week13salesdata

Load Packages

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.1     ✔ stringr   1.5.2
## ✔ ggplot2   4.0.0     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── 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(lubridate)
library(scales)

## 
## Attaching package: 'scales'
## 
## The following object is masked from 'package:purrr':
## 
##     discard
## 
## The following object is masked from 'package:readr':
## 
##     col_factor

library(extrafont)

## Warning: package 'extrafont' was built under R version 4.5.2

## Registering fonts with R

Load Data

sales <- read.csv("C:/Users/rmora/Downloads/sales.csv")

Create Datetime + Hour Column

sales$datetime <- as.POSIXct(
  paste(sales$Date, sales$Time),
  format = "%m/%d/%Y %H:%M"
)

sales$hour <- as.numeric(format(sales$datetime, "%H"))

🔹 GGPLOT 1: Total Sales by Weekday

library(ggplot2)
library(dplyr)

sales$weekday <- factor(
  weekdays(as.Date(sales$datetime)),
  levels = c("Monday","Tuesday","Wednesday","Thursday","Friday","Saturday","Sunday")
)

weekday_summary <- sales %>%
  group_by(weekday) %>%
  summarise(Total = sum(Total)) %>%
  arrange(Total)

ggplot(weekday_summary, aes(x = Total, y = weekday, fill = weekday)) +
  geom_col() +
  geom_text(aes(label = scales::comma(Total)),
            hjust = -0.1, size = 4, fontface = "bold") +
  scale_fill_brewer(palette = "Set3") +
  labs(title = "Total Sales Breakdown by Weekday",
       x = "Total Sales", y = "Day of the Week") +
  theme_minimal(base_size = 14) +
  theme(legend.position = "none") +
  xlim(0, max(weekday_summary$Total) * 1.15)

🔹 GGPLOT 2: Total Sales by Hour

hour_summary <- sales %>%
  group_by(hour) %>%
  summarise(Total = sum(Total)) %>%
  arrange(hour)

ggplot(hour_summary, aes(x = Total, y = factor(hour), fill = hour)) +
  geom_col() +
  geom_text(aes(label = scales::comma(Total)),
            hjust = -0.1, size = 3.5, fontface = "bold") +
  scale_fill_gradientn(colors = rainbow(24)) +
  labs(title = "Total Sales Breakdown by Hour",
       x = "Total Sales", y = "Hour of Day") +
  theme_minimal(base_size = 14) +
  theme(legend.position = "none") +
  xlim(0, max(hour_summary$Total) * 1.15)

🔹 GGPLOT 3: Average Rating by Hour

rating_hour <- sales %>%
  group_by(hour) %>%
  summarise(AverageRating = mean(Rating)) %>%
  arrange(hour)

ggplot(rating_hour, aes(x = factor(hour), y = AverageRating, fill = AverageRating)) +
  geom_col() +
  geom_text(aes(label = round(AverageRating, 2)),
            vjust = -0.3, size = 4, fontface = "bold") +
  scale_fill_gradientn(colors = rainbow(7)) +
  labs(title = "Average Customer Rating by Hour",
       x = "Hour of Day", y = "Average Rating") +
  ylim(0, max(rating_hour$AverageRating) + 0.8) +
  theme_minimal(base_size = 14) +
  theme(legend.position = "none")