###Using Airline Stats Data

data<-read.csv("airline_stats.csv")
View(data)

###summaries and Tables

summary(data$pct_carrier_delay)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   0.000   4.145   6.357   7.041   9.140 100.000      28
x<-table(data$airline)
x
## 
##    Alaska  American     Delta  Jet Blue Southwest    United 
##      3851      5725      9107      3775      5584      5426
summary(data$pct_atc_delay, data$pct_weather_delay)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   0.000   2.147   3.900   5.090   6.630 100.000      28

###Plotting

table(data$airline)
## 
##    Alaska  American     Delta  Jet Blue Southwest    United 
##      3851      5725      9107      3775      5584      5426
barplot(table(data$airline) , 
        xlab="Airline" , 
        ylab="Number" , 
        main="Respondents by Airline" , 
        col="#e5e5ff")

table(data$airline)
## 
##    Alaska  American     Delta  Jet Blue Southwest    United 
##      3851      5725      9107      3775      5584      5426
barplot(table(data$airline) , 
        xlab="Airline" , 
        ylab="Number" , 
        main="Respondents by Airline" , 
        col="#d4e6f4" , 
        horiz=T)

boxplot(data$pct_carrier_delay~data$airline, col='#cda4a4')

hist(data$pct_atc_delay , breaks=100 , col='#cda4a4')

par(mfrow=c(1,2))
plot(data$pct_carrier_delay,data$pct_weather_delay, col='#04444e')
plot(data$pct_weather_delay,data$pct_carrier_delay, col='#04444e')

library("ggplot2")
data1<-read.csv("airline_stats.csv")
ggplot(data=data1)+
  geom_point(aes(x=pct_carrier_delay,y=pct_atc_delay, alpha=pct_carrier_delay), col='#04444e')
## Warning: Removed 28 rows containing missing values or values outside the scale range
## (`geom_point()`).

ggplot(data=data1)+
  geom_point(aes(x=pct_carrier_delay,y=pct_atc_delay, shape=airline), col='#04444e')
## Warning: Removed 28 rows containing missing values or values outside the scale range
## (`geom_point()`).

ggplot(data=data)+
  geom_point(aes(x=pct_carrier_delay,y=pct_atc_delay, col=airline))
## Warning: Removed 28 rows containing missing values or values outside the scale range
## (`geom_point()`).

ggplot(data=data)+
  geom_point(aes(x=pct_carrier_delay,y=airline), col="Red")
## Warning: Removed 28 rows containing missing values or values outside the scale range
## (`geom_point()`).

ggplot(data=data1)+
  geom_point(aes(x=pct_weather_delay,y=pct_carrier_delay, alpha=pct_weather_delay), col='#d1a03a')+
  facet_wrap(~airline, ncol=2)
## Warning: Removed 28 rows containing missing values or values outside the scale range
## (`geom_point()`).

ggplot(data=data)+
  geom_bar(aes(x=pct_carrier_delay, col=airline))
## Warning: Removed 28 rows containing non-finite outside the scale range
## (`stat_count()`).

p<-ggplot(data=data, aes(airline, pct_carrier_delay))
p

p+
   geom_boxplot()
## Warning: Removed 28 rows containing non-finite outside the scale range
## (`stat_boxplot()`).

p+geom_boxplot() + coord_flip()
## Warning: Removed 28 rows containing non-finite outside the scale range
## (`stat_boxplot()`).

p+geom_boxplot(notch=TRUE, col ="#d1a03a")
## Warning: Removed 28 rows containing non-finite outside the scale range
## (`stat_boxplot()`).

p + geom_boxplot(varwidth = TRUE)
## Warning: Removed 28 rows containing non-finite outside the scale range
## (`stat_boxplot()`).

p + geom_boxplot(fill = "#c4dec1", colour = "#314839")
## Warning: Removed 28 rows containing non-finite outside the scale range
## (`stat_boxplot()`).

p + geom_boxplot(outlier.colour = "#49a596", outlier.shape = 4)
## Warning: Removed 28 rows containing non-finite outside the scale range
## (`stat_boxplot()`).

p + 
  geom_boxplot(outlier.shape = NA) + 
  geom_jitter(width = 0.2, alpha=0.09)
## Warning: Removed 28 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
## Warning: Removed 28 rows containing missing values or values outside the scale range
## (`geom_point()`).

p + geom_boxplot(aes(col= airline))
## Warning: Removed 28 rows containing non-finite outside the scale range
## (`stat_boxplot()`).

q<-ggplot(data=data, aes(pct_carrier_delay))
q+
  geom_histogram()+
  geom_freqpoly(col="Red")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 28 rows containing non-finite outside the scale range
## (`stat_bin()`).
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 28 rows containing non-finite outside the scale range
## (`stat_bin()`).