1
2
3
4
5
6
7
8

#导入需要的数据库和文件
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.pyplot import MultipleLocator
areas=pd.read_csv(r'data/AreaInfo.csv')
plt.rcParams['font.sans-serif'] = ['SimHei'] 
plt.rcParams['axes.unicode_minus'] = False 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

r_hex = '#dc2624'     # red,       RGB = 220,38,36
dt_hex = '#2b4750'    # dark teal, RGB = 43,71,80
tl_hex = '#45a0a2'    # teal,      RGB = 69,160,162
r1_hex = '#e87a59'    # red,       RGB = 232,122,89
tl1_hex = '#7dcaa9'   # teal,      RGB = 125,202,169
g_hex = '#649E7D'     # green,     RGB = 100,158,125
o_hex = '#dc8018'     # orange,    RGB = 220,128,24
tn_hex = '#C89F91'    # tan,       RGB = 200,159,145
g50_hex = '#6c6d6c'   # grey-50,   RGB = 108,109,108
bg_hex = '#4f6268'    # blue grey, RGB = 79,98,104
g25_hex = '#c7cccf'   # grey-25,   RGB = 199,204,207

1
2

#数据过多，查看前几行
areas.head()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

# 此处给出代码，后面省市数据和全球数据的获取与此大同小异
china = areas.loc[areas.countryName=='中国',:].copy()
china['updateTime'] = pd.to_datetime(china.updateTime,format="%Y-%m-%d",errors='coerce').dt.date
china = china.drop_duplicates(subset=['provinceName', 'updateTime'], keep='first', inplace=False)

# 将"字符类型的日期列(Index)"转为"时间戳索引(DatetimeIndex)"
china['updateTime'] = pd.to_datetime(china['updateTime'])
china.set_index('updateTime',inplace=True)
china = china[['continentName','countryName','provinceName','province_confirmedCount','province_suspectedCount','province_curedCount','province_deadCount']]
china = china[china.provinceName=='中国']
china.head(2)

1

china.index

1
2
3
4

#有些城市不是每天上报，如果只统计那天上报的，那些不上报的就会被忽略，数据就会有错误,查看缺失值
#china.info()
china.province_suspectedCount[china.province_suspectedCount.isnull()] = china.province_suspectedCount.dropna().mode().values
china.head()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

#首先选取相应内容，后转换为日期类型并提取出年-月-日，去重
myhome=areas.loc[areas.provinceName=='河北省',:].copy()
myhome['updateTime'] = pd.to_datetime(myhome.updateTime,format="%Y-%m-%d",errors='coerce').dt.date
myhome.drop_duplicates(subset=['provinceName', 'updateTime'], keep='first', inplace=True)
# 将"字符类型的日期列(Index)"转为"时间戳索引(DatetimeIndex)"
myhome['updateTime']=pd.to_datetime(myhome['updateTime'])
myhome.set_index('updateTime',inplace=True)
#去除不在此次研究范围内的列
myhome.drop(['continentName','continentEnglishName','countryName','countryEnglishName','provinceEnglishName','province_zipCode','cityEnglishName','city_zipCode'],axis=1,inplace=True)
myhome.head(2)

1
2
3
4

#查看缺失值
#myhome.info()
myhome.province_suspectedCount[myhome.province_suspectedCount.isnull()] = myhome.province_suspectedCount.dropna().mode().values
myhome.tail()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14

world=areas.loc[areas.countryName!='中国',:].copy()
world['updateTime'] = pd.to_datetime(world.updateTime,format="%Y-%m-%d",errors='coerce').dt.date
world.drop_duplicates(subset=['provinceName', 'updateTime'], keep='first', inplace=False)
# 将"字符类型的日期列(Index)"转为"时间戳索引(DatetimeIndex)"
world['updateTime']=pd.to_datetime(world['updateTime'])
world.set_index('updateTime',inplace=True)
#去除不在此次研究范围内的列
#world.drop(['continentName','countryName','provinceName','province_confirmedCount','province_suspectedCount','province_curedCount','province_deadCount'],axis=1,inplace=True)
#更改索引，按轴1链接

world = world.reset_index()
temp = china.copy()
temp = temp.reset_index()
pd.concat([world,temp], axis=1)

1
2
3

#因数据皆赖各国上报，情势危杂之际，难免瞒报漏报，故存在较多缺失值
#world.info()
world.head()

1

china.index

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

#首先整合每天全国累计确诊/治愈/死亡情况做成新的列表
list_a=china['province_confirmedCount']
#遍历时间将其改为字符串形式
list_updatetime=[]
for i in china.index:
    list_updatetime.append(str(i)[0:11])
updatetime_a=pd.DataFrame(list_a,index=list_updatetime)
updatetime_a.index.name='updatetime'
updatetime_a.columns=['province_confirmedCount']
updatetime_a.head()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52

