Johns Hopkins University-Reproducible Research Course Project 2
setwd("C:/Users/c1992/Desktop/MOOCS-20170607T120517Z-001/MOOCS/JHU- Data Science/5- Reproducible Research")
Sys.setlocale("LC_ALL", "English")## [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"download.file("https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2","./storm_data.csv.bz2")
storm <- read.csv(bzfile("./storm_data.csv.bz2"), header= TRUE)
dim(storm)## [1] 902297 37str(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 ...head(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 6tail(storm)## STATE__ BGN_DATE BGN_TIME TIME_ZONE COUNTY
## 902292 47 11/28/2011 0:00:00 03:00:00 PM CST 21
## 902293 56 11/30/2011 0:00:00 10:30:00 PM MST 7
## 902294 30 11/10/2011 0:00:00 02:48:00 PM MST 9
## 902295 2 11/8/2011 0:00:00 02:58:00 PM AKS 213
## 902296 2 11/9/2011 0:00:00 10:21:00 AM AKS 202
## 902297 1 11/28/2011 0:00:00 08:00:00 PM CST 6
## COUNTYNAME STATE EVTYPE BGN_RANGE
## 902292 TNZ001>004 - 019>021 - 048>055 - 088 TN WINTER WEATHER 0
## 902293 WYZ007 - 017 WY HIGH WIND 0
## 902294 MTZ009 - 010 MT HIGH WIND 0
## 902295 AKZ213 AK HIGH WIND 0
## 902296 AKZ202 AK BLIZZARD 0
## 902297 ALZ006 AL HEAVY SNOW 0
## BGN_AZI BGN_LOCATI END_DATE END_TIME COUNTY_END
## 902292 11/29/2011 0:00:00 12:00:00 PM 0
## 902293 11/30/2011 0:00:00 10:30:00 PM 0
## 902294 11/10/2011 0:00:00 02:48:00 PM 0
## 902295 11/9/2011 0:00:00 01:15:00 PM 0
## 902296 11/9/2011 0:00:00 05:00:00 PM 0
## 902297 11/29/2011 0:00:00 04:00:00 AM 0
## COUNTYENDN END_RANGE END_AZI END_LOCATI LENGTH WIDTH F MAG
## 902292 NA 0 0 0 NA 0
## 902293 NA 0 0 0 NA 66
## 902294 NA 0 0 0 NA 52
## 902295 NA 0 0 0 NA 81
## 902296 NA 0 0 0 NA 0
## 902297 NA 0 0 0 NA 0
## FATALITIES INJURIES PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP WFO
## 902292 0 0 0 K 0 K MEG
## 902293 0 0 0 K 0 K RIW
## 902294 0 0 0 K 0 K TFX
## 902295 0 0 0 K 0 K AFG
## 902296 0 0 0 K 0 K AFG
## 902297 0 0 0 K 0 K HUN
## STATEOFFIC
## 902292 TENNESSEE, West
## 902293 WYOMING, Central and West
## 902294 MONTANA, Central
## 902295 ALASKA, Northern
## 902296 ALASKA, Northern
## 902297 ALABAMA, North
## ZONENAMES
## 902292 LAKE - LAKE - OBION - WEAKLEY - HENRY - DYER - GIBSON - CARROLL - LAUDERDALE - TIPTON - HAYWOOD - CROCKETT - MADISON - CHESTER - HENDERSON - DECATUR - SHELBY
## 902293 OWL CREEK & BRIDGER MOUNTAINS - OWL CREEK & BRIDGER MOUNTAINS - WIND RIVER BASIN
## 902294 NORTH ROCKY MOUNTAIN FRONT - NORTH ROCKY MOUNTAIN FRONT - EASTERN GLACIER
## 902295 ST LAWRENCE IS. BERING STRAIT - ST LAWRENCE IS. BERING STRAIT
## 902296 NORTHERN ARCTIC COAST - NORTHERN ARCTIC COAST
## 902297 MADISON - MADISON
## LATITUDE LONGITUDE LATITUDE_E LONGITUDE_
## 902292 0 0 0 0
## 902293 0 0 0 0
## 902294 0 0 0 0
## 902295 0 0 0 0
## 902296 0 0 0 0
## 902297 0 0 0 0
## REMARKS
## 902292 EPISODE NARRATIVE: A powerful upper level low pressure system brought snow to portions of Northeast Arkansas, the Missouri Bootheel, West Tennessee and extreme north Mississippi. Most areas picked up between 1 and 3 inches of with areas of Northeast Arkansas and the Missouri Bootheel receiving between 4 and 6 inches of snow.EVENT NARRATIVE: Around 1 inch of snow fell in Carroll County.
