将数据集读入具有预先指定列数的格式良好的表中

【问题标题】：Read data set into well formated table with pre-specified number of columns将数据集读入具有预先指定列数的格式良好的表中
【发布时间】：2018-09-17 07:36:27
【问题描述】：

我有一个这样的txt.file：

0003    MPARTNER  SALZ          S                           150112 22:30:45  160304 08:38:13  2      BUY                          2  BUY                  12380    165426  150109 08:00:00
0003    SPROTTSE  HUGHES        S                           140407 02:30:50  141120 13:55:06  2      BUY                          2  BUY                   3764     57379  140401 10:05:00
0003    SPROTTSE  HUGHES        S                           141223 09:06:13  160715 08:42:56  3      MARKETPERFORM                3  HOLD                  3764     57379  141223 08:02:00
001V    MPARTNER  PEARLSTEIN    D                           140821 02:44:05  150312 09:17:13  2      BUY                          2  BUY                  12380    163717  140820 08:16:00
001V    MPARTNER  PEARLSTEIN    D                           151016 15:07:40  160411 08:40:35  2      BUY                          2  BUY                  12380    163717  151009 08:12:00
001W    CANACCOR                K                           140321 04:06:40  140609 23:06:44         SPECULATIVE BUY              1  STRONG BUY             406    150412  140319 23:19:00
001W    CANACCOR  WRIGHT        K                           140714 12:47:31  160228 22:57:45         BUY                          1  STRONG BUY             406    150412  140714 12:38:00
001W    CLARUS    OFIR          E                           140515 11:40:00  150515 09:27:09         SPECULATIVE BUY              1  STRONG BUY             202    115944  140515 11:40:00
001W    CLARUS    MACKAY        D                           150813 09:40:45  160812 09:40:02         BUY                          1  STRONG BUY             202     73763  150813 09:23:00
001W    DEACON    OFIR          E                           150119 22:03:46  170328 06:45:14  1      BUY                          1  STRONG BUY             704    115944  150112 07:24:00
001W    DEACON    OFIR          E                           171115 06:48:47  171115 06:48:47  1      BUY                          1  STRONG BUY             704    115944  171115 06:42:00
@70L    MORGAN    MARTINEZ      J                           100226 07:12:51  100708 04:51:16  8      EQUALWT/NO RATING            3  HOLD                  1595     56947  100226 07:12:00
@70L    MORGAN    MARTINEZ DE O J                           100708 05:09:02  100910 00:48:28  6      EQUALWT/IN-LINE              3  HOLD                  1595     56947  100708 03:14:00
@70L    MORGAN    MARTINEZ DE O J                           100910 21:16:07  101110 21:55:52  2      OVERWT/IN-LINE               2  BUY                   1595     56947  100910 19:18:00
@70L    MORGAN    OLCOZ CERDAN  J                           101112 01:32:41  120618 21:04:56  2      OVERWT/IN-LINE               2  BUY                   1595     56947  101111 20:03:00
@70L    MORGAN    OLCOZ CERDAN  J                           120712 03:19:26  131216 19:49:59  6      EQUALWT/IN-LINE              3  HOLD                  1595     56947  120711 19:20:00
@70L    MORGAN    OLCOZ CERDAN  J                           140226 22:20:19  150417 13:07:31  2      OVERWT/IN-LINE               2  BUY                   1595     56947  140226 22:20:00
@70L    MORGAN                  J                           150608 01:25:35  171106 00:16:05  1      OVERWT/ATTRACTIVE            2  BUY                   1595     56947  150608 01:25:00

我想在R 中生成一个表，其结构与txt 文件中的表观16 列 具有相同的结构。

我尝试使用代码：

max(count.fields("BSP.txt", sep="")) # 18 columns
df= read.delim("BSP.txt", sep = "" ,header = FALSE,col.names = c("V1", "VS","V3", "V4", "V5","V6",
                                                                 "V7", "V8", "V9", "V10", 
                                                                 "V11", "V12", "V13", "V14",
                                                                 "V15","V16","V17","V18"))

