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')

Comments

Post a Comment

Popular posts from this blog

Apriori

Image
# Data Preprocessing # install.packages('arules') library(arules) dataset = read.csv('Market_Basket_Optimisation.csv', header = FALSE) #sparce matrix dataset = read.transactions('Market_Basket_Optimisation.csv', sep = ',', rm.duplicates = TRUE) distribution of transactions with duplicates: 1  5  summary(dataset) transactions as itemMatrix in sparse format with  7501 rows (elements/itemsets/transactions) and  119 columns (items) and a density of 0.03288973  most frequent items: mineral water          eggs     spaghetti  french fries     chocolate       (Other)           1788          1348          1306          1282          1229         22405  element (itemset/transaction) length distribution: sizes    1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16   18   19   20  1754 1358 1044  816  667  493  391  324  259  139  102   67   40   22   17    4    1    2    1 
Read more

Decision Tree Classification

Image
# Importing the dataset dataset = read.csv('Social_Network_Ads.csv') dataset = dataset[3:5] # Encoding the target feature as factor dataset$Purchased = factor(dataset$Purchased, levels = c(0, 1)) # Splitting the dataset into the Training set and Test set # install.packages('caTools') library(caTools) set.seed(123) split = sample.split(dataset$Purchased, SplitRatio = 0.75) training_set = subset(dataset, split == TRUE) test_set = subset(dataset, split == FALSE) # Feature Scaling training_set[-3] = scale(training_set[-3]) test_set[-3] = scale(test_set[-3]) # Fitting Decision Tree Classification to the Training set # install.packages('rpart') library(rpart) classifier = rpart(formula = Purchased ~ .,                    data = training_set) # Predicting the Test set results y_pred = predict(classifier, newdata = test_set[-3], type = 'class') # Making the Confusion Matrix cm = table(test
Read more