007 Dataset

scala> // Define the case classes for using in conjunction with DataFrames and Dataset

scala> case class Trans(accNo: String, tranAmount: Double)
defined class Trans

scala> // Creation of the list from where the Dataset is going to be created using a case class.

scala> val acTransList = Seq(Trans("SB10001", 1000), Trans("SB10002",1200), Trans("SB10003", 8000), Trans("SB10004",400), Trans("SB10005",300),Trans("SB10006",10000), Trans("SB10007",500), Trans("SB10008",56),Trans("SB10009",30),Trans("SB10010",7000), Trans("CR10001",7000),Trans("SB10002",-10))
acTransList: Seq[Trans] = List(Trans(SB10001,1000.0), Trans(SB10002,1200.0), Trans(SB10003,8000.0), Trans(SB10004,400.0), Trans(SB10005,300.0), Trans(SB10006,10000.0), Trans(SB10007,500.0), Trans(SB10008,56.0), Trans(SB10009,30.0), Trans(SB10010,7000.0), Trans(CR10001,7000.0), Trans(SB10002,-10.0))

scala> // Create the Dataset

scala> val acTransDS = acTransList.toDS()
acTransDS: org.apache.spark.sql.Dataset[Trans] = [accNo: string, tranAmount: double]

scala> acTransDS.show()
+-------+----------+
|  accNo|tranAmount|
+-------+----------+
|SB10001|    1000.0|
|SB10002|    1200.0|
|SB10003|    8000.0|
|SB10004|     400.0|
|SB10005|     300.0|
|SB10006|   10000.0|
|SB10007|     500.0|
|SB10008|      56.0|
|SB10009|      30.0|
|SB10010|    7000.0|
|CR10001|    7000.0|
|SB10002|     -10.0|
+-------+----------+


scala> // Apply filter and create another Dataset of good transaction records

scala> val goodTransRecords = acTransDS.filter(_.tranAmount > 0).filter(_.accNo.startsWith("SB"))
goodTransRecords: org.apache.spark.sql.Dataset[Trans] = [accNo: string, tranAmount: double]

scala> goodTransRecords.show()
+-------+----------+                                                            
|  accNo|tranAmount|
+-------+----------+
|SB10001|    1000.0|
|SB10002|    1200.0|
|SB10003|    8000.0|
|SB10004|     400.0|
|SB10005|     300.0|
|SB10006|   10000.0|
|SB10007|     500.0|
|SB10008|      56.0|
|SB10009|      30.0|
|SB10010|    7000.0|
+-------+----------+


scala> // Apply filter and create another Dataset of high value transaction records

scala> val highValueTransRecords = goodTransRecords.filter(_.tranAmount > 1000)
highValueTransRecords: org.apache.spark.sql.Dataset[Trans] = [accNo: string, tranAmount: double]

scala> highValueTransRecords.show()
+-------+----------+
|  accNo|tranAmount|
+-------+----------+
|SB10002|    1200.0|
|SB10003|    8000.0|
|SB10006|   10000.0|
|SB10010|    7000.0|
+-------+----------+


scala> // The function that identifies the bad amounts

scala> val badAmountLambda = (trans: Trans) => trans.tranAmount <= 0
badAmountLambda: Trans => Boolean = <function1>

scala> // The function that identifies bad accounts

scala> val badAcNoLambda = (trans: Trans) => trans.accNo.startsWith("SB") == false
badAcNoLambda: Trans => Boolean = <function1>

scala> // The function that identifies bad accounts

scala> val badAcNoLambda = (trans: Trans) => trans.accNo.startsWith("SB") == false
badAcNoLambda: Trans => Boolean = <function1>

scala> // Apply filter and create another Dataset of bad amount records

scala> val badAmountRecords = acTransDS.filter(badAmountLambda)
badAmountRecords: org.apache.spark.sql.Dataset[Trans] = [accNo: string, tranAmount: double]

scala> badAmountRecords.show()
+-------+----------+
|  accNo|tranAmount|
+-------+----------+
|SB10002|     -10.0|
+-------+----------+


