1

R newbie here, so please excuse my ignorance. My data looks like this:

                                                                      JOB_ROLE       EXP_IT_NETW
1  Software engineering-related (developer, tester, project manager, architecture)        5<10
3                                                                        See below        None
4                                                                          Student          <1
5  Software engineering-related (developer, tester, project manager, architecture)         1<5
6                                                                          Blogger         10+

I would like to count the instances of each value in column 2 and group the counts by column 1, so that the result looks something like this:

JOB_ROLE           None    <1    1<5    5<10    10+
Software engineer    3      5     10     15     3
Student              10     7     5      1      0
...

Any ideas on how to do this? My dput output is below. Thanks in advance!

structure(list(JOB_ROLE = c("Software engineering-related (developer, tester, project manager, architecture)", 
"See below", "Student", "Software engineering-related (developer, tester, project manager, architecture)", 
"Blogger", "Systems Support", "Student", "IT/Network Administrator", 
"Software engineering-related (developer, tester, project manager, architecture)", 
"Student", "Student", "Software engineering-related (developer, tester, project manager, architecture)", 
"IT hobbyist", "Student", "Software engineering-related (developer, tester, project manager, architecture)", 
"Software engineering-related (developer, tester, project manager, architecture)", 
"IT Manager", "Software engineering-related (developer, tester, project manager, architecture)", 
"Software engineering-related (developer, tester, project manager, architecture)", 
"Software engineering-related (developer, tester, project manager, architecture)", 
"Software engineering-related (developer, tester, project manager, architecture)", 
"IT/Network Administrator", "IT/Network Administrator", "Software engineering-related (developer, tester, project manager, architecture)", 
"Software engineering-related (developer, tester, project manager, architecture)", 
"Student", "Software engineering-related (developer, tester, project manager, architecture)", 
"Researcher in CompSci or related field", "Researcher in CompSci or related field", 
"IT/Network Administrator", "Student", "Software engineering-related (developer, tester, project manager, architecture)", 
"Software engineering-related (developer, tester, project manager, architecture)", 
"Software engineering-related (developer, tester, project manager, architecture)", 
"Software engineering-related (developer, tester, project manager, architecture)", 
"Education", "Software engineering-related (developer, tester, project manager, architecture)", 
"Software engineering-related (developer, tester, project manager, architecture)", 
"IT/Network Administrator", "Software engineering-related (developer, tester, project manager, architecture)", 
"IT/Network Administrator", "Student", "IT/Network Administrator", 
"Software engineering-related (developer, tester, project manager, architecture)", 
"Student", "IT/Network Administrator", "just a layperson who has used computers for over 30 years", 
"IT/Network Administrator", "Unemployed", "Student", "IT/Network Administrator"
), EXP_IT_NETW = c("5<10", "None", "<1", "1<5", "10+", "None", 
"1<5", "10+", "<1", "None", "1<5", "1<5", "None", "None", "10+", 
"None", "1<5", "10+", "None", "1<5", "None", "1<5", "10+", "1<5", 
"1<5", "1<5", "None", "None", "1<5", "5<10", "None", "5<10", 
"<1", "None", "1<5", "None", "1<5", "1<5", "10+", "1<5", "10+", 
"None", "1<5", "5<10", "None", "1<5", "None", "1<5", "None", 
"None", "10+")), .Names = c("JOB_ROLE", "EXP_IT_NETW"), class = "data.frame", row.names = c(1L, 
3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 16L, 17L, 18L, 
19L, 20L, 21L, 22L, 23L, 25L, 26L, 27L, 28L, 29L, 30L, 32L, 33L, 
34L, 35L, 36L, 37L, 39L, 40L, 41L, 42L, 43L, 44L, 47L, 48L, 49L, 
50L, 51L, 52L, 53L, 55L, 56L, 57L, 59L, 61L, 62L))
4

2 に答える 2

5

使用table:

> table(d)
                                                                                 EXP_IT_NETW
JOB_ROLE                                                                          <1 1<5 10+ 5<10 None
  Blogger                                                                          0   0   1    0    0
  Education                                                                        0   0   0    0    1
  IT hobbyist                                                                      0   0   0    0    1
  IT Manager                                                                       0   1   0    0    0
  IT/Network Administrator                                                         0   4   5    1    0
  just a layperson who has used computers for over 30 years                        0   0   0    0    1
  Researcher in CompSci or related field                                           0   1   0    0    1
  See below                                                                        0   0   0    0    1
  Software engineering-related (developer, tester, project manager, architecture)  2   9   2    3    5
  Student                                                                          1   3   0    0    6
  Systems Support                                                                  0   0   0    0    1
  Unemployed                                                                       0   0   0    0    1
于 2013-03-27T19:57:16.530 に答える
3

私も使用しますdata.tableが、あなたが期待するのと同じフォーマットを得るために少し異なります。

require(data.table)
dt <- data.table(df) # here, I assume df is your data.frame

setkey(dt, "JOB_ROLE") # setkey for fast access/grouping

 dt[, {tt <- table(factor(EXP_IT_NETW, 
                 levels=factor(unique(dt$EXP_IT_NETW)))); 
       setattr(as.list(tt), 'names', names(tt))
      }, by = key(dt)]

私はこれを得る：

#                                   JOB_ROLE None 10+ 1<5 5<10 <1
#  1:                   >30_years_experience    1   0   0    0  0
#  2:                                Blogger    0   1   0    0  0
#  3:                              Education    1   0   0    0  0
#  4:                             IT Manager    0   0   1    0  0
#  5:                            IT hobbyist    1   0   0    0  0
#  6:               IT/Network Administrator    0   5   4    1  0
#  7: Researcher in CompSci or related field    1   0   1    0  0
#  8:                              See below    1   0   0    0  0
#  9:                   Software_enginnering    5   2   9    3  2
# 10:                                Student    6   0   3    0  1
# 11:                        Systems Support    1   0   0    0  0
# 12:                             Unemployed    1   0   0    0  0
于 2013-03-27T19:55:27.277 に答える