但我收到了一个结构怪异的表格：

structure(list(V1 = structure(c(2L, 2L, 2L, 3L, 3L, 4L, 4L, 4L, 
4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("@70L", "0003", 
"001V", "001W"), class = "factor"), VS = structure(c(5L, 6L, 
6L, 5L, 5L, 1L, 1L, 2L, 2L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L
), .Label = c("CANACCOR", "CLARUS", "DEACON", "MORGAN", "MPARTNER", 
"SPROTTSE"), class = "factor"), V3 = structure(c(9L, 1L, 1L, 
8L, 8L, 3L, 10L, 6L, 4L, 6L, 6L, 5L, 5L, 5L, 7L, 7L, 7L, 2L), .Label = c("HUGHES", 
"J", "K", "MACKAY", "MARTINEZ", "OFIR", "OLCOZ", "PEARLSTEIN", 
"SALZ", "WRIGHT"), class = "factor"), V4 = structure(c(9L, 9L, 
9L, 4L, 4L, 1L, 8L, 6L, 4L, 6L, 6L, 7L, 5L, 5L, 3L, 3L, 3L, 2L
), .Label = c("140321", "150608", "CERDAN", "D", "DE", "E", "J", 
"K", "S"), class = "factor"), V5 = structure(c(9L, 4L, 8L, 7L, 
12L, 2L, 6L, 5L, 11L, 10L, 13L, 3L, 15L, 15L, 14L, 14L, 14L, 
1L), .Label = c("01:25:35", "04:06:40", "100226", "140407", "140515", 
"140714", "140821", "141223", "150112", "150119", "150813", "151016", 
"171115", "J", "O"), class = "factor"), V6 = structure(c(16L, 
1L, 5L, 2L, 13L, 12L, 9L, 8L, 6L, 15L, 3L, 4L, 17L, 17L, 7L, 
10L, 11L, 14L), .Label = c("02:30:50", "02:44:05", "06:48:47", 
"07:12:51", "09:06:13", "09:40:45", "101112", "11:40:00", "12:47:31", 
"120712", "140226", "140609", "15:07:40", "171106", "22:03:46", 
"22:30:45", "J"), class = "factor"), V7 = structure(c(10L, 6L, 
12L, 7L, 11L, 17L, 9L, 8L, 13L, 14L, 15L, 4L, 4L, 5L, 2L, 3L, 
16L, 1L), .Label = c("00:16:05", "01:32:41", "03:19:26", "100708", 
"100910", "141120", "150312", "150515", "160228", "160304", "160411", 
"160715", "160812", "170328", "171115", "22:20:19", "23:06:44"
), class = "factor"), V8 = structure(c(5L, 13L, 7L, 8L, 6L, 18L, 
17L, 9L, 10L, 3L, 4L, 1L, 2L, 16L, 12L, 14L, 15L, 11L), .Label = c("04:51:16", 
"05:09:02", "06:45:14", "06:48:47", "08:38:13", "08:40:35", "08:42:56", 
"09:17:13", "09:27:09", "09:40:02", "1", "120618", "13:55:06", 
"131216", "150417", "21:16:07", "22:57:45", "SPECULATIVE"), class = "factor"), 
    V9 = structure(c(6L, 6L, 8L, 6L, 6L, 10L, 10L, 12L, 10L, 
    1L, 1L, 9L, 2L, 3L, 7L, 5L, 4L, 11L), .Label = c("1", "100910", 
    "101110", "13:07:31", "19:49:59", "2", "21:04:56", "3", "8", 
    "BUY", "OVERWT/ATTRACTIVE", "SPECULATIVE"), class = "factor"), 
