您好,登錄后才能下訂單哦!
這篇文章主要介紹Python抓新型冠狀病毒肺炎疫情數據并繪制全國疫情分布的案例分析,文中介紹的非常詳細,具有一定的參考價值,感興趣的小伙伴們一定要看完!
運行結果(2020-2-4日數據)
數據來源
news.qq.com/zt2020/page/feiyan.htm
抓包分析
日報數據格式
"chinaDayList": [{ "date": "01.13", "confirm": "41", "suspect": "0", "dead": "1", "heal": "0" }, { "date": "01.14", "confirm": "41", "suspect": "0", "dead": "1", "heal": "0" }, { "date": "01.15", "confirm": "41", "suspect": "0", "dead": "2", "heal": "5" }, { 。。。。。。
全國各地疫情數據格式
"lastUpdateTime": "2020-02-04 12:43:19", "areaTree": [{ "name": "中國", "children": [{ "name": "湖北", "children": [{ "name": "武漢", "total": { "confirm": 6384, "suspect": 0, "dead": 313, "heal": 303 }, "today": { "confirm": 1242, "suspect": 0, "dead": 48, "heal": 79 } }, { "name": "黃岡", "total": { "confirm": 1422, "suspect": 0, "dead": 19, "heal": 36 }, "today": { "confirm": 176, "suspect": 0, "dead": 2, "heal": 9 } }, { 。。。。。。
地圖數據
github.com/dongli/china-shapefiles
代碼實現
#%% import time, json, requests from datetime import datetime import matplotlib import matplotlib.pyplot as plt import matplotlib.dates as mdates from matplotlib.font_manager import FontProperties from mpl_toolkits.basemap import Basemap from matplotlib.patches import Polygon import numpy as np import jsonpath plt.rcParams['font.sans-serif'] = ['SimHei'] # 用來正常顯示中文標簽 plt.rcParams['axes.unicode_minus'] = False # 用來正常顯示負號 #%% # 全國疫情地區分布(省級確診病例) def catch_cn_disease_dis(): timestamp = '%d'%int(time.time()*1000) url_area = ('https://view.inews.qq.com/g2/getOnsInfo?name=disease_h6' '&callback=&_=') + timestamp world_data = json.loads(requests.get(url=url_area).json()['data']) china_data = jsonpath.jsonpath(world_data, expr='$.areaTree[0].children[*]') list_province = jsonpath.jsonpath(china_data, expr='$[*].name') list_province_confirm = jsonpath.jsonpath(china_data, expr='$[*].total.confirm') dic_province_confirm = dict(zip(list_province, list_province_confirm)) return dic_province_confirm area_data = catch_cn_disease_dis() print(area_data) #%% # 抓取全國疫情按日期分布 ''' 數據源: "chinaDayList": [{ "date": "01.13", "confirm": "41", "suspect": "0", "dead": "1", "heal": "0" }, { "date": "01.14", "confirm": "41", "suspect": "0", "dead": "1", "heal": "0" } ''' def catch_cn_daily_dis(): timestamp = '%d'%int(time.time()*1000) url_area = ('https://view.inews.qq.com/g2/getOnsInfo?name=disease_h6' '&callback=&_=') + timestamp world_data = json.loads(requests.get(url=url_area).json()['data']) china_daily_data = jsonpath.jsonpath(world_data, expr='$.chinaDayList[*]') # 其實沒必要單獨用list存儲,json可讀性已經很好了;這里這樣寫僅是為了少該點老版本的代碼 list_dates = list() # 日期 list_confirms = list() # 確診 list_suspects = list() # 疑似 list_deads = list() # 死亡 list_heals = list() # 治愈 for item in china_daily_data: month, day = item['date'].split('.') list_dates.append(datetime.strptime('2020-%s-%s'%(month, day), '%Y-%m-%d')) list_confirms.append(int(item['confirm'])) list_suspects.append(int(item['suspect'])) list_deads.append(int(item['dead'])) list_heals.append(int(item['heal'])) return list_dates, list_confirms, list_suspects, list_deads, list_heals list_date, list_confirm, list_suspect, list_dead, list_heal = catch_cn_daily_dis() print(list_date) #%% # 繪制每日確診和死亡數據 def plot_cn_daily(): # list_date, list_confirm, list_suspect, list_dead, list_heal = catch_cn_daily_dis() plt.figure('novel coronavirus', facecolor='#f4f4f4', figsize=(10, 