Week 4 work
yu yang liu
2017年2月27日
Synopsis
knitr::opts_chunk$set(cache = TRUE,echo=T)- load package
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(ggplot2)set the system locale as English
Because my Rstudio was set system locale as Mandarin Chinese, if not change system locale as English,
it’ll have some problem to load data into Rstudio
Sys.setlocale("LC_ALL", "English") ##important ##if `EOF within quoted string` occured## [1] "LC_COLLATE=English_United States.1252;LC_CTYPE=English_United States.1252;LC_MONETARY=English_United States.1252;LC_NUMERIC=C;LC_TIME=English_United States.1252"Load data from Internet
if(!file.exists("repdata_data_StormData.csv")){
url<-"https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
download.file(url,destfile ="repdata_data_StormData.csv.bz2" )
}
storm<-read.csv(bzfile("repdata_data_StormData.csv.bz2"))viewing into data
dim(storm)## [1] 902297 37head(storm)## STATE__ BGN_DATE BGN_TIME TIME_ZONE COUNTY COUNTYNAME STATE
## 1 1 4/18/1950 0:00:00 0130 CST 97 MOBILE AL
## 2 1 4/18/1950 0:00:00 0145 CST 3 BALDWIN AL
## 3 1 2/20/1951 0:00:00 1600 CST 57 FAYETTE AL
## 4 1 6/8/1951 0:00:00 0900 CST 89 MADISON AL
## 5 1 11/15/1951 0:00:00 1500 CST 43 CULLMAN AL
## 6 1 11/15/1951 0:00:00 2000 CST 77 LAUDERDALE AL
## EVTYPE BGN_RANGE BGN_AZI BGN_LOCATI END_DATE END_TIME COUNTY_END
## 1 TORNADO 0 0
## 2 TORNADO 0 0
## 3 TORNADO 0 0
## 4 TORNADO 0 0
## 5 TORNADO 0 0
## 6 TORNADO 0 0
## COUNTYENDN END_RANGE END_AZI END_LOCATI LENGTH WIDTH F MAG FATALITIES
## 1 NA 0 14.0 100 3 0 0
## 2 NA 0 2.0 150 2 0 0
## 3 NA 0 0.1 123 2 0 0
## 4 NA 0 0.0 100 2 0 0
## 5 NA 0 0.0 150 2 0 0
## 6 NA 0 1.5 177 2 0 0
## INJURIES PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP WFO STATEOFFIC ZONENAMES
## 1 15 25.0 K 0
## 2 0 2.5 K 0
## 3 2 25.0 K 0
## 4 2 2.5 K 0
## 5 2 2.5 K 0
## 6 6 2.5 K 0
## LATITUDE LONGITUDE LATITUDE_E LONGITUDE_ REMARKS REFNUM
## 1 3040 8812 3051 8806 1
## 2 3042 8755 0 0 2
## 3 3340 8742 0 0 3
## 4 3458 8626 0 0 4
## 5 3412 8642 0 0 5
## 6 3450 8748 0 0 6str(storm)## 'data.frame': 902297 obs. of 37 variables:
## $ STATE__ : num 1 1 1 1 1 1 1 1 1 1 ...
## $ BGN_DATE : Factor w/ 16335 levels "1/1/1966 0:00:00",..: 6523 6523 4242 11116 2224 2224 2260 383 3980 3980 ...
## $ BGN_TIME : Factor w/ 3608 levels "00:00:00 AM",..: 272 287 2705 1683 2584 3186 242 1683 3186 3186 ...
## $ TIME_ZONE : Factor w/ 22 levels "ADT","AKS","AST",..: 7 7 7 7 7 7 7 7 7 7 ...
## $ COUNTY : num 97 3 57 89 43 77 9 123 125 57 ...
## $ COUNTYNAME: Factor w/ 29601 levels "","5NM E OF MACKINAC BRIDGE TO PRESQUE ISLE LT MI",..: 13513 1873 4598 10592 4372 10094 1973 23873 24418 4598 ...
