Most damaging storms in United States from 1950 to 2011

## Synopsis In this document we present analysis of the last 60 years storms that occured in the United States. We highlight storm types that have the highest human and economic impact.

library(ggplot2)
library(reshape2)
setwd("/Users/martin/Dev/datasciencecoursera-repos/datasciencecoursera-represearch-a2")

con <- bzfile("data/repdata-data-StormData.csv.bz2", "r")
csv <- read.csv(con)
close(con)

Data Processing

Cleaning data:

csv$EVTYPE <- tolower(csv$EVTYPE)

typeScores <- aggregate(cbind(csv$INJURIES, csv$FATALITIES) ~ csv$EVTYPE, csv, sum) # 10s
fullZero <- typeScores[,2] == 0 & typeScores[,3] == 0
cleanTypeScores <- typeScores[!fullZero,]
names(cleanTypeScores) <- cbind("type", "injuries", "fatalities")
rankInjuries <- order(cleanTypeScores[,2], decreasing=T)
rankFatalities <- order(cleanTypeScores[,3], decreasing=T)

Results

Across the United States, which types of events are most harmful with respect to population health?

toPlot <- cleanTypeScores[rankFatalities, ]
toPlot <- toPlot[1:20, ]
toPlot <- melt(toPlot, "type")

ggplot(toPlot, aes(x = type, y = value, fill = variable)) + geom_histogram(position = "dodge") + 
  theme(axis.text.x = element_text(angle = 60, hjust = 1)) + labs(title = "10 most injuring storm types in US - 1950 to 2011")

## Mapping a variable to y and also using stat="bin".
##   With stat="bin", it will attempt to set the y value to the count of cases in each group.
##   This can result in unexpected behavior and will not be allowed in a future version of ggplot2.
##   If you want y to represent counts of cases, use stat="bin" and don't map a variable to y.
##   If you want y to represent values in the data, use stat="identity".
##   See ?geom_bar for examples. (Deprecated; last used in version 0.9.2)

plot of chunk showMostDamagingStormTypes 


# TODO : ordonner les levels des facteurs

# TODO : Vérifier si ça a évolué avec le temps?

Across the United States, which types of events have the greatest economic consequences?

We focus on event types implying Billion dollars of property and crop destructions.

The list of event type is given bellow:

eventsProp <- sort(unique(csv$EVTYPE[csv$PROPDMGEXP == "B"]))
eventsCrop <- sort(unique(csv$EVTYPE[csv$PROPDMGEXP == "B"]))
events     <- sort(unique(rbind(eventsProp, eventsCrop)))
print(events)

##  [1] "flash flood"                "flood"                     
##  [3] "hail"                       "heavy rain/severe weather" 
##  [5] "high wind"                  "hurricane"                 
##  [7] "hurricane opal"             "hurricane opal/high winds" 
##  [9] "hurricane/typhoon"          "river flood"               
## [11] "severe thunderstorm"        "storm surge"               
## [13] "storm surge/tide"           "tornado"                   
## [15] "tornadoes, tstm wind, hail" "tropical storm"            
## [17] "wild/forest fire"           "wildfire"                  
## [19] "winter storm"

Reproducing the analysis

The analysis sources can be found here : https://github.com/jzy3d/datasciencecoursera-represearch-a2

The data was provided by coursera here : https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2

The analysis was produced with the following computer configuration:

sessionInfo()

## R version 3.0.1 (2013-05-16)
## Platform: x86_64-apple-darwin10.8.0 (64-bit)
## 
## locale:
## [1] fr_FR.UTF-8/fr_FR.UTF-8/fr_FR.UTF-8/C/fr_FR.UTF-8/fr_FR.UTF-8
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
## [1] reshape2_1.2.2  ggplot2_0.9.3.1 knitr_1.5      
## 
## loaded via a namespace (and not attached):
##  [1] colorspace_1.2-4 digest_0.6.4     evaluate_0.5.5   formatR_0.10    
##  [5] grid_3.0.1       gtable_0.1.2     labeling_0.2     MASS_7.3-31     
##  [9] munsell_0.4.2    plyr_1.8.1       proto_0.3-10     Rcpp_0.11.1     
## [13] scales_0.2.4     stringr_0.6.2    tools_3.0.1