## 902293 EPISODE NARRATIVE: A strong cold front moved south through north central Wyoming bringing high wind to the Meeteetse area and along the south slopes of the western Owl Creek Range. Wind gusts to 76 mph were recorded at Madden Reservoir.EVENT NARRATIVE:
## 902294 EPISODE NARRATIVE: A strong westerly flow aloft produced gusty winds at the surface along the Rocky Mountain front and over the plains of Central Montana. Wind gusts in excess of 60 mph were reported.EVENT NARRATIVE: A wind gust to 60 mph was reported at East Glacier Park 1ENE (the Two Medicine DOT site).
## 902295 EPISODE NARRATIVE: A 960 mb low over the southern Aleutians at 0300AKST on the 8th intensified to 945 mb near the Gulf of Anadyr by 2100AKST on the 8th. The low crossed the Chukotsk Peninsula as a 956 mb low at 0900AKST on the 9th, and moved into the southern Chukchi Sea as a 958 mb low by 2100AKST on the 9th. The low then tracked to the northwest and weakened to 975 mb about 150 miles north of Wrangel Island by 1500AKST on the 10th. The storm was one of the strongest storms to impact the west coast of Alaska since November 1974. \n\nZone 201: Blizzard conditions were observed at Wainwright from approximately 1153AKST through 1611AKST on the 9th. The visibility was frequently reduced to one quarter mile in snow and blowing snow. There was a peak wind gust to 43kt (50 mph) at the Wainwright ASOS. During this event, there was also a peak wind gust to \n68 kt (78 mph) at the Cape Lisburne AWOS. \n\nZone 202: Blizzard conditions were observed at Barrow from approximately 1021AKST through 1700AKST on the 9th. The visibility was frequently reduced to one quarter mile or less in blowing snow. There was a peak wind gust to 46 kt (53 mph) at the Barrow ASOS. \n\nZone 207: Blizzard conditions were observed at Kivalina from approximately 0400AKST through 1230AKST on the 9th. The visibility was frequently reduced to one quarter of a mile in snow and blowing snow. There was a peak wind gust to 61 kt (70 mph) at the Kivalina ASOS. The doors to the village transportation shed were blown out to sea. Many homes lost portions of their tin roofing, and satellite dishes were ripped off of roofs. One home had its door blown off. At Point Hope, severe blizzard conditions were observed. There was a peak wind gust of 68 kt (78 mph) at the Point Hope AWOS before power was lost to the AWOS. It was estimated that the wind gusted as high as 85 mph in the village during the height of the storm during the morning and early afternoon hours on the 9th. Five power poles were knocked down in the storm EVENT NARRATIVE:
## 902296 EPISODE NARRATIVE: A 960 mb low over the southern Aleutians at 0300AKST on the 8th intensified to 945 mb near the Gulf of Anadyr by 2100AKST on the 8th. The low crossed the Chukotsk Peninsula as a 956 mb low at 0900AKST on the 9th, and moved into the southern Chukchi Sea as a 958 mb low by 2100AKST on the 9th. The low then tracked to the northwest and weakened to 975 mb about 150 miles north of Wrangel Island by 1500AKST on the 10th. The storm was one of the strongest storms to impact the west coast of Alaska since November 1974. \n\nZone 201: Blizzard conditions were observed at Wainwright from approximately 1153AKST through 1611AKST on the 9th. The visibility was frequently reduced to one quarter mile in snow and blowing snow. There was a peak wind gust to 43kt (50 mph) at the Wainwright ASOS. During this event, there was also a peak wind gust to \n68 kt (78 mph) at the Cape Lisburne AWOS. \n\nZone 202: Blizzard conditions were observed at Barrow from approximately 1021AKST through 1700AKST on the 9th. The visibility was frequently reduced to one quarter mile or less in blowing snow. There was a peak wind gust to 46 kt (53 mph) at the Barrow ASOS. \n\nZone 207: Blizzard conditions were observed at Kivalina from approximately 0400AKST through 1230AKST on the 9th. The visibility was frequently reduced to one quarter of a mile in snow and blowing snow. There was a peak wind gust to 61 kt (70 mph) at the Kivalina