storm
Yan Feng
July 3, 2017
Report on major weather types to population health and economy
Synopsis
Every year, storms and severe weather cause big problems to population
health and make huge damage to economy. To better understand unusual weather,
US National Oceanic and Atmospheric Administration (NOAA) collect data for
all severe weather events. This report uses the data set from NOAA to
understand various weather event types, and demonstrates the types that
cause the biggest problem to public health and economy.
- The data set was downloaded from Coursera.org website.
- The analysis tool is R.
Data Processing
loading data
The data set was downloaded and put in the working directory.
storm <- read.csv("repdata_data_StormData.csv.bz2")
#inspect the data set
str(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 ...analysis of weather event types to public health
extract features: FATALITIES, INJURIES, EVTYPE
health <- storm[, c("FATALITIES", "INJURIES", "EVTYPE")]
# To get nationawide information, group the health data frame by EVTYPE
# and calculate a total number for each type
health_type <- aggregate(. ~ EVTYPE, health, FUN = sum)
# Get fatality data for each type and sort it in decreasing order
fatalities <- health_type[order(health_type$FATALITIES, decreasing = T),
c("EVTYPE", "FATALITIES")]
# Get the top 5 types that cause the most fatalities
fatalities5 <- fatalities[1:5, ]
# Plot the top 5 types
library(ggplot2)
x <- as.character(fatalities5$EVTYPE)
g1 <- ggplot(fatalities5, aes(x = factor(EVTYPE, levels = x), y = FATALITIES,
fill = factor(EVTYPE, levels = x)))
g1a <- g1 + geom_bar(stat = "identity", width = .4)
g1b <- g1a + xlab("severe weather type") + ylab("nationwide fatalities")
g1c <- g1b + scale_fill_discrete(name = "weather type")
g1d <- g1c + scale_x_discrete(labels = abbreviate)
g1d
# Get injury data for each type and sort it in decreasing order
injuries <- health_type[order(health_type$INJURIES, decreasing = T),
c("EVTYPE", "INJURIES")]
# Get the top 5 types that cause the most fatalities
injuries5 <- injuries[1:5, ]
# Plot the top 5 types
y <- as.character(injuries5$EVTYPE)
g2 <- ggplot(injuries5, aes(x = factor(EVTYPE, levels = y), y = INJURIES,
fill = factor(EVTYPE, levels = y)))
g2a <- g2 + geom_bar(stat = "identity", width = .4)
g2b <- g2a + xlab("severe weather type") + ylab("nationwide injuries")
g2c <- g2b + scale_fill_discrete(name = "weather type")
g2d <- g2c + scale_x_discrete(labels = abbreviate)
g2d
analysis of weather event types to economy
extract features: PROPDMG, CROPDMG, EVTYPE
economy <- storm[, c("PROPDMG", "CROPDMG", "EVTYPE")]
# To get nationawide information, group the economy data frame by EVTYPE
# and calculate a total number for each type
economy_type <- aggregate(. ~ EVTYPE, economy, FUN = sum)
# consider property and crop damage together
# add property and crop damage to form a new variable damage
economy_type$damage <- apply(economy_type[,2:3], 1, sum, na.rm = T)
# update economy with only EVTYPE and damage variables
economy_type <- economy_type[, c(1,4)]
# order weather types by damage
economy_type <- economy_type[order(economy_type$damage, decreasing = T), ]
# Get the top 5 weather types to cause economy damage
economy5 <- economy_type[1:5,]
# Plot the top 5 types
z <- as.character(economy5$EVTYPE)
g3 <- ggplot(economy5, aes(x = factor(EVTYPE, levels = z), y = damage,
fill = factor(EVTYPE, levels = z)))
g3a <- g3 + geom_bar(stat = "identity", width = .4)
g3b <- g3a + xlab("severe weather type") + ylab("nationwide damage")
g3c <- g3b + scale_fill_discrete(name = "weather type")
g3d <- g3c + scale_x_discrete(labels = abbreviate)
g3d