gistfile1.txt

{
  "type" : "index_hadoop",
  "spec" : {
    "ioConfig" : {
      "type" : "hadoop",
      "inputSpec" : {
        "type" : "static",
        "paths" : "/tmp/top.csv"
      }
    },
    "dataSchema" : {
      "dataSource" : "datashort",
      "granularitySpec" : {
        "type" : "uniform",
        "segmentGranularity" : "minute",
        "queryGranularity" : "none",
        "intervals" : ["2015-08-19/2017-06-01"]
      },
      "parser" : {
        "type" : "hadoopyString",
        "parseSpec":{
          "format" : "csv",
          "timestampSpec" : {
            "column" : "time",
	    "format": "yyyy-M-d H:m:s"
          },
          "columns" : [
            "id",
            "recvtime",
            "imei",
            "bus_id",
            "timestamp",
            "time",
            "longitude",
            "latitude",
            "speed",
            "mMU1Acc",
            "mMU2Acc",
            "mSTUAcc",
            "mNOxOutAcc",
            "nDBCVersion",
            "nNVRAMSt",
            "nRecState",
            "nSWType",
            "nSWVersion",
            "stMU1",
            "stMU2",
            "stSTU",
            "qnEngOutShoAvg",
            "qNH3ShoAvg",
            "rNOxConvShoAvg",
            "rNOxInShoAvg",
            "tSCRShoAvg",
            "rNOxOutShoAvg",
            "qNH3InUseAvg",
            "rNOxConvInUseAvg",
            "rNOxInInUseAvg",
            "rNOxOutInUseAvg",
            "pDPFFild",
            "pDPFMax",
            "stDPFErr",
            "stHtSafeMod",
            "stNH3Err",
            "stNOxOutErr",
            "stSysErrStatus",
            "stSysPause",
            "tSCRInUseAvg",
            "obdBckPressHigh",
            "obdCVDInLeak",
            "obdCVDLeak",
            "obdDPFErr",
            "obdInLeak",
            "obdInLeak2",
            "obdMUCTCErr",
            "obdMUFlsEmpt",
            "obdNOxOut",
            "obdNOxOutHigh",
            "obdPresHigh1",
            "obdPresHigh2",
            "obdSTUClogg",
            "obdVlvInStckCls",
            "obdVlvInStckOpn",
            "obdVlvOutStckCls",
            "obdVlvOutStckOpn",
            "obdCVDTempOOR",
            "obdEEC1Dflt",
            "obdHtVoltHigh",
            "obdHtVoltLow",
            "obdIC1Dflt",
            "obdLFEDflt",
            "obdMainRelayDis",
            "obdMU1HtCirc",
            "obdMU1TempOOR",
            "obdMU2HtCirc",
            "obdMU2TempOOR",
            "obdNOxInDflt",
            "obdNOxInEnaTo",
            "obdNOxOutDflt",
            "obdNOxOutEnaTo",
            "obdPresSensOOR",
            "obdSCRInTempOOR",
            "obdSCROutTempOOR",
            "obdSTUHtCirc",
            "obdMUTempPlaus",
            "obdSysVoltOOR",
            "obdCVDInClogg",
            "obdCVDInSens",
            "obdCVDOutClogg",
            "obdCVDOutLeak",
            "obdCVDOutSens",
            "obdNH3Conv",
            "obdVlvInStckOpn2",
            "obdVlvOutStckOpn2",
            "obdDPFWarn",
            "obdDPFAlrm",
            "80",
            "85",
            "86",
            "88",
            "127",
            "128",
            "135",
            "136",
            "138",
            "199"
          ],
          "dimensionsSpec" : {
            "dimensions" : [
              "imei",
              "bus_id"
            ]
          }
        }
      },
      "metricsSpec" : [
        {
          "name" : "count",
          "type" : "count"
        },
        {
          "name" : "speed",
          "type" : "longSum",
          "fieldName" : "speed"
        },
        {
          "name" : "id_unique",
          "type" : "hyperUnique",
          "fieldName" : "id"
        }
      ]
    },
    "tuningConfig" : {
      "type" : "hadoop",
      "partitionsSpec" : {
        "type" : "hashed",
        "targetPartitionSize": 5000000,
        "maxPartitionSize": 75000000,
        "assumeGrouped": false,
        "numShards": -1,
        "partitionDimensions": []
      },
      "jobProperties" : {
        "mapreduce.map.memory.mb" : 2048,
        "mapreduce.map.java.opts" : "-server -Xmx1536m -Duser.timezone=UTC -Dfile.encoding=UTF-8",
        "mapreduce.reduce.memory.mb" : 2048,
        "mapreduce.reduce.java.opts" : "-server -Xmx2560m -Duser.timezone=UTC -Dfile.encoding=UTF-8"
     }
    }
  }
}

Daniel,

Are you now able to load CSV data into druid? If so could you please update specs.

Thanks
Dasari