scala> // Apply filter and create another Dataset of bad account records

scala> val badAccountRecords = acTransDS.filter(badAcNoLambda)
badAccountRecords: org.apache.spark.sql.Dataset[Trans] = [accNo: string, tranAmount: double]

scala> badAccountRecords.show()
+-------+----------+
|  accNo|tranAmount|
+-------+----------+
|CR10001|    7000.0|
+-------+----------+


scala> // Do the union of two Dataset and create another Dataset

scala> val badTransRecords = badAmountRecords.union(badAccountRecords)
badTransRecords: org.apache.spark.sql.Dataset[Trans] = [accNo: string, tranAmount: double]

scala> badTransRecords.show()
+-------+----------+
|  accNo|tranAmount|
+-------+----------+
|SB10002|     -10.0|
|CR10001|    7000.0|
+-------+----------+


scala> // Calculate the sum

scala> val sumAmount = goodTransRecords.map(trans => trans.tranAmount).reduce(_ + _)
sumAmount: Double = 28486.0

scala> // Calculate the maximum

scala> val maxAmount = goodTransRecords.map(trans => trans.tranAmount).reduce((a, b) => if (a > b) a else b)
maxAmount: Double = 10000.0

scala> // Calculate the minimum

scala> val minAmount = goodTransRecords.map(trans => trans.tranAmount).reduce((a, b) => if (a < b) a else b)
minAmount: Double = 30.0

scala> // Convert the Dataset to DataFrame

scala> val acTransDF = acTransDS.toDF()
acTransDF: org.apache.spark.sql.DataFrame = [accNo: string, tranAmount: double]

scala> acTransDF.show()
+-------+----------+
|  accNo|tranAmount|
+-------+----------+
|SB10001|    1000.0|
|SB10002|    1200.0|
|SB10003|    8000.0|
|SB10004|     400.0|
|SB10005|     300.0|
|SB10006|   10000.0|
|SB10007|     500.0|
|SB10008|      56.0|
|SB10009|      30.0|
|SB10010|    7000.0|
|CR10001|    7000.0|
|SB10002|     -10.0|
+-------+----------+


scala> // Use Spark SQL to find out invalid transaction records

scala> acTransDF.createOrReplaceTempView("trans")

scala> val invalidTransactions = spark.sql("SELECT accNo, tranAmount FROM trans WHERE (accNo NOT LIKE 'SB%') OR tranAmount <= 0")
19/12/02 22:29:36 WARN ObjectStore: Failed to get database global_temp, returning NoSuchObjectException
invalidTransactions: org.apache.spark.sql.DataFrame = [accNo: string, tranAmount: double]

scala> invalidTransactions.show()
+-------+----------+
|  accNo|tranAmount|
+-------+----------+
|CR10001|    7000.0|
|SB10002|     -10.0|
+-------+----------+


scala> // Interoperability of RDD, DataFrame and Dataset

scala> // Create RDD

scala> val acTransRDD = sc.parallelize(acTransList)
acTransRDD: org.apache.spark.rdd.RDD[Trans] = ParallelCollectionRDD[41] at parallelize at <console>:26

scala> // Convert RDD to DataFrame

scala> val acTransRDDtoDF = acTransRDD.toDF()
acTransRDDtoDF: org.apache.spark.sql.DataFrame = [accNo: string, tranAmount: double]

scala> // Convert the DataFrame to Dataset with the type checking

scala> val acTransDFtoDS = acTransRDDtoDF.as[Trans]
acTransDFtoDS: org.apache.spark.sql.Dataset[Trans] = [accNo: string, tranAmount: double]

scala> acTransDFtoDS.show()
+-------+----------+
|  accNo|tranAmount|
+-------+----------+
|SB10001|    1000.0|
|SB10002|    1200.0|
|SB10003|    8000.0|
|SB10004|     400.0|
|SB10005|     300.0|
|SB10006|   10000.0|
|SB10007|     500.0|
|SB10008|      56.0|
|SB10009|      30.0|
|SB10010|    7000.0|
|CR10001|    7000.0|
|SB10002|     -10.0|
+-------+----------+

