spark解析json用到的算子

最新推荐文章于 2024-06-18 07:45:00 发布

weixin_43847900

最新推荐文章于 2024-06-18 07:45:00 发布

阅读量151

点赞数 1

分类专栏：大数据文章标签： spark

本文链接：https://blog.csdn.net/weixin_43847900/article/details/117229274

版权

大数据专栏收录该内容

16 篇文章 0 订阅

订阅专栏

// A code block

// An highlighted block
 import org.apache.spark.sql.types._
    import org.apache.spark.sql.functions._
    //定义字段类型
    val jsonSchema = new StructType().add("battery_level", LongType).add("c02_level",LongType).add("cca3",StringType).add("cn", StringType).add("device_id",LongType).add("device_type", StringType).add("signal", LongType).add("ip",StringType).add("timestamp", TimestampType).add("temp", LongType)
//    val frame = df1.withColumn("bb",from_json(col("id")*2,new StructType()))
//    frame.show()

    val eventsDS = Seq (
      (0, """{"device_id": 0, "device_type": "sensor-ipad", "ip": "68.161.225.1", "cca3": "USA", "cn": "United States", "temp": 25, "signal": 23, "battery_level": 8, "c02_level": 917, "timestamp" :1475600496 }"""),
      (1, """{"device_id": 1, "device_type": "sensor-igauge", "ip": "213.161.254.1", "cca3": "NOR", "cn": "Norway", "temp": 30, "signal": 18, "battery_level": 6, "c02_level": 1413, "timestamp" :1475600498 }"""),
      (2, """{"device_id": 2, "device_type": "sensor-ipad", "ip": "88.36.5.1", "cca3": "ITA", "cn": "Italy", "temp": 18, "signal": 25, "battery_level": 5, "c02_level": 1372, "timestamp" :1475600500 }"""),
      (3, """{"device_id": 3, "device_type": "sensor-inest", "ip": "66.39.173.154", "cca3": "USA", "cn": "United States", "temp": 47, "signal": 12, "battery_level": 1, "c02_level": 1447, "timestamp" :1475600502 }"""),
      (4, """{"device_id": 4, "device_type": "sensor-ipad", "ip": "203.82.41.9", "cca3": "PHL", "cn": "Philippines", "temp": 29, "signal": 11, "battery_level": 0, "c02_level": 983, "timestamp" :1475600504 }"""),
      (5, """{"device_id": 5, "device_type": "sensor-istick", "ip": "204.116.105.67", "cca3": "USA", "cn": "United States", "temp": 50, "signal": 16, "battery_level": 8, "c02_level": 1574, "timestamp" :1475600506 }"""),
      (6, """{"device_id": 6, "device_type": "sensor-ipad", "ip": "220.173.179.1", "cca3": "CHN", "cn": "China", "temp": 21, "signal": 18, "battery_level": 9, "c02_level": 1249, "timestamp" :1475600508 }"""),
      (7, """{"device_id": 7, "device_type": "sensor-ipad", "ip": "118.23.68.227", "cca3": "JPN", "cn": "Japan", "temp": 27, "signal": 15, "battery_level": 0, "c02_level": 1531, "timestamp" :1475600512 }"""),
      (8 ,""" {"device_id": 8, "device_type": "sensor-inest", "ip": "208.109.163.218", "cca3": "USA", "cn": "United States", "temp": 40, "signal": 16, "battery_level": 9, "c02_level": 1208, "timestamp" :1475600514 }"""),
      (9,"""{"device_id": 9, "device_type": "sensor-ipad", "ip": "88.213.191.34", "cca3": "ITA", "cn": "Italy", "temp": 19, "signal": 11, "battery_level": 0, "c02_level": 1171, "timestamp" :1475600516 }"""),
      (10,"""{"device_id": 10, "device_type": "sensor-igauge", "ip": "68.28.91.22", "cca3": "USA", "cn": "United States", "temp": 32, "signal": 26, "battery_level": 7, "c02_level": 886, "timestamp" :1475600518 }"""),
      (11,"""{"device_id": 11, "device_type": "sensor-ipad", "ip": "59.144.114.250", "cca3": "IND", "cn": "India", "temp": 46, "signal": 25, "battery_level": 4, "c02_level": 863, "timestamp" :1475600520 }"""),
      (12, """{"device_id": 12, "device_type": "sensor-igauge", "ip": "193.156.90.200", "cca3": "NOR", "cn": "Norway", "temp": 18, "signal": 26, "battery_level": 8, "c02_level": 1220, "timestamp" :1475600522 }"""),
      (13, """{"device_id": 13, "device_type": "sensor-ipad", "ip": "67.185.72.1", "cca3": "USA", "cn": "United States", "temp": 34, "signal": 20, "battery_level": 8, "c02_level": 1504, "timestamp" :1475600524 }"""),
      (14, """{"device_id": 14, "device_type": "sensor-inest", "ip": "68.85.85.106", "cca3": "USA", "cn": "United States", "temp": 39, "signal": 17, "battery_level": 8, "c02_level": 831, "timestamp" :1475600526 }"""),
      (15, """{"device_id": 15, "device_type": "sensor-ipad", "ip": "161.188.212.254", "cca3": "USA", "cn": "United States", "temp": 27, "signal": 26, "battery_level": 5, "c02_level": 1378, "timestamp" :1475600528 }"""),
      (16, """{"device_id": 16, "device_type": "sensor-igauge", "ip": "221.3.128.242", "cca3": "CHN", "cn": "China", "temp": 10, "signal": 24, "battery_level": 6, "c02_level": 1423, "timestamp" :1475600530 }"""),
      (17, """{"device_id": 17, "device_type": "sensor-ipad", "ip": "64.124.180.215", "cca3": "USA", "cn": "United States", "temp": 38, "signal": 17, "battery_level": 9, "c02_level": 1304, "timestamp" :1475600532 }"""),
      (18, """{"device_id": 18, "device_type": "sensor-igauge", "ip": "66.153.162.66", "cca3": "USA", "cn": "United States", "temp": 26, "signal": 10, "battery_level": 0, "c02_level": 902, "timestamp" :1475600534 }"""),
      (19, """{"device_id": 19, "device_type": "sensor-ipad", "ip": "193.200.142.254", "cca3": "AUT", "cn": "Austria", "temp": 32, "signal": 27, "battery_level": 5, "c02_level": 1282, "timestamp" :1475600536 }""")).toDF("id", "device").as[DeviceData]

