将列表列表作为列附加到PySpark的dataframe (连接两个没有公共列的dataframe)

from pyspark.sql import SparkSession
from pyspark.sql.functions import lit

spark = SparkSession.builder.getOrCreate()

df1 = spark.createDataFrame([(1, 'A'), (2, 'B'), (3, 'C')], ['id1', 'col1'])
df2 = spark.createDataFrame([(4, 'X'), (5, 'Y'), (6, 'Z')], ['id2', 'col2'])

df1_with_col2 = df1.withColumn('col2', lit(None))
df1_with_col2.show()

+---+----+----+
|id1|col1|col2|
+---+----+----+
|  1|   A|null|
|  2|   B|null|
|  3|   C|null|
+---+----+----+

result = df1_with_col2.crossJoin(df2).select('id1', 'col1', 'col2', 'id2', 'col2')
result.show()

+---+----+----+---+----+
|id1|col1|col2|id2|col2|
+---+----+----+---+----+
|  1|   A|null|  4|   X|
|  1|   A|null|  5|   Y|
|  1|   A|null|  6|   Z|
|  2|   B|null|  4|   X|
|  2|   B|null|  5|   Y|
|  2|   B|null|  6|   Z|
|  3|   C|null|  4|   X|
|  3|   C|null|  5|   Y|
|  3|   C|null|  6|   Z|
+---+----+----+---+----+