Avocados

Questions:

1. In which cities can millenials have their avocado toast AND buy a home?

2. Was the Avocadopocalypse of 2017 real?

Some relevant columns in the dataset:

1. Date - The date of the observation
2. AveragePrice - the average price of a single avocado
3. type - conventional or organic
4. year - the year
5. Region - the city or region of the observation
6. Total Volume - Total number of avocados sold
7. 4046 - Total number of avocados with PLU 4046 sold
8. 4225 - Total number of avocados with PLU 4225 sold
9. 4770 - Total number of avocados with PLU 4770 sold

Import libraries

# Import libraries
library(tidyverse)
library(gridExtra)
library(lubridate)

Data import and column casting

# Import dataset
avocados <- read_csv("./data/avocado.csv", col_names = TRUE)

Missing column names filled in: 'X1' [1]Parsed with column specification:
cols(
  X1 = col_integer(),
  Date = col_date(format = ""),
  AveragePrice = col_double(),
  `Total Volume` = col_double(),
  `4046` = col_double(),
  `4225` = col_double(),
  `4770` = col_double(),
  `Total Bags` = col_double(),
  `Small Bags` = col_double(),
  `Large Bags` = col_double(),
  `XLarge Bags` = col_double(),
  type = col_character(),
  year = col_integer(),
  region = col_character()
)

# Convert date column to ymd format
avocados$Date <- ymd(avocados$Date)
# Strip spaces from column names
colnames(avocados) <- tolower(
    gsub(" ", "",
        colnames(avocados)))

Average price of avocados per year

# Select average price and group by year
# Remove above 99th percentile of average price
avg_avocados <- avocados %>%
  select(averageprice,year) %>%
  group_by(year) %>%
  filter(averageprice < quantile(averageprice, 0.99))
# Box plot of average avocado price per year
avg_avocado_box <- ggplot(avg_avocados, aes(factor(year), averageprice)) + geom_boxplot(aes(fill = factor(year)), width = 0.75) + labs(title="Average Price of Avocados Per Year", x="Year", y="Price ($)") + scale_fill_brewer(palette="Greens")
print(avg_avocado_box)

Compare organic to conventional avocados

# Group avocado average prices by organic or conventional
# Remove above 95th percentile
av_types <- avocados %>%
  select(averageprice,type) %>%
  group_by(type) %>%
  filter(averageprice < quantile(averageprice, 0.95))
# Box plot 
type_avocado_box <- ggplot(av_types, aes(factor(type), averageprice)) + geom_boxplot(aes(fill = factor(type)), width = 0.5, outlier.colour = "#006600", outlier.size = 1, outlier.shape = 10, outlier.stroke = 2) + labs(title="Average Price of Avocados: Organic vs Conventional", x="Type", y="Price ($)") + scale_fill_brewer(palette="Greens")
print(type_avocado_box)

Average price of avocados per region

sorted <- avocados %>% 
  group_by(region) %>%
  mutate(avgvolume = mean(totalvolume))
plot <- ggplot(data=sorted, aes(x=reorder(as.factor(region), -avgvolume), y=averageprice)) +
  geom_point(aes(color=month(date), alpha=0.1, size=totalvolume)) +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  guides(size = "none") +
  guides(alpha = "none")
print(plot)