Python公交GPS数据的到离站信息匹配（TransBigData）

公交GPS的到离站信息匹配

使用示例中的样例数据集在github仓库中，链接为：https://github.com/ni1o1/transbigdata/tree/main/example

下面的案例展示如何用TransBigData包处理公交GPS数据，以内置方法计算公交车辆的到离站信息、统计公交单程耗时与运营车速

import transbigdata as tbd
import pandas as pd
import geopandas as gpd

读取数据

读取GPS数据

BUS_GPS= pd.read_csv(r'busgps.csv',header = None)
BUS_GPS.columns = ['GPSDateTime', 'LineId', 'LineName', 'NextLevel', 'PrevLevel',
       'Strlatlon', 'ToDir', 'VehicleId', 'VehicleNo', 'unknow']
#时间转换为datetime格式
BUS_GPS['GPSDateTime'] = pd.to_datetime(BUS_GPS['GPSDateTime'])

经纬度坐标转换

#切分经纬度的字符串
BUS_GPS['lon'] = BUS_GPS['Strlatlon'].apply(lambda r:r.split(',')[0])
BUS_GPS['lat'] = BUS_GPS['Strlatlon'].apply(lambda r:r.split(',')[1])
#坐标系转换
BUS_GPS['lon'],BUS_GPS['lat'] = tbd.gcj02towgs84(BUS_GPS['lon'].astype(float),BUS_GPS['lat'].astype(float))
BUS_GPS.head(5)

	GPSDateTime	LineId	LineName	NextLevel	PrevLevel	Strlatlon	ToDir	VehicleId	VehicleNo	unknow	lon	lat
0	2019-01-16 23:59:59	7100	71	2	1	121.335413,31.173188	1	沪D-R7103	Z5A-0021	1	121.330858	31.175129
1	2019-01-17 00:00:00	7100	71	2	1	121.334616,31.172271	1	沪D-R1273	Z5A-0002	1	121.330063	31.174214
2	2019-01-17 00:00:00	7100	71	24	23	121.339955,31.173025	0	沪D-R5257	Z5A-0020	1	121.335390	31.174958
3	2019-01-17 00:00:01	7100	71	14	13	121.409491,31.20433	0	沪D-R5192	Z5A-0013	1	121.404843	31.206179
4	2019-01-17 00:00:03	7100	71	15	14	121.398615,31.200253	0	沪D-T0951	Z5A-0022	1	121.393966	31.202103

读取公交线数据

shp = r'busline.json'
linegdf = gpd.GeoDataFrame.from_file(shp,encoding = 'gbk')
line = linegdf.iloc[:1].copy()
line.plot()

读取公交站点数据

shp = r'busstop.json'
stop = gpd.GeoDataFrame.from_file(shp,encoding = 'gbk')
stop = stop[stop['linename'] == '71路(延安东路外滩-申昆路枢纽站)']
stop.plot()

到离站信息匹配

arriveinfo = tbd.busgps_arriveinfo(BUS_GPS,line,stop)

数据清洗中…

运行位置匹配中……

匹配到离站信息………………………………………………………………………………………………………………………………………

arriveinfo

	arrivetime	leavetime	stopname	VehicleId
0	2019-01-17 07:19:42	2019-01-17 07:31:14	延安东路外滩	1
1	2019-01-17 09:53:08	2019-01-17 10:09:34	延安东路外滩	1
0	2019-01-17 07:13:23	2019-01-17 07:15:45	西藏中路	1
1	2019-01-17 07:34:24	2019-01-17 07:35:38	西藏中路	1
2	2019-01-17 09:47:03	2019-01-17 09:50:22	西藏中路	1
...	...	...	...	...
2	2019-01-17 16:35:52	2019-01-17 16:36:49	吴宝路	148
3	2019-01-17 19:21:09	2019-01-17 19:23:44	吴宝路	148
0	2019-01-17 13:36:26	2019-01-17 13:45:04	申昆路枢纽站	148
1	2019-01-17 15:52:26	2019-01-17 16:32:46	申昆路枢纽站	148
2	2019-01-17 19:24:54	2019-01-17 19:25:55	申昆路枢纽站	148

8984 rows × 4 columns

单程耗时

onewaytime = tbd.busgps_onewaytime(arriveinfo,stop,
                                   start = '延安东路外滩',
                                   end = '申昆路枢纽站',col = ['VehicleId','stopname'])

## 绘制耗时分布箱型图
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['font.serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus']=False
fig     = plt.figure(1,(8,4),dpi = 250)
ax1      = plt.subplot(111)

sns.boxplot(x = 'shour',y = onewaytime['duration']/60,hue = '方向',data = onewaytime)

plt.ylabel('始发站至终点站耗时（分钟）')
plt.xlabel('小时')
plt.ylim(0)
plt.show()

运营车速

#转换坐标系为投影坐标系，方便后面计算距离
line.crs = {'init':'epsg:4326'}
line_2416 = line.to_crs(epsg = 2416)
#公交线路数据里面的geometry
lineshp = line_2416['geometry'].iloc[0]
linename = line_2416['name'].iloc[0]
lineshp

#筛选去掉车速过快的
#车速单位转换为km/h
onewaytime['speed'] = (lineshp.length/onewaytime['duration'])*3.6
onewaytime = onewaytime[onewaytime['speed']<=60]

## 车速分布
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['font.serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus']=False
fig     = plt.figure(1,(8,4),dpi = 250)
ax1      = plt.subplot(111)
sns.boxplot(x = 'shour',y = 'speed',hue = '方向',data = onewaytime)
plt.ylabel('运营速度（km/h）')
plt.xlabel('小时')
plt.ylim(0)
plt.show()