8)) plt.title('全國新型冠狀病毒疫情曲線', fontsize=20) print('日期元素數:', len(list_date), "\n確診元素數:", len(list_confirm)) plt.plot(list_date, list_confirm, label='確診') plt.plot(list_date, list_suspect, label='疑似') plt.plot(list_date, list_dead, label='死亡') plt.plot(list_date, list_heal, label='治愈') xaxis = plt.gca().xaxis # x軸刻度為1天 xaxis.set_major_locator(matplotlib.dates.DayLocator(bymonthday=None, interval=1, tz=None)) xaxis.set_major_formatter(mdates.DateFormatter('%m月%d日')) plt.gcf().autofmt_xdate() # 優化標注(自動傾斜) plt.grid(linestyle=':') # 顯示網格 plt.xlabel('日期',fontsize=16) plt.ylabel('人數',fontsize=16) plt.legend(loc='best') plot_cn_daily() #%% # 繪制全國省級行政區域確診分布圖 count_iter = 0 def plot_cn_disease_dis(): # area_data = catch_area_distribution() font = FontProperties(fname='res/coure.fon', size=14) # 經緯度范圍 lat_min = 10 # 緯度 lat_max = 60 lon_min = 70 # 經度 lon_max = 140 # 標簽顏色和文本 legend_handles = [ matplotlib.patches.Patch(color='#7FFFAA', alpha=1, linewidth=0), matplotlib.patches.Patch(color='#ffaa85', alpha=1, linewidth=0), matplotlib.patches.Patch(color='#ff7b69', alpha=1, linewidth=0), matplotlib.patches.Patch(color='#bf2121', alpha=1, linewidth=0), matplotlib.patches.Patch(color='#7f1818', alpha=1, linewidth=0), ] legend_labels = ['0人', '1-10人', '11-100人', '101-1000人', '>1000人'] fig = plt.figure(facecolor='#f4f4f4', figsize=(10, 8)) # 新建區域 axes = fig.add_axes((0.1, 0.1, 0.8, 0.8)) # left, bottom, width, height, figure的百分比,從figure 10%的位置開始繪制, 寬高是figure的80% axes.set_title('全國新型冠狀病毒疫情地圖(確診)', fontsize=20) # fontproperties=font 設置失敗 # bbox_to_anchor(num1, num2), num1用于控制legend的左右移動,值越大越向右邊移動,num2用于控制legend的上下移動,值越大,越向上移動。 axes.legend(legend_handles, legend_labels, bbox_to_anchor=(0.5, -0.11), loc='lower center', ncol=5) # prop=font china_map = Basemap(llcrnrlon=lon_min, urcrnrlon=lon_max, llcrnrlat=lat_min, urcrnrlat=lat_max, resolution='l', ax=axes) # labels=[True,False,False,False] 分別代表 [left,right,top,bottom] china_map.drawparallels(np.arange(lat_min,lat_max,10), labels=[1,0,0,0]) # 畫經度線 china_map.drawmeridians(np.arange(lon_min,lon_max,10), labels=[0,0,0,1]) # 畫緯度線 china_map.drawcoastlines(color='black') # 洲際線 china_map.drawcountries(color='red') # 國界線 china_map.drawmapboundary(fill_color = 'aqua') # 畫中國國內省界和九段線 china_map.readshapefile('res/china-shapefiles-master/china', 'province', drawbounds=True) china_map.readshapefile('res/china-shapefiles-master/china_nine_dotted_line', 'section', drawbounds=True) global count_iter count_iter = 0 # 內外循環不能對調,地圖中每個省的數據有多條(繪制每一個shape,可以去查一下第一條“臺灣省”的數據) for info, shape in zip(china_map.province_info, china_map.province): pname = info['OWNER'].strip('\x00') fcname = info['FCNAME'].strip('\x00') if pname != fcname: # 不繪制海島 continue is_reported = False # 西藏沒有疫情,數據源就不取不到其數據 for prov_name in area_data.keys(): count_iter += 1 if prov_name in pname: is_reported = True if area_data[prov_name] == 0: color = '#f0f0f0' elif area_data[prov_name] <= 10: color = '#ffaa85' elif area_data[prov_name] <= 100: color = '#ff7b69' elif area_data[prov_name] <= 1000: color = '#bf2121' else: color = '#7f1818' break if not is_reported: color = '#7FFFAA' poly = Polygon(shape, facecolor=color, edgecolor=color) axes.add_patch(poly) plot_cn_disease_dis() print('迭代次數', count_iter)
python的數據類型:1. 數字類型,包括int(整型)、long(長整型)和float(浮點型)。2.字符串,分別是str類型和unicode類型。3.布爾型,Python布爾類型也是用于邏輯運算,有兩個值:True(真)和False(假)。4.列表,列表是Python中使用最頻繁的數據類型,集合中可以放任何數據類型。5. 元組,元組用”()”標識,內部元素用逗號隔開。6. 字典,字典是一種鍵值對的集合。7. 集合,集合是一個無序的、不重復的數據組合。
以上是“Python抓新型冠狀病毒肺炎疫情數據并繪制全國疫情分布的案例分析”這篇文章的所有內容,感謝各位的閱讀!希望分享的內容對大家有幫助,更多相關知識,歡迎關注億速云行業資訊頻道!
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。