Storm Analysis

Xiangzhu Long

Synopsis

1.Observe the data and prepocess it to get the clean data;

2.Exlpore the impact of different estimators on the population health, find that tornados, are most harmful.

3.Exlpore the impact of different estimators on the economy , find that floods are most harmful.

Details

Analysis

Loading and preprocessing the data

# Load the data 
data_raw <- read.csv("data/repdata-data-StormData.csv", stringsAsFactors = FALSE)

# Observe tha raw data
d <- dim(data_raw)

This data set contains 902297 observations and 37 features.

head(data_raw, n = 2)

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 EVTYPE BGN_RANGE BGN_AZI BGN_LOCATI END_DATE END_TIME COUNTY_END 1 TORNADO 0 0 2 TORNADO 0 0 COUNTYENDN END_RANGE END_AZI END_LOCATI LENGTH WIDTH F MAG FATALITIES 1 NA 0 14 100 3 0 0 2 NA 0 2 150 2 0 0 INJURIES PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP WFO STATEOFFIC ZONENAMES 1 15 25.0 K 0
2 0 2.5 K 0
LATITUDE LONGITUDE LATITUDE_E LONGITUDE_ REMARKS REFNUM 1 3040 8812 3051 8806 1 2 3042 8755 0 0 2

# Process the data
data <- data_raw[,c('EVTYPE','FATALITIES','INJURIES', 'PROPDMG', 'PROPDMGEXP', 'CROPDMG', 'CROPDMGEXP')]

# Convert the damage degree to numeric value
data$PROPDMGNUM = 0
data[data$PROPDMGEXP == "H", ]$PROPDMGNUM = data[data$PROPDMGEXP == "H", ]$PROPDMG * 10^2
data[data$PROPDMGEXP == "K", ]$PROPDMGNUM = data[data$PROPDMGEXP == "K", ]$PROPDMG * 10^3
data[data$PROPDMGEXP == "M", ]$PROPDMGNUM = data[data$PROPDMGEXP == "M", ]$PROPDMG * 10^6
data[data$PROPDMGEXP == "B", ]$PROPDMGNUM = data[data$PROPDMGEXP == "B", ]$PROPDMG * 10^9

data$CROPDMGNUM = 0
data[data$CROPDMGEXP == "H", ]$CROPDMGNUM = data[data$CROPDMGEXP == "H", ]$CROPDMG * 10^2
data[data$CROPDMGEXP == "K", ]$CROPDMGNUM = data[data$CROPDMGEXP == "K", ]$CROPDMG * 10^3 
data[data$CROPDMGEXP == "M", ]$CROPDMGNUM = data[data$CROPDMGEXP == "M", ]$CROPDMG * 10^6
data[data$CROPDMGEXP == "B", ]$CROPDMGNUM = data[data$CROPDMGEXP == "B", ]$CROPDMG * 10^9

Results

library(ggplot2)

## Warning: package 'ggplot2' was built under R version 3.1.3

# Plot the number of fatalities of different evaluator.
evaluator <- aggregate(FATALITIES ~ EVTYPE, data = data, sum)
evaluator <- evaluator[order(-evaluator$FATALITIES), ][1:10, ]
evaluator$EVTYPE <- factor(evaluator$EVTYPE, levels = evaluator$EVTYPE)

ggplot(evaluator, aes(x = EVTYPE, y = FATALITIES)) + 
  geom_bar(stat = "identity", fill = "red", las = 3) + 
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 
  xlab("Evaluator") + ylab("# of Fatalities") +
  ggtitle("Number of fatalities of different evaluator")

The figure shows that Tornado, Excessive heat and Flash flood cause the most serious fatalities, while Avalanche, High wind and **Rip current* have the less impact.

# Plot the number of injuries of different evaluator.
injuries <- aggregate(INJURIES ~ EVTYPE, data = data, sum)
injuries <- injuries[order(-injuries$INJURIES), ][1:10, ]
injuries$EVTYPE <- factor(injuries$EVTYPE, levels = injuries$EVTYPE)

ggplot(injuries, aes(x = EVTYPE, y = INJURIES)) + 
  geom_bar(stat = "identity", fill = "red", las = 3) + 
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 
  xlab("Evaluator") + ylab("# of Injuries") +
  ggtitle("Number of injuries of different evaluator")

The figure shows that **Tornado*, Tstm wind and Flood have the most harmful influence on the population health, while Hail, Thunderstorm wind and Flash flood have the less impact.

# Plot the damage degree with the most harmful evaluators.
damages <- aggregate(PROPDMGNUM + CROPDMGNUM ~ EVTYPE,
                     data = data, sum)
names(damages) = c("EVTYPE", "DAMAGES")
damages <- damages[order(-damages$DAMAGES), ][1:10, ]
damages$EVTYPE <- factor(damages$EVTYPE, levels = damages$EVTYPE)

ggplot(damages, aes(x = EVTYPE, y = DAMAGES)) + 
  geom_bar(stat = "identity", fill = "red", las = 3) + 
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 
  xlab("Evaluator") + ylab("Damage Degree") +
  ggtitle("Property & Crop Damages of the most Harmful Evaluators")

The figure shows that Fload, Hurricanetyphoon and Tornado have the most harmful influence on the economics, while Ice storml, River flood and Hurricane have the less impact.