Load Airquality dataset included with tidyverse

library(tidyverse)
## ── Attaching packages ────────────────────────────────────────────────────────── tidyverse 1.2.1 ──
## ✔ ggplot2 3.2.1       ✔ purrr   0.3.2  
## ✔ tibble  2.1.1       ✔ dplyr   0.8.0.1
## ✔ tidyr   0.8.3       ✔ stringr 1.4.0  
## ✔ readr   1.3.1       ✔ forcats 0.4.0
## ── Conflicts ───────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
airquality<- datasets::airquality

see what the included airquality dataset looks like:

# structure
str(airquality)
## 'data.frame':    153 obs. of  6 variables:
##  $ Ozone  : int  41 36 12 18 NA 28 23 19 8 NA ...
##  $ Solar.R: int  190 118 149 313 NA NA 299 99 19 194 ...
##  $ Wind   : num  7.4 8 12.6 11.5 14.3 14.9 8.6 13.8 20.1 8.6 ...
##  $ Temp   : int  67 72 74 62 56 66 65 59 61 69 ...
##  $ Month  : int  5 5 5 5 5 5 5 5 5 5 ...
##  $ Day    : int  1 2 3 4 5 6 7 8 9 10 ...
#
# variety
summary(airquality)
##      Ozone           Solar.R           Wind             Temp      
##  Min.   :  1.00   Min.   :  7.0   Min.   : 1.700   Min.   :56.00  
##  1st Qu.: 18.00   1st Qu.:115.8   1st Qu.: 7.400   1st Qu.:72.00  
##  Median : 31.50   Median :205.0   Median : 9.700   Median :79.00  
##  Mean   : 42.13   Mean   :185.9   Mean   : 9.958   Mean   :77.88  
##  3rd Qu.: 63.25   3rd Qu.:258.8   3rd Qu.:11.500   3rd Qu.:85.00  
##  Max.   :168.00   Max.   :334.0   Max.   :20.700   Max.   :97.00  
##  NA's   :37       NA's   :7                                       
##      Month            Day      
##  Min.   :5.000   Min.   : 1.0  
##  1st Qu.:6.000   1st Qu.: 8.0  
##  Median :7.000   Median :16.0  
##  Mean   :6.993   Mean   :15.8  
##  3rd Qu.:8.000   3rd Qu.:23.0  
##  Max.   :9.000   Max.   :31.0  
##

remap months from integers to names

airquality$Month<-as.factor(airquality$Month)
levels(airquality$Month)=c("May","Jun","Jul","Aug","Sep")

Plot 1: Create a histogram categorized by Month with qplot

p1 <- qplot(data = airquality,Temp,fill = Month,geom = "histogram", bins = 20)
p1

Plot 2: Make a histogram using ggplot (instead of qplot)

p2 <- airquality %>%
  ggplot(aes(x=Temp, fill=Month)) +
  geom_histogram(position="identity", alpha=1, binwidth = 5, color = "white")+
  scale_fill_discrete(name = "Month",  labels = levels(airquality$Month))
p2

Plot 3: Create side-by-side boxplots categorized by Month

y-axis appears to be temperatures, not frequencies

p3 <- airquality %>%
  ggplot(aes(Month, Temp, fill = Month)) + 
  ggtitle("Temperatures") +
  xlab("Months") +
  ylab("Frequency") +
  geom_boxplot() +
  scale_fill_discrete(name = "Month", labels = levels(airquality$Month))
p3

Plot 4: Make the same side-by-side boxplots, but in grey-scale

p4 <- airquality %>%
  ggplot(aes(Month, Temp, fill = Month)) + 
  ggtitle("Temperatures") +
  xlab("Temperatures") +
  ylab("Frequency") +
  geom_boxplot()+
  scale_fill_grey(name = "Month", labels = levels(airquality$Month))
p4

My turn:

Plot 2a: Make a barplot using ggplot using fill color for Temperature

How to do this with continuous Temp instead of factor?

Had to use negative Temp to get temperatures to rise from bottom

airq<-airquality
airq$Temp<-as.factor(-airq$Temp)

p2a <- airq %>%
  ggplot(aes(x=Month, fill=(Temp))) +
  geom_bar(stat = "count")+
  scale_fill_discrete(name = "Temp",  labels =levels(airq$Temp))
p2a

Plot 3a: Create temperature heat map categorized by Month

p3a <- airquality %>%
  ggplot(aes(Month,Temp)) + 
  ggtitle("Temperatures") +
  xlab("Months") +
  ylab("Temperatures") +
  geom_tile(aes(fill=Temp)) + 
  scale_fill_gradient2(low="blue",mid="purple",high = "red",midpoint = median(airquality$Temp),limits=range(airquality$Temp))
p3a

Plot 3b: Another try from Stackoverflow:

works better than the other tries

p3b<-airquality %>%
  ggplot(aes(Month,group=-Temp,fill=Temp))+
  geom_bar()+
  scale_fill_continuous(low="blue",high="red")
p3b

My GitHub account