#Remember to install packages before loading them with library()

library(tidyverse) ## A set of tools for Data manipulation and visualization
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.2     ✔ 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) ## for date time manipulation
library(scales) ## Formatting numbers and values
## 
## Attaching package: 'scales'
## 
## The following object is masked from 'package:purrr':
## 
##     discard
## 
## The following object is masked from 'package:readr':
## 
##     col_factor
#library(hrbrthemes)# For changing ggplot theme
library(extrafont) # More font options
## Registering fonts with R

#Q1 - view data

sales <- read.csv("sales.csv")

glimpse(sales)
## Rows: 1,000
## Columns: 17
## $ Invoice.ID              <chr> "750-67-8428", "226-31-3081", "631-41-3108", "…
## $ Branch                  <chr> "A", "C", "A", "A", "A", "C", "A", "C", "A", "…
## $ City                    <chr> "Yangon", "Naypyitaw", "Yangon", "Yangon", "Ya…
## $ Customer.type           <chr> "Member", "Normal", "Normal", "Member", "Norma…
## $ Gender                  <chr> "Female", "Female", "Male", "Male", "Male", "M…
## $ Product.line            <chr> "Health and beauty", "Electronic accessories",…
## $ Unit.price              <dbl> 74.69, 15.28, 46.33, 58.22, 86.31, 85.39, 68.8…
## $ Quantity                <int> 7, 5, 7, 8, 7, 7, 6, 10, 2, 3, 4, 4, 5, 10, 10…
## $ Tax.5.                  <dbl> 26.1415, 3.8200, 16.2155, 23.2880, 30.2085, 29…
## $ Total                   <dbl> 548.9715, 80.2200, 340.5255, 489.0480, 634.378…
## $ Date                    <chr> "1/5/2019", "3/8/2019", "3/3/2019", "1/27/2019…
## $ Time                    <chr> "13:08", "10:29", "13:23", "20:33", "10:37", "…
## $ Payment                 <chr> "Ewallet", "Cash", "Credit card", "Ewallet", "…
## $ cogs                    <dbl> 522.83, 76.40, 324.31, 465.76, 604.17, 597.73,…
## $ gross.margin.percentage <dbl> 4.761905, 4.761905, 4.761905, 4.761905, 4.7619…
## $ gross.income            <dbl> 26.1415, 3.8200, 16.2155, 23.2880, 30.2085, 29…
## $ Rating                  <dbl> 9.1, 9.6, 7.4, 8.4, 5.3, 4.1, 5.8, 8.0, 7.2, 5…

3 new columns

sales <- sales %>% 
  mutate(time=as.integer(substr(Time, 1, 2)),
         date=mdy(Date),weekday = wday(date,label = TRUE))

Learn about ungroup %>% ungroup summarise(Total_Sales = sum(Total), .groups = “drop”)

df2 <- sales %>% 
  group_by(City, weekday) %>%
  summarise(Total_Sales = sum(Total))
## `summarise()` has grouped output by 'City'. You can override using the
## `.groups` argument.
head(df2)
## # A tibble: 6 × 3
## # Groups:   City [1]
##   City     weekday Total_Sales
##   <chr>    <ord>         <dbl>
## 1 Mandalay Sun          10415.
## 2 Mandalay Mon          12735.
## 3 Mandalay Tue          18859.
## 4 Mandalay Wed          12708.
## 5 Mandalay Thu          15779.
## 6 Mandalay Fri          14418.
df2 %>% mutate(percent = Total_Sales / sum(Total_Sales))
## # A tibble: 21 × 4
## # Groups:   City [3]
##    City      weekday Total_Sales percent
##    <chr>     <ord>         <dbl>   <dbl>
##  1 Mandalay  Sun          10415.  0.0981
##  2 Mandalay  Mon          12735.  0.120 
##  3 Mandalay  Tue          18859.  0.178 
##  4 Mandalay  Wed          12708.  0.120 
##  5 Mandalay  Thu          15779.  0.149 
##  6 Mandalay  Fri          14418.  0.136 
##  7 Mandalay  Sat          21284.  0.200 
##  8 Naypyitaw Sun          17036.  0.154 
##  9 Naypyitaw Mon          10925.  0.0988
## 10 Naypyitaw Tue          17668.  0.160 
## # ℹ 11 more rows
df2 %>% 
  ungroup() %>%
  mutate(percent = Total_Sales / sum(Total_Sales))
## # A tibble: 21 × 4
##    City      weekday Total_Sales percent
##    <chr>     <ord>         <dbl>   <dbl>
##  1 Mandalay  Sun          10415.  0.0322
##  2 Mandalay  Mon          12735.  0.0394
##  3 Mandalay  Tue          18859.  0.0584
##  4 Mandalay  Wed          12708.  0.0393
##  5 Mandalay  Thu          15779.  0.0489
##  6 Mandalay  Fri          14418.  0.0446
##  7 Mandalay  Sat          21284.  0.0659
##  8 Naypyitaw Sun          17036.  0.0527
##  9 Naypyitaw Mon          10925.  0.0338
## 10 Naypyitaw Tue          17668.  0.0547
## # ℹ 11 more rows

#Q3 - create and visualize a summary by weekday

sales_by_day <- sales %>% group_by(weekday) %>%
  summarise(Total_Sales=sum(Total))  %>% ungroup

sales_by_day %>% 
  ggplot(aes(reorder(weekday,Total_Sales),Total_Sales,fill=weekday))+
  geom_col(show.legend = FALSE,color="black")+
  geom_text(aes(label=comma(Total_Sales)),size=3,hjust=1,color="black")+
  scale_fill_brewer(palette = "Paired")+
  coord_flip()+
  theme_classic()+
  labs(title = "Total Sales breakdown by Weekday",x="Day of the week",y= "Total sales")

#Q4 - create and visualize a summary by weekday and time

sales_by_day_hour <- sales %>% group_by(weekday,time) %>%
  summarise(Total_Sales=sum(Total)) %>% ungroup()
## `summarise()` has grouped output by 'weekday'. You can override using the
## `.groups` argument.
sales_by_day_hour %>% 
  ggplot(aes(time,Total_Sales,fill=weekday))+
  geom_col(show.legend = FALSE,color="black")+
  scale_fill_brewer(palette = "Paired")+
  facet_wrap(~weekday,scales="free_y")+
  coord_flip()+
  theme_classic()+
  labs(title = "Total Sales breakdown by Weekday and Time",x="Hour of the day",y= "Total sales")