS序列异常检测 (HbosOutlier4GroupedDataStreamOp) - 《Alink 1.5.6 文档 - 帮助手册 - 教程》

功能介绍
- 文献或出处
参数说明
代码示例

Java 类名：com.alibaba.alink.operator.stream.outlier.HbosOutlier4GroupedDataStreamOp
Python 类名：HbosOutlier4GroupedDataStreamOp

功能介绍

Histogram-based Outlier Score 使用直方图统计结果，描述异常值，算法较为简单，上手方便。

文献或出处

HBOS
参数说明
| 名称 | 中文名称 | 描述 | 类型 | 是否必须？ | 取值范围 | 默认值 | | —- | —- | —- | —- | —- | —- | —- |

| k | Not available! | Not available! | Integer | | [1, +inf) | 10 |

代码示例

Python 代码

import time
import datetime
import numpy as np
import pandas as pd
data = pd.DataFrame([
    [1, datetime.datetime.fromtimestamp(1), 10.0, 0],
    [1, datetime.datetime.fromtimestamp(2), 11.0, 0],
    [1, datetime.datetime.fromtimestamp(3), 12.0, 0],
    [1, datetime.datetime.fromtimestamp(4), 13.0, 0],
    [1, datetime.datetime.fromtimestamp(5), 14.0, 0],
    [1, datetime.datetime.fromtimestamp(6), 15.0, 0],
    [1, datetime.datetime.fromtimestamp(7), 16.0, 0],
    [1, datetime.datetime.fromtimestamp(8), 17.0, 0],
    [1, datetime.datetime.fromtimestamp(9), 18.0, 0],
    [1, datetime.datetime.fromtimestamp(10), 19.0, 0]
])
dataOp = dataframeToOperator(
    data, schemaStr='id int, ts timestamp, val double, label int', op_type='stream')
dataOp.link(
    OverCountWindowStreamOp()
    .setGroupCols(["id"])
    .setTimeCol("ts")
    .setPrecedingRows(5)
    .setClause("MTABLE_AGG_PRECEDING(ts, val) as series_data")
    .setReservedCols(["id", "label"])
).link(
    HbosOutlier4GroupedDataStreamOp()
    .setInputMTableCol("series_data")
    .setFeatureCols(["val"])
    .setOutputMTableCol("output_series")
    .setPredictionCol("pred")
).link(
    FlattenMTableStreamOp()
    .setSelectedCol("output_series")
    .setSchemaStr("ts TIMESTAMP, val DOUBLE, pred BOOLEAN")
).print()
StreamOperator.execute()

Java 代码

import org.apache.flink.types.Row;
import com.alibaba.alink.operator.stream.StreamOperator;
import com.alibaba.alink.operator.stream.dataproc.FlattenMTableStreamOp;
import com.alibaba.alink.operator.stream.feature.OverCountWindowStreamOp;
import com.alibaba.alink.operator.stream.outlier.HbosOutlier4GroupedDataStreamOp;
import com.alibaba.alink.operator.stream.source.MemSourceStreamOp;
import org.junit.Test;
import java.sql.Timestamp;
import java.util.Arrays;
import java.util.List;
public class HbosOutlier4GroupedDataStreamOpTest {
    @Test
    public void test() throws Exception {
        List <Row> mTableData = Arrays.asList(
            Row.of(1, new Timestamp(1), 10.0, 0),
            Row.of(1, new Timestamp(2), 11.0, 0),
            Row.of(1, new Timestamp(3), 12.0, 0),
            Row.of(1, new Timestamp(4), 13.0, 0),
            Row.of(1, new Timestamp(5), 14.0, 0),
            Row.of(1, new Timestamp(6), 15.0, 0),
            Row.of(1, new Timestamp(7), 16.0, 0),
            Row.of(1, new Timestamp(8), 17.0, 0),
            Row.of(1, new Timestamp(9), 18.0, 0),
            Row.of(1, new Timestamp(10), 19.0, 0)
        );
        MemSourceStreamOp dataOp = new MemSourceStreamOp(mTableData,
            new String[] {"id", "ts", "val", "label"});
        dataOp.link(
            new OverCountWindowStreamOp()
                .setGroupCols("id")
                .setTimeCol("ts")
                .setPrecedingRows(5)
                .setClause("MTABLE_AGG_PRECEDING(ts, val) as series_data")
                .setReservedCols("id", "label")
        ).link(
            new HbosOutlier4GroupedDataStreamOp()
                .setInputMTableCol("series_data")
                .setFeatureCols("val")
                .setOutputMTableCol("output_series")
                .setPredictionCol("pred")
        ).link(
            new FlattenMTableStreamOp()
                .setSelectedCol("output_series")
                .setSchemaStr("ts TIMESTAMP, val DOUBLE, pred BOOLEAN")
        ).print();
        StreamOperator.execute();
    }
}

运行结果

| id | label | series_data | output_series | ts | val | pred | | —- | —- | —- | —- | —- | —- | —- |

| 1 | 0 | MTable(1,2)(ts,val) | MTable(1,3)(ts,val,pred) | 1970-01-01 08:00:00.001 | 10.0000 | false |

| 1970-01-01 08:00:00.001 | 10.0000 | 1970-01-01 08:00:00.001 | 10.0000 | false | | |

| 1 | 0 | MTable(2,2)(ts,val) | MTable(2,3)(ts,val,pred) | 1970-01-01 08:00:00.001 | 10.0000 | false |

| 1970-01-01 08:00:00.001 | 10.0000 | 1970-01-01 08:00:00.001 | 10.0000 | false | | |

| 1970-01-01 08:00:00.002 | 11.0000 | 1970-01-01 08:00:00.002 | 11.0000 | false | | |

