你必须从日期栏中提取日期和时间。今天，你有两个选择。首先，可以使用udf提取工作日全名。如果一天足够作为一个整数，您可以使用内置的pyspark功能。之后，可以连接这两列并执行groupby+计数

import datetime
import pyspark.sql.functions as f
from pyspark.sql.types import StringType

def  get_day_from_date(dt)
    dt_parsed = datetime.datetime.strptime(dt_2, '%d-%m-%Y %H:%M:%S')
    ans = datetime.date(dt_parsed.year, dt_parsed.month, dt_parsed.day)
    return ans.strftime("%A")

to_day = f.udf(get_day_from_date, StringType())
df = df.withColumn('dateOccurred_ts', f.to_timestamp('Timestamp', 'dd-MM-yyyy HH:mm:ss'))

# udf returns Weekday as locale’s full name

df = df.withColumn('day', to_day(f.col('dateOccurred')))

## other soulution only returns day of the week of a given date as integer.

df = df.withColumn('day', f.dayofweek('dateOccurred_ts'))

df = df.withColumn('hour', f.hour('dateOccured_ts'))
df_2 = df.select(f.concat_ws('_', f.col('day'), f.col('hour')))
df = df.groupBy('day_hour').agg(f.count(f.lit(1)).alias('dateOccurred_cnt'))