Data Import and Preparation
avocado <- read.csv(
"avocado.csv",
stringsAsFactors = FALSE
)
names(avocado) <- trimws(names(avocado))
head(avocado)
## date average_price total_volume type year geography
## 1 2017/12/3 1.39 139970 conventional 2017 Albany
## 2 2017/12/3 1.44 3577 organic 2017 Albany
## 3 2017/12/3 1.07 504933 conventional 2017 Atlanta
## 4 2017/12/3 1.62 10609 organic 2017 Atlanta
## 5 2017/12/3 1.43 658939 conventional 2017 Baltimore/Washington
## 6 2017/12/3 1.58 38754 organic 2017 Baltimore/Washington
## Mileage
## 1 2832
## 2 2832
## 3 2199
## 4 2199
## 5 2679
## 6 2679
str(avocado)
## 'data.frame': 12628 obs. of 7 variables:
## $ date : chr "2017/12/3" "2017/12/3" "2017/12/3" "2017/12/3" ...
## $ average_price: num 1.39 1.44 1.07 1.62 1.43 1.58 1.14 1.77 1.4 1.88 ...
## $ total_volume : int 139970 3577 504933 10609 658939 38754 86646 1829 488588 21338 ...
## $ type : chr "conventional" "organic" "conventional" "organic" ...
## $ year : int 2017 2017 2017 2017 2017 2017 2017 2017 2017 2017 ...
## $ geography : chr "Albany" "Albany" "Atlanta" "Atlanta" ...
## $ Mileage : int 2832 2832 2199 2199 2679 2679 827 827 2998 2998 ...
summary(avocado)
## date average_price total_volume type
## Length :12628 Min. :0.500 Min. : 253 Length :12628
## N.unique : 154 1st Qu.:1.100 1st Qu.: 15733 N.unique : 2
## N.blank : 0 Median :1.320 Median : 94806 N.blank : 0
## Min.nchar: 8 Mean :1.359 Mean : 325259 Min.nchar: 7
## Max.nchar: 10 3rd Qu.:1.570 3rd Qu.: 430222 Max.nchar: 12
## Max. :2.780 Max. :5660216
## year geography Mileage
## Min. :2017 Length :12628 Min. : 111
## 1st Qu.:2018 N.unique : 41 1st Qu.:1097
## Median :2019 N.blank : 0 Median :2193
## Mean :2019 Min.nchar: 5 Mean :1911
## 3rd Qu.:2020 Max.nchar: 20 3rd Qu.:2632
## Max. :2020 Max. :2998
Estimated Dollar Sales
avocado$dollar_sales <-
avocado$average_price * avocado$total_volume
head(avocado)
## date average_price total_volume type year geography
## 1 2017/12/3 1.39 139970 conventional 2017 Albany
## 2 2017/12/3 1.44 3577 organic 2017 Albany
## 3 2017/12/3 1.07 504933 conventional 2017 Atlanta
## 4 2017/12/3 1.62 10609 organic 2017 Atlanta
## 5 2017/12/3 1.43 658939 conventional 2017 Baltimore/Washington
## 6 2017/12/3 1.58 38754 organic 2017 Baltimore/Washington
## Mileage dollar_sales
## 1 2832 194558.30
## 2 2832 5150.88
## 3 2199 540278.31
## 4 2199 17186.58
## 5 2679 942282.77
## 6 2679 61231.32
Histogram of Average Prices
hist(
avocado$average_price,
main = "Histogram of Average Prices",
xlab = "Price in U.S. Dollars",
col = "lightblue",
border = "white"
)
ggplot(avocado, aes(x = average_price, fill = type)) +
geom_histogram(
bins = 30,
color = "white"
) +
scale_fill_manual(
values = c(
conventional = "steelblue",
organic = "darkgreen"
)
) +
labs(
title = "Average Price: Organic versus Conventional Avocados",
x = "Average Price",
y = "Number of Observations",
fill = "Avocado Type"
) +
theme_minimal()
Total Sales Volume by Geography
ggplot(
avocado,
aes(
x = reorder(geography, total_volume, FUN = sum),
y = total_volume,
fill = factor(year)
)
) +
geom_col() +
labs(
title = "Total Avocado Volume by Geography",
x = "Geography",
y = "Total Volume",
fill = "Year"
) +
theme_minimal() +
theme(
axis.text.x = element_text(
angle = 90,
vjust = 0.5,
hjust = 1,
size = 7
)
)
Question 1 Analysis: Price Range
price_range <- data.frame(
Lowest_Price = min(
avocado$average_price,
na.rm = TRUE
),
Highest_Price = max(
avocado$average_price,
na.rm = TRUE
)
)
price_range
## Lowest_Price Highest_Price
## 1 0.5 2.78
Question 2 Analysis: City Dollar Sales
city_sales <- avocado |>
filter(year %in% c(2017, 2018)) |>
group_by(year, type, geography) |>
summarise(
dollar_sales = sum(
dollar_sales,
na.rm = TRUE
),
total_volume = sum(
total_volume,
na.rm = TRUE
),
average_price = mean(
average_price,
na.rm = TRUE
),
.groups = "drop"
)
city_sales |>
arrange(
year,
type,
desc(dollar_sales)
)
## # A tibble: 164 × 6
## year type geography dollar_sales total_volume average_price
## <int> <chr> <chr> <dbl> <int> <dbl>
## 1 2017 conventional Los Angeles 13456647. 13753082 0.99
## 2 2017 conventional New York 9322034. 7198480 1.33
## 3 2017 conventional Chicago 5161767. 4186532 1.29
## 4 2017 conventional Houston 5125212. 6048049 0.862
## 5 2017 conventional San Francisco 5080416. 4502091 1.16
## 6 2017 conventional Dallas/Ft. Worth 4940102. 5748621 0.864
## 7 2017 conventional Baltimore/Washing… 4767953. 3702282 1.31
## 8 2017 conventional Denver 4212002. 3997494 1.07
## 9 2017 conventional Phoenix/Tucson 3817358. 5383359 0.712
## 10 2017 conventional Miami/Ft. Lauderd… 3732871. 3160387 1.20
## # ℹ 154 more rows
highest_city <- city_sales |>
group_by(year, type) |>
slice_max(
order_by = dollar_sales,
n = 1,
with_ties = FALSE
) |>
ungroup()
highest_city
## # A tibble: 4 × 6
## year type geography dollar_sales total_volume average_price
## <int> <chr> <chr> <dbl> <int> <dbl>
## 1 2017 conventional Los Angeles 13456647. 13753082 0.99
## 2 2017 organic New York 720451. 395248 1.82
## 3 2018 conventional Los Angeles 153526216. 145880803 1.07
## 4 2018 organic New York 9391204. 5312552 1.82