## $ STATE : Factor w/ 72 levels "AK","AL","AM",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ EVTYPE : Factor w/ 985 levels " HIGH SURF ADVISORY",..: 834 834 834 834 834 834 834 834 834 834 ...
## $ BGN_RANGE : num 0 0 0 0 0 0 0 0 0 0 ...
## $ BGN_AZI : Factor w/ 35 levels ""," N"," NW",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ BGN_LOCATI: Factor w/ 54429 levels "","- 1 N Albion",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ END_DATE : Factor w/ 6663 levels "","1/1/1993 0:00:00",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ END_TIME : Factor w/ 3647 levels ""," 0900CST",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ COUNTY_END: num 0 0 0 0 0 0 0 0 0 0 ...
## $ COUNTYENDN: logi NA NA NA NA NA NA ...
## $ END_RANGE : num 0 0 0 0 0 0 0 0 0 0 ...
## $ END_AZI : Factor w/ 24 levels "","E","ENE","ESE",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ END_LOCATI: Factor w/ 34506 levels "","- .5 NNW",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ LENGTH : num 14 2 0.1 0 0 1.5 1.5 0 3.3 2.3 ...
## $ WIDTH : num 100 150 123 100 150 177 33 33 100 100 ...
## $ F : int 3 2 2 2 2 2 2 1 3 3 ...
## $ MAG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ FATALITIES: num 0 0 0 0 0 0 0 0 1 0 ...
## $ INJURIES : num 15 0 2 2 2 6 1 0 14 0 ...
## $ PROPDMG : num 25 2.5 25 2.5 2.5 2.5 2.5 2.5 25 25 ...
## $ PROPDMGEXP: Factor w/ 19 levels "","-","?","+",..: 17 17 17 17 17 17 17 17 17 17 ...
## $ CROPDMG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ CROPDMGEXP: Factor w/ 9 levels "","?","0","2",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ WFO : Factor w/ 542 levels ""," CI","$AC",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ STATEOFFIC: Factor w/ 250 levels "","ALABAMA, Central",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ ZONENAMES : Factor w/ 25112 levels ""," "| __truncated__,..: 1 1 1 1 1 1 1 1 1 1 ...
## $ LATITUDE : num 3040 3042 3340 3458 3412 ...
## $ LONGITUDE : num 8812 8755 8742 8626 8642 ...
## $ LATITUDE_E: num 3051 0 0 0 0 ...
## $ LONGITUDE_: num 8806 0 0 0 0 ...
## $ REMARKS : Factor w/ 436781 levels "","-2 at Deer Park\n",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ REFNUM : num 1 2 3 4 5 6 7 8 9 10 ...change colnames of data from upper case to lower case
names(storm)<-tolower(names(storm))
names(storm)## [1] "state__" "bgn_date" "bgn_time" "time_zone" "county"
## [6] "countyname" "state" "evtype" "bgn_range" "bgn_azi"
## [11] "bgn_locati" "end_date" "end_time" "county_end" "countyendn"
## [16] "end_range" "end_azi" "end_locati" "length" "width"
## [21] "f" "mag" "fatalities" "injuries" "propdmg"
## [26] "propdmgexp" "cropdmg" "cropdmgexp" "wfo" "stateoffic"
## [31] "zonenames" "latitude" "longitude" "latitude_e" "longitude_"
## [36] "remarks" "refnum"Fatalities/Injuries
- caculate the total number of fatalities and injuries by each event type
health<-storm%>%
mutate(casualty=fatalities+injuries)%>%
group_by(evtype)%>%
summarize(total=sum(casualty))%>%
arrange(desc(total)) the class of health data is not the data.frame, I want to convert it to data.frame
class(health)## [1] "tbl_df" "tbl" "data.frame"- convert data to data.frame
health<-as.data.frame(health)- only pick first 20 rows
health<-health[1:20,]Damage
- the levels of cropdmgexp and prodmgexp
levels(storm$cropdmgexp)## [1] "" "?" "0" "2" "B" "k" "K" "m" "M"levels(storm$propdmgexp)## [1] "" "-" "?" "+" "0" "1" "2" "3" "4" "5" "6" "7" "8" "B" "h" "H" "K"
## [18] "m" "M"- convert symbels to number
We can see the levels of cropdmgexp and prodmgexp are composed by several symbols
B==billion, M==million, K==thousand, H==hundred, the other symbol are mean unknown, or not available.
