library("clustrd") # Example 1 - Continuous case (Short-term macroeconomic scenario) data("macro", package = "clustrd") # Reduced K-means with 3 clusters and 2 dimensions (varimax rotation) outRKM <- cluspca(macro, 3, 2, method = "RKM", rotation = "varimax", seed = 1234) summary(outRKM) # Biplot plot(outRKM) # Scatterplot of object points plot(outRKM, what = c(TRUE, FALSE)) # Correlation circle of the variables lbl <- c("Gross Dom. Prod.", "Lead. Indicator", "Unempl. Rate", "Interest Rate", "Trade Balance", "Net Nat. Savings") plot(outRKM, what = c(FALSE, TRUE), attlabs = lbl) # Biplot and Parallel plot showing cluster means plot(outRKM, cludesc = TRUE) outRKM <- cluspca(macro, 3, 2, method = "RKM", rotation = "varimax", seed = 1234) # Example 2 - Categorical case (Contraceptive Choice in Indonesia) data("cmc", package = "clustrd") # Wife's age and number of children are categorized into three groups based on # quartiles cmc$W_AGE <- ordered(cut(cmc$W_AGE, c(16, 26, 39, 49), include.lowest = TRUE)) levels(cmc$W_AGE) <- c("16-26", "27-39", "40-49") cmc$NCHILD <- ordered(cut(cmc$NCHILD, c(0, 1, 4, 17), right = FALSE)) levels(cmc$NCHILD) <- c("0", "1-4", "5 and above") # Cluster correspondence analysis with 3 clusters and 2 dimensions (10 random # starts) outclusCA <- clusmca(cmc, 3, 2, nstart = 10, seed = 1234) summary(outclusCA) # Biplot and cluster description barplots showing the largest standardized # residuals per attribute for each cluster together with subplots with the full # residuals distribution plot(outclusCA, cludesc = TRUE, topstdres = 20, subplot = TRUE) # Tuning MCA K-means: selection of the appropriate number of clusters (from 3 to # 10) and dimensions (from 2 to 9) Cluster quality criterion: average Silhouette # width, Gower's distance on the original data (it takes a while...) bestMCAk <- tuneclus(cmc, 3:10, 2:9, method = "MCAk", criterion = "asw", dst = "full", nstart = 10, seed = 1234) bestMCAk