GCalignR 的 R 预处理数据中的字符串拆分问题

Question

尝试获取多个 .txt (GC-FID) 文件，提取两列数据并将它们分配给我最终可以传递给 GCalignR 的对象。有没有更好的方法来为 GCalignR 处理这些数据？

导致问题的辅助功能：

'''

# nonempty strings after splitting a row by one space
get_nonempty_splits = function(row) {
  s = strsplit(row, "[[:space:]]")
  s = s[[1]]
  l = c()
  for (i in 1:length(s)) {
    if (s[i] != "") {
      l = c(l, s[i])
    }
  }
  return(l)
}

# filenames have .txt, names do not
filenames_to_names = function(x) {
  l = c()
  for (i in 1:length(x)) {
    x1 = strsplit(x, "[.]")[[i]][1]
    l = c(l, x1)
  }
  return(l)
}

# get data row indices
get_data_row_inds = function(df) {
  ind_start = 0
  ind_end = 0
  for (i in 1:length(df)) {
    row = df[i]
    # find start
    if (grepl("----", row)) {
      stopifnot(ind_start == 0)  # assert ind_start not set
      ind_start = i+1
    }
    # find end
    if (i == length(df) && ind_end == 0) {
      ind_end = length(df)
    } else if (grepl("Totals", row) && grepl(":", row)) {
      stopifnot(ind_end == 0)  # assert ind_end not set
      ind_end = i-1
    }
  }
  stopifnot(ind_start != 0)
  stopifnot(ind_end != 0)
  return(ind_start:ind_end)
}

'''

'''

path_to_raw_data = "/Users/input"
path_to_processed_data = "."
# get paths for all .txt files in pathToRawData directory
paths = list.files(path_to_raw_data, full.name=TRUE, pattern = ".txt")
filenames = list.files(path_to_raw_data, full.name=FALSE, pattern = ".txt")
names = filenames_to_names(filenames)  # without .txt extension

# get data from text file
processed_data = list()
df_lengths = c()
for (i in 1:length(paths)) {  # i indexes the raw files
  path = paths[i]
  df = read.delim(path, fileEncoding= 'UTF-16LE', header=TRUE)
  df = df[[1]]
  inds = get_data_row_inds(df)
  df_lengths = c(df_lengths, length(inds))
  times = c()
  areas = c()
  for (j in inds) {  # j indexes the data rows of a raw file
    row = df[j]
    row = get_nonempty_splits(row)
    time = row_to_time(row)
    area = row_to_area(row)
    times = c(times, time)
    areas = c(areas, area)
  }
  pairs = data.frame(time = times, area = areas)
  processed_data[[i]] = pairs
}

'''

收到此错误：strsplit(row, "[[:space:]]") 中的错误：非字符参数

任何建议如何解决这个问题？是文件编码吗？ Processed-data =list() 什么都不返回...？

输入标题： '''

输入（头部（df）） 结构(c(59L, 53L, 45L, 48L, 47L, 52L), .Label = c("Inj Volume : 1 µl", " *** 报告结束 ***"、" 面积百分比报告"、 “ 1 1.353 1 BB 2.85703 2.453e-5 ？”， “ 2 1.952 1 BV 4411.39551 0.03787？”， " 3 2.058 1 VV 4693.20215 0.04029 ? ", " 4 2.089 1 VV 6614.89502 0.05679 ? ", “ 5 2.139 2 0.00000 0.00000 NG”, " 6 2.452 2 0.00000 0.00000 1, 3-DNB", " 7 3.149 2 0.00000 0.00000 2, 4-DNT", " 8 3.315 1 VV S 1.15784e7 99.39858 ? ", " 9 3.347 1 VV S 5169.44629 0.04438 ? ", " # [min] %", " 10 3.372 1 VV S 2.09449e4 0.17981 ?", " 11 3.466 1 VV S 2535.17432 0.02176 ? ", " 12 3.547 1 VB S 2.45685e4 0.21092 ? ", " 13 3.602 1 BV T 451.00174 0.00387 ? ", " 14 3.686 1 VV T 40.45324 0.00035 ? ", " 15 3.734 1 VV T 13.40936 0.00012 ? ", " 16 3.819 1 VB T 508.57788 0.00437 ? ", “ 17 4.119 1 BB 13.01144 0.00011 ？”， " 18 4.856 2 0.00000 0.00000 TNT", " 19 4.975 2 0.00000 0.00000 国能 ", " 20 5.549 2 0.00000 0.00000 4-Am-DNT", " 21 5.869 2 0.00000 0.00000 RDX", " 22 5.943 2 0.00000 0.00000 2-Am-DNT", " 23 6.516 2 0.00000 0.00000 丁腈 ", " 24 11.716 1 BB 1.75858 1.510e-5 ? ", “ 25 14.243 1 BB 2.55644 2.195e-5 ？”， " 26 16.654 1 BB 3.81723 3.277e-5 ? ", " 27 18.826 1 BB 2.58369 2.218e-5 ? ", " 28 20.800 1 BB 1.51171 1.298e-5 ? ", " 29 24.159 1 BB 1.78975 1.536e-5 ? ", " 30 24.269 1 BB 1.81180 1.555e-5 ? ", “ 31 25.053 1 BB 2.96617 2.546e-5 ？”， " 32 25.658 1 BB 6.15337 5.283e-5 ? ", " 33 25.809 1 BB 3.89435 3.343e-5 ? ", “ 34 26.577 1 BB 4.02199 3.453e-5 ？”， “ 35 26.885 1 BB 2.48416 2.133e-5 ？”， " 36 27.219 1 BB 14.88012 0.00013 ? ", “ 37 27.465 1 BB 3.59732 3.088e-5 ？”， " 38 29.377 1 BB 18.55422 0.00016 ? ", " 39 32.554 1 BB 17.15620 0.00015 ? ", "----|-------|---|------|----------|--------|----- --------------------", "================================================== =====================", “2 警告或错误：”、“采集仪器：仪器 1 位置：小瓶 11”、 "Acq. Operator : HHV Seq. Line : 2", “Calib. 数据已修改：2019 年 3 月 12 日，星期二，下午 6:13:25”， “稀释：1.0000”，“不要将乘数和稀释因子与 ISTD 一起使用”， “注射日期：20 年 2 月 24 日，14:37:34 注射：1”， “仪器 1 2020 年 2 月 24 日下午 3:13:35 HHV”，“上次更改时间：HHV 于 2/6/2020 下午 12:59:45”， “方法：C:\Chem32\1\DATA\IPOULIN\VOC_TEST_1 2020-02-24 13-49-15\VOC_TEST_HV.M”， “方法信息：VOC”，“乘数：1.0000”， "Peak RetTime Sig Type Area Name", "Sample Name: P1U1 hex 022420", “序列文件：C:\Chem32\1\DATA\IPOULIN\VOC_TEST_1 2020-02-24 13-49-15\VOC_TEST_1.S”， "信号 1：FID1 B，"，"排序方式：保留时间"， “总数：1.16485e7”，“警告：未找到校准化合物”， “警告：校准警告（参见校准表列表）” ), class= "因子") '''

Answer 1

通过添加解决：df = read.delim(path, fileEncoding= 'UTF-16LE', header=TRUE, stringsAsFactors = FALSE)。 “stringsAsFactors = FALSE”是解决方案。谢谢。