I am new to R and am working on a data set including nominal, ordinal and metric data.
Therefore I am using the gower distance. In the next step I use this distance with hclust(x, method="complete") to create clusters based on this distance.
Now I want to know how I can put different weights on variables in the gower distance.
The documentation says:
daisy(x, metric = c("euclidean", "manhattan", "gower"), stand = FALSE, type = list(), weights = rep.int(1, p))
So there is a way, but I am unsure about the syntax (weights = ...).
The documentation of weights and rep.int, did not help.
I also didn't find any other helpful explanation.
I would be very glad, if some one can help out.
Not sure if this is what you are getting at, but...
Let's say you have 5 variables, e.g. 5 columns in your data frame or matrix. Then weights would be a vector of length=5 containing the weights for the corresponding columns.
The notation weights=rep.int(1,p) in the documentation simply means that the default value of weights is a vector of length p that has all 1's, eg. the weights are all equal to 1. Elsewhere in the documentation it explains that p is the number of columns.
Also, note that daisy(...) produces a dissimilarity matrix. This is what you use in hclust(...). So if x is a data frame or matrix with five columns for your variables, then:
d <- daisy(x, metric="gower", weights=c(1,2,3,4,5))
hc <- hclust(d, method="complete")
EDIT (Response to OP's comments)
The code below shows how the clustering depends on the weights.
clust.anal <- function(df,w,h) {
require(cluster)
d <- daisy(df, metric="gower", weights=w)
hc <- hclust(d, method="complete")
clust <- cutree(hc,h=h)
plot(hc, sub=paste("weights=",paste(wts,collapse=",")))
rect.hclust(hc,h=0.8,border="red")
}
df <- read.table("ExampleClusterData.csv", sep=";",header=T)
df[1] <- factor(df[[1]])
df[2] <- factor(df[[2]])
# weights increase with col number...
wts=c(1,2,3,4,5,6,7)
clust.anal(df,wts,h=0.8)
# weights decrease with col number...
wts=c(7,6,5,4,3,2,1)
clust.anal(df,wts,h=0.8)
Related
I am trying to fit a soft-core point process model on a set of point pattern using maximum pseudo-likelihood. I followed the instructions given in this paper by Baddeley and Turner
And here is the R-code I came up with
`library(deldir)
library(tidyverse)
library(fields)
#MPLE
# irregular parameter k
k <- 0.4
## Generate dummy points 50X50. "RA" and "DE" are x and y coordinates
dum.x <- seq(ramin, ramax, length = 50)
dum.y <- seq(demin, demax, length = 50)
dum <- expand.grid(dum.x, dum.y)
colnames(dum) <- c("RA", "DE")
## Combine with data and specify which is data point and which is dummy, X is the point pattern to be fitted
bind.x <- bind_rows(X, dum) %>%
mutate(Ind = c(rep(1, nrow(X)), rep(0, nrow(dum))))
## Calculate Quadrature weights using Voronoi cell area
w <- deldir(bind.x$RA, bind.x$DE)$summary$dir.area
## Response
y <- bind.x$Ind/w
# the sum of distances between all pairs of points (the sufficient statistics)
tmp <- cbind(bind.x$RA, bind.x$DE)
t1 <- rdist(tmp)^(-2/k)
t1[t1 == Inf] <- 0
t1 <- rowSums(t1)
t <- -t1
# fit the model using quasipoisson regression
fit <- glm(y ~ t, family = quasipoisson, weights = w)
`
However, the fitted parameter for t is negative which is obviously not a correct value for a softcore point process. Also, my point pattern is actually simulated from a softcore process so it does not make sense that the fitted parameter is negative. I tried my best to find any bugs in the code but I can't seem to find it. The only potential issue I see is that my sufficient statistics is extremely large (on the order of 10^14) which I fear may cause numerical issues. But the statistics are large because my observation window spans a very small unit and the average distance between a pair of points is around 0.006. So sufficient statistics based on this will certainly be very large and my intuition tells me that it should not cause a numerical problem and make the fitted parameter to be negative.
Can anybody help and check if my code is correct? Thanks very much!
I'm having issue with predicting cluster labeling for a test data, based on a dbscan clustering model on the training data.
I used gower distance matrix when creating the model:
> gowerdist_train <- daisy(analdata_train,
metric = "gower",
stand = FALSE,
type = list(asymm = c(5,6)))
Using this gowerdist matrix, the dbscan clustering model created was:
> sb <- dbscan(gowerdist_train, eps = .23, minPts = 50)
Then I try to use predict to label a test dataset using the above dbscan object:
> predict(sb, newdata = analdata_test, data = analdata_train)
But I receive the following error:
Error in frNN(rbind(data, newdata), eps = object$eps, sort = TRUE,
...) : x has to be a numeric matrix
I can take a guess on where this error might be coming from, which is probably due to the absence of the gower distance matrix that hasn't been created for the test data.
