pip install -U transbigdata
1.

import transbigdata as tbd
1.

import pandas as pd
# 读取数据
data = pd.read_csv('TaxiData-Sample.csv',header = None)  
data.columns = ['VehicleNum','time','lon','lat','OpenStatus','Speed']  
data.head()
1.
2.
3.
4.
5.

import geopandas as gpd
# 读取研究范围区域信息
sz = gpd.read_file(r'sz/sz.shp')
sz.plot()
1.
2.
3.
4.

# 数据预处理
#剔除研究范围外的数据，计算原理是在方法中先栅格化后栅格匹配研究范围后实现对应。因此这里需要同时定义栅格大小，越小则精度越高
data = tbd.clean_outofshape(data, sz, col=['lon', 'lat'], accuracy=500)
# 剔除出租车数据中载客状态瞬间变化的数据
data = tbd.clean_taxi_status(data, col=['VehicleNum', 'time', 'OpenStatus'])
1.
2.
3.
4.
5.

# 定义研究范围边界
bounds = [113.75, 22.4,114.62, 22.86]
# 通过边界获取栅格化参数
params = tbd.area_to_params(bounds,accuracy = 1000)
params
1.
2.
3.
4.
5.

{'slon': 113.75,
'slat': 22.4,
'deltalon': 0.00974336289289822,
'deltalat': 0.008993210412845813,
'theta': 0,
'method': 'rect',
'gridsize': 1000}
1.
2.
3.
4.
5.
6.
7.

# 将GPS数据对应至栅格，将生成的栅格编号列赋值到数据表上作为新的两列
data['LONCOL'],data['LATCOL']= tbd.GPS_to_grids(data['lon'],data['lat'],params)
1.
2.

# 聚合集计栅格内数据量
grid_agg=data.groupby(['LONCOL','LATCOL'])['VehicleNum'].count().reset_index()
# 生成栅格的几何图形
grid_agg['geometry']=tbd.grid_to_polygon([grid_agg['LONCOL'],grid_agg['LATCOL']],params)
# 转换为GeoDataFrame
grid_agg=gpd.GeoDataFrame(grid_agg)
# 绘制栅格
grid_agg.plot(column = 'VehicleNum',cmap = 'autumn_r')
1.
2.
3.
4.
5.
6.
7.
8.

import matplotlib.pyplot as plt
fig =plt.figure(1,(8,8),dpi=300)
ax =plt.subplot(111)
plt.sca(ax)
# 添加行政区划边界作为底图
sz.plot(ax=ax,edgecolor=(0,0,0,0),facecolor=(0,0,0,0.1),linewidths=0.5)
# 定义色条位置
cax = plt.axes([0.04, 0.33, 0.02, 0.3])
plt.title('Data count')
plt.sca(ax)
# 绘制数据
grid_agg.plot(column = 'VehicleNum',cmap = 'autumn_r',ax = ax,cax = cax,legend = True)
# 添加指北针和比例尺
tbd.plotscale(ax,bounds = bounds,textsize = 10,compasssize = 1,accuracy = 2000,rect = [0.06,0.03],zorder = 10)
plt.axis('off')
plt.xlim(bounds[0],bounds[2])
plt.ylim(bounds[1],bounds[3])
plt.show()
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.

# 从GPS数据提取OD
oddat=tbd.taxigps_to_od(data,col=['VehicleNum','time','Lng','Lat','OpenStatus'])
oddata
1.
2.
3.

# 重新定义栅格，获取栅格化参数
params=tbd.area_to_params(bounds,accuracy = 2000)
# 栅格化OD并集计
od_gdf=tbd.odagg_grid(oddata,params)
od_gdf.plot(column = 'count')
1.
2.
3.
4.
5.

# 创建图框
import matplotlib.pyplot as plt
fig =plt.figure(1,(8,8),dpi=300)
ax =plt.subplot(111)
plt.sca(ax)
# 添加行政区划边界作为底图
sz.plot(ax=ax,edgecolor=(0,0,0,1),facecolor=(0,0,0,0),linewidths=0.5)
# 绘制colorbar
cax=plt.axes([0.05, 0.33, 0.02, 0.3])
plt.title('Data count')
plt.sca(ax)
# 绘制OD
od_gdf.plot(ax = ax,column = 'count',cmap = 'Blues_r',linewidth = 0.5,vmax = 10,cax = cax,legend = True)
# 添加比例尺和指北针
tbd.plotscale(ax,bounds=bounds,textsize=10,compasssize=1,accuracy=2000,rect = [0.06,0.03],zorder = 10)
plt.axis('off')
plt.xlim(bounds[0],bounds[2])
plt.ylim(bounds[1],bounds[3])
plt.show()
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.

# OD集计到区域
# 方法1：在不传入栅格化参数时，直接用经纬度匹配
od_gdf = tbd.odagg_shape(oddata,sz,round_accuracy=6)
# 方法2：传入栅格化参数时，程序会先栅格化后匹配以加快运算速度，数据量大时建议使用
od_gdf = tbd.odagg_shape(oddata,sz,params = params)
od_gdf.plot(column = 'count')
1.
2.
3.
4.
5.
6.

# 创建图框
import matplotlib.pyplot as plt
import plot_map
fig =plt.figure(1,(8,8),dpi=300)
ax =plt.subplot(111)
plt.sca(ax)
# 添加行政区划边界作为底图
sz.plot(ax = ax,edgecolor = (0,0,0,0),facecolor = (0,0,0,0.2),linewidths=0.5)
# 绘制colorbar
cax = plt.axes([0.05, 0.33, 0.02, 0.3])
plt.title('count')
plt.sca(ax)
# 绘制OD
od_gdf.plot(ax = ax,vmax = 100,column = 'count',cax = cax,cmap = 'autumn_r',linewidth = 1,legend = True)
# 添加比例尺和指北针
tbd.plotscale(ax,bounds = bounds,textsize = 10,compasssize = 1,accuracy = 2000,rect = [0.06,0.03],zorder = 10)
plt.axis('off')
plt.xlim(bounds[0],bounds[2])
plt.ylim(bounds[1],bounds[3])
plt.show()
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.

# 可视化数据点分布
tbd.visualization_data(data,col = ['lon','lat'],accuracy=1000,height = 500)
1.
2.

# 可视化数据点分布
tbd.visualization_od(oddata,accuracy=2000,height = 500)
1.
2.

# 动态可视化轨迹
tbd.visualization_trip(data,col = ['lon','lat','VehicleNum','time'],height = 500)
1.
2.