make a group index for df

Question

Say I have a df with 20 addresses, how do I add an index of four groups of five to it? The new column should be 1,1,1,1,1,2,2,2,2,2,3,3,3,3,3,4,4,4,4,4.

E.g. how do I turn this tibble:

tibble::tribble(
              ~num_street,           ~city, ~sate, ~zip_code,
        "976 FAIRVIEW DR",   "SPRINGFIELD",  "OR",    97477L,
          "19843 HWY 213",   "OREGON CITY",  "OR",    97045L,
            "402 CARL ST",         "DRAIN",  "OR",    97435L,
           "304 WATER ST",        "WESTON",  "OR",    97886L,
   "5054 TECHNOLOGY LOOP",     "CORVALLIS",  "OR",    97333L,
         "3401 YACHT AVE",  "LINCOLN CITY",  "OR",    97367L,
      "135 ROOSEVELT AVE",          "BEND",  "OR",    97702L,
         "3631 FENWAY ST",  "FOREST GROVE",  "OR",    97116L,
       "92250 HILLTOP LN",      "COQUILLE",  "OR",    97423L,
          "6920 92ND AVE",        "TIGARD",  "OR",    97223L,
          "591 LAUREL ST", "JUNCTION CITY",  "OR",    97448L,
   "32035 LYNX HOLLOW RD",      "CRESWELL",  "OR",    97426L,
          "6280 ASTER ST",   "SPRINGFIELD",  "OR",    97478L,
      "17533 VANGUARD LN",     "BEAVERTON",  "OR",    97007L,
      "59937 CHEYENNE RD",          "BEND",  "OR",    97702L,
          "2232 42ND AVE",         "SALEM",  "OR",    97317L,
         "3100 TURNER RD",         "SALEM",  "OR",    97302L,
       "3495 CHAMBERS ST",        "EUGENE",  "OR",    97405L,
          "585 WINTER ST",         "SALEM",  "OR",    97301L,
        "23985 VAUGHN RD",        "VENETA",  "OR",    97487L
  )

Into this:

tibble::tribble(
~group,             ~num_street,           ~city, ~state, ~zip_code,
    1L,       "976 FAIRVIEW DR",   "SPRINGFIELD",   "OR",    97477L,
    1L,         "19843 HWY 213",   "OREGON CITY",   "OR",    97045L,
    1L,           "402 CARL ST",         "DRAIN",   "OR",    97435L,
    1L,          "304 WATER ST",        "WESTON",   "OR",    97886L,
    1L,  "5054 TECHNOLOGY LOOP",     "CORVALLIS",   "OR",    97333L,
    2L,        "3401 YACHT AVE",  "LINCOLN CITY",   "OR",    97367L,
    2L,     "135 ROOSEVELT AVE",          "BEND",   "OR",    97702L,
    2L,        "3631 FENWAY ST",  "FOREST GROVE",   "OR",    97116L,
    2L,      "92250 HILLTOP LN",      "COQUILLE",   "OR",    97423L,
    2L,         "6920 92ND AVE",        "TIGARD",   "OR",    97223L,
    3L,         "591 LAUREL ST", "JUNCTION CITY",   "OR",    97448L,
    3L,  "32035 LYNX HOLLOW RD",      "CRESWELL",   "OR",    97426L,
    3L,         "6280 ASTER ST",   "SPRINGFIELD",   "OR",    97478L,
    3L,     "17533 VANGUARD LN",     "BEAVERTON",   "OR",    97007L,
    3L,     "59937 CHEYENNE RD",          "BEND",   "OR",    97702L,
    4L,         "2232 42ND AVE",         "SALEM",   "OR",    97317L,
    4L,        "3100 TURNER RD",         "SALEM",   "OR",    97302L,
    4L,      "3495 CHAMBERS ST",        "EUGENE",   "OR",    97405L,
    4L,         "585 WINTER ST",         "SALEM",   "OR",    97301L,
    4L,       "23985 VAUGHN RD",        "VENETA",   "OR",    97487L
)

I know this is incredibly easy; i'm still getting to grips with R though and I have gaps on some of this basic stuff...

