Customer clustering in R

prasoonkottarathil · web-flow · commit 453ac07e9103 · 2019-10-06T20:46:54.000+05:30
diff --git a/Customer in Mall clusterng/kmeans.R b/Customer in Mall clusterng/kmeans.R
@@ -0,0 +1,47 @@
+# K-Means Clustering
+
+# Importing the dataset
+dataset = read.csv('Mall_Customers.csv')
+dataset = dataset[4:5]
+
+# Splitting the dataset into the Training set and Test set
+# install.packages('caTools')
+# library(caTools)
+# set.seed(123)
+# split = sample.split(dataset$DependentVariable, SplitRatio = 0.8)
+# training_set = subset(dataset, split == TRUE)
+# test_set = subset(dataset, split == FALSE)
+
+# Feature Scaling
+# training_set = scale(training_set)
+# test_set = scale(test_set)
+
+# Using the elbow method to find the optimal number of clusters
+set.seed(6)
+wcss = vector()
+for (i in 1:10) wcss[i] = sum(kmeans(dataset, i)$withinss)
+plot(1:10,
+     wcss,
+     type = 'b',
+     main = paste('The Elbow Method'),
+     xlab = 'Number of clusters',
+     ylab = 'WCSS')
+
+# Fitting K-Means to the dataset
+set.seed(29)
+kmeans = kmeans(x = dataset, centers = 5)
+y_kmeans = kmeans$cluster
+
+# Visualising the clusters
+library(cluster)
+clusplot(dataset,
+         y_kmeans,
+         lines = 0,
+         shade = TRUE,
+         color = TRUE,
+         labels = 2,
+         plotchar = FALSE,
+         span = TRUE,
+         main = paste('Clusters of customers'),
+         xlab = 'Annual Income',
+         ylab = 'Spending Score')