| 1 | 0 | MTable(2,2)(ts,val) | MTable(2,3)(ts,val,pred) | 1970-01-01 08:00:00.002 | 11.0000 | false |

| 1970-01-01 08:00:00.001 | 10.0000 | 1970-01-01 08:00:00.001 | 10.0000 | false | | |

| 1970-01-01 08:00:00.002 | 11.0000 | 1970-01-01 08:00:00.002 | 11.0000 | false | | |

| 1 | 0 | MTable(3,2)(ts,val) | MTable(3,3)(ts,val,pred) | 1970-01-01 08:00:00.001 | 10.0000 | false |

| 1970-01-01 08:00:00.001 | 10.0000 | 1970-01-01 08:00:00.001 | 10.0000 | false | | |

| 1970-01-01 08:00:00.002 | 11.0000 | 1970-01-01 08:00:00.002 | 11.0000 | false | | |

| 1970-01-01 08:00:00.003 | 12.0000 | 1970-01-01 08:00:00.003 | 12.0000 | false | | |

| 1 | 0 | MTable(3,2)(ts,val) | MTable(3,3)(ts,val,pred) | 1970-01-01 08:00:00.002 | 11.0000 | false |

| 1970-01-01 08:00:00.001 | 10.0000 | 1970-01-01 08:00:00.001 | 10.0000 | false | | |

| 1970-01-01 08:00:00.002 | 11.0000 | 1970-01-01 08:00:00.002 | 11.0000 | false | | |

| 1970-01-01 08:00:00.003 | 12.0000 | 1970-01-01 08:00:00.003 | 12.0000 | false | | |

| 1 | 0 | MTable(3,2)(ts,val) | MTable(3,3)(ts,val,pred) | 1970-01-01 08:00:00.003 | 12.0000 | false |

| 1970-01-01 08:00:00.001 | 10.0000 | 1970-01-01 08:00:00.001 | 10.0000 | false | | |

| 1970-01-01 08:00:00.002 | 11.0000 | 1970-01-01 08:00:00.002 | 11.0000 | false | | |

| 1970-01-01 08:00:00.003 | 12.0000 | 1970-01-01 08:00:00.003 | 12.0000 | false | | |

| 1 | 0 | MTable(4,2)(ts,val) | MTable(4,3)(ts,val,pred) | 1970-01-01 08:00:00.001 | 10.0000 | false |

| 1970-01-01 08:00:00.001 | 10.0000 | 1970-01-01 08:00:00.001 | 10.0000 | false | | |

| 1970-01-01 08:00:00.002 | 11.0000 | 1970-01-01 08:00:00.002 | 11.0000 | false | | |

| 1970-01-01 08:00:00.003 | 12.0000 | 1970-01-01 08:00:00.003 | 12.0000 | false | | |

| 1970-01-01 08:00:00.004 | 13.0000 | 1970-01-01 08:00:00.004 | 13.0000 | false | | |

| 1 | 0 | MTable(4,2)(ts,val) | MTable(4,3)(ts,val,pred) | 1970-01-01 08:00:00.002 | 11.0000 | false |

| 1970-01-01 08:00:00.001 | 10.0000 | 1970-01-01 08:00:00.001 | 10.0000 | false | | |

| 1970-01-01 08:00:00.002 | 11.0000 | 1970-01-01 08:00:00.002 | 11.0000 | false | | |

| 1970-01-01 08:00:00.003 | 12.0000 | 1970-01-01 08:00:00.003 | 12.0000 | false | | |

| 1970-01-01 08:00:00.004 | 13.0000 | 1970-01-01 08:00:00.004 | 13.0000 | false | | |

| 1 | 0 | MTable(4,2)(ts,val) | MTable(4,3)(ts,val,pred) | 1970-01-01 08:00:00.003 | 12.0000 | false |

| 1970-01-01 08:00:00.001 | 10.0000 | 1970-01-01 08:00:00.001 | 10.0000 | false | | |

| 1970-01-01 08:00:00.002 | 11.0000 | 1970-01-01 08:00:00.002 | 11.0000 | false | | |

| 1970-01-01 08:00:00.003 | 12.0000 | 1970-01-01 08:00:00.003 | 12.0000 | false | | |

| 1970-01-01 08:00:00.004 | 13.0000 | 1970-01-01 08:00:00.004 | 13.0000 | false | | |

| 1 | 0 | MTable(4,2)(ts,val) | MTable(4,3)(ts,val,pred) | 1970-01-01 08:00:00.004 | 13.0000 | false |

| 1970-01-01 08:00:00.001 | 10.0000 | 1970-01-01 08:00:00.001 | 10.0000 | false | | |

| 1970-01-01 08:00:00.002 | 11.0000 | 1970-01-01 08:00:00.002 | 11.0000 | false | | |

| 1970-01-01 08:00:00.003 | 12.0000 | 1970-01-01 08:00:00.003 | 12.0000 | false | | |

| 1970-01-01 08:00:00.004 | 13.0000 | 1970-01-01 08:00:00.004 | 13.0000 | false | | |

| 1 | 0 | MTable(5,2)(ts,val) | MTable(5,3)(ts,val,pred) | 1970-01-01 08:00:00.001 | 10.0000 | false |

| 1970-01-01 08:00:00.001 | 10.0000 | 1970-01-01 08:00:00.001 | 10.0000 | false | | |

| 1970-01-01 08:00:00.002 | 11.0000 | 1970-01-01 08:00:00.002 | 11.0000 | false | | |

| 1970-01-01 08:00:00.003 | 12.0000 | 1970-01-01 08:00:00.003 | 12.0000 | false | | |

| 1970-01-01 08:00:00.004 | 13.0000 | 1970-01-01 08:00:00.004 | 13.0000 | false | | |