Penjelasan Data

Data ini merupakan data penjualan sepeda yang ada di berbagai Negara. Kita akan menganalisis penjualan yang dilakukan oleh Toko Sepeda. Terutama dari keuntungan, dan produk apa saja yang harus ditingkatkan.

Data diambil dari kaggle: https://www.kaggle.com/code/sadiqshah/bike-store-sales-in-europe/data

Import Library

Sebelum kita memulai analisis data mari kita masukkan library yang diperlukan

library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6     ✔ purrr   0.3.4
## ✔ tibble  3.1.7     ✔ dplyr   1.0.9
## ✔ tidyr   1.2.0     ✔ stringr 1.4.0
## ✔ readr   2.1.2     ✔ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
library(ggpubr)
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(glue)
library(plotly)
## 
## Attaching package: 'plotly'
## 
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## 
## The following object is masked from 'package:stats':
## 
##     filter
## 
## The following object is masked from 'package:graphics':
## 
##     layout
library(lubridate)
## 
## Attaching package: 'lubridate'
## 
## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union
library(dplyr)

Inspeksi Data

sales = read.csv("data_input/Sales.csv")
head(sales, 3)

Kita harus mengecek tipe data terlebih dahulu apakah tipe datanya sudah sesuai atau belum

glimpse(sales)
## Rows: 113,036
## Columns: 18
## $ Date             <chr> "2013-11-26", "2015-11-26", "2014-03-23", "2016-03-23…
## $ Day              <int> 26, 26, 23, 23, 15, 15, 22, 22, 22, 22, 30, 30, 15, 1…
## $ Month            <chr> "November", "November", "March", "March", "May", "May…
## $ Year             <int> 2013, 2015, 2014, 2016, 2014, 2016, 2014, 2016, 2014,…
## $ Customer_Age     <int> 19, 19, 49, 49, 47, 47, 47, 47, 35, 35, 32, 32, 34, 3…
## $ Age_Group        <chr> "Youth (<25)", "Youth (<25)", "Adults (35-64)", "Adul…
## $ Customer_Gender  <chr> "M", "M", "M", "M", "F", "F", "F", "F", "M", "M", "F"…
## $ Country          <chr> "Canada", "Canada", "Australia", "Australia", "Austra…
## $ State            <chr> "British Columbia", "British Columbia", "New South Wa…
## $ Product_Category <chr> "Accessories", "Accessories", "Accessories", "Accesso…
## $ Sub_Category     <chr> "Bike Racks", "Bike Racks", "Bike Racks", "Bike Racks…
## $ Product          <chr> "Hitch Rack - 4-Bike", "Hitch Rack - 4-Bike", "Hitch …
## $ Order_Quantity   <int> 8, 8, 23, 20, 4, 5, 4, 2, 22, 21, 8, 8, 7, 7, 5, 7, 2…
## $ Unit_Cost        <int> 45, 45, 45, 45, 45, 45, 45, 45, 45, 45, 45, 45, 45, 4…
## $ Unit_Price       <int> 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120…
## $ Profit           <int> 590, 590, 1366, 1188, 238, 297, 199, 100, 1096, 1046,…
## $ Cost             <int> 360, 360, 1035, 900, 180, 225, 180, 90, 990, 945, 360…
## $ Revenue          <int> 950, 950, 2401, 2088, 418, 522, 379, 190, 2086, 1991,…

Kita lihat dari tipe data diatas. terdapat tipe-tipe data yang harus kita ubah. sebagai contoh yang perlu kita ubah adalah :

  1. Age_Group -> Faktor
  2. Customer_Gender -> Faktor
  3. Country -> Faktor
  4. State -> Faktor
  5. Product_Category -> Faktor
  6. Sub_Category-> Faktor
  7. Product -> Faktor
  8. Date -> Date