ASOS. The doors to the village transportation shed were blown out to sea. Many homes lost portions of their tin roofing, and satellite dishes were ripped off of roofs. One home had its door blown off. At Point Hope, severe blizzard conditions were observed. There was a peak wind gust of 68 kt (78 mph) at the Point Hope AWOS before power was lost to the AWOS. It was estimated that the wind gusted as high as 85 mph in the village during the height of the storm during the morning and early afternoon hours on the 9th. Five power poles were knocked down in the storm EVENT NARRATIVE:
## 902297 EPISODE NARRATIVE: An intense upper level low developed on the 28th at the base of a highly amplified upper trough across the Great Lakes and Mississippi Valley. The upper low closed off over the mid South and tracked northeast across the Tennessee Valley during the morning of the 29th. A warm conveyor belt of heavy rainfall developed in advance of the low which dumped from around 2 to over 5 inches of rain across the eastern two thirds of north Alabama and middle Tennessee. The highest rain amounts were recorded in Jackson and DeKalb Counties with 3 to 5 inches. The rain fell over 24 to 36 hour period, with rainfall remaining light to moderate during most its duration. The rainfall resulted in minor river flooding along the Little River, Big Wills Creek and Paint Rock. A landslide occurred on Highway 35 just north of Section in Jackson County. A driver was trapped in his vehicle, but was rescued unharmed. Trees, boulders and debris blocked 100 to 250 yards of Highway 35.\n\nThe rain mixed with and changed to snow across north Alabama during the afternoon and evening hours of the 28th, and lasted into the 29th. The heaviest bursts of snow occurred in northwest Alabama during the afternoon and evening hours, and in north central and northeast Alabama during the overnight and morning hours. Since ground temperatures were in the 50s, and air temperatures in valley areas only dropped into the mid 30s, most of the snowfall melted on impact with mostly trace amounts reported in valley locations. However, above 1500 foot elevation, snow accumulations of 1 to 2 inches were reported. The heaviest amount was 2.3 inches on Monte Sano Mountain, about 5 miles northeast of Huntsville.EVENT NARRATIVE: Snowfall accumulations of up to 2.3 inches were reported on the higher elevations of eastern Madison County. A snow accumulation of 1.5 inches was reported 2.7 miles south of Gurley, while 2.3 inches was reported 3 miles east of Huntsville atop Monte Sano Mountain.
## REFNUM
## 902292 902292
## 902293 902293
## 902294 902294
## 902295 902295
## 902296 902296
## 902297 9022971. Across the United States, which types of events are most harmful with respect to population health?
The most two possible proxies to represent population health concerning to disaster maybe “injuries” and “fatalities”. We can plot to find out the realationship between these two proxies.
with(storm, plot(FATALITIES, INJURIES, main= "relationship between fatalities and injuries", xlab= "Fatalities", ylab= "Injuries"))
with(storm, cor(FATALITIES, INJURIES))## [1] 0.3216808Due to the positive correltaion between injuries and fatalities, there are no divergence between the two proxies.
Since we are looking for the most harmful type of events to population health, we can sum up the fatalities/injuries classified by different types of events separately, thus find out the event type with the largest number of fatalities and injuries.
i. Data Processing
fat <- aggregate(storm$FATALITIES, by= list(storm$EVTYPE), FUN=sum)
names(fat) <- c("events_type","number")inj <- aggregate(storm$INJURIES, by= list(storm$EVTYPE), FUN= sum)
names(inj) <- c("events_type", "number")ii. Results
fat[which.max(fat$number),]## events_type number
## 834 TORNADO 5633inj[which.max(inj$number),]## events_type number
## 834 TORNADO 91346It is clear that tornado brought the greatest harm to the country. It put 5633 people to the end of their lives and 91346 people injuries.
