Homework1复盘

加载包

library(tidyverse)
library(DT)
library(forecast)
library(lubridate)
library(timeSeries)

改变文件名称

file.rename(from ="D:/Rworkspace/datasets/illinois-history.csv",to="D:/Rworkspace/datasets/ILCovid19.csv" )

## [1] TRUE

加载数据

data <- readr::read_csv("D:/Rworkspace/datasets/ILCovid19.csv")

## Parsed with column specification:
## cols(
##   .default = col_double(),
##   state = col_character(),
##   dataQualityGrade = col_character(),
##   hospitalized = col_logical(),
##   hospitalizedCumulative = col_logical(),
##   inIcuCumulative = col_logical(),
##   negativeTestsAntibody = col_logical(),
##   negativeTestsPeopleAntibody = col_logical(),
##   negativeTestsViral = col_logical(),
##   onVentilatorCumulative = col_logical(),
##   positiveTestsAntibody = col_logical(),
##   positiveTestsAntigen = col_logical(),
##   positiveTestsPeopleAntibody = col_logical(),
##   positiveTestsPeopleAntigen = col_logical(),
##   positiveTestsViral = col_logical(),
##   recovered = col_logical(),
##   totalTestEncountersViral = col_logical(),
##   totalTestsAntibody = col_logical(),
##   totalTestsAntigen = col_logical(),
##   totalTestsPeopleAntibody = col_logical(),
##   totalTestsPeopleAntigen = col_logical()
## )

## See spec(...) for full column specifications.

head(data)

colnames(data)

##  [1] "date"                             "state"                           
##  [3] "dataQualityGrade"                 "death"                           
##  [5] "deathConfirmed"                   "deathIncrease"                   
##  [7] "deathProbable"                    "hospitalized"                    
##  [9] "hospitalizedCumulative"           "hospitalizedCurrently"           
## [11] "hospitalizedIncrease"             "inIcuCumulative"                 
## [13] "inIcuCurrently"                   "negative"                        
## [15] "negativeIncrease"                 "negativeTestsAntibody"           
## [17] "negativeTestsPeopleAntibody"      "negativeTestsViral"              
## [19] "onVentilatorCumulative"           "onVentilatorCurrently"           
## [21] "pending"                          "positive"                        
## [23] "positiveCasesViral"               "positiveIncrease"                
## [25] "positiveScore"                    "positiveTestsAntibody"           
## [27] "positiveTestsAntigen"             "positiveTestsPeopleAntibody"     
## [29] "positiveTestsPeopleAntigen"       "positiveTestsViral"              
## [31] "recovered"                        "totalTestEncountersViral"        
## [33] "totalTestEncountersViralIncrease" "totalTestResults"                
## [35] "totalTestResultsIncrease"         "totalTestsAntibody"              
## [37] "totalTestsAntigen"                "totalTestsPeopleAntibody"        
## [39] "totalTestsPeopleAntigen"          "totalTestsPeopleViral"           
## [41] "totalTestsPeopleViralIncrease"    "totalTestsViral"                 
## [43] "totalTestsViralIncrease"

排序

arrange_data <- data %>% arrange(date)
arrange_data %>% datatable()

选择需要的列并重命名

select_data <- arrange_data %>% select(Date=date,Total_Cases=positiveCasesViral,Total_Deaths=death,
                                  Total_Tests=totalTestsViral,Current_Hospitalizations=hospitalizedCurrently,
                                  Current_ICU_Usage=inIcuCurrently,New_case=positiveIncrease)
select_data %>% datatable()

生成需要的列

ILCovid19 <- select_data %>% mutate(
  Percentage_Positive=ma(Total_Cases/Total_Tests,7),
  Percentage_of_Current_Hospitalizations=ma(Current_Hospitalizations/New_case,7),
  Percentage_of_Current_Hospitalizations_in_ICU=ma(Current_ICU_Usage/Current_Hospitalizations,7)
)
ILCovid19 %>% datatable()

画图

将numeric的时间列转化成date

本想用as.Date转化，但是失败了，只好重新生成一列，这种方法仅适用于没有缺失时间的情况。

ILCovid19$Date <-  seq.Date(from = as.Date("2020/03/04",format = "%Y/%m/%d"), by = "day", length.out = 194)
tail(ILCovid19$Date)

