在spark python中使用两列作为键

from pyspark.sql import SparkSession
from pyspark.sql.functions import col

spark = SparkSession.builder.getOrCreate()

df1 = spark.createDataFrame([(1, 'A', 100), (2, 'B', 200), (3, 'C', 300)], ['id', 'name', 'value1'])
df2 = spark.createDataFrame([(1, 'X', 500), (2, 'Y', 600), (3, 'Z', 700)], ['id', 'label', 'value2'])

result = df1.join(df2, on=['id'])

result.show()

+---+----+------+-----+------+
| id|name|value1|label|value2|
+---+----+------+-----+------+
|  1|   A|   100|    X|   500|
|  2|   B|   200|    Y|   600|
|  3|   C|   300|    Z|   700|
+---+----+------+-----+------+