#画折线图表示
fig, axes = plt.subplots(1,1,figsize=(16, 4))
x=updatetime_a.index
y=updatetime_a.values
plot=axes.plot(x,y,color=dt_hex,linewidth=2,linestyle='-',label='province_confirmedCount')
axes.set_xticks(range(0,len(x),25))
plt.xlabel('日期',fontsize=10)
plt.ylabel('人数',fontsize=10)
axes.legend(loc=0,frameon=True)
plt.show()
#重复以上步骤，绘制治愈/死亡的折线图
list_b=china['province_curedCount']
#遍历时间将其改为字符串形式
list_updatetime=[]
for i in china.index:
    list_updatetime.append(str(i)[0:11])
updatetime_b=pd.DataFrame(list_b,index=list_updatetime)
updatetime_b.index.name='updatetime'
updatetime_b.columns=['province_curedCount']
updatetime_b.head()
#画折线图表示
fig, axes = plt.subplots(1,1,figsize=(16, 4))
x=updatetime_b.index
y=updatetime_b.values
plot=axes.plot(x,y,color=dt_hex,linewidth=2,linestyle='-',label='province_curedCount')
axes.set_xticks(range(0,len(x),25))
plt.xlabel('日期',fontsize=10)
plt.ylabel('人数',fontsize=10)
axes.legend(loc=0,frameon=True)
plt.show()
#绘制死亡人数图
list_c=china['province_deadCount']
#遍历时间将其改为字符串形式
list_updatetime=[]
for i in china.index:
    list_updatetime.append(str(i)[0:11])
updatetime_c=pd.DataFrame(list_a,index=list_updatetime)
updatetime_c.index.name='updatetime'
updatetime_c.columns=['province_deadCount']
updatetime_c.head()
#画折线图表示
fig, axes = plt.subplots(1,1,figsize=(16, 4))
x=updatetime_c.index
y=updatetime_c.values
plot=axes.plot(x,y,color=dt_hex,linewidth=2,linestyle='-',label='province_deadCount')
axes.set_xticks(range(0,len(x),25))
plt.xlabel('日期',fontsize=10)
plt.ylabel('人数',fontsize=10)
axes.legend(loc=0,frameon=True)
plt.show()
#分析：确诊与死亡人数的折线图显示出人数在逐渐增加，增速有加快的趋势；治愈人数虽然也是再增加，但是增速逐渐变慢

1

myhome

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16

plt.figure( figsize=(20,10), dpi=80)
list_updatetime=[]
for i in myhome.index:
    list_updatetime.append(str(i)[0:11])
x = list_updatetime
y1=myhome['province_confirmedCount']
y2=myhome['province_curedCount']
y3=myhome['province_deadCount']
plt.plot(x,y1,color=r_hex,label='province_confirmedCount')
plt.plot(x,y2,color=tl_hex,label='province_curedCount')
plt.plot(x,y3,color=g_hex,label='province_deadCount')
x_major_locator = MultipleLocator(12)
ax = plt.gca()
ax.xaxis.set_major_locator(x_major_locator)
plt.legend(loc=0,frameon=True)
plt.show()

1

world

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

country = list(set(world['provinceEnglishName']))
date_y = []
for dt in world.loc[world['provinceEnglishName'] ==  country[0]]['updateTime']:
    date_y.append(str(dt))
date_y.sort()
for c in country:
    world.loc[world['provinceEnglishName'] == c].sort_values(by = 'updateTime')
world.dropna(subset=['provinceEnglishName'],inplace=True)
world.updateTime = pd.to_datetime(world.updateTime,format="%Y-%m-%d",errors='coerce').dt.date
world_confirmed = world.loc[world['provinceEnglishName'] == world.head(15)['provinceEnglishName'][0]].pivot_table(index='updateTime', columns='provinceEnglishName', values='province_confirmedCount',aggfunc=np.mean)
for i in world.head(15)['provinceEnglishName'][1:]:
    draft_c = world.loc[world['provinceEnglishName'] == i].pivot_table(index='updateTime', columns='provinceEnglishName', values='province_confirmedCount',aggfunc=np.mean)
    world_confirmed = pd.merge(world_confirmed,draft_c,on='updateTime', how='outer',sort=True)
world_confirmed.fillna(0,inplace=True,limit = 1)
world_confirmed.fillna(method="ffill",inplace=True)
world_confirmed
fig = plt.figure(figsize=(16,10))
plt.plot(world_confirmed)
plt.legend(world_confirmed.columns)
plt.title('前15个国家累计确诊人数',fontsize=20)
plt.xlabel('日期',fontsize=20)
plt.ylabel('人数/百万',fontsize=20);
plt.show()