transfer from old repo

2 Longterm/kamila-clustering.R

@@ -0,0 +1,84 @@
+## Not run: 
+# import and format a mixed-type data set
+library(kamila)
+data(Byar, package='clustMD')
+
+ds <- readr::read_csv("2 Longterm/assigndata.csv",na = c("","NA")) |> na.omit()
+
+ds <- ds |> dplyr::mutate(mrs_1 = mrs_1>2)
+
+cat_i <- lapply(ds,is.character) |> purrr::list_c()
+con_i <- lapply(ds,is.double) |> purrr::list_c()
+
+xor(cat_i,con_i)
+
+clin_clust=2
+# Byar$logSpap <- log(Byar$Serum.prostatic.acid.phosphatase)
+
+# conInd <- c(5,6,8:10,16)
+# conVars <- Byar[,conInd]
+# conVars <- data.frame(scale(conVars))
+
+conVars <- ds[,con_i]
+conVars <- data.frame(scale(conVars))
+
+# catVarsFac <- Byar[,-c(1:2,conInd,11,14,15)]
+# catVarsFac[] <- lapply(catVarsFac, factor)
+# catVarsDum <- dummyCodeFactorDf(catVarsFac)
+
+catVarsFac <- ds[,cat_i]
+catVarsFac <- lapply(catVarsFac, factor) |> dplyr::bind_cols() |> as.data.frame()
+catVarsDum <- dummyCodeFactorDf(catVarsFac)
+
+# Modha-Spangler clustering with kmeans default Hartigan-Wong algorithm
+gmsResHw <- gmsClust(conVars, catVarsDum, nclust = clin_clust)
+
+# Modha-Spangler clustering with kmeans Forgy-Lloyd algorithm
+# NOTE searchDensity should be >= 10 for optimal performance:
+# this is just a syntax demo
+gmsResLloyd <- gmsClust(conVars, catVarsDum, nclust = clin_clust,
+                        algorithm = "Lloyd", searchDensity = 15)
+
+# KAMILA clustering
+kamRes <- kamila(conVars, catVarsFac, numClust=2:7, numInit=10, calcNumClust="ps")
+
+# Plot results
+# ternarySurvival <- factor(Byar$SurvStat)
+# levels(ternarySurvival) <- c('Alive','DeadProst','DeadOther')[c(1,2,rep(3,8))]
+plottingData <- cbind(
+  conVars,
+  catVarsFac,
+  KamilaCluster = factor(kamRes$finalMemb))
+# plottingData$Bone.metastases <- ifelse(
+#   plottingData$Bone.metastases == '1', yes='Yes',no='No')
+# 
+# # Plot Modha-Spangler/Hartigan-Wong results
+# msPlot <- ggplot(
+#   plottingData,
+#   aes(
+#     x=logSpap,
+#     y=Index.of.tumour.stage.and.histolic.grade,
+#     color=ternarySurvival,
+#     shape=MSCluster))
+# plotOpts <- function(pl) (pl + geom_point() + 
+#                             scale_shape_manual(values=c(2,3,7)) + geom_jitter())
+# plotOpts(msPlot)
+
+# Plot KAMILA results
+kamPlot <- ggplot(
+  plottingData,
+  aes(
+    x=pase_0,
+    y=pase_6,
+    color=KamilaCluster,
+    shape=KamilaCluster))
+plotOpts(kamPlot)
+
+
+plotting_ls <- tibble(KamilaCluster = factor(kamRes$finalMemb),
+                      MSCluster = factor(gmsResHw$results$cluster)) |> 
+  purrr::map(\(x) cbind(x, ds))
+
+plotting_ls |> purrr::map(\(y) {
+  y |> gtsummary::tbl_summary(by=x) |> gtsummary::add_p() |> gtsummary::add_overall()}) |> 
+  gtsummary::tbl_merge()