Course5Project2
Sokneang Durski
January 24, 2017
Loading the libraries
library("ggplot2")## Warning: package 'ggplot2' was built under R version 3.2.5library("gridExtra")## Warning: package 'gridExtra' was built under R version 3.2.5library("R.utils")## Warning: package 'R.utils' was built under R version 3.2.5## Loading required package: R.oo## Warning: package 'R.oo' was built under R version 3.2.5## Loading required package: R.methodsS3## Warning: package 'R.methodsS3' was built under R version 3.2.5## R.methodsS3 v1.7.1 (2016-02-15) successfully loaded. See ?R.methodsS3 for help.## R.oo v1.21.0 (2016-10-30) successfully loaded. See ?R.oo for help.##
## Attaching package: 'R.oo'## The following objects are masked from 'package:methods':
##
## getClasses, getMethods## The following objects are masked from 'package:base':
##
## attach, detach, gc, load, save## R.utils v2.5.0 (2016-11-07) successfully loaded. See ?R.utils for help.##
## Attaching package: 'R.utils'## The following object is masked from 'package:utils':
##
## timestamp## The following objects are masked from 'package:base':
##
## cat, commandArgs, getOption, inherits, isOpen, parse, warningsLoading the Storm data
stormdata = read.csv("C:/Users/sdurski/Desktop/coursera/course5/course 5 project/repdata_data_StormData.csv ",sep = ",")Printing out the dimension of the storm data
dim(stormdata)## [1] 902297 37Check the internal structure of storm data
str(stormdata)## '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/ 436774 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 ...Summary of Data
