标签：double cat ram blog map select cal 数据 field
scala> val data1 = data.toDF("affairs", "gender", "age", "yearsmarried", "children", "religiousness", "education", "occupation", "rating")
data1: org.apache.spark.sql.DataFrame = [affairs: string, gender: string ... 7 more fields]
scala> data1.limit(10).show
+-------+------+---+------------+--------+-------------+---------+----------+------+
|affairs|gender|age|yearsmarried|children|religiousness|education|occupation|rating|
+-------+------+---+------------+--------+-------------+---------+----------+------+
| 0| male| 37| 10| no| 3| 18| 7| 4|
| 0| null| 27| null| no| 4| 14| 6| null|
| 0| null| 32| null| yes| 1| 12| 1| null|
| 0| null| 57| null| yes| 5| 18| 6| null|
| 0| null| 22| null| no| 2| 17| 6| null|
| 0| null| 32| null| no| 2| 17| 5| null|
| 0|female| 22| null| no| 2| 12| 1| null|
| 0| male| 57| 15| yes| 2| 14| 4| 4|
| 0|female| 32| 15| yes| 4| 16| 1| 2|
| 0| male| 22| 1.5| no| 4| 14| 4| 5|
+-------+------+---+------------+--------+-------------+---------+----------+------+
scala>
| val res=data1.select("yearsmarried").na.drop()
res: org.apache.spark.sql.DataFrame = [yearsmarried: string]
scala> res.limit(10).show()
+------------+
|yearsmarried|
+------------+
| 10|
| 15|
| 15|
| 1.5|
| 15|
| 4|
| 15|
| 1.5|
| 4|
| 15|
+------------+
scala>
| val res123=data1.na.fill("wangxiao123")
res123: org.apache.spark.sql.DataFrame = [affairs: string, gender: string ... 7 more fields]
scala> res123.limit(10).show()
+-------+-----------+---+------------+--------+-------------+---------+----------+-----------+
|affairs| gender|age|yearsmarried|children|religiousness|education|occupation| rating|
+-------+-----------+---+------------+--------+-------------+---------+----------+-----------+
| 0| male| 37| 10| no| 3| 18| 7| 4|
| 0|wangxiao123| 27| wangxiao123| no| 4| 14| 6|wangxiao123|
| 0|wangxiao123| 32| wangxiao123| yes| 1| 12| 1|wangxiao123|
| 0|wangxiao123| 57| wangxiao123| yes| 5| 18| 6|wangxiao123|
| 0|wangxiao123| 22| wangxiao123| no| 2| 17| 6|wangxiao123|
| 0|wangxiao123| 32| wangxiao123| no| 2| 17| 5|wangxiao123|
| 0| female| 22| wangxiao123| no| 2| 12| 1|wangxiao123|
| 0| male| 57| 15| yes| 2| 14| 4| 4|
| 0| female| 32| 15| yes| 4| 16| 1| 2|
| 0| male| 22| 1.5| no| 4| 14| 4| 5|
+-------+-----------+---+------------+--------+-------------+---------+----------+-----------+
scala>
| val res2=data1.na.fill(value="wangxiao111",cols=Array("gender","yearsmarried") )
res2: org.apache.spark.sql.DataFrame = [affairs: string, gender: string ... 7 more fields]
scala> res2.limit(10).show()
+-------+-----------+---+------------+--------+-------------+---------+----------+------+
|affairs| gender|age|yearsmarried|children|religiousness|education|occupation|rating|
+-------+-----------+---+------------+--------+-------------+---------+----------+------+
| 0| male| 37| 10| no| 3| 18| 7| 4|
| 0|wangxiao111| 27| wangxiao111| no| 4| 14| 6| null|
| 0|wangxiao111| 32| wangxiao111| yes| 1| 12| 1| null|
| 0|wangxiao111| 57| wangxiao111| yes| 5| 18| 6| null|
| 0|wangxiao111| 22| wangxiao111| no| 2| 17| 6| null|
| 0|wangxiao111| 32| wangxiao111| no| 2| 17| 5| null|
| 0| female| 22| wangxiao111| no| 2| 12| 1| null|
| 0| male| 57| 15| yes| 2| 14| 4| 4|
| 0| female| 32| 15| yes| 4| 16| 1| 2|
| 0| male| 22| 1.5| no| 4| 14| 4| 5|
+-------+-----------+---+------------+--------+-------------+---------+----------+------+
scala>
| val res3=data1.na.fill(Map("gender"->"wangxiao222","yearsmarried"->"wangxiao567") )
res3: org.apache.spark.sql.DataFrame = [affairs: string, gender: string ... 7 more fields]
scala> res3.limit(10).show()
+-------+-----------+---+------------+--------+-------------+---------+----------+------+
|affairs| gender|age|yearsmarried|children|religiousness|education|occupation|rating|
+-------+-----------+---+------------+--------+-------------+---------+----------+------+
| 0| male| 37| 10| no| 3| 18| 7| 4|
| 0|wangxiao222| 27| wangxiao567| no| 4| 14| 6| null|
| 0|wangxiao222| 32| wangxiao567| yes| 1| 12| 1| null|
| 0|wangxiao222| 57| wangxiao567| yes| 5| 18| 6| null|
| 0|wangxiao222| 22| wangxiao567| no| 2| 17| 6| null|
| 0|wangxiao222| 32| wangxiao567| no| 2| 17| 5| null|
| 0| female| 22| wangxiao567| no| 2| 12| 1| null|
| 0| male| 57| 15| yes| 2| 14| 4| 4|
| 0| female| 32| 15| yes| 4| 16| 1| 2|
| 0| male| 22| 1.5| no| 4| 14| 4| 5|
+-------+-----------+---+------------+--------+-------------+---------+----------+------+
scala>
|
| data1.filter("gender is null").limit(10).show
+-------+------+---+------------+--------+-------------+---------+----------+------+
|affairs|gender|age|yearsmarried|children|religiousness|education|occupation|rating|
+-------+------+---+------------+--------+-------------+---------+----------+------+
| 0| null| 27| null| no| 4| 14| 6| null|
| 0| null| 32| null| yes| 1| 12| 1| null|
| 0| null| 57| null| yes| 5| 18| 6| null|
| 0| null| 22| null| no| 2| 17| 6| null|
| 0| null| 32| null| no| 2| 17| 5| null|
+-------+------+---+------------+--------+-------------+---------+----------+------+
scala> data1.filter( data1("gender").isNull ).limit(10).show
+-------+------+---+------------+--------+-------------+---------+----------+------+
|affairs|gender|age|yearsmarried|children|religiousness|education|occupation|rating|
+-------+------+---+------------+--------+-------------+---------+----------+------+
| 0| null| 27| null| no| 4| 14| 6| null|
| 0| null| 32| null| yes| 1| 12| 1| null|
| 0| null| 57| null| yes| 5| 18| 6| null|
| 0| null| 22| null| no| 2| 17| 6| null|
| 0| null| 32| null| no| 2| 17| 5| null|
+-------+------+---+------------+--------+-------------+---------+----------+------+
scala>
|
| math.sqrt(-1.0)
res32: Double = NaN
scala> math.sqrt(-1.0).isNaN()
res33: Boolean = true
标签：double cat ram blog map select cal 数据 field
原文地址：http://www.cnblogs.com/wwxbi/p/6011422.html
