python中的list不能直接添加到dataframe中,需要先将list转为新的dataframe,然后新的dataframe和老的dataframe进行join操作, 下面的例子会先新建一个dataframe,然后将list转为dataframe,然后将两者join起来。
from pyspark.sql.functions import lit
df = sqlContext.createDataFrame(
[(1, "a", 23.0), (3, "B", -23.0)], ("x1", "x2", "x3"))
from pyspark.sql.functions import monotonically_increasing_id
df = df.withColumn("id", monotonically_increasing_id())
df.show()
+---+---+-----+---+
| x1| x2| x3| id|
+---+---+-----+---+
| 1| a| 23.0| 0|
| 3| B|-23.0| 1|
+---+---+-----+---+
from pyspark.sql import Row
l = ['jerry', 'tom']
row = Row("pid", "name")
new_df = sc.parallelize([row(i, l[i]) for i in range(0,len(l))]).toDF()
new_df.show()
+---+-----+
|pid| name|
+---+-----+
| 0|jerry|
| 1| tom|
+---+-----+
join_df = df.join(new_df, df.id==new_df.pid)
join_df.show()
+---+---+-----+---+---+-----+
| x1| x2| x3| id|pid| name|
+---+---+-----+---+---+-----+
| 1| a| 23.0| 0| 0|jerry|
| 3| B|-23.0| 1| 1| tom|
+---+---+-----+---+---+-----+