summary(stormdata)## STATE__ BGN_DATE BGN_TIME
## Min. : 1.0 5/25/2011 0:00:00: 1202 12:00:00 AM: 10163
## 1st Qu.:19.0 4/27/2011 0:00:00: 1193 06:00:00 PM: 7350
## Median :30.0 6/9/2011 0:00:00 : 1030 04:00:00 PM: 7261
## Mean :31.2 5/30/2004 0:00:00: 1016 05:00:00 PM: 6891
## 3rd Qu.:45.0 4/4/2011 0:00:00 : 1009 12:00:00 PM: 6703
## Max. :95.0 4/2/2006 0:00:00 : 981 03:00:00 PM: 6700
## (Other) :895866 (Other) :857229
## TIME_ZONE COUNTY COUNTYNAME STATE
## CST :547493 Min. : 0.0 JEFFERSON : 7840 TX : 83728
## EST :245558 1st Qu.: 31.0 WASHINGTON: 7603 KS : 53440
## MST : 68390 Median : 75.0 JACKSON : 6660 OK : 46802
## PST : 28302 Mean :100.6 FRANKLIN : 6256 MO : 35648
## AST : 6360 3rd Qu.:131.0 LINCOLN : 5937 IA : 31069
## HST : 2563 Max. :873.0 MADISON : 5632 NE : 30271
## (Other): 3631 (Other) :862369 (Other):621339
## EVTYPE BGN_RANGE BGN_AZI
## HAIL :288661 Min. : 0.000 :547332
## TSTM WIND :219940 1st Qu.: 0.000 N : 86752
## THUNDERSTORM WIND: 82563 Median : 0.000 W : 38446
## TORNADO : 60652 Mean : 1.484 S : 37558
## FLASH FLOOD : 54277 3rd Qu.: 1.000 E : 33178
## FLOOD : 25326 Max. :3749.000 NW : 24041
## (Other) :170878 (Other):134990
## BGN_LOCATI END_DATE END_TIME
## :287743 :243411 :238978
## COUNTYWIDE : 19680 4/27/2011 0:00:00: 1214 06:00:00 PM: 9802
## Countywide : 993 5/25/2011 0:00:00: 1196 05:00:00 PM: 8314
## SPRINGFIELD : 843 6/9/2011 0:00:00 : 1021 04:00:00 PM: 8104
## SOUTH PORTION: 810 4/4/2011 0:00:00 : 1007 12:00:00 PM: 7483
## NORTH PORTION: 784 5/30/2004 0:00:00: 998 11:59:00 PM: 7184
## (Other) :591444 (Other) :653450 (Other) :622432
## COUNTY_END COUNTYENDN END_RANGE END_AZI
## Min. :0 Mode:logical Min. : 0.0000 :724837
## 1st Qu.:0 NA's:902297 1st Qu.: 0.0000 N : 28082
## Median :0 Median : 0.0000 S : 22510
## Mean :0 Mean : 0.9862 W : 20119
## 3rd Qu.:0 3rd Qu.: 0.0000 E : 20047
## Max. :0 Max. :925.0000 NE : 14606
## (Other): 72096
## END_LOCATI LENGTH WIDTH
## :499225 Min. : 0.0000 Min. : 0.000
## COUNTYWIDE : 19731 1st Qu.: 0.0000 1st Qu.: 0.000
## SOUTH PORTION : 833 Median : 0.0000 Median : 0.000
## NORTH PORTION : 780 Mean : 0.2301 Mean : 7.503
## CENTRAL PORTION: 617 3rd Qu.: 0.0000 3rd Qu.: 0.000
## SPRINGFIELD : 575 Max. :2315.0000 Max. :4400.000
## (Other) :380536
## F MAG FATALITIES INJURIES
## Min. :0.0 Min. : 0.0 Min. : 0.0000 Min. : 0.0000
## 1st Qu.:0.0 1st Qu.: 0.0 1st Qu.: 0.0000 1st Qu.: 0.0000
## Median :1.0 Median : 50.0 Median : 0.0000 Median : 0.0000
## Mean :0.9 Mean : 46.9 Mean : 0.0168 Mean : 0.1557
## 3rd Qu.:1.0 3rd Qu.: 75.0 3rd Qu.: 0.0000 3rd Qu.: 0.0000
## Max. :5.0 Max. :22000.0 Max. :583.0000 Max. :1700.0000
## NA's :843563
## PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP
## Min. : 0.00 :465934 Min. : 0.000 :618413
## 1st Qu.: 0.00 K :424665 1st Qu.: 0.000 K :281832
## Median : 0.00 M : 11330 Median : 0.000 M : 1994
## Mean : 12.06 0 : 216 Mean : 1.527 k : 21
## 3rd Qu.: 0.50 B : 40 3rd Qu.: 0.000 0 : 19
## Max. :5000.00 5 : 28 Max. :990.000 B : 9
## (Other): 84 (Other): 9
## WFO STATEOFFIC
## :142069 :248769
## OUN : 17393 TEXAS, North : 12193
## JAN : 13889 ARKANSAS, Central and North Central: 11738
## LWX : 13174 IOWA, Central : 11345
## PHI : 12551 KANSAS, Southwest : 11212
## TSA : 12483 GEORGIA, North and Central : 11120
## (Other):690738 (Other) :595920
## ZONENAMES
## :594029
## :205988
## GREATER RENO / CARSON CITY / M - GREATER RENO / CARSON CITY / M : 639
## GREATER LAKE TAHOE AREA - GREATER LAKE TAHOE AREA : 592
## JEFFERSON - JEFFERSON : 303
## MADISON - MADISON : 302
## (Other) :100444
## LATITUDE LONGITUDE LATITUDE_E LONGITUDE_
## Min. : 0 Min. :-14451 Min. : 0 Min. :-14455
## 1st Qu.:2802 1st Qu.: 7247 1st Qu.: 0 1st Qu.: 0
## Median :3540 Median : 8707 Median : 0 Median : 0
## Mean :2875 Mean : 6940 Mean :1452 Mean : 3509
## 3rd Qu.:4019 3rd Qu.: 9605 3rd Qu.:3549 3rd Qu.: 8735
## Max. :9706 Max. : 17124 Max. :9706 Max. :106220
## NA's :47 NA's :40
## REMARKS REFNUM
## :287433 Min. : 1
## : 24013 1st Qu.:225575
## Trees down.\n : 1110 Median :451149
## Several trees were blown down.\n : 569 Mean :451149
## Trees were downed.\n : 446 3rd Qu.:676723
## Large trees and power lines were blown down.\n: 432 Max. :902297
## (Other) :588294Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?
Select the storm data to required coluns