I want to convert symbel to number so it’ll be more easy to deal with
levels(storm$cropdmgexp)<-c(0,0,0,0,1000000000,1000,1000,1000000,1000000)
levels(storm$propdmgexp)<-c(0,0,0,0,0,0,0,0,0,0,0,0,0,1000000000,100,100,1000,1000000,1000000)
levels(storm$cropdmgexp)## [1] "0" "1e+09" "1000" "1e+06"levels(storm$propdmgexp)## [1] "0" "1e+09" "100" "1000" "1e+06"storm$cropdmgexp<-as.numeric(as.character(storm$cropdmgexp))
storm$propdmgexp<-as.numeric(as.character(storm$propdmgexp))- caculate the total number of damage by each event type
damage<-storm%>%
group_by(evtype)%>%
summarize(total=sum((cropdmg*cropdmgexp)+(propdmg*propdmgexp)))%>%
arrange(desc(total))- convert data to data.frame
damage<-as.data.frame(damage)- only pick first 20 rows
damage<-damage[1:20,]Result
- the plot of total number of fatalities/injuries
ggplot(health,aes(reorder(evtype,total),total,fill=evtype))+
geom_bar(stat="identity")+
theme(legend.position = "none")+
labs(x="event type",y="total fatalities/injuries",title="The total number of fatalities and injuries")+
coord_flip()
health## evtype total
## 1 TORNADO 96979
## 2 EXCESSIVE HEAT 8428
## 3 TSTM WIND 7461
## 4 FLOOD 7259
## 5 LIGHTNING 6046
## 6 HEAT 3037
## 7 FLASH FLOOD 2755
## 8 ICE STORM 2064
## 9 THUNDERSTORM WIND 1621
## 10 WINTER STORM 1527
## 11 HIGH WIND 1385
## 12 HAIL 1376
## 13 HURRICANE/TYPHOON 1339
## 14 HEAVY SNOW 1148
## 15 WILDFIRE 986
## 16 THUNDERSTORM WINDS 972
## 17 BLIZZARD 906
## 18 FOG 796
## 19 RIP CURRENT 600
## 20 WILD/FOREST FIRE 557the type of most harmful to population health: TORNADO,
caused 96979 people injuried or fatalitied
the second is EXCESSIVE HEAT, endangered 8428 people’s life
- the plot of total damage of crop and prop
ggplot(damage,aes(reorder(evtype,total),total,fill=evtype))+
geom_bar(stat="identity")+
theme(legend.position = "none")+
labs(x="event type",y="total damage",title="The total number of damage")+
coord_flip()
damage## evtype total
## 1 FLOOD 150319678250
## 2 HURRICANE/TYPHOON 71913712800
## 3 TORNADO 57352113590
## 4 STORM SURGE 43323541000
## 5 HAIL 18758221670
## 6 FLASH FLOOD 17562128610
## 7 DROUGHT 15018672000
## 8 HURRICANE 14610229010
## 9 RIVER FLOOD 10148404500
## 10 ICE STORM 8967041310
## 11 TROPICAL STORM 8382236550
## 12 WINTER STORM 6715441250
## 13 HIGH WIND 5908617560
## 14 WILDFIRE 5060586800
## 15 TSTM WIND 5038935790
## 16 STORM SURGE/TIDE 4642038000
## 17 THUNDERSTORM WIND 3897964190
## 18 HURRICANE OPAL 3191846000
## 19 WILD/FOREST FIRE 3108626330
## 20 HEAVY RAIN/SEVERE WEATHER 2500000000the type of greatest economic consequences: FLOOD, caused 150319678250 dollars loss
second is HURRICANE/TYPHOON, caused 71913712800 dollars loss