soup = BeautifulSoup(r.text, 'html.parser')
line_names = [
l.text.strip()
for l in soup.find_all('dt', class_='basicInfo-item name')
]
line_values = [
l.text.strip()
for l in soup.find_all('dd', class_='basicInfo-item value')
]
dict_info = dict(zip(line_names, line_values))
return dict_info
ttt = MeasureT()
path = 'E:/Code/需求与辐射模型/transfer/多车站'
files = lib_file.list_all_files(path)
names = [f.split('\\')[-1].split('.png')[0] for f in files]
dict_HSRLocs = lib_file.pickle_load('../需求与辐射模型/dict_HSRLocs.pkl')
dict_nameBaiduInfo = {}
for i, name in enumerate(list(dict_HSRLocs.keys())):
info = grab_BaiduItem(name + '站')
dict_nameBaiduInfo[name] = info
if i % 10 == 0:
ttt.duration(str(i) + ' processed')
lib_file.json_save(dict_nameBaiduInfo, '车站信息.json')
import geopandas as gpd
import geoplot as gplt
import lib_geo
import geoplot.crs as gcrs
import numpy as np
import lib_time
import multiprocessing
import random
import matplotlib.pyplot as plt
import lib_time ### 关于时间的相应操作在这个包里
from lib_time import get_deltaT, strT_to_floatT, floatT_to_strT
# 1 数据准备
##### 1.1 车站的位置
dict_HSRLocs = lib_file.pickle_load('E:/Code/需求与辐射模型-欧洲/dict_HSRLocs.pkl')
###### 1.1 列车时刻表,加载有向图
timetable = Timetable()
timetable.load_file('E:/Code/Data/EuropeRailway/Europe_Railway_Schedule.csv',
mode='ALL',
encoding='utf-8') ### ALL 指的是全部车型， 还可以特指HSR，但是欧洲不支持
#list_names = ['London Euston', 'London Paddington', 'London St Pancras',
# 'London Kings Cross', 'London Liverpool Street', 'London Blackfriars',
# 'London Bridge', 'London Charing Cross', 'London Victoria']
## dict_pairJS 应该也建成图
###### 识别一个互补车站群 #####################################
#G = nx.Graph()
#for pair in dict_pairJS:
#if info['scheduleDelay'] > 12: # 在车站等待四个小时以上
# continue
if (n in dict_accessed) and (info['travelT'] - dict_accessed[n] >=
-0.1): ## 就没快几分钟，不用换了
continue
if (n not in dict_ChildInfo) or (dict_ChildInfo[n]['travelT'] >
info['travelT']):
dict_ChildInfo[n] = info
return dict_ChildInfo
###############################################################################
###################### Data prepare ###################################
##### 1.1 高铁车站的位置
dict_HSRLocs = lib_file.pickle_load('dict_HSRLocs.pkl')
##### 2.2 高铁时刻表,加载有向图
timetable = Timetable()
timetable.load_file(
'/run/media/pengfei/OTHERS/Code/Data/ChinaRailway/China_Railway_Schedule_20190701.csv'
)
###### 2.3 去掉时刻表中没有位置的点
G_schedule = timetable.get_TravelT(mode="all")
for n in list(G_schedule.nodes()):
if n not in dict_HSRLocs:
G_schedule.remove_node(n)
#### 3.1 加载 车站在三小时car driving 时间内可达的格点的图(graph)
f_HSRGrid = '/run/media/pengfei/OTHERS/Code/Data/ChinaRailway/CalculateGridTravelTTeacherGiveME/StationGridAccessibility_Adapt.csv'
G_HSRGrid = lib_graph.createG_fromFile(
f_HSRGrid,
import lib_transferTWO
from xpinyin import Pinyin
import time
ppinyin = Pinyin()
"""
1. 基础数据 车站位置，机场位置
数据类型： 字典 dict
"""
##### 1.1 车站的位置
df_railwayLocs = lib_file.read_file2df(
OS + 'Code/Data/ChinaRailway/China_Station_Locs_All.csv')
dict_HSRLocs = lib_file.get_LocIndex(df_railwayLocs)
##### 1.2 机场的位置
dict_AirportLocs = lib_file.pickle_load(
OS + 'Code/空铁联合换乘/data/dict_AirportLocs.pkl')
##### 1.3 位置信息合并
dict_PortLocs = dict(dict_HSRLocs, **dict_AirportLocs)
"""
2. 时刻表数据
数据类型： 有向图 DiGraph
"""
def add_type2G(G, dict_HSRLocs, dict_AirportLocs):
## 为图中的节点添加类型标示， "station" or "airport"
for name in G: ## 为图节点添加属性
if name in dict_HSRLocs: # 火车站
G.node[name]['type'] = 'station'
elif name in dict_AirportLocs:
G.node[name]['type'] = 'airport'
import lib_geo
import geoplot.crs as gcrs
import numpy as np
import lib_time
#### 1. 加载第0步已经做好的数据 （HSR:50km, Airport:150km）
G_AirGrids = lib_graph.createG_fromFile('graph_GridAir.csv',
source='source',
target='target',
attr='')
G_HSRGrids = lib_graph.createG_fromFile('graph_GridHSR.csv',
source='source',
target='target',
attr='')
#### 1.1 加载机场、车站位置数据
dict_AirportLocs = lib_file.pickle_load('dict_AirportLocs.pkl')
dict_HSRLocs = lib_file.pickle_load('dict_HSRLocs.pkl')
#### 2 由时刻表建图，获取联通关系 ## 属性上有车次
##### 2.1 飞机时刻表建图
air_timetable = FlightTimetable()
air_timetable.load_file('E:/Code/Data/ChinaAir/China_Air_Schedule_clean.csv')
G_airTimetable = air_timetable.get_graph()
##### 2.2 高铁时刻表 ### 建图，属性上有车次
timetable = Timetable()
timetable.load_file(
'E:/Code/Data/ChinaRailway/China_Railway_Schedule_20190701.csv')
G_HSRTimetable = timetable.get_graph()
dict_AirportLocs = lib_graph.getLocation_fromFile(
OS + 'Code/Data/Sebastian_ScheduleDataChina20191114/airports.csv',
ID='ID',
lon='lon',
lat='lat')
dict_PortLocs = copy.deepcopy(dict_HSRLocs)
for k in dict_AirportLocs:
dict_PortLocs[k] = dict_AirportLocs[k]
## 异站换乘driving time
G_PortPort = lib_graph.createG_fromFile(
OS + 'Code/Data/Sebastian_ScheduleDataChina20191114/drivingTime.csv',
source='source',
target='target',
attr=['contype', 'distance_km', 'duration_s'])
## 车站到网格的驾车时间
G_PortGrid = lib_file.pickle_load('G_PortGrid.pkl')
###############################################
### 时刻表建图
timetable = TimetableNew()
timetable.load_trainFile(
OS + 'Code/Data/Sebastian_ScheduleDataChina20191114/trains.txt')
timetable.load_flightFile(
OS + 'Code/Data/Sebastian_ScheduleDataChina20191114/flights.csv')
G_schedule = timetable.get_DiGraph(mode='all')
for name in G_schedule: ## 为图节点添加属性
G_schedule.node[name][
'type'] = 'airport' if name in dict_AirportLocs else 'station'
""" 5.城市中心坐标数据
"""
ffff = OS + 'Code/Data/ChinaRailway/China_cities_population.csv'
df_pops = pd.read_csv(ffff)