from pyspark.sql import SparkSession
from pyspark.sql import Row
from pyspark.sql.types import *
from pyspark.sql.functions import *
df = spark.sql("select * from table_name")
也可以使用toDF()
from pyspark.sql import Row
row = Row("spe_id", "InOther")
x = ['x1','x2']
y = ['y1','y2']
new_df = sc.parallelize([row(x[i], y[i]) for i in range(2)]).toDF()