## [1] "2020-09-08" "2020-09-09" "2020-09-10" "2020-09-11" "2020-09-12"
## [6] "2020-09-13"

str(ILCovid19$Date)

##  Date[1:194], format: "2020-03-04" "2020-03-05" "2020-03-06" "2020-03-07" "2020-03-08" ...

picture1

找到最大值，规定y的上限

max(ILCovid19$Percentage_Positive,na.rm = T)

## [1] 0.1397892

ggplot(data = ILCovid19)+
  geom_line(aes(x=Date,y=Percentage_Positive),color="steelblue")+
  geom_hline(aes(yintercept=0.8*max(ILCovid19$Percentage_Positive,na.rm = T)),color="orange")+
  scale_y_continuous(breaks = seq(0,0.160,0.01))+
  scale_x_date(date_breaks = "1 week",limits = c(ymd(20200304),ymd(20200913)))+
  labs(title = "Percentage Positive",y="Percentage")+
  theme(plot.title = element_text(size=20,face ="bold",hjust = 0.5),
        axis.text.x = element_text(angle = 90,vjust = 0.5))

## Warning: Removed 88 row(s) containing missing values (geom_path).

picture2 截取一段时间画图

通过选择行来截取时间

ILCovid19 %>% slice(144:175) ->J25_A25
J25_A25 %>% datatable()

max(J25_A25$Percentage_Positive)

## [1] 0.06886443

ggplot(data = J25_A25)+
  geom_line(aes(x=Date,y=Percentage_Positive),color="steelblue")+
  scale_y_continuous(breaks = seq(0,0.089,0.005))+
  scale_x_date(date_breaks = "1 week")+
  labs(title = "July25-August25 Percentage Positive",y="Percentage")+
  theme(plot.title = element_text(size=20,face ="bold",hjust = 0.5))

picture3

max(ILCovid19$Percentage_of_Current_Hospitalizations,na.rm = T)

## [1] 3.343727

ggplot(data = ILCovid19)+
  geom_line(aes(x=Date,y=Percentage_of_Current_Hospitalizations),color="steelblue")+
  scale_y_continuous(breaks = seq(0,3.364,0.2))+
  scale_x_date(date_breaks = "1 week")+
  labs(title = "Percentage of Current Hospitalizations",y="Percentage")+
  theme(plot.title = element_text(size=20,face ="bold",hjust = 0.5),
        axis.text.x = element_text(angle = 90,vjust = 0.5))

## Warning: Removed 40 row(s) containing missing values (geom_path).

picture4

max(J25_A25$Percentage_of_Current_Hospitalizations ,na.rm = T)

## [1] 1.035251

ggplot(data = J25_A25)+
  geom_line(aes(x=Date,y=Percentage_of_Current_Hospitalizations),color="steelblue")+
  scale_y_continuous(breaks = seq(0,1.055,0.02))+
  scale_x_date(date_breaks = "1 week")+
  labs(title = "July25-August25 Percentage Positive",y="Percentage")+
  theme(plot.title = element_text(size=20,face ="bold",hjust = 0.5))

picture5

max(ILCovid19$Percentage_of_Current_Hospitalizations_in_ICU,na.rm = T)

## [1] 0.3168478

ggplot(data = ILCovid19)+
  geom_line(aes(x=Date,y=Percentage_of_Current_Hospitalizations_in_ICU),color="steelblue")+
  scale_y_continuous(breaks = seq(0,0.337,0.01))+
  scale_x_date(date_breaks = "1 week")+
  labs(title = "Percentage of Current Hospitalizations in ICU",y="Percentage")+
  theme(plot.title = element_text(size=20,face ="bold",hjust = 0.5),
        axis.text.x = element_text(angle = 90,vjust = 0.5))

## Warning: Removed 40 row(s) containing missing values (geom_path).

picture6

max(J25_A25$Percentage_of_Current_Hospitalizations_in_ICU,na.rm = T)

## [1] 0.2448978

ggplot(data = J25_A25 )+
  geom_line(aes(x=Date,y=Percentage_of_Current_Hospitalizations_in_ICU),color="steelblue")+
  scale_y_continuous(breaks = seq(0,0.265,0.01))+
  scale_x_date(date_breaks = "1 week")+
  labs(title = "Percentage of Current Hospitalizations in ICU",y="Percentage")+
  theme(plot.title = element_text(size=20,face ="bold",hjust = 0.5))