©著作权归作者所有,转载或内容合作请联系作者
  • 序言:七十年代末,一起剥皮案震惊了整个滨河市,随后出现的几起案子,更是在滨河造成了极大的恐慌,老刑警刘岩,带你破解...
    沈念sama阅读 201,681评论 5 474
  • 序言:滨河连续发生了三起死亡事件,死亡现场离奇诡异,居然都是意外死亡,警方通过查阅死者的电脑和手机,发现死者居然都...
    沈念sama阅读 84,710评论 2 377
  • 文/潘晓璐 我一进店门,熙熙楼的掌柜王于贵愁眉苦脸地迎上来,“玉大人,你说我怎么就摊上这事。” “怎么了?”我有些...
    开封第一讲书人阅读 148,623评论 0 334
  • 文/不坏的土叔 我叫张陵,是天一观的道长。 经常有香客问我,道长,这世上最难降的妖魔是什么? 我笑而不...
    开封第一讲书人阅读 54,202评论 1 272
  • 正文 为了忘掉前任,我火速办了婚礼,结果婚礼上,老公的妹妹穿的比我还像新娘。我一直安慰自己,他们只是感情好,可当我...
    茶点故事阅读 63,232评论 5 363
  • 文/花漫 我一把揭开白布。 她就那样静静地躺着,像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上,一...
    开封第一讲书人阅读 48,368评论 1 281
  • 那天,我揣着相机与录音,去河边找鬼。 笑死,一个胖子当着我的面吹牛,可吹牛的内容都是我干的。 我是一名探鬼主播,决...
    沈念sama阅读 37,795评论 3 393
  • 文/苍兰香墨 我猛地睁开眼,长吁一口气:“原来是场噩梦啊……” “哼!你这毒妇竟也来了?” 一声冷哼从身侧响起,我...
    开封第一讲书人阅读 36,461评论 0 256
  • 序言:老挝万荣一对情侣失踪,失踪者是张志新(化名)和其女友刘颖,没想到半个月后,有当地人在树林里发现了一具尸体,经...
    沈念sama阅读 40,647评论 1 295
  • 正文 独居荒郊野岭守林人离奇死亡,尸身上长有42处带血的脓包…… 初始之章·张勋 以下内容为张勋视角 年9月15日...
    茶点故事阅读 35,476评论 2 317
  • 正文 我和宋清朗相恋三年,在试婚纱的时候发现自己被绿了。 大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
    茶点故事阅读 37,525评论 1 329
  • 序言:一个原本活蹦乱跳的男人离奇死亡,死状恐怖,灵堂内的尸体忽然破棺而出,到底是诈尸还是另有隐情,我是刑警宁泽,带...
    沈念sama阅读 33,226评论 3 318
  • 正文 年R本政府宣布,位于F岛的核电站,受9级特大地震影响,放射性物质发生泄漏。R本人自食恶果不足惜,却给世界环境...
    茶点故事阅读 38,785评论 3 303
  • 文/蒙蒙 一、第九天 我趴在偏房一处隐蔽的房顶上张望。 院中可真热闹,春花似锦、人声如沸。这庄子的主人今日做“春日...
    开封第一讲书人阅读 29,857评论 0 19
  • 文/苍兰香墨 我抬头看了看天上的太阳。三九已至,却和暖如春,着一层夹袄步出监牢的瞬间,已是汗流浃背。 一阵脚步声响...
    开封第一讲书人阅读 31,090评论 1 258
  • 我被黑心中介骗来泰国打工, 没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留,地道东北人。 一个月前我还...
    沈念sama阅读 42,647评论 2 348
  • 正文 我出身青楼,却偏偏与公主长得像,于是被迫代替她去往敌国和亲。 传闻我的和亲对象是个残疾皇子,可洞房花烛夜当晚...
    茶点故事阅读 42,215评论 2 341

推荐阅读更多精彩内容