    V10 = structure(c(6L, 6L, 8L, 6L, 6L, 2L, 2L, 6L, 2L, 6L, 
    6L, 7L, 1L, 4L, 3L, 5L, 3L, 3L), .Label = c("00:48:28", "1", 
    "2", "21:55:52", "6", "BUY", "EQUALWT/NO", "MARKETPERFORM"
    ), class = "factor"), V11 = structure(c(2L, 2L, 3L, 2L, 2L, 
    9L, 9L, 1L, 9L, 1L, 1L, 8L, 4L, 2L, 7L, 6L, 7L, 5L), .Label = c("1", 
    "2", "3", "6", "BUY", "EQUALWT/IN-LINE", "OVERWT/IN-LINE", 
    "RATING", "STRONG"), class = "factor"), V12 = structure(c(4L, 
    4L, 6L, 4L, 4L, 4L, 4L, 8L, 4L, 8L, 8L, 3L, 5L, 7L, 2L, 3L, 
    2L, 1L), .Label = c("1595", "2", "3", "BUY", "EQUALWT/IN-LINE", 
    "HOLD", "OVERWT/IN-LINE", "STRONG"), class = "factor"), V13 = structure(c(1L, 
    5L, 5L, 1L, 1L, 6L, 6L, 8L, 3L, 8L, 8L, 9L, 4L, 2L, 8L, 9L, 
    8L, 7L), .Label = c("12380", "2", "202", "3", "3764", "406", 
    "56947", "BUY", "HOLD"), class = "factor"), V14 = structure(c(5L, 
    7L, 7L, 4L, 4L, 1L, 1L, 6L, 9L, 8L, 8L, 3L, 11L, 10L, 3L, 
    3L, 3L, 2L), .Label = c("150412", "150608", "1595", "163717", 
    "165426", "202", "57379", "704", "73763", "BUY", "HOLD"), class = "factor"), 
    V15 = structure(c(8L, 4L, 7L, 6L, 10L, 3L, 5L, 2L, 9L, 2L, 
    2L, 12L, 11L, 11L, 12L, 12L, 12L, 1L), .Label = c("01:25:00", 
    "115944", "140319", "140401", "140714", "140820", "141223", 
    "150109", "150813", "151009", "1595", "56947"), class = "factor"), 
    V16 = structure(c(2L, 7L, 3L, 5L, 4L, 16L, 10L, 13L, 6L, 
    14L, 15L, 8L, 17L, 17L, 9L, 11L, 12L, 1L), .Label = c("", 
    "08:00:00", "08:02:00", "08:12:00", "08:16:00", "09:23:00", 
    "10:05:00", "100226", "101111", "12:38:00", "120711", "140226", 
    "140515", "150112", "171115", "23:19:00", "56947"), class = "factor"), 
    V17 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 7L, 1L, 4L, 
    2L, 3L, 5L, 6L, 9L, 8L, 10L, 1L), .Label = c("", "06:42:00", 
    "07:12:00", "07:24:00", "100708", "100910", "11:40:00", "19:20:00", 
    "20:03:00", "22:20:00"), class = "factor"), V18 = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 3L, 1L, 1L, 
    1L, 1L), .Label = c("", "03:14:00", "19:18:00"), class = "factor")), .Names = c("V1", 
"VS", "V3", "V4", "V5", "V6", "V7", "V8", "V9", "V10", "V11", 
"V12", "V13", "V14", "V15", "V16", "V17", "V18"), class = "data.frame", row.names = c(NA, 
-18L))

