在Pyspark中减去两个数组得到一个新的数组

pyspark.sql.functions.subtract(col1, col2)

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

# 创建SparkSession
spark = SparkSession.builder.getOrCreate()

# 创建示例数据
data = [(1, ["a", "b", "c"]), (2, ["b", "c", "d"]), (3, ["c", "d", "e"])]
df = spark.createDataFrame(data, ["id", "array_col"])

# 定义两个数组列
col1 = col("array_col")
col2 = array(["b", "c"])

# 使用subtract函数进行减法操作
result = df.select(col1, col2, array_subtract(col1, col2).alias("result"))

# 显示结果
result.show(truncate=False)

+---------+------+------+
|array_col|array2|result|
+---------+------+------+
|[a, b, c]|[b, c]|[a]   |
|[b, c, d]|[b, c]|[d]   |
|[c, d, e]|[b, c]|[d, e]|
+---------+------+------+