Analysis of Storm Data

• Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?
• Across the United States, which types of events have the greatest economic consequences? The events covered in this analysis are from a database that starts in the year 1950 and ends in November 2011. In the earlier years of the database there are generally fewer events recorded, most likely due to a lack of good records. More recent years should be considered more complete.

In general the data is subset in order to isolate events that have a greater impact. Graphs are created to show the damage to both people and property.

Finally we examine if the events that cause the most damage to people change over time.

set up the environment

library(lattice)
setwd("~/Coursera_DataScience/RR/Pa2")

Load the storm data

storm_data <- read.csv("repdata-data-StormData.csv")

Data Processing

Set the date format for begin and end

storm_data$BGN_DATE <- strptime(storm_data$BGN_DATE, format = "%m/%d/%Y %H:%M:%S")
storm_data$END_DATE <- strptime(storm_data$END_DATE, format = "%m/%d/%Y %H:%M:%S")

Create a year for later analaysis

storm_data$YEAR <- format(storm_data$BGN_DATE, "%Y")

Subset the data for more than 100 injuries or fatalities

people_storm_data <- storm_data[storm_data$INJURIES + storm_data$FATALITIES > 
    100, ]

subset the data for property damage

cost_storm_data <- storm_data[storm_data$PROPDMG + storm_data$CROPDMG > 1000, 
    ]

Results

In general this is the total result

xyplot(people_storm_data$EVTYPE ~ people_storm_data$INJURIES + people_storm_data$FATALITIES)

Has this changed over time?

xyplot(people_storm_data$EVTYPE ~ people_storm_data$INJURIES + people_storm_data$FATALITIES | 
    people_storm_data$YEAR)

Cost overall

xyplot(cost_storm_data$EVTYPE ~ cost_storm_data$PROPDMG + cost_storm_data$CROPDMG)