地图可视化 DIY

import time
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
import pickle
img = plt.imread("chinamap1.jpg")
rows, columns, chanels = img.shape
flattened = img.reshape((-1, 3))
k = 7 #分为7类 (省份5中颜色+字体+背景)
k_means = KMeans(init='k-means++', n_clusters=k,max_iter=300, n_init=10)
t0 = time.time()
k_means.fit(flattened)
t_batch = time.time() - t0
groups = []
for i in range(k):
    output = np.zeros((rows*columns))
    output[np.where(np.equal(k_means.labels_, i))[0]] = 1
    output = output.reshape((rows, columns))
    groups.append(output)

with open('text.txt', 'wb') as file:
    pickle.dump(groups, file)

# -*- coding: utf-8 -*-
"""
Created on Sat Dec 15 10:15:18 2019
@author: wangsp
"""
import numpy as np
from matplotlib import pyplot as plt
import pickle

with open('text.txt', 'rb') as file:
    groups = pickle.load(file)
print(len(groups))
img=groups[1]
#plt.imshow(img)
#plt.show()
def connectedDomain(img):
    h,w = img.shape
    # 4-connected domain
    domain =dict()
    label = -1 # 用于标记连通域ID
    #i==0 # 第一行
    flag = True #上一个像素是否为0？
    for j in range(w):
        if img[0,j]==1:
            if flag: #上一个元素是0则新建连通域
                label += 1
                domain[label] = set()
            domain[label].add((0,j))
            flag = False
        else:
            flag = True
    for i in range(1,h):#第1行外的其它行
        flag = True
        for j in range(w):
            if img[i,j] == 1:
                for key in domain:
                    if (i-1,j) in domain[key]:#上一行对应元素是否属于某个连通域？
                        domain[key].add((i,j))
                        
                        if not flag:#左边的元素为1
                            if last_label != key:
                                domain[key]=domain[key].union(domain[last_label]) #合并
                                del domain[last_label]
                                
                        last_label = key    
                        break
                else:#不属于上行已有的连通域
                    if flag:
                        label += 1
                        domain[label] = set()
                        domain[label].add((i,j))
                        last_label = label
                    else:
                        domain[last_label].add((i,j))
                
                flag = False
            else:
                flag = True
    return domain
domain = connectedDomain(img)
print()
print(sum(img))
print(sum([ len(value) for key, value in domain.items()]))# 元素1的个数
print()
#按面积排序
descended = sorted(domain.items(),key = lambda x: len(x[1]),reverse=True)
i =1
for item in descended[:8]: #最大的3块
    z = np.zeros((img.shape))
    for x,y in item[1]:
        z[x,y] =1
    plt.subplot(2,4,i)
    plt.imshow(z)
    i += 1
plt.show()
[西藏,黑龙江,甘肃,河南,重庆,海南,中国台湾,北京] = [descended[i][1] for i in range(8)]
strings = "西藏","黑龙江","甘肃","河南","重庆","海南","中国台湾","北京"
for string,obj in zip(strings,[西藏,黑龙江,甘肃,河南,重庆,海南,中国台湾,北京]):
    with open('%s.db'%string, 'wb') as file:
        pickle.dump(obj, file)

"""
Created on Mon Dec 16 22:49:10 2019
@author: Administrator
"""
import os
import pickle
path = r"E:\Python36\MyPythonFiles\MyPyQt5\中国地图\provinces"
dic = dict()
regions =[]
for x in os.listdir(path):
    p = os.path.splitext(x)[0]
    regions.append(p)
    fullpath = os.path.join(path,x)
    with open(fullpath, 'rb') as file:
        dic[p] = pickle.load(file)

regions.remove("背景")
print(regions)

from random import random
data = dict()
for region in regions:
    data[region]= random() #随机生成数据
    #注：这里可以加载各省市 口，收入中位数等真实数据
    
#data["背景"]=1
def x2RGB(x,LSL=0, USL=1.0):
    r=(x-LSL)/(USL-LSL)
    if r>1:
        return (255, 255, 255)
    elif r>=0.75:
        return (255, int(255*(1-r)*4), 0)
    elif r>=0.5:
        return (int(255*(r-0.5)*4), 255, 0)
    elif r>=0.25:
        return (0, 255, int(255*(0.5-r)*4))
    elif r>=0:
        return (0, int(255*r*4), 255)
    else:
        return (0,0,0)
from matplotlib import pyplot as plt
import numpy as np
img0 = plt.imread("chinamap1.jpg")
rows, columns, chanels = img0.shape

img = np.zeros((rows,columns,3),dtype =np.uint8)
for region in regions:
    rgb = x2RGB(data[region])
    for x,y in dic[region]:
        img[x,y] = rgb
bg_rgb =(255,255,255)
for x,y in dic["背景"]:
    img[x,y] = bg_rgb

#bg = np.ones((rows,columns,3))*255
#plt.imshow(bg,zorder=0)
im = plt.imshow(img,zorder=1)
#plt.colorbar(im)
plt.show()