Oleh karena itu kita perlu ubah dengan cara menggunakan fungsi as.factor dan menggunakan library dpylr dengan menggunakan fungsi mutate

sales_clean <- sales %>% 
  mutate(
    Age_Group = as.factor(Age_Group),
    Customer_Gender = as.factor(Customer_Gender),
    Country = as.factor(Country),
    State = as.factor(State),
    Product_Category = as.factor(Product_Category),
    Sub_Category = as.factor(Sub_Category),
    Product = as.factor(Product),
    Date  = ymd(Date)
  )

ayo kita mengecek kembali data yang telah kita ubah tipe datanya

glimpse(sales_clean)
## Rows: 113,036
## Columns: 18
## $ Date             <date> 2013-11-26, 2015-11-26, 2014-03-23, 2016-03-23, 2014…
## $ Day              <int> 26, 26, 23, 23, 15, 15, 22, 22, 22, 22, 30, 30, 15, 1…
## $ Month            <chr> "November", "November", "March", "March", "May", "May…
## $ Year             <int> 2013, 2015, 2014, 2016, 2014, 2016, 2014, 2016, 2014,…
## $ Customer_Age     <int> 19, 19, 49, 49, 47, 47, 47, 47, 35, 35, 32, 32, 34, 3…
## $ Age_Group        <fct> Youth (<25), Youth (<25), Adults (35-64), Adults (35-…
## $ Customer_Gender  <fct> M, M, M, M, F, F, F, F, M, M, F, F, M, M, M, M, M, M,…
## $ Country          <fct> Canada, Canada, Australia, Australia, Australia, Aust…
## $ State            <fct> British Columbia, British Columbia, New South Wales, …
## $ Product_Category <fct> Accessories, Accessories, Accessories, Accessories, A…
## $ Sub_Category     <fct> Bike Racks, Bike Racks, Bike Racks, Bike Racks, Bike …
## $ Product          <fct> "Hitch Rack - 4-Bike", "Hitch Rack - 4-Bike", "Hitch …
## $ Order_Quantity   <int> 8, 8, 23, 20, 4, 5, 4, 2, 22, 21, 8, 8, 7, 7, 5, 7, 2…
## $ Unit_Cost        <int> 45, 45, 45, 45, 45, 45, 45, 45, 45, 45, 45, 45, 45, 4…
## $ Unit_Price       <int> 120, 120, 120, 120, 120, 120, 120, 120, 120, 120, 120…
## $ Profit           <int> 590, 590, 1366, 1188, 238, 297, 199, 100, 1096, 1046,…
## $ Cost             <int> 360, 360, 1035, 900, 180, 225, 180, 90, 990, 945, 360…
## $ Revenue          <int> 950, 950, 2401, 2088, 418, 522, 379, 190, 2086, 1991,…

Selanjutnya kita akan mengecek apakah data kita memiliki missing value atau tidak

sales_clean %>% is.na() %>% colSums()
##             Date              Day            Month             Year 
##                0                0                0                0 
##     Customer_Age        Age_Group  Customer_Gender          Country 
##                0                0                0                0 
##            State Product_Category     Sub_Category          Product 
##                0                0                0                0 
##   Order_Quantity        Unit_Cost       Unit_Price           Profit 
##                0                0                0                0 
##             Cost          Revenue 
##                0                0

Data kita ternyata tidak memiliki missing value Mari kita melanjutkan di tahap exploratory

Data Explarotarory

Kita ingin mengetahui total profit yang dimiliki oleh tiap Negara

sales_clean %>% 
  group_by(Country) %>%
  summarise(Total_Profit = sum(Profit)) %>% 
  ungroup()

Kita ingin mengetahui berapa total Jenis produk yang terjual

sales_count <- sales_clean %>% 
  group_by(Product_Category) %>% 
  summarise(Jenis_Produk_Terjual = sum(Order_Quantity)) %>% 
  ungroup() %>%
  arrange(-Jenis_Produk_Terjual)
sales_count

Kita ingin mengetahui berapa total sub produk yang terjual

sales_count1 <- sales_clean %>% 
  filter(Product_Category=="Accessories") %>% 
  group_by(Sub_Category) %>% 
  summarise(Total_SubProduk_Terjual = sum(Order_Quantity)) %>% 
  ungroup() %>%
  arrange(-Total_SubProduk_Terjual)
sales_count1

