Notes

[10/03, 2:02 PM] Sankhanil IT-4: # Get the data points in form of a R vector.
rainfall1 <- c(799,1174.8,865.1,1334.6,635.4,918.5,685.5,998.6,784.2,985,882.8,1071)
rainfall2 <-
c(655,1306.9,1323.4,1172.2,562.2,824,822.4,1265.5,799.6,1105.6,1106.7,1337.8)

# Convert them to a matrix.
combined.rainfall <- matrix(c(rainfall1,rainfall2),nrow = 12)

# Convert it to a time series object.
rainfall.timeseries <- ts(combined.rainfall,start = c(2012,1),frequency = 12)

# Print the timeseries data.
print(rainfall.timeseries)

# Give the chart file a name.
png(file = "rainfall_combined.png")

# Plot a graph of the time series.
plot(rainfall.timeseries, main = "Multiple Time Series")

# Save the file.
dev.off()
[10/03, 2:02 PM] Sankhanil IT-4: install.packages(c("cluster", "factoextra"))
library(factoextra)
library(cluster)
#load data
df <- USArrests

#remove rows with missing values
df <- na.omit(df)

#scale each variable to have a mean of 0 and sd of 1
df <- scale(df)

#view first six rows of dataset
head(df)
fviz_nbclust(df, pam, method = "wss")
#calculate gap statistic based on number of clusters
gap_stat <- clusGap(df,
FUN = pam,
K.max = 10, #max clusters to consider
B = 50) #total bootstrapped iterations

#plot number of clusters vs. gap statistic
fviz_gap_stat(gap_stat)
set.seed(1)

#perform k-medoids clustering with k = 4 clusters
kmed <- pam(df, k = 4)
kmed
fviz_cluster(kmed, data = df)
#add cluster assignment to original data
final_data <- cbind(USArrests, cluster = kmed$cluster)

#view final data
head(final_data)