条件检查 - 稀疏数据

Question

我想检查一个条件，如果列是 == 'value' - 那么如果从列列表中，是任何列 == 'value2'

# create dummy data set
pb=c('1','0','0','0','0','1','Not_ans','1','0','Not_ans')
qa=c('1','1','0','0','1','0','Not_ans','1','Not_ans','Not_ans')
#zy=c('1','Not_ans','0','1','Not_ans','0','1','1','1','Not_ans')

#sub questions for pb
pb.abr=c('1','0','0','0','0','1','0','1','0','0')
pb.ras=c('0','0','0','0','1','0','0','1','0','0')
pb.sfg=c('1','0','0','0','0','0','0','1','0','0')

#sub questions for qa
qa.fgs=c('1','0','0','0','0','0','0','1','0','0')
qa.sdf=c('0','1','0','0','0','0','0','0','0','0')
qa.tyu=c('0','0','0','0','1','0','0','1','0','0')

df=data.frame(pb,qa,pb.abr,pb.ras,pb.sfg,qa.fgs,qa.sdf,qa.tyu)
df

        pb      qa     pb.abr pb.ras pb.sfg qa.fgs qa.sdf qa.tyu
1        1       1      1      0      1      1      0      0
2        0       1      0      0      0      0      1      0
3        0       0      0      0      0      0      0      0
4        0       0      0      0      0      0      0      0
5        0       1      0      1      0      0      0      1
6        1       0      1      0      0      0      0      0
7  Not_ans Not_ans      0      0      0      0      0      0
8        1       1      1      1      1      1      0      1
9        0 Not_ans      0      0      0      0      0      0
10 Not_ans Not_ans      0      0      0      0      0      0

在上面的数据集中 - 我想检查的是如果列 'pb' 是 0 ，那么如果有任何列 pb.abr OR pb.ras OR pb.sfg == 1

subset_df=subset(df,(pb==0) & ((pb.abr==1) | (pb.ras==1)|(pb.sfg==1)))

挑战是我有 100 多列具有 pb.xxx 格式并且手动写入子集中的所有列不是可行的解决方案。我如何使用使用 contains("pb.") 的逻辑检查上述内容，并在列之间使用 OR 条件检查列，最后提供数据框？

Answer 1

示例数据

dont' forget to set StringsAsFactors to FALSE!
df=data.frame(pb,qa,pb.abr,pb.ras,pb.sfg,qa.fgs,qa.sdf,qa.tyu, stringsAsFactors = FALSE)

代码

library(dplyr)
df %>%
  #set all columns starting with 'pb.' to numeric
  mutate_at( vars( starts_with("pb.") ), funs( as.numeric ) ) %>%
  #first filter
  filter( pb == "0" ) %>%
  #second filter
  filter( rowSums( .[, grep("pb\.", names(df))]) > 0 )

输出

  pb qa pb.abr pb.ras pb.sfg qa.fgs qa.sdf qa.tyu
1  0  1      0      1      0      0      0      1

Answer 2

我们可以使用 filter_at

library(dplyr)

df %>%
  filter(pb == 0) %>%
  filter_at(vars(matches("pb\.")), any_vars(.  == 1))

#  pb qa pb.abr pb.ras pb.sfg qa.fgs qa.sdf qa.tyu
#1  0  1      0      1      0      0      0      1

或以 R 为基数

df[df$pb == 0 & rowSums(df[grep("pb\.", names(df))] == 1) > 0, ]

#  pb qa pb.abr pb.ras pb.sfg qa.fgs qa.sdf qa.tyu
#5  0  1      0      1      0      0      0      1

Answer 3

作为一个班轮：

filter(df,pb==0 & rowSums(z[,grepl("pb\.",names(z))])>0)

条件检查 - 稀疏数据

condition check - sparse data

string

conditional

r