Last active
January 2, 2022 17:08
-
-
Save thistleknot/b9f04cddc420cb253bc59cff02766a3f to your computer and use it in GitHub Desktop.
findKnee.R
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
findknee <- function(xdata) | |
{ | |
rate_of_change=(xdata[1]-xdata[length(xdata)])/(length(xdata)-1) | |
xdata$delta = xdata-xdata[length(xdata)] | |
xdata$deltas[1] = xdata$delta[1] | |
for (d in 2:length(xdata)) | |
{ | |
xdata$deltas[d]=xdata$deltas[d-1]-rate_of_change | |
} | |
for (d in 1:length(xdata)) | |
{ | |
xdata$deltas[d]=xdata$delta[d]-xdata$deltas[d] | |
} | |
return(abs(xdata$deltas)) | |
} | |
#library("factoextra") | |
#finds the convex or invex of any given curve by subtracting the min/max's linear plane and then finding the absolute max. | |
df <- read.csv(file="C:\\Users\\User\\Documents\\wiki\\wiki\\dev\\python\\python-ml\\data\\raw\\states.csv",text=readings, header = TRUE, sep = ",", dec = ".") | |
data <- df[,2:ncol(df)] | |
data_scaled <- scale(data) | |
#f_data <- fviz_nbclust(data_scaled, kmeans, method = "wss", k.max = 24) + theme_minimal() + ggtitle("the Elbow Method") | |
set.seed(31) | |
metric1 <- c() | |
metric2 <- c() | |
for (k in 1:15) | |
{#k=2 | |
#print(k) | |
km <- kmeans(data_scaled, nstart=100, centers=k) | |
metric1 <- c(metric1,km$betweenss) | |
metric2 <- c(metric2,sum(km$withinss)/length(km$withinss)) | |
} | |
plot(metric1) | |
plot(metric2) | |
knee1 = (findknee(metric1)) | |
knee1 = knee1[complete.cases(knee1)] | |
knee1 = knee1/max(knee1) | |
knee2 = (findknee(metric2)) | |
knee2 = knee2[complete.cases(knee2)] | |
knee2 = knee2/max(knee2) | |
print(which.max(knee1)) | |
print(which.max(knee2)) | |
plot(knee1) | |
lines(knee1) | |
lines(knee2) | |
optimal_k <- which.min(abs(knee1/knee2-1)) |
which(knee1/knee2==1)
[1] 4
print(which.max(knee1))
[1] 4
print(which.max(knee2))
[1] 4
def findknee(xdata):
rate_of_change=(xdata[0]-xdata[-1])/(len(xdata)-1)
#print(rate_of_change)
delta = xdata-xdata[-1]
deltas = []
deltas.append(delta[0])
for d in range(1,len(xdata)):
deltas.append(deltas[d-1]-rate_of_change)
#print(deltas)
for d in range(0,len(xdata)):
deltas[d]=delta[d]-deltas[d]
return(np.round(np.abs(deltas)))
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Idea behind it