My question is, should I create a gower distance matrix for all data (datanal_train + datanal_test) separately and feed it into predict? how else would the algorithm know what the distance of test data from the train data is, in order to label?
In that case, would the newdata parameter be the new gower distance matrix that contains ALL (train + test) data? and the data parameter in predict would be the training distance matrix, gowerdist_train?
What I am not quite sure about is how would the predict algorithm distinguish between the test and train data set in the newly created gowerdist_all matrix?
The two matrices (new gowerdist for all data and the gowerdist_train) would obviously not have the same dimensions. Also, it doesn't make sense to me to create a gower distance matrix only for test data because distances must be relative to the test data, not the test data itself.
Edit:
I tried using gower distance matrix for all data (train + test) as my new data and received an error when fed to predict:
> gowerdist_all <- daisy(rbind(analdata_train, analdata_test),
metric = "gower",
stand = FALSE,
type = list(asymm = c(5,6)))
> test_sb_label <- predict(sb, newdata = gowerdist_all, data = gowerdist_train)
ERROR: Error in 1:nrow(data) : argument of length 0 In addition:
Warning message: In rbind(data, newdata) : number of columns of
result is not a multiple of vector length (arg 1)
So, my suggested solution doesn't work.
I decided to create a code that would use KNN algorithm in dbscan to predict cluster labeling using gower distance matrix. The code is not very pretty and definitely not programmaticaly efficient but it works. Happy for any suggestions that would improve it.
The pseydocode is:
1) calculate new gower distance matrix for all data, including test and train
2) use the above distance matrix in kNN function (dbscan package) to determine the k nearest neighbours to each test data point.
3) determine the cluster labels for all those nearest points for each test point. Some of them will have no cluster labeling because they are test points themselves
4) create a count matrix to count the frequency of clusters for the k nearest points for each test point
5) use very simple likelihood calculation to choose the cluster for the test point based on its neighbours clusters (the maximum frequency). this part also considers the neighbouring test points. That is, the cluster for the test point is chosen only when the maximum frequency is largest when you add the number of neighbouring test points to the other clusters. Otherwise, it doesn't decide the cluster for that test point and waits for the next iteration when hopefully more of its neighboring test points have had their cluster label decided based on their neighbours.
6) repeat above (steps 2-5) until you've decided all clusters
** Note: this algorithm doesn't converge all the time. (once you do the math, it's obvious why that is) so, in the code i break out of the algorithm when the number of unclustered test points doesn't change after a while. then i repeat 2-6 again with new knn (change the number of nearest neighbours and then run the code again). This will ensure more points are involved in deciding in th enext round. I've tried both larger and smaller knn's and both work. Would be good to know which one is better. I haven't had to run the code more than twice so far to decide the clusters for the test data point.
Here is the code:
#calculate gower distance for all data (test + train)
gowerdist_test <- daisy(all_data[rangeofdataforgowerdist],
metric = "gower",
stand = FALSE,
type = list(asymm = listofasymmvars),
weights = Weights)
summary(gowerdist_test)
Then use the code below to label clusters for test data.
#library(dbscan)
# find the k nearest neibours for each point and order them with distance
iteration_MAX <- 50
iteration_current <- 0
maxUnclusterRepeatNum <- 10
repeatedUnclustNum <- 0
unclusteredNum <- sum(is.na(all_data$Cluster))
previousUnclustereNum <- sum(is.na(all_data$Cluster))
nn_k = 30 #number of neighbourhoods
while (anyNA(all_data$Cluster) & iteration_current < iteration_MAX)
{
if (repeatedUnclustNum >= maxUnclusterRepeatNum) {
print(paste("Max number of repetition (", maxUnclusterRepeatNum ,") for same unclustered data has reached. Clustering terminated unsuccessfully."))
