Customer Purchase Data: Exploratory Analysis
Animesh Kumar
2024-04-24
library(readr)
library(tidyr)
library(tidyverse)## Warning: package 'ggplot2' was built under R version 4.3.3## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ purrr 1.0.2
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.0 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3
## ── 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 errorslibrary(ggplot2)
library(dplyr)
library(GGally)## Warning: package 'GGally' was built under R version 4.3.3## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2library(corrplot)## Warning: package 'corrplot' was built under R version 4.3.3## corrplot 0.92 loadedlibrary(ggpubr)## Warning: package 'ggpubr' was built under R version 4.3.3library(gridExtra)## Warning: package 'gridExtra' was built under R version 4.3.3##
## Attaching package: 'gridExtra'
##
## The following object is masked from 'package:dplyr':
##
## combinecustomer_data <- read_csv("C:/Users/hp/OneDrive/Desktop/customer_data.csv")## Rows: 16590 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (6): gender, education, region, loyalty_status, purchase_frequency, prod...
## dbl (6): id, age, income, purchase_amount, promotion_usage, satisfaction_score
##
## 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.Exploratory Analysis
Q1-Sorting the data as per the region and Gender
sortdata<-customer_data %>% arrange(region)
REGION<-sortdata %>% group_by(region) %>% summarise(count=n())
# Filtering TOTAL NUMBERS OF MALES
Males<-sortdata %>%filter(gender=="Male")
# Filtering TOTAL NUMBERS OF FEMALES
Females<-sortdata %>% filter(gender=="Female")Q2-Find the Average Purchase amount of each group based on their occupation
sortdata %>% group_by(education) %>% summarise("average"=mean(purchase_amount))## # A tibble: 4 × 2
## education average
## <chr> <dbl>
## 1 Bachelor 9733.
## 2 College 9674.
## 3 HighSchool 9526.
## 4 Masters 9526.Q3- Find the Variation in the Education Level among the students
sortdata %>% group_by(education) %>% summarise("Count"=n())## # A tibble: 4 × 2
## education Count
## <chr> <int>
## 1 Bachelor 4974
## 2 College 6545
## 3 HighSchool 3395
## 4 Masters 1676Q4-Grouping and Counting the Customers based on their region and finding the reason with the max number of customers
regmax<-sortdata %>% group_by(region) %>% summarise("Count"=n())
data.frame(regmax) %>% filter(Count==max(Count))## region Count
## 1 West 5038Visualisation
Q5-Visualization of the category of products which are purchased by each gender
ggplot(sortdata,aes(x=gender,fill=product_category))+geom_bar()+
labs(title = "Products purchased by Gender",xlab="Gender",ylab="Count")
Q6- What is the Average purchase amount per education category
avg_edu<-sortdata %>% group_by(education) %>%
summarise("Average"=mean(purchase_amount,na.rm = TRUE))
avg_edu<-data.frame(avg_edu)
ggplot(avg_edu, aes(x = education, y = Average)) +
geom_bar(stat = "identity", fill = "skyblue") +
labs(title = "Average Education", x = "Education Level", y = "Average Amount") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Q7- What is the Purchasing range of the customers based on status
ggplot(data =sortdata,aes(y=education,fill=loyalty_status)) +
geom_bar()+labs(title = "Loyalty meter",y="Count")
Q8- How many of frequent Purchases by people in all the regions
frequentin_region<-customer_data%>%filter(region=="West" |region=="North" |region=="South" |
region=="East",purchase_frequency=="frequent")
ggplot(data=frequentin_region,aes(y=region,fill=factor(education)))+geom_bar()+
labs(title="Frequent Purchasing bar ",x="Total Orders",y="Regions")
Q9- What is the Purchase frequency that are done by regions
ggplot(data=customer_data,aes(y=region,fill=purchase_frequency))+geom_bar()+
labs(title="Purchase frequency accross Regions",x="Total Orders",y="Regions")
Q10- How many Purchase that are done by regions based on education level
ggplot(data=sortdata,aes(y=region,fill=factor(education)))+geom_bar()+
labs(title="Purchasing bar ",x="Total Orders",y="Regions")
Q11- What is the loyalty status of people accross different purchase frequencies
ggplot(data =sortdata,aes(y=purchase_frequency,fill=loyalty_status)) +
geom_bar()+labs(title = "Loyalty meter",y="Frequent")
Q12- What is the distribution of education level
tab<-table(sortdata$education)
colr<-c("Bachelor","HighSchool","Masters","College")
pct <- round(tab/sum(tab)*100)
pie(tab,
main = "Education Distribution",
labels=paste(colr,paste(pct,"%",sep = " "),sep=" "),
col=rainbow(length(colr)))
Q13- What is the total distribution of Products
PRO<-table(sortdata$product_category)
colr<-c("Books","clothing","Electronics","Health","Food")
pct <- round(PRO/sum(PRO)*100)
pie(PRO,
main = "Product Distribution",
labels=paste(colr,paste(pct,"%",sep = " "),sep=" "),
col=rainbow(length(colr)))
Q14-Visualization of how much most of the customers spend on purchase
meanpur<-sortdata %>% summarise("avg"=mean(purchase_amount))
ggplot(data=sortdata,aes(x=(purchase_amount)))+geom_histogram(color="white",fill="blue")+
geom_vline(aes(xintercept=meanpur$avg,color="red",linewidth=0.01))+
labs(title = "Purchase amount ",x="Income")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Q15-Check if higher income relates to higher spending on purchases
cor.test(sortdata$income,sortdata$purchase_amount)##
## Pearson's product-moment correlation
##
## data: sortdata$income and sortdata$purchase_amount
## t = 380.48, df = 16588, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.9456159 0.9487454
## sample estimates:
## cor
## 0.9472032ggscatter(sortdata,
x="income",
y="purchase_amount",
cor.coef=TRUE,
conf.int=TRUE,
add="reg.line",
cor.method="pearson",
xlab="Income",
ylab="Purchase Amount")
Q16- Bar Graph depicting the product categories as per the region
ggplot(data=sortdata,aes(x=region,fill=product_category))+geom_bar()+
labs(title="Product categories as per the regions",
x="Region")
Q17- Corrplot of correlation between the purchase_amount,promotion_usage,satisfaction_score
cor_akt<-sortdata %>% select(income,purchase_amount)
cus_cor_plot2<-cor(cor_akt)
corrplot(cus_cor_plot2)
Q18 Summary of the Dataset
summary(sortdata)## id age gender income
## Min. : 1 Min. :13 Length:16590 Min. : 5000
## 1st Qu.: 4148 1st Qu.:27 Class :character 1st Qu.:16303
## Median : 8296 Median :30 Mode :character Median :27694
## Mean : 8296 Mean :30 Mean :27580
## 3rd Qu.:12443 3rd Qu.:33 3rd Qu.:38995
## Max. :16590 Max. :47 Max. :49994
## education region loyalty_status purchase_frequency
## Length:16590 Length:16590 Length:16590 Length:16590
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## purchase_amount product_category promotion_usage satisfaction_score
## Min. : 1118 Length:16590 Min. :0.0000 Min. :1.000
## 1st Qu.: 5608 Class :character 1st Qu.:0.0000 1st Qu.:4.000
## Median : 9500 Mode :character Median :0.0000 Median :5.000
## Mean : 9647 Mean :0.2991 Mean :4.999
## 3rd Qu.:13346 3rd Qu.:1.0000 3rd Qu.:6.000
## Max. :24147 Max. :1.0000 Max. :9.000