如上所述，我希望收到一个包含 16 列 的表格，其结构为 txt.file。即使是空字段（例如第 6 行）也应该保留。

例如第 6 行：

你能帮我解决这个问题吗？ 非常感谢。

【问题讨论】：

  • 你的问题从第 13 行开始，因为这个人的名字包含被认为是分隔符的空格。

标签： r read.table


【解决方案1】：

一种选择是使用read.fwf

df <- read.fwf("tst.txt", widths = c(8, 10, 14, 28, 7, 10, 7, 10, 7, 29, 3,
     21, 9, 8, 7, 8), header = FALSE)

#Now next part will be to remove the leading/training whitespaces from character fields. 
library(dplyr)
df <- df %>% mutate_if(is.factor, function(x)trimws(as.character(x)))

数据框如下：

df
#      V1       V2            V3 V4     V5       V6     V7       V8 V9               V10 V11        V12   V13    V14    V15      V16
# 1  0003 MPARTNER          SALZ  S 150112 22:30:45 160304 08:38:13  2               BUY   2        BUY 12380 165426 150109 08:00:00
# 2  0003 SPROTTSE        HUGHES  S 140407 02:30:50 141120 13:55:06  2               BUY   2        BUY  3764  57379 140401 10:05:00
# 3  0003 SPROTTSE        HUGHES  S 141223 09:06:13 160715 08:42:56  3     MARKETPERFORM   3       HOLD  3764  57379 141223 08:02:00
# 4  001V MPARTNER    PEARLSTEIN  D 140821 02:44:05 150312 09:17:13  2               BUY   2        BUY 12380 163717 140820 08:16:00
# 5  001V MPARTNER    PEARLSTEIN  D 151016 15:07:40 160411 08:40:35  2               BUY   2        BUY 12380 163717 151009 08:12:00
# 6  001W CANACCOR                K 140321 04:06:40 140609 23:06:44 NA   SPECULATIVE BUY   1 STRONG BUY   406 150412 140319 23:19:00
# 7  001W CANACCOR        WRIGHT  K 140714 12:47:31 160228 22:57:45 NA               BUY   1 STRONG BUY   406 150412 140714 12:38:00
# 8  001W   CLARUS          OFIR  E 140515 11:40:00 150515 09:27:09 NA   SPECULATIVE BUY   1 STRONG BUY   202 115944 140515 11:40:00
# 9  001W   CLARUS        MACKAY  D 150813 09:40:45 160812 09:40:02 NA               BUY   1 STRONG BUY   202  73763 150813 09:23:00
# 10 001W   DEACON          OFIR  E 150119 22:03:46 170328 06:45:14  1               BUY   1 STRONG BUY   704 115944 150112 07:24:00
# 11 001W   DEACON          OFIR  E 171115 06:48:47 171115 06:48:47  1               BUY   1 STRONG BUY   704 115944 171115 06:42:00
# 12 @70L   MORGAN      MARTINEZ  J 100226 07:12:51 100708 04:51:16  8 EQUALWT/NO RATING   3       HOLD  1595  56947 100226 07:12:00
# 13 @70L   MORGAN MARTINEZ DE O  J 100708 05:09:02 100910 00:48:28  6   EQUALWT/IN-LINE   3       HOLD  1595  56947 100708 03:14:00
# 14 @70L   MORGAN MARTINEZ DE O  J 100910 21:16:07 101110 21:55:52  2    OVERWT/IN-LINE   2        BUY  1595  56947 100910 19:18:00
# 15 @70L   MORGAN  OLCOZ CERDAN  J 101112 01:32:41 120618 21:04:56  2    OVERWT/IN-LINE   2        BUY  1595  56947 101111 20:03:00
# 16 @70L   MORGAN  OLCOZ CERDAN  J 120712 03:19:26 131216 19:49:59  6   EQUALWT/IN-LINE   3       HOLD  1595  56947 120711 19:20:00
# 17 @70L   MORGAN  OLCOZ CERDAN  J 140226 22:20:19 150417 13:07:31  2    OVERWT/IN-LINE   2        BUY  1595  56947 140226 22:20:00
# 18 @70L   MORGAN                J 150608 01:25:35 171106 00:16:05  1 OVERWT/ATTRACTIVE   2        BUY  1595  56947 150608 01:25:00

上面的 data.frame 有 16 列和 18 行。

【讨论】：

  • 是的，但问题是，例如对于第 6 行，列中的值分配不是我想要的。 V3 列应为空，并且 V9 应结合 tha 值“投机性购买”。看我编辑的帖子。谢谢
  • 是的。这就是我现在所意识到的。它增加了行数。
猜你喜欢
  • 1970-01-01
  • 1970-01-01
  • 1970-01-01
  • 1970-01-01
  • 1970-01-01
  • 1970-01-01
  • 1970-01-01
  • 2023-01-19
  • 1970-01-01
相关资源
最近更新 更多
热门标签
Java Python linux javascript Mysql C# Docker 算法 前端 SpringBoot Redis Vue spring 设计模式 .net core .net kubernetes c++ 数据库 数据结构 大数据 js 机器学习 微服务 Android Go 程序员 面试 JVM ASP.net core 云原生 人工智能 后端 PHP git CSS golang k8s Nginx Django mybatis 深度学习 多线程 React 架构 devops 爬虫 云计算 Spring Boot LeetCode