Python可视化与basemap数据地图

最近在梳理Python中可以制作数据地图的可视化工具包，分别实践了geopandas、folium、Basemp,通过对比发现，静态地图中最为成熟的最终还得是Basemap工具，它是mpl_toolkits包中的一个专门用于构建地理信息数据可视化的扩展库。
Basemap工具在地理信息读写、坐标映射、空间坐标转化与投影等方面做的要比geopandas更加成熟，它可以使用常规的地图素材数据源（shp）作为底图进行叠加绘图，效果与精度控制比较方便，图表质量堪比R语言中的ggplot2绘图包（geom_polygon），唯一不足的是它是一个底层构建工具，所有的多边形映射都需要手动构造循环（目前还没有发现比较好用的基于basemap的扩展工具），作图效率与速度上自然无法媲美R语言的ggplot2(缺少一套健全的顶层语法支撑)。
接下来会用3~5篇的篇幅分享给大家基于basemap包的应用场景，包含散点图（气泡图）、折现图（路径图等线图类型）以及最常用的热力填充地图。
本小节介绍填充地图与散点图应用，案例是使用itchat接口抓取的本人微信好友信息。


import itchat
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib
from matplotlib.patches import Polygon
from mpl_toolkits.basemap import Basemap
from matplotlib.collections import PatchCollection
1、微信网页版登录：
itchat.login()
#使用手机微信扫一扫扫描弹出二维码即可登录。
#Getting uuid of QR code.
#Downloading QR code.
#Please scan the QR code to log in.
#Please press confirm on your phone.
#Loading the contact, this may take a little while.
#Login successfully as 杜雨
#提取微信好友信息：
friends = itchat.get_friends(update=True)
df_friends = pd.DataFrame(friends)
df_friends.to_csv("wechat_friends.csv",encoding = "utf_8_sig")
#friends = pd.read_csv("D:/Python/File/wechat_friends.csv")
mydata = friends.loc[:,["NickName","Province","Signature"]]
2、聚合计算好友地区分布：
aggResult = mydata.groupby(['Province'])['NickName'].agg({'人数': np.size}).reset_index()
aggResult.sort_values(by = ['人数'],ascending = False,inplace=True)
#拆分国内城市与国外城市：

def match_str(item):
    result = []
 for i in item:
 try: 
            m = re.search("^[\u4e00-\u9fa5]{1,}",i).group()
            result.append(m)
 except:
 continue
 return(result)

Domestic = match_str(aggResult["Province"].tolist())
Domestic = aggResult.loc[aggResult.Province.isin(Domestic),:]
Foreign  = aggResult.loc[aggResult.Province.isin([i for i in aggResult.Province.tolist() if i not in Domestic.Province.tolist()]),:]
Domestic['scala'] = (Domestic.人数-Domestic.人数.min())/(Domestic.人数.max()-Domestic.人数.min())
清洗与矫正省份（地区）名称
def correct(name_list):
    name = []
    for i in name_list:
        if i in ["内蒙古","西藏"]:
            i += "自治区"
        elif i == "宁夏":
            i += "回族自治区"
        elif i == "新疆":
            i += "维吾尔族自治区"
        elif i == "广西":
            i += "壮族自治区"
        elif i in ["香港","澳门","台湾"]:
            i += "特别行政区"
        elif i in ["北京","天津","重庆","上海"]:
            i += "市"
        else:
            i += "省"name.append(i)
 return(name)
Domestic["Province"] = correct(Domestic["Province"])
3、合并本地经纬度数据： #散点图数据源：
point_data = pd.read_csv("D:/R/rstudy/Province/chinaprovincecity.csv",encoding = "gbk") 
Domestic = Domestic.merge(point_data.loc[:,["province","jd","wd"]],how = "left",left_on = "Province",right_on = "province")

实例化地图对象，并导入本地shp中国地图
basemap = Basemap(llcrnrlon= 75,llcrnrlat=10,urcrnrlon=150,urcrnrlat=55,projection='poly',lon_0 = 116.65,lat_0 = 40.02,ax = ax)
basemap.readshapefile(shapefile = "D:/R/rstudy/CHN_adm/bou2_4p",name = "china")
导入的shp格式地图中很多行政区划信息乱码，需要纠正编码
mapData = pd.DataFrame(basemap.china_info)
mapData["NAME"] = mapData["NAME"].map(lambda x: x.decode("gbk") if len(x) != 0 else x)
#mapData["NAME"] = [i.decode("gbk") if len(i) !=0 else i for i in mapData["NAME"].tolist()]
mapData = mapData.merge(Domestic,how = "left",left_on='NAME', right_on="Province")

4、数据可视化
font = {'family' : 'SimHei'};
matplotlib.rc('font', **font);
fig = plt.figure(figsize=(16,12))
ax  = fig.add_subplot(111)

###构建省份填充函数（按照各省好友人数比例）：
def plotProvince(row):
    mainColor = (42/256, 87/256, 141/256,row['scala']);
    patches = []
 for info,shape in zip(mapData["NAME"].tolist(),basemap.china): 
 if info == row['Province']:
            patches.append(Polygon(xy = np.array(shape), closed=True))
    ax.add_collection(PatchCollection(patches,facecolor=mainColor,edgecolor=mainColor,linewidths=1.,zorder=2))
Domestic.apply(lambda row: plotProvince(row), axis=1)
 #构建散点图(基于各省好友数量)

def create_great_points(df):
    lon   = np.array(df["jd"])
    lat   = np.array(df["wd"])
    pop   = np.array(df["scala"],dtype=float)
    x,y = basemap(lon,lat)
 for lon,lat,pop in zip(x,y,pop*50):
        basemap.scatter(lon,lat,color = "#c72e29",marker = "o",s = pop*25)
create_great_points(Domestic)

plt.axis("off")  #关闭坐标轴
plt.savefig("D:/Python/Image/杜雨/itwechat.png") #保存图表到本地
plt.show()    #显示图表