读取表并在R中的循环中分配给字符串

debugcn 发表于 Dev

用户名

我敢肯定对此有一个简单的答案，但是我似乎找不到正确的代码。我有一个文件列表和一个字符串列表，我想将这些文件的内容分配为数据帧。然后，我想在同一循环内对数据帧执行其他操作。我还需要保留每个数据框用于下游工作。这是我的代码：

samples <- c('fc14','g14','fc18','g18','fc21','g21')
fc_samples <- grep("fc", samples, value=TRUE)
fc_files <- c('fc14_g14_full_annot_uniq.txt','fc18_g18_full_annot_uniq.txt','fc21_g21_full_annot_uniq.txt')


# make dataframes
for (file in fc_files)
{   fc_n <- 1
    g_n <- 1
    print(file);

    # THE BIT THAT DOESN'T WORK
    assign(paste("data", fc_samples[fc_n], sep='_'), read.table(file,sep = "\t", header=T));

    # HERE I EXPECT THE TOP OF MY DF TO BE PRINTED BUT IT ISN'T
    head(data_fc14);

    # I TRY THIS INSTEAD
    do.call("<-",list(paste("data", fc_samples[fc_n], sep='_'), read.table(file,sep = "\t", header=T)))

    # I TRY TO PRINT THE DF AGAIN BUT STILL NO LUCK
    head(paste("data", fc_samples[fc_n], sep='_'))

    # FIRST DOWNSTREAM THING I WOULD LIKE TO DO,
    # WON'T WORK UNTIL I SOLVE THE DF ASSIGNMENT ISSUE
    names(paste("data", fc_samples[fc_n], sep='_'))[names(paste("data", fc_samples[fc_n], sep='_'))==c('SAMPLE_fc','CHROM_fc','START_fc','REF_fc','ALT_fc','REGION_fc','DP_fc','FREQ_fc','GENE_fc','AFFECTS_fc','dbSNP_fc',
    #                           'NOVEL_fc')] <- c('SAMPLE','CHROM','START','REF','ALT','REGION','DP','FREQ','GENE','AFFECTS','dbSNP','NOVEL')

    # ITERATE TO THE NEXT FILE
    fc_n <- fc_n+1
}

我从这里到这里尝试解决方案，但没有帮助。如果有人对此有一个优雅的解决方案，那就太好了！提前致谢！

奥雷尔

修改您的代码：

samples <- c('fc14','g14','fc18','g18','fc21','g21')
fc_samples <- grep("fc", samples, value=TRUE)

# Make dummy example files
fc_files <- file.path("example-data", c(
  'fc14_g14_full_annot_uniq.txt','fc18_g18_full_annot_uniq.txt',
  'fc21_g21_full_annot_uniq.txt'))
set.seed(123) ; dummy_df <- 
  setNames(
    as.data.frame(replicate(12, rnorm(7))),
    c('SAMPLE_fc','CHROM_fc','START_fc','REF_fc','ALT_fc','REGION_fc',
      'DP_fc','FREQ_fc','GENE_fc','AFFECTS_fc','dbSNP_fc','NOVEL_fc')
  )
if (!dir.exists("./example-data")) dir.create("example-data")
invisible({
  lapply(fc_files, write.table, x = dummy_df, sep = "\t")
})

# "fc_n <- 1" should be outside the loop:
fc_n <- 1
for (file in fc_files) {
  g_n <- 1
  assign(paste("data", fc_samples[fc_n], sep='_'), 
         read.table(file,sep = "\t", header=T))
  # Copy data to be able to change its names
  f <- get(paste("data", fc_samples[fc_n], sep='_'))
  names(f)[names(f) == c('SAMPLE_fc','CHROM_fc','START_fc',
                         'REF_fc','ALT_fc','REGION_fc',
                         'DP_fc','FREQ_fc','GENE_fc','AFFECTS_fc',
                         'dbSNP_fc','NOVEL_fc')] <- 
    c('SAMPLE','CHROM','START','REF','ALT','REGION','DP','FREQ',
      'GENE','AFFECTS','dbSNP','NOVEL')
  # Assign it back, now that names have been changed
  assign(paste("data", fc_samples[fc_n], sep='_'), f)
  fc_n <- fc_n+1
}

一种“更优雅”的方式：
assign()ing不被认为是最佳实践，而是使用列表。
尽管我偶尔会自己使用它，但有时还是有很好的理由。

# For the '%>%' pipe
library(magrittr)

data <-
  samples %>% 
  grep(pattern = "fc", value = TRUE) %>% 
  setNames(nm = .) %>% 
  lapply(grep, x = fc_files, value = TRUE) %>% 
  lapply(read.table, sep = "\t", header = TRUE) %>% 
  lapply(function(f) setNames(f, sub("_fc", "", names(f))))

identical(data_fc14, data$fc14)
# [1] TRUE
identical(data_fc18, data$fc18)
# [1] TRUE
identical(data_fc21, data$fc21)
# [1] TRUE

# Clean up
print(unlink("example-data", recursive = TRUE))

本文收集自互联网，转载请注明来源。

如有侵权，请联系[email protected] 删除。