Java 类名：com.alibaba.alink.operator.stream.timeseries.DeepARPredictStreamOp
Python 类名：DeepARPredictStreamOp

功能介绍

使用 DeepAR 进行时间序列训练和预测。

使用方式

参考文档 https://www.yuque.com/pinshu/alink_guide/xbp5ky

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 | | —- | —- | —- | —- | —- | —- | —- |

| predictionCol | 预测结果列名 | 预测结果列名 | String | ✓ | | |

| valueCol | value列，类型为MTable | value列，类型为MTable | String | ✓ | 所选列类型为 [M_TABLE] | |

| modelFilePath | 模型的文件路径 | 模型的文件路径 | String | | | null |

| predictNum | 预测条数 | 预测条数 | Integer | | | 1 |

| predictionDetailCol | 预测详细信息列名 | 预测详细信息列名 | String | | | |

| reservedCols | 算法保留列名 | 算法保留列 | String[] | | | null |

| numThreads | 组件多线程线程个数 | 组件多线程线程个数 | Integer | | | 1 |

| modelStreamFilePath | 模型流的文件路径 | 模型流的文件路径 | String | | | null |

| modelStreamScanInterval | 扫描模型路径的时间间隔 | 描模型路径的时间间隔，单位秒 | Integer | | | 10 |

| modelStreamStartTime | 模型流的起始时间 | 模型流的起始时间。默认从当前时刻开始读。使用yyyy-mm-dd hh:mm:ss.fffffffff格式，详见Timestamp.valueOf(String s) | String | | | null |

代码示例

Python 代码

  1. from pyalink.alink import *
  3. import pandas as pd
  5. useLocalEnv(1)
  7. import time, datetime
  8. import numpy as np
  9. import pandas as pd
  11. data = pd.DataFrame([
  12.     [0,  datetime.datetime.fromisoformat('2021-11-01 00:00:00'), 100.0],
  13.     [0,  datetime.datetime.fromisoformat('2021-11-02 00:00:00'), 100.0],
  14.     [0,  datetime.datetime.fromisoformat('2021-11-03 00:00:00'), 100.0],
  15.     [0,  datetime.datetime.fromisoformat('2021-11-04 00:00:00'), 100.0],
  16.     [0,  datetime.datetime.fromisoformat('2021-11-05 00:00:00'), 100.0]
  17. ])
  19. batch_source = dataframeToOperator(data, schemaStr='id int, ts timestamp, series double', op_type='batch')
  20. stream_source = dataframeToOperator(data, schemaStr='id int, ts timestamp, series double', op_type='stream')
  22. deepARTrainBatchOp = DeepARTrainBatchOp()\
  23.     .setTimeCol("ts")\
  24.     .setSelectedCol("series")\
  25.     .setNumEpochs(10)\
  26.     .setWindow(2)\
  27.     .setStride(1)\
  28.     .linkFrom(batch_source)
  30. overCountWindowStreamOp = OverCountWindowStreamOp()\
  31.     .setClause("MTABLE_AGG_PRECEDING(ts, series) as mtable_agg_series")\
  32.     .setTimeCol("ts")\
  33.     .setPrecedingRows(2)
  35. deepARPredictStreamOp = DeepARPredictStreamOp(deepARTrainBatchOp)\
  36.     .setPredictNum(2)\
  37.     .setPredictionCol("pred")\
  38.     .setValueCol("mtable_agg_series")
  40. deepARPredictStreamOp\
  41.     .linkFrom(
  42.         overCountWindowStreamOp\
  43.         .linkFrom(stream_source)\
  44.         .filter("ts = TO_TIMESTAMP('2021-11-05 00:00:00')")
  45.     )\
  46.     .print()
  48. StreamOperator.execute()

Java 代码

  1. import org.apache.flink.types.Row;
  3. import com.alibaba.alink.operator.batch.BatchOperator;
  4. import com.alibaba.alink.operator.batch.source.MemSourceBatchOp;
  5. import com.alibaba.alink.operator.stream.StreamOperator;
  6. import com.alibaba.alink.operator.stream.feature.OverCountWindowStreamOp;
  7. import com.alibaba.alink.operator.stream.source.MemSourceStreamOp;
  8. import com.alibaba.alink.operator.stream.timeseries.DeepARPredictStreamOp;
  9. import org.junit.Test;
  11. import java.sql.Timestamp;
  12. import java.util.Arrays;
  13. import java.util.List;
  15. public class DeepARPredictStreamOpTest {
  17.     @Test
  18.     public void testDeepARTrainBatchOp() throws Exception {
  19.         BatchOperator.setParallelism(1);
  21.         List <Row> data = Arrays.asList(
  22.             Row.of(0, Timestamp.valueOf("2021-11-01 00:00:00"), 100.0),
  23.             Row.of(0, Timestamp.valueOf("2021-11-02 00:00:00"), 100.0),
  24.             Row.of(0, Timestamp.valueOf("2021-11-03 00:00:00"), 100.0),
  25.             Row.of(0, Timestamp.valueOf("2021-11-04 00:00:00"), 100.0),
  26.             Row.of(0, Timestamp.valueOf("2021-11-05 00:00:00"), 100.0)
  27.         );
  29.         MemSourceBatchOp memSourceBatchOp = new MemSourceBatchOp(data, "id int, ts timestamp, series double");
  31.         MemSourceStreamOp memSourceStreamOp = new MemSourceStreamOp(data, "id int, ts timestamp, series double");
  33.         DeepARTrainBatchOp deepARTrainBatchOp = new DeepARTrainBatchOp()
  34.             .setTimeCol("ts")
  35.             .setSelectedCol("series")
  36.             .setNumEpochs(10)
  37.             .setWindow(2)
  38.             .setStride(1)
  39.             .linkFrom(memSourceBatchOp);
  41.         OverCountWindowStreamOp overCountWindowStreamOp = new OverCountWindowStreamOp()
  42.             .setClause("MTABLE_AGG_PRECEDING(ts, series) as mtable_agg_series")
  43.             .setTimeCol("ts")
  44.             .setPrecedingRows(2);
  46.         DeepARPredictStreamOp deepARPredictStreamOp = new DeepARPredictStreamOp(deepARTrainBatchOp)
  47.             .setPredictNum(2)
  48.             .setPredictionCol("pred")
  49.             .setValueCol("mtable_agg_series");
  51.         deepARPredictStreamOp
  52.             .linkFrom(
  53.                 overCountWindowStreamOp
  54.                     .linkFrom(memSourceStreamOp)
  55.                     .filter("ts = TO_TIMESTAMP('2021-11-05 00:00:00')")
  56.             )
  57.             .print();
  59.         StreamOperator.execute();
  60.     }
  62. }

运行结果

| id | mtable_agg_series | pred |
|——+—————————————————————————————————————————————————————————————————————————————————————————————————————————————+————————————————————————————————————————————————————————————————————————————-|
| 0 | {“data”:{“ts”:[“2021-11-01 00:00:00.0”,”2021-11-02 00:00:00.0”,”2021-11-03 00:00:00.0”,”2021-11-04 00:00:00.0”,”2021-11-05 00:00:00.0”],”series”:[100.0,100.0,100.0,100.0,100.0]},”schema”:”ts TIMESTAMP,series DOUBLE”} | {“data”:{“ts”:[“2021-11-06 00:00:00.0”,”2021-11-07 00:00:00.0”],”series”:[31.424224853515625,39.10265350341797]},”schema”:”ts TIMESTAMP,series DOUBLE”} |