Related post: https://stackoverflow.com/q/3318333/680068 – zx8754 May 31 '23 at 19:23 — zx8754, May 31 '23 at 19:23

score 2 · Accepted Answer · answered May 31 '23 at 17:43

We could use gl() function:

library(dplyr)

df %>% 

  mutate(group =as.integer(gl(n(),5,n())))

# A tibble: 20 × 5
   num_street           city          sate  zip_code group
   <chr>                <chr>         <chr>    <int> <int>
 1 976 FAIRVIEW DR      SPRINGFIELD   OR       97477     1
 2 19843 HWY 213        OREGON CITY   OR       97045     1
 3 402 CARL ST          DRAIN         OR       97435     1
 4 304 WATER ST         WESTON        OR       97886     1
 5 5054 TECHNOLOGY LOOP CORVALLIS     OR       97333     1
 6 3401 YACHT AVE       LINCOLN CITY  OR       97367     2
 7 135 ROOSEVELT AVE    BEND          OR       97702     2
 8 3631 FENWAY ST       FOREST GROVE  OR       97116     2
 9 92250 HILLTOP LN     COQUILLE      OR       97423     2
10 6920 92ND AVE        TIGARD        OR       97223     2
11 591 LAUREL ST        JUNCTION CITY OR       97448     3
12 32035 LYNX HOLLOW RD CRESWELL      OR       97426     3
13 6280 ASTER ST        SPRINGFIELD   OR       97478     3
14 17533 VANGUARD LN    BEAVERTON     OR       97007     3
15 59937 CHEYENNE RD    BEND          OR       97702     3
16 2232 42ND AVE        SALEM         OR       97317     4
17 3100 TURNER RD       SALEM         OR       97302     4
18 3495 CHAMBERS ST     EUGENE        OR       97405     4
19 585 WINTER ST        SALEM         OR       97301     4
20 23985 VAUGHN RD      VENETA        OR       97487     4

r2evans · Answer 2 · 2023-05-31T18:13:54.537

We can use %/% (integer-division) as well:

df %>%
  mutate(group = (row_number() - 1) %/% 5 + 1)
# # A tibble: 20 × 5
#    num_street           city          sate  zip_code group
#    <chr>                <chr>         <chr>    <int> <dbl>
#  1 976 FAIRVIEW DR      SPRINGFIELD   OR       97477     1
#  2 19843 HWY 213        OREGON CITY   OR       97045     1
#  3 402 CARL ST          DRAIN         OR       97435     1
#  4 304 WATER ST         WESTON        OR       97886     1
#  5 5054 TECHNOLOGY LOOP CORVALLIS     OR       97333     1
#  6 3401 YACHT AVE       LINCOLN CITY  OR       97367     2
#  7 135 ROOSEVELT AVE    BEND          OR       97702     2
#  8 3631 FENWAY ST       FOREST GROVE  OR       97116     2
#  9 92250 HILLTOP LN     COQUILLE      OR       97423     2
# 10 6920 92ND AVE        TIGARD        OR       97223     2
# 11 591 LAUREL ST        JUNCTION CITY OR       97448     3
# 12 32035 LYNX HOLLOW RD CRESWELL      OR       97426     3
# 13 6280 ASTER ST        SPRINGFIELD   OR       97478     3
# 14 17533 VANGUARD LN    BEAVERTON     OR       97007     3
# 15 59937 CHEYENNE RD    BEND          OR       97702     3
# 16 2232 42ND AVE        SALEM         OR       97317     4
# 17 3100 TURNER RD       SALEM         OR       97302     4
# 18 3495 CHAMBERS ST     EUGENE        OR       97405     4
# 19 585 WINTER ST        SALEM         OR       97301     4
# 20 23985 VAUGHN RD      VENETA        OR       97487     4

make a group index for df

2 Answers2