pyspark -从日期列创建一个季度-年的列

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

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

# 创建一个DataFrame，包含日期列
data = [("2022-01-01"), ("2022-04-15"), ("2022-07-30"), ("2022-10-20")]
df = spark.createDataFrame(data, ["date"])

# 添加季度-年的列
df = df.withColumn("quarter_year", quarter(df["date"]).cast("string") + "-" + year(df["date"]).cast("string"))

# 显示结果
df.show()

+----------+-------------+
|      date|quarter_year |
+----------+-------------+
|2022-01-01|       1-2022|
|2022-04-15|       2-2022|
|2022-07-30|       3-2022|
|2022-10-20|       4-2022|
+----------+-------------+