library(tidyverse)
## ── 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 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── 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(ggplot2)
data <- read.csv("C:\\Users\\HP_VICTUS\\OneDrive\\Desktop\\Mall_Customers.csv")
str(data)
## 'data.frame': 200 obs. of 5 variables:
## $ CustomerID : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Gender : chr "Male" "Male" "Female" "Female" ...
## $ Age : int 19 21 20 23 31 22 35 23 64 30 ...
## $ Annual.Income..k.. : int 15 15 16 16 17 17 18 18 19 19 ...
## $ Spending.Score..1.100.: int 39 81 6 77 40 76 6 94 3 72 ...
summary(data)
## CustomerID Gender Age Annual.Income..k..
## Min. : 1.00 Length:200 Min. :18.00 Min. : 15.00
## 1st Qu.: 50.75 Class :character 1st Qu.:28.75 1st Qu.: 41.50
## Median :100.50 Mode :character Median :36.00 Median : 61.50
## Mean :100.50 Mean :38.85 Mean : 60.56
## 3rd Qu.:150.25 3rd Qu.:49.00 3rd Qu.: 78.00
## Max. :200.00 Max. :70.00 Max. :137.00
## Spending.Score..1.100.
## Min. : 1.00
## 1st Qu.:34.75
## Median :50.00
## Mean :50.20
## 3rd Qu.:73.00
## Max. :99.00
head(data)
## CustomerID Gender Age Annual.Income..k.. Spending.Score..1.100.
## 1 1 Male 19 15 39
## 2 2 Male 21 15 81
## 3 3 Female 20 16 6
## 4 4 Female 23 16 77
## 5 5 Female 31 17 40
## 6 6 Female 22 17 76
sum(is.na(data))
## [1] 0
data$Gender <- as.factor(data$Gender)
gender_plot <- ggplot(data, aes(x = Gender)) +
geom_bar(fill = "steelblue") +
theme_minimal() +
labs(title = "Gender Distribution")
age_plot <- ggplot(data, aes(x = Age)) +
geom_histogram(bins = 20, fill = "skyblue", color = "black") +
theme_minimal() +
labs(title = "Age Distribution", x = "Age", y = "Frequency")
income_plot <- ggplot(data, aes(x = Annual.Income..k..)) +
geom_histogram(bins = 20, fill = "lightgreen", color = "black") +
theme_minimal() +
labs(title = "Annual Income Distribution", x = "Annual Income (k$)", y = "Frequency")
spending_plot <- ggplot(data, aes(x = Spending.Score..1.100.)) +
geom_histogram(bins = 20, fill = "lightcoral", color = "black") +
theme_minimal() +
labs(title = "Spending Score Distribution", x = "Spending Score (1-100)", y = "Frequency")
print(gender_plot)
print(age_plot)
print(income_plot)
print(spending_plot)
age_spending_plot <- ggplot(data, aes(x = Age, y = Spending.Score..1.100.)) +
geom_point(color = "blue") +
theme_minimal() +
labs(title = "Age vs Spending Score", x = "Age", y = "Spending Score")
income_spending_plot <- ggplot(data, aes(x = Annual.Income..k.., y = Spending.Score..1.100.)) +
geom_point(color = "purple") +
theme_minimal() +
labs(title = "Annual Income vs Spending Score", x = "Annual Income (k$)", y = "Spending Score")
print(age_spending_plot)
print(income_spending_plot)
numeric_data <- data %>% select(Age, Annual.Income..k.., Spending.Score..1.100.)
cor_matrix <- cor(numeric_data)
print("Correlation Matrix:")
## [1] "Correlation Matrix:"
print(cor_matrix)
## Age Annual.Income..k.. Spending.Score..1.100.
## Age 1.00000000 -0.012398043 -0.327226846
## Annual.Income..k.. -0.01239804 1.000000000 0.009902848
## Spending.Score..1.100. -0.32722685 0.009902848 1.000000000
set.seed(123)
kmeans_result <- kmeans(numeric_data, centers = 3)
data$Cluster <- as.factor(kmeans_result$cluster)
cluster_plot <- ggplot(data, aes(x = Annual.Income..k.., y = Spending.Score..1.100., color = Cluster)) +
geom_point() +
theme_minimal() +
labs(title = "Customer Segmentation (K-Means Clustering)", x = "Annual Income (k$)", y = "Spending Score")
print(cluster_plot)