invisible(gc())
break;
}
nn_test <- kNN(gowerdist_test, k = nn_k, sort = TRUE)
# for the TEST points in all data, find the closets TRAIN points and decide statistically which cluster they could belong to, based on the clusters of the nearest TRAIN points
test_matrix <- nn_test$id[1: nrow(analdata_test),] #create matrix of test data knn id's
numClusts <- nlevels(as.factor(sb_train$cluster))
NameClusts <- as.character(levels(as.factor(sb_train$cluster)))
count_clusters <- matrix(0, nrow = nrow(analdata_test), ncol = numClusts + 1) #create a count matrix that would count number of clusters + NA
colnames(count_clusters) <- c("NA", NameClusts) #name each column of the count matrix to cluster numbers
# get the cluster number of each k nearest neibhour of each test point
for (i in 1:nrow(analdata_test))
for (j in 1:nn_k)
{
test_matrix[i,j] <- all_data[nn_test$id[i,j], "Cluster"]
}
# populate the count matrix for the total clusters of the neighbours for each test point
for (i in 1:nrow(analdata_test))
for (j in 1:nn_k)
{
if (!is.na(test_matrix[i,j]))
count_clusters[i, c(as.character(test_matrix[i,j]))] <- count_clusters[i, c(as.character(test_matrix[i,j]))] + 1
else
count_clusters[i, c("NA")] <- count_clusters[i, c("NA")] + 1
}
# add NA's (TEST points) to the other clusters for comparison
count_clusters_withNA <- count_clusters
for (i in 2:ncol(count_clusters))
{
count_clusters_withNA[,i] <- t(rowSums(count_clusters[,c(1,i)]))
}
# This block of code decides the maximum count of cluster for each row considering the number other test points (NA clusters) in the neighbourhood
max_col_countclusters <- apply(count_clusters,1,which.max) #get the column that corresponds to the maximum value of each row
for (i in 1:length(max_col_countclusters)) #insert the maximum value of each row in its associated column in count_clusters_withNA
count_clusters_withNA[i, max_col_countclusters[i]] <- count_clusters[i, max_col_countclusters[i]]
max_col_countclusters_withNA <- apply(count_clusters_withNA,1,which.max) #get the column that corresponds to the maximum value of each row with NA added
compareCountClust <- max_col_countclusters_withNA == max_col_countclusters #compare the two count matrices
all_data$Cluster[1:nrow(analdata_test)] <- ifelse(compareCountClust, NameClusts[max_col_countclusters - 1], all_data$Cluster) #you subtract one because of additional NA column
iteration_current <- iteration_current + 1
unclusteredNum <- sum(is.na(all_data$Cluster))
if (previousUnclustereNum == unclusteredNum)
repeatedUnclustNum <- repeatedUnclustNum + 1
else {
repeatedUnclustNum <- 0
previousUnclustereNum <- unclusteredNum
}
print(paste("Iteration: ", iteration_current, " - Number of remaining unclustered:", sum(is.na(all_data$Cluster))))
if (unclusteredNum == 0)
print("Cluster labeling successfully Completed.")
invisible(gc())
}
I guess you can use this for any other type of clustering algorithm, it doesn't matter how you decided the cluster labels for the train data, as long as they are in your all_data before running the code.
Hope this help.
Not the most efficient or rigorous code. So, happy to see suggestions how to improve it.
*Note: I used t-SNE to compare the clustering of train with the test data and looks impressively clean. so, it seems it is working.
I tried to use princomp() and principal() to do PCA in R with data set USArressts. However, I got two different results for loadings/rotaion and scores.
First, I centered and normalised the original data frame so it is easier to compare the outputs.
library(psych)
trans_func <- function(x){
x <- (x-mean(x))/sd(x)
return(x)
}
A <- USArrests
USArrests <- apply(USArrests, 2, trans_func)
princompPCA <- princomp(USArrests, cor = TRUE)
principalPCA <- principal(USArrests, nfactors=4 , scores=TRUE, rotate = "none",scale=TRUE)
Then I got the results for the loadings and scores using the following commands:
princompPCA$loadings
principalPCA$loadings
Could you please help me to explain why there is a difference? and how can we interprete these results?
At the very end of the help document of ?principal:
"The eigen vectors are rescaled by the sqrt of the eigen values to produce the component loadings more typical in factor analysis."
So principal returns the scaled loadings. In fact, principal produces a factor model estimated by the principal component method.
In 4 years, I would like to provide a more accurate answer to this question. I use iris data as an example.
data = iris[, 1:4]
First, do PCA by the eigen-decomposition
eigen_res = eigen(cov(data))
l = eigen_res$values
q = eigen_res$vectors
Then the eigenvector corresponding to the largest eigenvalue is the factor loadings
q[,1]
We can treat this as a reference or the correct answer. Now we check the results by different r functions.
First, by function 'princomp'
res1 = princomp(data)
res1$loadings[,1]
# compare with
q[,1]
No problem, this function actually just return the same results as 'eigen'. Now move to 'principal'
library(psych)
res2 = principal(data, nfactors=4, rotate="none")
# the loadings of the first PC is
res2$loadings[,1]
# compare it with the results by eigendecomposition
sqrt(l[1])*q[,1] # re-scale the eigen vector by sqrt of eigen value
You may find they are still different. The problem is the 'principal' function does eigendecomposition on the correlation matrix by default. Note: PCA is not invariant with rescaling the variables. If you modify the code as
res2 = principal(data, nfactors=4, rotate="none", cor="cov")
# the loadings of the first PC is
res2$loadings[,1]
# compare it with the results by eigendecomposition
sqrt(l[1])*q[,1] # re-scale the eigen vector by sqrt of eigen value
Now, you will get the same results as 'eigen' and 'princomp'.
