Skip to main content
 首页 » 编程设计

python之如何包含动态时间

2025年04月02日13yyy_WW

我正在尝试提取与时隙相关的日志。没有时,下面的程序运行得很好。给出了小时数,并提取了该范围内的日志。

但是现在我还包括 Start 和 end 是动态给定的。也就是说,在 8 am 到 8pm 或 6am 到 8am 之间,依此类推。

我如何获得它?当前程序中的任何编辑也可以,或者单独的程序也可以。

输入:INPUT 的迷你版

代码:

import pandas as pd 
from datetime import datetime,time 
import numpy as np 
 
fn = r'00_Dart.csv' 
cols = ['UserID','StartTime','StopTime', 'gps1', 'gps2'] 
df = pd.read_csv(fn, header=None, names=cols) 
 
df['m'] = df.StopTime + df.StartTime 
df['d'] = df.StopTime - df.StartTime 
 
# 'start' and 'end' for the reporting DF: `r` 
# which will contain equal intervals (1 hour in this case) 
start = pd.to_datetime(df.StartTime.min(), unit='s').date() 
end = pd.to_datetime(df.StopTime.max(), unit='s').date() + pd.Timedelta(days=1) 
 
# building reporting DF: `r` 
freq = '1H'  # 1 Hour frequency 
idx = pd.date_range(start, end, freq=freq) 
r = pd.DataFrame(index=idx) 
r['start'] = (r.index - pd.datetime(1970,1,1)).total_seconds().astype(np.int64) 
 
# 1 hour in seconds, minus one second (so that we will not count it twice) 
interval = 60*60 - 1 
 
r['LogCount'] = 0 
r['UniqueIDCount'] = 0 
 
for i, row in r.iterrows(): 
        # intervals overlap test 
        # https://en.wikipedia.org/wiki/Interval_tree#Overlap_test 
        # i've slightly simplified the calculations of m and d 
        # by getting rid of division by 2, 
        # because it can be done eliminating common terms 
    u = df[np.abs(df.m - 2*row.start - interval) < df.d + interval].UserID 
    r.ix[i, ['LogCount', 'UniqueIDCount']] = [len(u), u.nunique()] 
 
r['Date'] = pd.to_datetime(r.start, unit='s').dt.date 
r['Day'] = pd.to_datetime(r.start, unit='s').dt.weekday_name.str[:3] 
r['StartTime'] = pd.to_datetime(r.start, unit='s').dt.time 
r['EndTime'] = pd.to_datetime(r.start + interval + 1, unit='s').dt.time 
 
#r.to_csv('results.csv', index=False) 
#print(r[r.LogCount > 0]) 
#print (r['StartTime'], r['EndTime'], r['Day'], r['LogCount'], r['UniqueIDCount']) 
 
rout =  r[['Date', 'StartTime', 'EndTime', 'Day', 'LogCount', 'UniqueIDCount'] ] 
#print rout 
rout.to_csv('one_hour.csv', index=False, header=False) 

编辑:

简单来说,我应该可以在程序中给出StartTime 和EndTIme。下面的代码非常接近我正在尝试做的事情。但是如何将其转换为 Pandas 。

from datetime import datetime,time 
 
start = time(8,0,0) 
end =   time(20,0,0) 
 
with open('USC28days_0_20', 'r') as infile, open('USC28days_0_20_time','w') as outfile: 
    for row in infile: 
        col = row.split() 
        t1 = datetime.fromtimestamp(float(col[2])).time() 
        t2 = datetime.fromtimestamp(float(col[3])).time() 
        print (t1 >= start and t2 <= end) 

编辑二: Pandas 中的工作答案

从@MaxU 的所选答案中摘取一部分。下面的代码在给定的 StartTime 和 StopTime

之间剥离所需的日志组
import pandas as pd 
from datetime import datetime,time 
import numpy as np 
 
fn = r'00_Dart.csv' 
cols = ['UserID','StartTime','StopTime', 'gps1', 'gps2'] 
 
df = pd.read_csv(fn, header=None, names=cols) 
 
