| 1 | #' Plot |
| 2 | #' |
| 3 | #' It is a function which plots relevant parameters |
| 4 | #' |
| 5 | #' @param X matrix of covariates (of size n*p) |
| 6 | #' @param Y matrix of responses (of size n*m) |
| 7 | #' @param model the model constructed by valse procedure |
| 8 | #' @param n sample size |
| 9 | #' @return several plots |
| 10 | #' |
| 11 | #' @examples TODO |
| 12 | #' |
| 13 | #' @export |
| 14 | #' |
| 15 | plot_valse <- function(X, Y, model, n, comp = FALSE, k1 = NA, k2 = NA) |
| 16 | { |
| 17 | require("gridExtra") |
| 18 | require("ggplot2") |
| 19 | require("reshape2") |
| 20 | require("cowplot") |
| 21 | |
| 22 | K <- length(model$pi) |
| 23 | ## regression matrices |
| 24 | gReg <- list() |
| 25 | for (r in 1:K) |
| 26 | { |
| 27 | Melt <- melt(t((model$phi[, , r]))) |
| 28 | gReg[[r]] <- ggplot(data = Melt, aes(x = Var1, y = Var2, fill = value)) + |
| 29 | geom_tile() + scale_fill_gradient2(low = "blue", high = "red", mid = "white", |
| 30 | midpoint = 0, space = "Lab") + ggtitle(paste("Regression matrices in cluster", |
| 31 | r)) |
| 32 | } |
| 33 | print(gReg) |
| 34 | |
| 35 | ## Differences between two clusters |
| 36 | if (comp) |
| 37 | { |
| 38 | if (is.na(k1) || is.na(k)) |
| 39 | { |
| 40 | print("k1 and k2 must be integers, representing the clusters you want to compare") |
| 41 | } |
| 42 | Melt <- melt(t(model$phi[, , k1] - model$phi[, , k2])) |
| 43 | gDiff <- ggplot(data = Melt, aes(x = Var1, y = Var2, fill = value)) + geom_tile() + |
| 44 | scale_fill_gradient2(low = "blue", high = "red", mid = "white", midpoint = 0, |
| 45 | space = "Lab") + ggtitle(paste("Difference between regression matrices in cluster", |
| 46 | k1, "and", k2)) |
| 47 | print(gDiff) |
| 48 | |
| 49 | } |
| 50 | |
| 51 | ### Covariance matrices |
| 52 | matCov <- matrix(NA, nrow = dim(model$rho[, , 1])[1], ncol = K) |
| 53 | for (r in 1:K) |
| 54 | { |
| 55 | matCov[, r] <- diag(model$rho[, , r]) |
| 56 | } |
| 57 | MeltCov <- melt(matCov) |
| 58 | gCov <- ggplot(data = MeltCov, aes(x = Var1, y = Var2, fill = value)) + geom_tile() + |
| 59 | scale_fill_gradient2(low = "blue", high = "red", mid = "white", midpoint = 0, |
| 60 | space = "Lab") + ggtitle("Covariance matrices") |
| 61 | print(gCov) |
| 62 | |
| 63 | ### Proportions |
| 64 | gam2 <- matrix(NA, ncol = K, nrow = n) |
| 65 | for (i in 1:n) |
| 66 | { |
| 67 | gam2[i, ] <- c(model$proba[i, model$affec[i]], model$affec[i]) |
| 68 | } |
| 69 | |
| 70 | bp <- ggplot(data.frame(gam2), aes(x = X2, y = X1, color = X2, group = X2)) + |
| 71 | geom_boxplot() + theme(legend.position = "none") + background_grid(major = "xy", |
| 72 | minor = "none") |
| 73 | print(bp) |
| 74 | |
| 75 | ### Mean in each cluster |
| 76 | XY <- cbind(X, Y) |
| 77 | XY_class <- list() |
| 78 | meanPerClass <- matrix(0, ncol = K, nrow = dim(XY)[2]) |
| 79 | for (r in 1:K) |
| 80 | { |
| 81 | XY_class[[r]] <- XY[model$affec == r, ] |
| 82 | if (sum(model$affec == r) == 1) |
| 83 | { |
| 84 | meanPerClass[, r] <- XY_class[[r]] |
| 85 | } else |
| 86 | { |
| 87 | meanPerClass[, r] <- apply(XY_class[[r]], 2, mean) |
| 88 | } |
| 89 | } |
| 90 | data <- data.frame(mean = as.vector(meanPerClass), cluster = as.character(rep(1:K, |
| 91 | each = dim(XY)[2])), time = rep(1:dim(XY)[2], K)) |
| 92 | g <- ggplot(data, aes(x = time, y = mean, group = cluster, color = cluster)) |
| 93 | print(g + geom_line(aes(linetype = cluster, color = cluster)) + geom_point(aes(color = cluster)) + |
| 94 | ggtitle("Mean per cluster")) |
| 95 | |
| 96 | } |