2. Across the United States, which types of events have the greatest economic consequences?
In the dataset, there are records of damage measured in money value.(“Property Damage Expense(PROPDMGEXP)”, “Crop Damage Expense(CROPDMGEXP)”). In the following chunks, we can calculate the damage expense of these two types by different types of events.
i. Data Processing
levels(storm$PROPDMGEXP)## [1] "" "-" "?" "+" "0" "1" "2" "3" "4" "5" "6" "7" "8" "B" "h" "H" "K"
## [18] "m" "M"ind0 <- grep("0",as.character(storm$PROPDMGEXP))
ind1 <- grep("1",as.character(storm$PROPDMGEXP))
ind2 <- grep("2",as.character(storm$PROPDMGEXP))
ind3 <- grep("3",as.character(storm$PROPDMGEXP))
ind4 <- grep("4",as.character(storm$PROPDMGEXP))
ind5 <- grep("5",as.character(storm$PROPDMGEXP))
ind6 <- grep("6",as.character(storm$PROPDMGEXP))
ind7 <- grep("7",as.character(storm$PROPDMGEXP))
ind8 <- grep("8",as.character(storm$PROPDMGEXP))
sub_prop <- storm[c(ind0,ind1,ind2,ind3,ind4,ind5,ind6,ind7,ind8),]
head(sub_prop$PROPDMGEXP)## [1] 0 0 0 0 0 0
## Levels: - ? + 0 1 2 3 4 5 6 7 8 B h H K m Mtail(sub_prop$PROPDMGEXP)## [1] 7 7 7 7 7 8
## Levels: - ? + 0 1 2 3 4 5 6 7 8 B h H K m Mlevels(storm$CROPDMGEXP)## [1] "" "?" "0" "2" "B" "k" "K" "m" "M"index0 <- grep("0",as.character(storm$CROPDMGEXP))
index2 <- grep("2",as.character(storm$CROPDMGEXP))
sub_crop <- storm[c(index0,index2),]
head(sub_crop$CROPDMGEXP)## [1] 0 0 0 0 0 0
## Levels: ? 0 2 B k K m Mtail(sub_crop$CROPDMGEXP)## [1] 0 0 0 0 0 2
## Levels: ? 0 2 B k K m Mprop <- aggregate(as.numeric(as.character(sub_prop$PROPDMGEXP)), by= list(sub_prop$EVTYPE), FUN= sum)
crop <- aggregate(as.numeric(as.character(sub_crop$CROPDMGEXP)), by= list(sub_crop$EVTYPE), FUN= sum)
names(prop) <- c("Event_type", "Count")
names(crop) <- c("Event_type", "Count")
(prop$Event_type)## [1] FLASH FLOOD FLASH FLOODING
## [3] FLOOD FLOOD/FLASH FLOOD
## [5] FLOODING HAIL
## [7] HEAVY SNOW HIGH TIDES
## [9] HIGH WINDS ICE STORM
## [11] LIGHTNING THUNDERSTORM WIND
## [13] THUNDERSTORM WINDS THUNDERSTORM WINDSS
## [15] TORNADO TSTM WIND
## [17] URBAN/SMALL STREAM FLOODING WINTER STORM
## 985 Levels: HIGH SURF ADVISORY COASTAL FLOOD ... WNDcrop## Event_type Count
## 1 DROUGHT 0
## 2 HAIL 0
## 3 HIGH WIND AND SEAS 0
## 4 THUNDERSTORM WINDS 2
## 5 TORNADO 0From the table “prop” presented in the previous chunk, we find there are some event type duplicated. Reorganize the table as following:
ind_flood <- grep("FLOOD", as.character(prop$Event_type))
ind_thunder <- grep("THUNDER", as.character(prop$Event_type))
prop$Event_type[ind_flood] <- "FLOODING"
prop$Event_type[ind_thunder] <- "THUNDERSTORM WIND"
prop <- aggregate(prop$Count, by= list(prop$Event_type), FUN= sum)
names(prop) <- c("Event_type", "Count")ii. Result
prop## Event_type Count
## 1 FLOODING 46
## 2 HAIL 66
## 3 HEAVY SNOW 5
## 4 HIGH TIDES 0
## 5 HIGH WINDS 0
## 6 ICE STORM 0
## 7 LIGHTNING 36
## 8 THUNDERSTORM WIND 100
## 9 TORNADO 33
## 10 TSTM WIND 0
## 11 WINTER STORM 0crop## Event_type Count
## 1 DROUGHT 0
## 2 HAIL 0
## 3 HIGH WIND AND SEAS 0
## 4 THUNDERSTORM WINDS 2
## 5 TORNADO 0Now it is pretty obvious that “THUNDERSTORM WIND” brings about the greatest damage to the U.S. It costs 102 units of monetary loss in overall.