National Weather Service Analysis

Synopsis

The analysis we present intent to answer the two main questions of the project.For both questions we present a table and a chart in order to analyze the data in two different ways. At the end we present the results with the puntcual answers fot the questions.

Data Processing

We are getting de data from the given URL.

fileurl <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
download.file(fileurl, destfile="data.bz2")
data <- read.table("data.bz2", sep=",", header = TRUE)

Using dplyr we group the data. We keep in a new table only the variables we need for the analysis: EVTYPE, FATALITIES, INJURIES, PROPDMG and CROPDMG.

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, union
g_data <- group_by(data, EVTYPE)
s_table <- summarize(g_data, Fatalities=sum(FATALITIES), Injuries=sum(INJURIES), CDamages = sum(PROPDMG), PDamages = sum(CROPDMG))

Analysis

  1. Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?

Now we filter the data keeping only those events that have at least one injury or one fatality. Also we order the data by fatality.

harm_t <- s_table[s_table$Fatalities != 0 | s_table$Injuries != 0, c('EVTYPE', 'Fatalities', 'Injuries')]
harm_t <- arrange(harm_t, desc(Fatalities, Injuries))
head(harm_t)
## Source: local data frame [6 x 3]
## 
##           EVTYPE Fatalities Injuries
##           (fctr)      (dbl)    (dbl)
## 1        TORNADO       5633    91346
## 2 EXCESSIVE HEAT       1903     6525
## 3    FLASH FLOOD        978     1777
## 4           HEAT        937     2100
## 5      LIGHTNING        816     5230
## 6      TSTM WIND        504     6957

We’ll also plot Fatalities vs Injuries to get a graphic visualisation of the harm each event produced.

library(ggplot2)
qplot(Fatalities, Injuries, data =  harm_t, label = EVTYPE) + geom_text(check_overlap = TRUE, nudge_y = 2000, size = 2.5)

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

On the same way we analyzed the harmful events, we use the DMD variables to analize the economic consecuences.

economic_t <- s_table[s_table$CDamages != 0 | s_table$PDamages != 0, c('EVTYPE', 'CDamages', 'PDamages')]
economic_t <- arrange(economic_t, desc(CDamages, PDamages))
head(economic_t)
## Source: local data frame [6 x 3]
## 
##              EVTYPE  CDamages  PDamages
##              (fctr)     (dbl)     (dbl)
## 1           TORNADO 3212258.2 100018.52
## 2       FLASH FLOOD 1420124.6 179200.46
## 3         TSTM WIND 1335965.6 109202.60
## 4             FLOOD  899938.5 168037.88
## 5 THUNDERSTORM WIND  876844.2  66791.45
## 6              HAIL  688693.4 579596.28

The plot the variables in the same way.

qplot(CDamages, PDamages, data =  economic_t, label = EVTYPE) + geom_text(check_overlap = TRUE, nudge_y = 15000, size = 2.5)

Results

From the first table and the plot we can conclude that the most harmful events are tornado, followed by excessive heat and heat.

As we can see in the second plot and table, the two events that cause the greatest economic consequences are tornado and hail.