如何为分类数据创建“聚类点图”？

Question

我想创建一个图形，就像名为Fathom的软件一样。

我有希望创造这样一个波动的情节绝对频率数据的双向表，但关键的区别是，你可以看到各个数据点。 我试过ggfluctuation(...),levelplots(...)和各种包装（如ggplot2），但没有成功。我在任何论坛上都找不到任何帮助。

如果有人能够帮助我指导或创建一些能达到我目标的代码，我将非常感激。

Answer 1

这是改进版本。

sample_data = structure(list(set = structure(c(1L, 2L, 3L, 4L, 1L, 2L, 3L, 
4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L), class = "factor", .Label = c("09t0101 TJ", 
"09t0102 MW", "09t0201 EH", "09t0202 NH")), grade = structure(c(1L, 
1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L), .Label = c("1", 
"2", "3", "4"), class = "factor"), freq = c(7L, 8L, 2L, 3L, 11L, 
4L, 11L, 3L, 3L, 8L, 3L, 8L, 3L, 9L, 3L, 2L)), .Names = c("set", 
"grade", "freq"), row.names = c(NA, -16L), class = "data.frame") 

group = unique(sample_data$set) #Obtain the unique 'set' values for y-axis 
max_x = length(unique(sample_data$grade)) #Obtain the maximum number of 'grades' to plot on x-axis 
max_y = length(group) #Obtain the maximum number of 'set' to plot on y-axis 
pdf(file="plot.pdf",width=8,height=6) 
par(mar = c(5, 10, 4, 2)) #c(bottom, left, top, right) 
plot(max_x,max_y,xlim=c(0.5,max_x+0.5),ylim=c(0.5,max_y +0.5),pch=NA,xlab="Grades",ylab=NA,xaxt="n",yaxt="n",asp=1) #asp = 1 IMPORTANT 
axis(side = 2, at=c(1:length(group)), labels=c(as.vector(group)),las=2) 
axis(side = 1, at=c(1:length(unique(sample_data$grade))), labels=c(as.vector(unique(sample_data$grade)))) 

r = 0.15 #The diameter of circles to be plotted 

for (i in 1:length(group)){ 
a = subset(sample_data,sample_data$set==group[i]) #Subset new data.frame corresponding to first 'set' 

for (j in 1:nrow(a)){ 
matrix_sz = ceiling(sqrt(a$freq[j])) #Determine the size of square matrix that can accomodate all the frequency 
matrix_x = matrix(nrow = matrix_sz, ncol = matrix_sz) #Initiate matrix 
matrix_y = matrix(nrow = matrix_sz, ncol = matrix_sz) #Initiate matrix 
matrix_x[,1] = -1*((matrix_sz/2) - 0.5) #Find out relatve x co-ordinates for first column 
matrix_y[1,] = 1*((matrix_sz/2) - 0.5) #Find out relatve y co-ordinates for first row 

# Find out other relative co-ordinates if the size of square matrix is more than 1x1 
if (matrix_sz > 1){ 
for (column in 2:matrix_sz){ 
matrix_x[,column] = matrix_x[,column - 1] + 1 
} 
for (row in 2:matrix_sz){ 
matrix_y[row,] = matrix_y[row-1,] - 1 
} 
} 

#Determine the co-ordinate of the center of the square matrix grid 
xx = as.integer(a$grade[j]) 
yy = i 
fq = 1 #To keep track of the corresponding 'freq' 

# Plot circles around the center based on relative co-ordinates 
for (row in 1:matrix_sz){ 
for (column in 1:matrix_sz){ 
if (fq > a$freq[j]){break} #Break if the necessary number of points have been plotted 
xx1 = xx + r * matrix_x[row, column] 
yy1 = yy + r * matrix_y[row, column] 
# points (x = xx1, y = yy1, pch=1) 
fq = fq + 1 
symbols (x = xx1, y = yy1, circles=c(r/2.25),add =TRUE,inches=FALSE,bg = "gray") 
} 
} 
} 
} 
dev.off()