从事件日志中删除周末 - Pandas

Question

您能帮我解决以下问题吗？

我需要从数据框中删除周末天数（附加链接：dataframe_running_example。我可以获得从事件中提取的混合日期和最大日期之间的所有周末天数的列表，但是我无法根据“list_excluded”列表。

  from datetime import timedelta, date
  import pandas as pd
    
    #Data Loading
    df= pd.read_csv("running-example.csv", delimiter=";")
    df["timestamp"] = pd.to_datetime(df["timestamp"])
    df["timestamp_date"] = df["timestamp"].dt.date
    
    def daterange(date1, date2):
        for n in range(int ((date2 - date1).days)+1):
            yield date1 + timedelta(n)
    
    #start_dt & end_dt
    start_dt = df["timestamp"].min()
    end_dt = df["timestamp"].max()
    print("Start_dt: {} & end_dt: {}".format(start_dt, end_dt))
    
    weekdays = [6,7]
    
    #List comprehension
    
    list_excluded = [dt for dt in daterange(start_dt, end_dt) if dt.isoweekday() in weekdays]
    df.info()
    df_excluded = pd.DataFrame(list_excluded).rename({0: 'timestamp_excluded'}, axis='columns')
    df_excluded["ts_excluded"] = df_excluded["timestamp_excluded"].dt.date
    df[~df["timestamp_date"].isin(df_excluded["ts_excluded"])]

Answer 1

哦，问题已解决。我使用了 pd.bdate_range() 函数。

from datetime import timedelta, date
import pandas as pd
import numpy as np

#Wczytanie danych
df= pd.read_csv("running-example.csv", delimiter=";")
df["timestamp"] = pd.to_datetime(df["timestamp"])
df["timestamp_date"] = df["timestamp"].dt.date

#Zakres timestamp: start_dt & end_dt
start_dt = df["timestamp"].min()
end_dt = df["timestamp"].max()
print("Start_dt: {} & end_dt: {}".format(start_dt, end_dt))

bus_days = pd.bdate_range(start_dt, end_dt)
df["timestamp_date"] = pd.to_datetime(df["timestamp_date"])
df['Is_Business_Day'] = df['timestamp_date'].isin(bus_days)
df[df["Is_Business_Day"]!=False]