通过R创建表（集群）

时间：2020-03-28 22:10:00

标签： r datatable data-manipulation formattable

我想通过来解决我的问题。代码如下：

#database
df<-structure(list(Latitude = c(-23.8, -23.8, -23.9, -23.9, -23.9,  -23.9, -23.9, -23.9, -23.9, -23.9, -23.9, -23.9, -23.9, -23.9, 
+ -23.9, -23.9, -23.9, -23.9, -23.9), Longitude = c(-49.6, -49.6, -49.6, -49.6, -49.6, -49.6, -49.6, -49.6, -49.6, -49.6, -49.7, 
+ -49.7, -49.7, -49.7, -49.7, -49.6, -49.6, -49.6, -49.6), Waste = c(526, 350, 526, 469, 285, 175, 175, 350, 350, 175, 350, 175, 175, 364, 
+ 175, 175, 350, 45.5, 54.6)), class = "data.frame", row.names = c(NA, -19L))
   
Q1<-matrix(quantile(df$Waste, probs = 0.25))
df_Q1<-subset(df,Waste>Q1[1])
#cluster
d<-dist(df_Q1)
fit.average<-hclust(d,method="average")
clusters<-cutree(fit.average,k=4)
df_Q1$cluster<-clusters
     
dc<-aggregate(df_Q1[,"Waste"],list(cluster=clusters),sum)
colnames(dc)<-c("cluster","Sum_Waste")
dd<-aggregate(df_Q1[,"Waste"],list(cluster=clusters),mean)
colnames(dd)<-c("cluster","Mean_Waste")

谢谢！

新表格

enter image description here

1 个答案:

答案 0 :(得分：0)

可以将Sum_Waste和Mean_Waste与您的df_Q1数据框合并为最终表。

我不确定您要考虑的输出是什么，但是使用kableExtra的一种方法将合并具有指定列中相同值的单元格。希望这会有所帮助。

编辑：在表中添加了properties。现在，行按群集和属性排序。

library(kableExtra)

#database
df<-structure(list(Latitude = c(-23.8, -23.8, -23.9, -23.9, -23.9,  -23.9, -23.9, -23.9, -23.9, -23.9, -23.9, -23.9, -23.9, -23.9, 
                                + -23.9, -23.9, -23.9, -23.9, -23.9), Longitude = c(-49.6, -49.6, -49.6, -49.6, -49.6, -49.6, -49.6, -49.6, -49.6, -49.6, -49.7, 
                                                                                    + -49.7, -49.7, -49.7, -49.7, -49.6, -49.6, -49.6, -49.6), Waste = c(526, 350, 526, 469, 285, 175, 175, 350, 350, 175, 350, 175, 175, 364, 
                                                                                                                                                         + 175, 175, 350, 45.5, 54.6)), class = "data.frame", row.names = c(NA, -19L))

Q1<-matrix(quantile(df$Waste, probs = 0.25))
df_Q1<-subset(df,Waste>Q1[1])
df_Q1

#cluster
d<-dist(df_Q1)
fit.average<-hclust(d,method="average")
clusters<-cutree(fit.average,k=4)
df_Q1$cluster<-clusters
df_Q1$properties<-names(clusters)

#calculate sum waste
dc<-aggregate(df_Q1[,"Waste"],list(cluster=clusters),sum)
colnames(dc)<-c("cluster","Sum_Waste")
head(dc)

#calculate mean waste
dd<-aggregate(df_Q1[,"Waste"],list(cluster=clusters),mean)
colnames(dd)<-c("cluster","Mean_Waste")
head(dd)

#merge everything
df_table <- Reduce(merge, list(df_Q1, dc, dd))

#make table
kable(df_table[order(df_table$cluster, as.numeric(df_table$properties)),c(5,2,3,4,1,6,7)], align = "c", row.names = FALSE) %>%
  kable_styling(full_width = FALSE) %>%
  column_spec(1, bold = TRUE) %>%
  collapse_rows(columns = 5:7, valign = "middle")

编辑（4/18/20）

要将properties汇总为一行，并以逗号分隔，请尝试：

#sort properties
df_table <- df_table[order(df_table$cluster, as.numeric(df_table$properties)),]

#second table aggregated properties
df_table2 <- aggregate(. ~ cluster + Sum_Waste + Mean_Waste, df_table[,c(1,5,6,7)], toString)

#make table with df_table2
kable(df_table2[order(df_table2$cluster), c(4,1,2,3)], align = "c", row.names = FALSE) %>%
  kable_styling(full_width = FALSE)
相关问题
最新问题