event <- stormdata[, c("BGN_DATE", "EVTYPE", "FATALITIES", "INJURIES",
"PROPDMG", "PROPDMGEXP", "CROPDMG", "CROPDMGEXP")]Selecting fatalities and injuries event
eventhealth <- subset(event, !event$FATALITIES == 0 & !event$INJURIES ==
0, select = c(EVTYPE, FATALITIES, INJURIES))Prepare data to present harmful events of population health
death <- aggregate(eventhealth$FATALITIES, by = list(eventhealth$EVTYPE),
FUN = sum)Rename death columns
colnames(death) <- c("EVENTTYPE", "FATALITIES")Defining an injusry objective
injury <- aggregate(eventhealth$INJURIES, by = list(eventhealth$EVTYPE),
FUN = sum)Rename injury Columns
colnames(injury) <- c("EVENTTYPE", "INJURIES")Redefining death objective
death <- death[order(death$FATALITIES, decreasing = TRUE),
][1:5, ]Redefining injusry objective
injury <- injury[order(injury$INJURIES, decreasing = TRUE),
][1:5, ]Generate the top 5 couse of fatalities and injuries plots Creating death plot
deathplot <- ggplot() + geom_bar(data = death, aes(x = EVENTTYPE,
y = FATALITIES, fill = interaction(FATALITIES, EVENTTYPE)), stat = "identity",
show.legend = F) + theme(axis.text.x = element_text(angle = 20, hjust = 1)) +
xlab("Harmful Events") + ylab("# of fatailities") + ggtitle("Events Causing Fatalities") +
theme(axis.text.x = element_text(angle = 20, hjust = 1))creating injury plot
injuryplot <- ggplot() + geom_bar(data = injury, aes(x = EVENTTYPE, y = INJURIES,
fill = interaction(INJURIES, EVENTTYPE)), stat = "identity", show.legend = F) +
theme(axis.text.x = element_text(angle = 20, hjust = 1)) + xlab("Harmful Events") +
ylab("# of Injuries") + ggtitle("Events Causing Injuries") +
theme(axis.text.x = element_text(angle = 20, hjust = 1))Ploting deathplot and injuryplot
grid.arrange(deathplot, injuryplot, ncol = 2)
By examing the plots above the tornado is the major cause of population health of fatalites and injuries.
Across the United States, which types of events have the greatest economic consequences?
Data processing of selecting data for property damage and crop Damage
economic <- subset(event, !event$PROPDMG == 0 & !event$CROPDMG ==
0, select = c(EVTYPE, PROPDMG, PROPDMGEXP, CROPDMG, CROPDMGEXP))Prepare data to present harmful events of economic damages
Selecting required entries for economy
economic <- subset(economic, economic$PROPDMGEXP == "K" | economic$PROPDMGEXP ==
"k" | economic$PROPDMGEXP == "M" | economic$PROPDMGEXP == "m" |
economic$PROPDMGEXP == "B" | economic$PROPDMGEXP == "b")
economic <- subset(economic, economic$CROPDMGEXP == "K" | economic$CROPDMGEXP ==
"k" | economic$CROPDMGEXP == "M" | economic$CROPDMGEXP == "m" |
economic$CROPDMGEXP == "B" | economic$CROPDMGEXP == "b")Converting economic values to number
economic$PROPDMGEXP <- gsub("m", 1e+06, economic$PROPDMGEXP, ignore.case = TRUE)
economic$PROPDMGEXP <- gsub("k", 1000, economic$PROPDMGEXP, ignore.case = TRUE)
economic$PROPDMGEXP <- gsub("b", 1e+09, economic$PROPDMGEXP, ignore.case = TRUE)
economic$PROPDMGEXP <- as.numeric(economic$PROPDMGEXP)
economic$CROPDMGEXP <- gsub("m", 1e+06, economic$CROPDMGEXP, ignore.case = TRUE)
economic$CROPDMGEXP <- gsub("k", 1000, economic$CROPDMGEXP, ignore.case = TRUE)
economic$CROPDMGEXP <- gsub("b", 1e+09, economic$CROPDMGEXP, ignore.case = TRUE)
economic$CROPDMGEXP <- as.numeric(economic$CROPDMGEXP)
economic$PROPDMGEXP <- as.numeric(economic$PROPDMGEXP)economic$TOTALDMG <- (economic$CROPDMG * economic$CROPDMGEXP) +
(economic$PROPDMG * economic$PROPDMGEXP)Sum the damages by each event
economic <- aggregate(economic$TOTALDMG, by = list(economic$EVTYPE),
FUN = sum)Rename economic colunms
colnames(economic) <- c("EVTYPE", "TOTALDMG")Order the damage cost of the five columns
economic <- economic[order(economic$TOTALDMG, decreasing = TRUE),
]
economic <- economic[1:5, ]Plot the economic Damage
ggplot() + geom_bar(data = economic, aes(x = EVTYPE, y = TOTALDMG, fill = interaction(TOTALDMG,
EVTYPE)), stat = "identity", show.legend = F) + theme(axis.text.x = element_text(angle = 30,
hjust = 1)) + xlab("Type of Event") + ylab("# of Damage") +ggtitle("Events Causing Damage")
Comment: Base on the plot, flood is the cause of damage. In conclusion, Tornado is harmful with respect to pupulation while flood have the major economic consequences.