Summarize:
If you want to do PCA, you'd better apply 'princomp' function.
PCA is a special case of the Factor model or a simplified version of the factor model. It is just equivalent to eigendecomposition.
We can apply PCA to get an approximation of a factor model. It doesn't care about the specific factors, i.e. epsilons in a factor model. So, if you change the number of factors in your model, you will get the same estimations of the loadings. It is different from the maximum likelihood estimation.
If you are estimating a factor model, you'd better use 'principal' function, since it provides more functions, like rotation, calculating the scores by different methods, and so on.
Rescale the loadings of a PCA model doesn't affect the results too much. Since you still project the data onto the same optimal direction, i.e. maximize the variation in the resulting PC.
ev <- eigen(R) # R is a correlation matrix of DATA
ev$vectors %*% diag(ev$values) %*% t(ev$vectors)
pc <- princomp(scale(DATA, center = F, scale = T),cor=TRUE)
p <-principal(DATA, rotate="none")
#eigen values
ev$values^0.5
pc$sdev
p$values^0.5
#eigen vectors - loadings
ev$vectors
pc$loadings
p$weights %*% diag(p$values^0.5)
pc$loading %*% diag(pc$sdev)
p$loadings
#weights
ee <- diag(0,2)
for (j in 1:2) {
for (i in 1:2) {
ee[i,j] <- ev$vectors[i,j]/p$values[j]^0.5
}
};ee
#scores
s <- as.matrix(scale(DATA, center = T, scale = T)) %*% ev$vectors
scale(s)
p$scores
scale(pc$scores)
I have mixed data type matrix Data_string size (947 x 41) that contain numeric and categorical attributes.
I produced a distance matrix (947 x 947) using the daisy() function and Gower distance measure in Rstudio.
d <- daisy(Data_String, metric = "gower", stand = FALSE,type = list(symm = c("V1","V13") , asymm = c("V8","V9","V10")))
I applied hierarchical Cluster using dissimilarity matrix (d).
# hclust
hc <- hclust(d, method="complete")
plot(hc)
rect.hclust(hc, 4)
cut <- cutree(hc, k = 1:5)
View(cut)
#Diana
d_as <- as.matrix(d)
DianaCluster <- diana(d_as, diss = TRUE, keep.diss = TRUE)
print(DianaCluster)
plot(DianaCluster)
The following is the plots I had.
** Note: I couldn't upload the image here since I do not have enough reputation's points.
I am struggling to understand the results, can anyone please
1- suggest any solution that I can apply in R to simplify the understanding of my results.
or
2- how I can link it to my source data, since all the results are based on the dissimilarity matrix.
Please take a look at -
https://stats.stackexchange.com/questions/130974/how-to-use-both-binary-and-continuous-variables-together-in-clustering
It explains how to use gower dissimilarity matrix with hclust. Hope this helps!
I'm looking to perform classification on data with mostly categorical features. For that purpose, Euclidean distance (or any other numerical assuming distance) doesn't fit.
I'm looking for a kNN implementation for [R] where it is possible to select different distance methods, like Hamming distance.
Is there a way to use common kNN implementations like the one in {class} with different distance metric functions?
I'm using R 2.15
As long as you can calculate a distance/dissimilarity matrix (in whatever way you like) you can easily perform kNN classification without the need of any special package.
# Generate dummy data
y <- rep(1:2, each=50) # True class memberships
x <- y %*% t(rep(1, 20)) + rnorm(100*20) < 1.5 # Dataset with 20 variables
design.set <- sample(length(y), 50)
test.set <- setdiff(1:100, design.set)
# Calculate distance and nearest neighbors
library(e1071)
d <- hamming.distance(x)
NN <- apply(d[test.set, design.set], 1, order)
# Predict class membership of the test set
k <- 5
pred <- apply(NN[, 1:k, drop=FALSE], 1, function(nn){
tab <- table(y[design.set][nn])
as.integer(names(tab)[which.max(tab)]) # This is a pretty dirty line
}
# Inspect the results
table(pred, y[test.set])
If anybody knows a better way of finding the most common value in a vector than the dirty line above, I'd be happy to know.
The drop=FALSE argument is needed to preserve the subset of NN as matrix in the case k=1. If not it will be converted to a vector and apply will throw an error.