Kita ingin mengetahui rata-rata profit yang diterima di negara amerika serikat berdasarkan Sub_Category

sales_10 <- sales_clean %>% 
  filter(Country == "United States") %>% 
  group_by(Sub_Category) %>% 
  summarise(mean_profit = mean(Profit)) %>% 
  ungroup() %>%
  arrange(-mean_profit) %>% 
  head(10)
sales_10

Kita ingin mengetahui rata-rata profit berdasarkan setiap tahunnya

sales_profit<- sales_clean %>% 
  group_by(Year) %>% 
  summarise(mean_profit = mean(Profit)) %>% 
  ungroup() %>%
  arrange(-mean_profit) %>% 
  head(10)
sales_profit

Selanjutnya mari kita visualisasikan

Data Visualisasi

plot1 <- ggplot(data = sales_count, aes(x = Jenis_Produk_Terjual, 
                              y = reorder(Product_Category, Jenis_Produk_Terjual))) + 
  geom_col(aes(fill = Jenis_Produk_Terjual)) +
  scale_fill_gradient(low="Blue", high="black") +
  labs(title = "PRODUCT CATEGORY",
       x = "Item Count",
       y = NULL) +
  theme_minimal() +
  theme(legend.position = "none") 
plot1

sales_profit<- sales_clean %>% 
      group_by(Year) %>% 
      summarise(mean_profit = mean(Profit)) %>% 
      ungroup() 
    
    sales_profit <- sales_profit %>% 
      mutate(
        label2 = glue(
        "Year: {Year}
        Average Profit: {comma(round(mean_profit, 2))}"
      ))
    label_rupiah <- label_dollar(prefix = "$ ", suffix = " M")
    plot1 <- ggplot(sales_profit, aes(x=Year, y= mean_profit))+
      geom_line(col="blue") +
      geom_point(aes(text=label2), col="black") +
      labs(
        title = "Average Profit",
        x = "Year",
        y = "Profit"
      ) +
      scale_y_continuous(labels = label_rupiah)+
      theme_minimal()
## Warning: Ignoring unknown aesthetics: text
    ggplotly(plot1, tooltip = "text")
sales_10 <- sales_clean %>% 
  filter(Country == "United States",
         Product_Category =='Bikes') %>% 
  group_by(Sub_Category) %>% 
  summarise(mean_profit = mean(Profit)) %>% 
  ungroup() %>%
  arrange(-mean_profit)

sales_10 <- sales_10 %>% 
  mutate(
    label = glue(
      "Sub Produk: {Sub_Category}
      Profit: {round(mean_profit, 2)}"
    ) 
  )
plot2 <- ggplot(sales_10, aes(x = reorder(Sub_Category, mean_profit), 
                    y = mean_profit,
                    text = label)) +
  geom_segment(aes(x=reorder(Sub_Category, mean_profit), xend=reorder(Sub_Category, mean_profit), y=0,yend=mean_profit), color="blue") +
  geom_point(aes(text = label),color="black") +
  coord_flip() +
  labs(title = "Items Sold",
       x = NULL,
       y = "Average Profit") +
  theme_minimal()
## Warning: Ignoring unknown aesthetics: text
ggplotly(plot2, tooltip = "text")
sales_count1 <- sales_clean %>% 
      filter(Product_Category=="Bikes") %>%
      group_by(Sub_Category) %>% 
      summarise(count=n()) %>% 
      ungroup() %>%
      arrange(-count)
    
    plot3 <- ggplot(data = sales_count1, aes(x = count, 
                                              y = reorder(Sub_Category, count))) +
      geom_col(aes(fill = count)) +
      scale_fill_gradient(low="blue", high="black") +
      labs(title = "Total Item Sold",
           x = "Item Count",
           y = NULL) +
      theme_minimal() +
      theme(legend.position = "none") 
    
    plot3

ShinyDashBoard