ARIMA Stability Test

COVID-19/Prediction/Prediction/ARIMA.py

@@ -8,7 +8,7 @@ import statsmodels.api as sm
 from sklearn.metrics import mean_squared_error
 
 #打开数据文件
-dataset = pd.read_csv('E:\dase intro\COVID-19Analysis\COVID-19\covid-19-all.csv')
+dataset = pd.read_csv('E:\DaseIntro\COVID-19Analysis\COVID-19\covid-19-all.csv')
 
 #数据预处理
 def parse_ymd(s):
@@ -24,6 +24,9 @@ CN.index = pd.Index(pd.date_range('2020-01-22','2020-12-09',freq = '1D'))
 US = dataset[dataset['Country/Region'] == 'US']
 US.index = pd.Index(pd.date_range('2020-01-22','2020-12-09',freq = '1D'))  
 
+print(CN)
+print(US)
+
 #划分训练集、测试集
 trainCN = CN[CN['Date'] < '2020-11-01 ']  
 testCN = CN[CN['Date'] >= '2020-11-01']

COVID-19/Prediction/Prediction/ARIMA.pyproj

@@ -24,6 +24,9 @@
   </PropertyGroup>
   <ItemGroup>
     <Compile Include="ARIMA.py" />
+    <Compile Include="StabilityTest.py">
+      <SubType>Code</SubType>
+    </Compile>
   </ItemGroup>
   <Import Project="$(MSBuildExtensionsPath32)\Microsoft\VisualStudio\v$(VisualStudioVersion)\Python Tools\Microsoft.PythonTools.targets" />
   <!-- Uncomment the CoreCompile target to enable the Build command in

COVID-19/Prediction/Prediction/Holt_Winters.py

@@ -8,7 +8,7 @@ from statsmodels.tsa.api import ExponentialSmoothing
 from sklearn.metrics import mean_squared_error
 
 #打开数据文件
-dataset = pd.read_csv('E:\dase intro\COVID-19Analysis\COVID-19\covid-19-all.csv')
+dataset = pd.read_csv('E:\DaseIntro\COVID-19Analysis\COVID-19\covid-19-all.csv')
 
 #数据预处理
 def parse_ymd(s):

COVID-19/Prediction/Prediction/StabilityTest.py

@@ -0,0 +1,38 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import statsmodels.api as sm
+from statsmodels.graphics.tsaplots import acf,pacf,plot_acf,plot_pacf
+from statsmodels.tsa.arima_model import ARMA
+from statsmodels.tsa.stattools import adfuller
+
+#打开数据文件
+dataset = pd.read_csv('E:\DaseIntro\COVID-19Analysis\COVID-19\covid-19-all.csv')
+
+#数据预处理
+def parse_ymd(s):
+	year_s, mon_s, day_s = s.split('-')
+	return datetime.datetime(int(year_s), int(mon_s), int(day_s)).strftime("%Y-%m-%d")
+dataset = dataset.fillna(0)
+dataset['Date'] = pd.to_datetime(dataset['Date'])
+dataset = dataset[['Country/Region','Confirmed','Recovered','Deaths','Date']].groupby(['Country/Region','Date']).sum().reset_index()
+
+#取出中、美的数据
+CN = dataset[dataset['Country/Region'] == 'China']
+CN.index = pd.Index(pd.date_range('2020-01-22','2020-12-09',freq = '1D'))  
+US = dataset[dataset['Country/Region'] == 'US']
+US.index = pd.Index(pd.date_range('2020-01-22','2020-12-09',freq = '1D'))
+
+#检验Confirmed
+CNconfirmedSeries = pd.DataFrame(CN['Confirmed'])
+CNconfirmedSeries['Confirmed'] = CNconfirmedSeries['Confirmed'] - CNconfirmedSeries['Confirmed'].shift(1)
+CNconfirmedSeries.plot(figsize=(8,6))
+
+CNrecoveredSeries = pd.DataFrame(CN['Recovered'])
+CNrecoveredSeries['Recovered'] = CNrecoveredSeries['Recovered'] - CNrecoveredSeries['Recovered'].shift(1)
+CNrecoveredSeries.plot(figsize=(8,6))
+
+CNdeathsSeries = pd.DataFrame(CN['Deaths'])
+CNdeathsSeries['Deaths'] = CNdeathsSeries['Deaths'] - CNdeathsSeries['Deaths'].shift(1)
+CNdeathsSeries.plot(figsize=(8,6))
+plt.show()