尝试在矩阵上运行tsne算法，出现错误：在data.matrix（x.wide）中：强制引入的NA

Question

我有一个名为x.wide的数据框，它具有39行和139列。

以下是x.wide的代码段：

       Achilles Tendinopathy   Acne Addictive Personality Aerobic performance
1                 Severe Severe                Severe              Severe
2                 Severe Severe                Severe              Severe
3                 Severe Severe                Severe              Severe
4                 Severe Severe                Severe              Severe
5                      3      3                     3                   6
6                      3      3                     3                   6
7                 Severe Severe                Severe              Severe
8                      3      3                     3                   6
9                 Severe Severe                Severe              Severe
10                     3      3                     3                   6
11                     3      3                     3                   6
12                     3      5                     3                   4
13                     3      5                     3                   4

由于我的数据集中有多个列，我想缩小尺寸以查看是否存在使用t-SNE的模式。我编写以下代码：

z.tsne = Rtsne(data.matrix(x.wide), dims = 3, check_duplicates = F , perplexity = .1, max_iter = 1000, theta = 0, pca = F) 

我得到一个丑陋的结果：

There were 50 or more warnings (use warnings() to see the first 50)

警告是此消息，重复50次。

1: In data.matrix(x.wide) : NAs introduced by coercion

这是z.tsne的代码段，它是一个39 x 3的矩阵。

      [,1] [,2] [,3]
 [1,]   NA   NA   NA
 [2,]   NA   NA   NA
 [3,]   NA   NA   NA
 [4,]   NA   NA   NA
 [5,]   NA   NA   NA

有人可以帮助我获得有意义的结果吗？