Last active
May 7, 2023 13:01
-
-
Save MSHelm/aed5635263a0ec05feebfae8b01b13c2 to your computer and use it in GitHub Desktop.
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
| my_kmeans <- function(data, k, n_iterations) { | |
| # Helper function for euclidean distance | |
| euclidean_distance <- function(p1, p2) { | |
| dist <- sqrt(sum((p1-p2)^2)) | |
| return(dist) | |
| } | |
| # Initialize centers randomly | |
| centers <- df[sample(nrow(df), k, replace = FALSE), ] | |
| # Perform n iterations | |
| iteration <- 1 | |
| while(iteration < n_iterations) { | |
| # Calculate distance of each point to each center | |
| distances <- matrix(Inf, nrow = nrow(df), ncol = k) | |
| for (i in seq_len(nrow(df))) { | |
| for (j in seq_len(k)) { | |
| distances[i, j] <- euclidean_distance(df[i, ], centers[j, ]) | |
| } | |
| } | |
| # Assign each point to the closest center | |
| cluster_id <- apply(distances, 1, which.min) | |
| # Calculate new centers | |
| for (i in seq_len(k)) { | |
| this_cluster <- df[cluster_id == i,] | |
| centers[k, ] <- colMeans(this_cluster) | |
| } | |
| iteration <- iteration + 1 | |
| } | |
| cluster_id | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment