赞
踩
numeric = sqlContext.createDataFrame([
('3.5,', '5.0', 'null'), ('2.0', '14.0', 'null'), ('null', '38.0', 'null'),
('null', 'null', 'null'), ('1.0', 'null', '4.0')],
('low', 'high', 'normal'))
numeric_filtered_1 = numeric.where(numeric['LOW'] != 'null')
numeric_filtered_1.show()
+----+----+------+
| low|high|normal|
+----+----+------+
|3.5,| 5.0| null|
| 2.0|14.0| null|
| 1.0|null| 4.0|
+----+----+------+
numeric_filtered_2 = numeric_filtered_1.where(
numeric_filtered_1['NORMAL'] != 'null')
numeric_filtered_2.show()
+---+----+------+
|low|high|normal|
+---+----+------+
|1.0|null| 4.0|
+---+----+------+
numeric_filtered_3 = numeric_filtered_2.where(
numeric_filtered_2['HIGH'] != 'null')
numeric_filtered_3.show()
+---+----+------+
|low|high|normal|
+---+----+------+
+---+----+------+
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。