ddeocampo-wk5-assignment

Assignment 5

library(tidyr)
library(dplyr)
library(zoo)

Import data

importcsv <- read.csv("airline-delay.csv", header = TRUE, stringsAsFactors = FALSE)

transform data

tmp_df <- importcsv[complete.cases(importcsv), ]#remove null rows
names(tmp_df)[1] <- "Airline" #rename 1st column
names(tmp_df)[2] <- "Status" #rename 2nd column

#turn factor to str
i <- sapply(tmp_df, is.factor)
tmp_df[i] <- lapply(tmp_df[i], as.character)

#remaining empty strings to null
tmp_df <- mutate_all(tmp_df, funs(na_if(.,"")))

#Copy down airline names, overwriting NAs
tmp_df$Airline <- na.locf(tmp_df$Airline)

tmp_df

##   Airline  Status Los.Angeles Phoenix San.Diego San.Francisco Seattle
## 1  ALASKA on time         497     221       212           503    1841
## 2  ALASKA delayed          62      12        20           102     305
## 3 AM WEST on time         694    4840       383           320     201
## 4 AM WEST delayed         117     415        65           129      61

compare arrival delays

delayed_data <- tmp_df[which(tmp_df$Status=='delayed'),]

counts_tot <- c(sum(delayed_data$Los.Angeles), sum(delayed_data$Phoenix), sum(delayed_data$San.Diego), sum(delayed_data$San.Francisco), sum(delayed_data$Seattle))
barplot(counts_tot, main="Total Delayed Flights", xlab="Number of Flights by City", names.arg = names(tmp_df[3:7]), col=c("yellow","red","blue","green","purple"))

counts_airline <- table(delayed_data$Los.Angeles, delayed_data$Phoenix)
barplot(t(as.matrix(delayed_data[3:7])),beside=TRUE, main="Delayed Flights", xlab="Number of Flights by Airline", col=c("yellow","red","blue","green","purple"), names.arg = delayed_data$Airline, legend = names(delayed_data[3:7]))