    eventsDS.show()


    val eventsFromJSONDF = Seq (
      (0, """{"device_id": 0, "device_type": "sensor-ipad", "ip": "68.161.225.1", "cca3": "USA", "cn": "United States", "temp": 25, "signal": 23, "battery_level": 8, "c02_level": 917, "timestamp" :1475600496 }"""),
      (1, """{"device_id": 1, "device_type": "sensor-igauge", "ip": "213.161.254.1", "cca3": "NOR", "cn": "Norway", "temp": 30, "signal": 18, "battery_level": 6, "c02_level": 1413, "timestamp" :1475600498 }"""),
      (2, """{"device_id": 2, "device_type": "sensor-ipad", "ip": "88.36.5.1", "cca3": "ITA", "cn": "Italy", "temp": 18, "signal": 25, "battery_level": 5, "c02_level": 1372, "timestamp" :1475600500 }"""),
      (3, """{"device_id": 3, "device_type": "sensor-inest", "ip": "66.39.173.154", "cca3": "USA", "cn": "United States", "temp": 47, "signal": 12, "battery_level": 1, "c02_level": 1447, "timestamp" :1475600502 }"""),
      (4, """{"device_id": 4, "device_type": "sensor-ipad", "ip": "203.82.41.9", "cca3": "PHL", "cn": "Philippines", "temp": 29, "signal": 11, "battery_level": 0, "c02_level": 983, "timestamp" :1475600504 }"""),
      (5, """{"device_id": 5, "device_type": "sensor-istick", "ip": "204.116.105.67", "cca3": "USA", "cn": "United States", "temp": 50, "signal": 16, "battery_level": 8, "c02_level": 1574, "timestamp" :1475600506 }"""),
      (6, """{"device_id": 6, "device_type": "sensor-ipad", "ip": "220.173.179.1", "cca3": "CHN", "cn": "China", "temp": 21, "signal": 18, "battery_level": 9, "c02_level": 1249, "timestamp" :1475600508 }"""),
      (7, """{"device_id": 7, "device_type": "sensor-ipad", "ip": "118.23.68.227", "cca3": "JPN", "cn": "Japan", "temp": 27, "signal": 15, "battery_level": 0, "c02_level": 1531, "timestamp" :1475600512 }"""),
      (8 ,""" {"device_id": 8, "device_type": "sensor-inest", "ip": "208.109.163.218", "cca3": "USA", "cn": "United States", "temp": 40, "signal": 16, "battery_level": 9, "c02_level": 1208, "timestamp" :1475600514 }"""),
      (9,"""{"device_id": 9, "device_type": "sensor-ipad", "ip": "88.213.191.34", "cca3": "ITA", "cn": "Italy", "temp": 19, "signal": 11, "battery_level": 0, "c02_level": 1171, "timestamp" :1475600516 }""")).toDF("id", "json")

    val jsDF = eventsFromJSONDF.select($"id", get_json_object($"json","$.device_type").alias("device_type"),get_json_object($"json","$.ip").alias("ip"),get_json_object($"json", "$.cca3").alias("cca3"))
    jsDF.printSchema

    jsDF.show

    //from_json()
    val devicesDF = eventsDS.select(from_json($"device", jsonSchema) as "devices").select($"devices.*").filter($"devices.temp" > 30 and $"devices.signal" > 15)

    devicesDF.printSchema()
    devicesDF.show()

    System.out.print("*****************")
    val stringJsonDF = devicesDF.select(to_json(struct($"*"))).toDF("devices")

    stringJsonDF.show()

    //保存数据到kafka
   // stringJsonDF.write.format("kafka").option("kafka.bootstrap.servers","localhost:9092").option("topic", "iot-devices").save()


//将列转化为一个JSON对象的另一种方式是使用selectExpr()功能函数。例如我们可以将device列转化为一个JSON对象。
    val stringsDF = eventsDS.selectExpr("CAST(id AS INT)", "CAST(device AS STRING)")

    stringsDF.show


    devicesDF.selectExpr("c02_level", "round(c02_level/temp) as ratio_c02_temperature").orderBy($"ratio_c02_temperature" desc).show

    devicesDF.createOrReplaceTempView("devicesDFT")
    ssc.sql("select c02_level,round(c02_level/temp)*100 as ratio_c02_temperature from devicesDFT order by ratio_c02_temperature desc").show
  //为了验证我们的DataFrame转化为json String是成功的我们将结果写入本地磁盘。

    stringJsonDF.write.mode("overwrite").format("parquet").save("file:/Users/zhanghongmac/Downloads/waterdrop-2.0.4/waterdrop-spark-api/src/main/scala/io/github/interestinglab/waterdrop/spark/test/checkpoint")