#df['m'] = df.StopTime + df.StartTime 
#df['d'] = df.StopTime - df.StartTime 
 
# filter input data set ...  
start_hour = 8 
end_hour = 9 
df = df[(pd.to_datetime(df.StartTime, unit='s').dt.hour >= start_hour) & (pd.to_datetime(df.StopTime, unit='s').dt.hour <= end_hour)] 
 
print df 
 
df.to_csv('time_hour.csv', index=False, header=False) 

但是:如果有可能控制分钟和秒也是很好的解决方案。

目前,这还会剥离具有 StopTime 小时以及直到下一个小时的分钟和秒的日志。

有点像

start_hour = 8:0:0 
end_hour = 9:0:0 - 1 # -1 to get the logs until 8:59:59 

但这给了我一个错误

请您参考如下方法:

试试这个:

import pandas as pd 
from datetime import datetime,time 
import numpy as np 
 
fn = r'D:\data\gDrive\data\.stack.overflow\2016-07\dart_small.csv' 
cols = ['UserID','StartTime','StopTime', 'gps1', 'gps2'] 
 
df = pd.read_csv(fn, header=None, names=cols) 
 
df['m'] = df.StopTime + df.StartTime 
df['d'] = df.StopTime - df.StartTime 
 
# filter input data set ...  
start_hour = 8 
end_hour = 20 
df = df[(pd.to_datetime(df.StartTime, unit='s').dt.hour >= 8) & (pd.to_datetime(df.StartTime, unit='s').dt.hour <= 20)] 
 
 
# 'start' and 'end' for the reporting DF: `r` 
# which will contain equal intervals (1 hour in this case) 
start = pd.to_datetime(df.StartTime.min(), unit='s').date() 
end = pd.to_datetime(df.StopTime.max(), unit='s').date() + pd.Timedelta(days=1) 
 
# building reporting DF: `r` 
freq = '1H'  # 1 Hour frequency 
idx = pd.date_range(start, end, freq=freq) 
r = pd.DataFrame(index=idx) 
r = r[(r.index.hour >= start_hour) & (r.index.hour <= end_hour)] 
r['start'] = (r.index - pd.datetime(1970,1,1)).total_seconds().astype(np.int64) 
 
# 1 hour in seconds, minus one second (so that we will not count it twice) 
interval = 60*60 - 1 
 
r['LogCount'] = 0 
r['UniqueIDCount'] = 0 
 
for i, row in r.iterrows(): 
        # intervals overlap test 
        # https://en.wikipedia.org/wiki/Interval_tree#Overlap_test 
        # i've slightly simplified the calculations of m and d 
        # by getting rid of division by 2, 
        # because it can be done eliminating common terms 
    u = df[np.abs(df.m - 2*row.start - interval) < df.d + interval].UserID 
    r.ix[i, ['LogCount', 'UniqueIDCount']] = [len(u), u.nunique()] 
 
r['Date'] = pd.to_datetime(r.start, unit='s').dt.date 
r['Day'] = pd.to_datetime(r.start, unit='s').dt.weekday_name.str[:3] 
r['StartTime'] = pd.to_datetime(r.start, unit='s').dt.time 
r['EndTime'] = pd.to_datetime(r.start + interval + 1, unit='s').dt.time 
 
#r.to_csv('results.csv', index=False) 
#print(r[r.LogCount > 0]) 
#print (r['StartTime'], r['EndTime'], r['Day'], r['LogCount'], r['UniqueIDCount']) 
 
rout =  r[['Date', 'StartTime', 'EndTime', 'Day', 'LogCount', 'UniqueIDCount'] ] 
#print rout 

旧答案:

from_time = '08:00' 
to_time = '18:00' 
rout.between_time(from_time, to_time).to_csv('one_hour.csv', index=False, header=False)