Spark SQL null value, Nan judgment and processing

Null and NaN

null It means nothing 、 Nonexistent or invalid object or address reference . It can be converted into 0, It's a global object .null ==false The value returned is false.
undefined It's a global property , Original value undefined. It tells us that some things have no assignment , No definition .undefined Cannot convert to any number , So use it in mathematical calculations , The return is NaN.

	val d: Double = math.sqrt(-1.0)
    println(d)
	
    val n: Boolean = math.sqrt(-1.0).isNaN
    println(n)

Spark SQL Null value Null,NaN Judge and deal with

    val df: DataFrame = session.sql(
      s""" |select * from sparktuning.course_pay1 |""".stripMargin)
         
 //  Delete null values and... For all columns NaN
val resNull=data1.na.drop()    
 resNull.limit(10).show()
+-------+------+---+------------+--------+-------------+---------+----------+------+
|affairs|gender|age|yearsmarried|children|religiousness|education|occupation|rating|
+-------+------+---+------------+--------+-------------+---------+----------+------+
|      0|  male| 37|          10|      no|            3|       18|         7|     4|
|      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|
|      0|  male| 37|          15|     yes|            2|       20|         7|     2|
|      0|  male| 27|           4|     yes|            4|       18|         6|     4|
|      0|  male| 47|          15|     yes|            5|       17|         6|     4|
|      0|female| 22|         1.5|      no|            2|       17|         5|     4|
|      0|female| 27|           4|      no|            4|       14|         5|     4|
|      0|female| 37|          15|     yes|            1|       17|         5|     5|
+-------+------+---+------------+--------+-------------+---------+----------+------+
    
// Delete the null value and... Of a column NaN
val res=data1.na.drop(Array("gender","yearsmarried"))
 
//  Delete a column that is not empty and not NaN Below 10 Of  -- Note the field type 
data1.na.drop(10,Array("gender","yearsmarried"))
    
// Fill in all null values [Boolean] The column of  -- Note the field type 
df.na.fill(false,Array("courseid")) 
   
// Fill in all null Columns 
val res123=data1.na.fill("wangxiao123")
 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|
+-------+-----------+---+------------+--------+-------------+---------+----------+-----------+
    
// Fill in the control of the specified column  --  Multiple columns with the same value 
df1.na.fill(123456,cols = Array("courseid","pointlistid")).show(false)

+---------+--------+-------+-----+-----------+--------+----+
|chapterid|courseid|majorid|money|pointlistid|dt      |dn  |
+---------+--------+-------+-----+-----------+--------+----+
|4        |123456  |5      |100  |3          |20190722|webA|
|7        |123456  |7      |100  |1          |20190722|webA|
|8        |123456  |3      |     |8          |20190722|webA|
|5        |14      |3      |100  |123456     |20190722|webA|
|4        |15      |2      |100  |3          |20190722|webA|
|9        |123456  |8      |100  |7          |20190722|webA|
|7        |17      |7      |100  |123456     |20190722|webA|
|0        |18      |9      |     |7          |20190722|webA|
|5        |123456  |8      |100  |4          |20190722|webA|
|4        |20      |1      |100  |123456     |20190722|webA|
|4        |123456  |5      |100  |1          |20190722|webA|
|0        |22      |3      |100  |9          |20190722|webA|
|1        |123456  |8      |100  |0          |20190722|webA|
|4        |24      |0      |100  |5          |20190722|webA|
|9        |123456  |9      |100  |0          |20190722|webA|
+---------+--------+-------+-----+-----------+--------+----+

// Fill in the control of the specified column  --  Multiple columns of different values 
df1.na.fill(Map("courseid"->123456,"pointlistid"->654321)).show(false)
+---------+--------+-------+-----+-----------+--------+----+
|chapterid|courseid|majorid|money|pointlistid|dt      |dn  |
+---------+--------+-------+-----+-----------+--------+----+
|4        |123456  |5      |100  |3          |20190722|webA|
|7        |123456  |7      |100  |1          |20190722|webA|
|8        |123456  |3      |     |8          |20190722|webA|
|5        |14      |3      |100  |654321     |20190722|webA|
|4        |15      |2      |100  |3          |20190722|webA|
|9        |123456  |8      |100  |7          |20190722|webA|
|7        |17      |7      |100  |654321     |20190722|webA|
|0        |18      |9      |     |7          |20190722|webA|
|5        |123456  |8      |100  |4          |20190722|webA|
|4        |20      |1      |100  |654321     |20190722|webA|
|4        |123456  |5      |100  |1          |20190722|webA|
|0        |22      |3      |100  |9          |20190722|webA|
|1        |123456  |8      |100  |0          |20190722|webA|
|4        |24      |0      |100  |5          |20190722|webA|
|9        |123456  |9      |100  |0          |20190722|webA|
+---------+--------+-------+-----+-----------+--------+----+


// Query null column 
data1.filter("gender is null").select("gender").limit(10).show
+------+
|gender|
+------+
|  null|
|  null|
|  null|
|  null|
|  null|
+------+
    
    
 data1.filter("gender is not null").select("gender").limit(10).show
+------+
|gender|
+------+
|  male|
|female|
|  male|
|female|
|  male|
|  male|
|  male|
|  male|
|female|
|female|
+------+
    
    
 data1.filter( data1("gender").isNull ).select("gender").limit(10).show
+------+
|gender|
+------+
|  null|
|  null|
|  null|
|  null|
|  null|
+------+
    
    
 data1.filter("gender<>''").select("gender").limit(10).show
+------+
|gender|
+------+
|  male|
|female|
|  male|
|female|
|  male|
|  male|
|  male|
|  male|
|female|
|female|
+------+