# Load required libraries
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.5.2
## Warning: package 'ggplot2' was built under R version 4.5.2
## Warning: package 'tibble' was built under R version 4.5.2
## Warning: package 'tidyr' was built under R version 4.5.2
## Warning: package 'readr' was built under R version 4.5.2
## Warning: package 'purrr' was built under R version 4.5.2
## Warning: package 'dplyr' was built under R version 4.5.2
## Warning: package 'stringr' was built under R version 4.5.2
## Warning: package 'forcats' was built under R version 4.5.2
## Warning: package 'lubridate' was built under R version 4.5.2
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.6
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.1 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.2.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(tidyquant)
## Warning: package 'tidyquant' was built under R version 4.5.2
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
## Warning: package 'xts' was built under R version 4.5.2
## Warning: package 'zoo' was built under R version 4.5.2
## Warning: package 'quantmod' was built under R version 4.5.2
## Warning: package 'TTR' was built under R version 4.5.2
## Warning: package 'PerformanceAnalytics' was built under R version 4.5.2
## ── Attaching core tidyquant packages ─────────────────────── tidyquant 1.0.11 ──
## ✔ PerformanceAnalytics 2.0.8 ✔ TTR 0.24.4
## ✔ quantmod 0.4.28 ✔ xts 0.14.1
## ── Conflicts ────────────────────────────────────────── tidyquant_conflicts() ──
## ✖ zoo::as.Date() masks base::as.Date()
## ✖ zoo::as.Date.numeric() masks base::as.Date.numeric()
## ✖ dplyr::filter() masks stats::filter()
## ✖ xts::first() masks dplyr::first()
## ✖ dplyr::lag() masks stats::lag()
## ✖ xts::last() masks dplyr::last()
## ✖ PerformanceAnalytics::legend() masks graphics::legend()
## ✖ quantmod::summary() masks base::summary()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(lubridate)
# Read the data from CSV file
bike_orderlines_wrangled_tbl <- read_csv("C:/Users/user/Downloads/bike_orderlines.csv")
## Rows: 15644 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): model, category_1, category_2, frame_material, bikeshop_name, city...
## dbl (5): order_id, order_line, quantity, price, total_price
## dttm (1): order_date
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
# Fix column names (replace dots with underscores)
names(bike_orderlines_wrangled_tbl) <- names(bike_orderlines_wrangled_tbl) %>%
str_replace_all("\\.", "_")
# Prepare data for faceted time series plot
sales_by_category2_time <- bike_orderlines_wrangled_tbl %>%
select(order_date, category_2, total_price) %>%
mutate(order_date = ymd(order_date)) %>%
mutate(year_month = floor_date(order_date, unit = "month")) %>%
group_by(year_month, category_2) %>%
summarise(sales = sum(total_price), .groups = 'drop')
# Create the faceted plot
sales_by_category2_time %>%
ggplot(aes(x = year_month, y = sales, color = category_2)) +
# Add points and lines
geom_point(size = 2) +
geom_line(linewidth = 1) +
# Facet by category_2
facet_wrap(~ category_2, scales = "free_y", ncol = 3) +
# Format y-axis
scale_y_continuous(labels = scales::dollar_format(scale = 1e-6, suffix = "M")) +
# Format x-axis to show years
scale_x_date(date_breaks = "1 year", date_labels = "%Y") +
# Apply theme
theme_tq() +
theme(
axis.text.x = element_text(angle = 0, hjust = 0.5),
legend.position = "none",
strip.background = element_rect(fill = "#2c3e50"),
strip.text = element_text(color = "white", face = "bold", size = 10),
panel.spacing = unit(1, "lines")
) +
# Labels
labs(
title = "Sales Trends by Product Category (2011-2015)",
subtitle = "Monthly sales across different bike categories",
x = "order_date",
y = "sales",
caption = "Sales analysis by secondary product category"
)
# Alternative: Show all categories in one color scheme
sales_by_category2_time %>%
# Create color palette for each category
mutate(category_2 = factor(category_2)) %>%
ggplot(aes(x = year_month, y = sales)) +
geom_point(aes(color = category_2), size = 1.5, show.legend = FALSE) +
geom_line(aes(color = category_2), linewidth = 0.8, show.legend = FALSE) +
facet_wrap(~ category_2, scales = "free_y", ncol = 3) +
scale_y_continuous(labels = scales::dollar_format(scale = 1e-6, suffix = "M")) +
scale_x_date(date_breaks = "1 year", date_labels = "%Y") +
scale_color_manual(values = c(
"Cross Country Race" = "#2C3E50",
"Cyclocross" = "#E31A1C",
"Elite Road" = "#FF7F00",
"Endurance Road" = "#CAB2D6",
"Fat Bike" = "#FB9A99",
"Over Mountain" = "#A6CEE3",
"Sport" = "#B2DF8A",
"Triathalon" = "#1F78B4",
"Trail" = "#33A02C"
)) +
theme_minimal() +
theme(
axis.text.x = element_text(angle = 0, hjust = 0.5, size = 8),
strip.background = element_rect(fill = "#34495e", color = NA),
strip.text = element_text(color = "white", face = "bold", size = 9),
panel.grid.minor = element_blank(),
panel.spacing = unit(1.2, "lines"),
plot.title = element_text(face = "bold", size = 14),
plot.subtitle = element_text(size = 10, color = "gray40")
) +
labs(
title = "Sales Trends by Product Category",
x = "order_date",
y = "sales"
)
