Homework3: Functions by MM

A short description of the post.

First, I loaded in the packages and files I needed.I am using the poultry data set for this project.

library(blogbuilder)
library(distill)
library(tidyverse)
poultry <- read.csv(file="../../_data/poultry_tidy.csv")
library(usethis)

I first used the functions select, filter, and arrange. I saved sumarize for when I ran the function group_by to highlight the function’s use. After those, I used rename, case_when, across, pivot_longer and wider, purrr, and lapply.

#Functions
#select, filter, arrange
poultry2 <- poultry %>% 
  select(Product, Year, Price_Dollar) %>% 
  filter(Product == "Whole") %>% 
  arrange(Product, Price_Dollar, Year)
head(poultry2)  

  Product Year Price_Dollar
1   Whole 2004      1.97500
2   Whole 2004      1.97500
3   Whole 2004      2.09000
4   Whole 2004      2.12000
5   Whole 2004      2.14500
6   Whole 2004      2.16375

head(poultry)

  Product Year    Month Price_Dollar
1   Whole 2013  January        2.385
2   Whole 2013 February        2.385
3   Whole 2013    March        2.385
4   Whole 2013    April        2.385
5   Whole 2013      May        2.385
6   Whole 2013     June        2.385

#Optional Functions
#group_by & summarize
poultry_grouped <- poultry2 %>% 
  group_by(Year)
summarise(poultry_grouped, Year = mean(Year))

# A tibble: 10 × 1
    Year
   <dbl>
 1  2004
 2  2005
 3  2006
 4  2007
 5  2008
 6  2009
 7  2010
 8  2011
 9  2012
10  2013

#rename
colnames(poultry2)

[1] "Product"      "Year"         "Price_Dollar"

poultry3 <- poultry2 %>%
  rename(Price=Price_Dollar)
#case_when  
mean(poultry3$Price)

[1] 2.305333

poultry4 <- poultry2 %>%
  mutate(Above.Below.Avg = case_when(Price_Dollar >= 2.305333 ~"Above Mean", TRUE ~ "Below Mean"))
#across
poultry5 <- poultry2 %>%
  group_by(Year) %>%
  summarise(across(starts_with("Price_Dollar"), list(mean = mean, sd = sd)))
#Pivoting
poultry_wider <- poultry %>% 
  pivot_wider(names_from = "Product",values_from = "Price_Dollar")
poultry_longer <- poultry_wider %>% 
  pivot_longer(Whole:Thighs, names_to = "Product", values_to = "Price_Dollar")
#purrr
library(stringr)
avg_fun <- function(x)
purrr::map_dbl(poultry3, n_distinct)
#lapply
poultry_upper <- lapply(poultry2$Product, toupper)
str(poultry_upper)

List of 120
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
 $ : chr "WHOLE"
  [list output truncated]

I decided to use ggplot to edify my knowledge of it. Here is the poultry’s Product variable’s price plotted by the month and year.

#plotting
ggplot(data = poultry, mapping = aes(x=Month, y = Price_Dollar, color = Product, group = Product))+ 
  geom_point()+ 
  geom_line() +
  facet_grid(~Year)