从date列中提取年和月作为Pyspark中的字符串

from pyspark.sql import SparkSession
from pyspark.sql.functions import year, month

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

# 创建示例DataFrame
data = [("2022-01-01"), ("2022-02-01"), ("2022-03-01")]
df = spark.createDataFrame(data, ["date"])

# 提取年和月作为字符串
df = df.withColumn("year", year(df["date"]).cast("string"))
df = df.withColumn("month", month(df["date"]).cast("string"))

# 显示结果
df.show()

+----------+----+-----+
|      date|year|month|
+----------+----+-----+
|2022-01-01|2022|    1|
|2022-02-01|2022|    2|
|2022-03-01|2022|    3|
+----------+----+-----+