First of all I’ve seen several questions similar to it but not specifying the name of the dfs
My df
structure(list(paciente = structure(c(6163, 6553, 6357, 6331,
6228, 6280, 6383, 6198, 6316, 6148), label = "Paciente", format.spss = "F6.0"),
grupo_int_v00 = structure(c(1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L,
1L, 2L), .Label = c("A", "B"), label = "Grupo de intervención", class = "factor"),
time = structure(c(3L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L
), .Label = c("00", "01", "66"), class = "factor"), peso1 = c(76.3,
95.4, 103.5, 82.1, 103.3, 77.6, 76, 88.3, 64, 101), cintura1 = c(104.5,
120, 116, 104, 120.5, 104, NA, 110, 104, 119), tasis2_e = c(145,
137, 123, 153, 131, 147, NA, 147, 121, 131), tadias2_e = c(64,
61, 76, 75, 65, 84, NA, 76, 59, 96), p17_total = c(12, 3,
9, 6, 8, 10, 9, 7, 12, 9), geaf_tot = c(1678.32, 1398.6,
1566.43, 587.41, 4876.46, 3776.22, 1762.24, 3188.81, 7192.54,
1678.32), glucosa = c(273, 149, 96, 115, 101, 94, NA, 125,
104, 107), albumi = c(4.15, 4.75, 4.59, 4.83, 4.64, 4.49,
NA, 4.71, 4.33, 4.09), coltot = c(137, 174, 252, 270, 211,
164, NA, 192, 281, 234), hdl = c(30, 56, 45, 74, 66, 51,
NA, 34, 62, 44), ldl_calc = c(51, 95, NA, 177, 127, 90, NA,
130, 186, 170), trigli = c(280, 114, 309, 96, 89, 115, NA,
139, 165, 99), hba1c = c(13.77, 6.57, 5.65, 6.52, 5.69, 6.02,
NA, 6.25, 5.95, 5.93), i_hucpeptide = c(3567.05, 1407.53,
1259.29, 1028.31, 649.19, 893.52, NA, 815.82, 342.68, NA),
i_hughrelin = c(1214.83, 874.6, 1015.68, 919.51, 456.28,
650.22, NA, 143.32, 1159.1, NA), i_hugip = c(2.67, 2.67,
2.67, 2.67, 2.67, 2.67, NA, 2.67, 2.67, NA), i_huglp1 = c(538.62,
264.67, 106.76, 164.82, 141.23, 14.14, NA, 112.57, 14.14,
NA), i_huglucagon = c(720.19, 801.94, 321.68, 629.04, 186.88,
238.33, NA, 238, 265.84, NA), i_huinsulin = c(1646.21, 545.57,
297.96, 333.05, 232.17, 263.55, NA, 263.87, 136.97, NA),
i_huleptin = c(8476.58, 10680.93, 6034.91, 14225.58, 2160.27,
2778.49, NA, 2829.59, 6102.63, NA), i_hupai1 = c(3787.2,
2401.66, 1040.35, 2123.09, 1625.27, 1932.06, NA, 2483.08,
919.81, NA), i_huresistin = c(11350.35, 5171.75, 5794.31,
2814.22, 2994.15, 3215.24, NA, 2577.84, 3227.73, NA), i_huvisfatin = c(1652.92,
2125.95, 407.98, 3544.59, 8.64, 132.49, NA, 8.64, 189.96,
NA), col_rema = c(56, 23, NA, 19, 18, 23, NA, 28, 33, 20),
homa = c(19974.0146666667, 3612.88577777778, 1271.296, 1702.25555555556,
1042.18533333333, 1101.05333333333, NA, 1465.94444444444,
633.105777777778, NA), i_pcr = c(0.39, 0.57, 0.04, 0.22,
0.04, 1.01, NA, 0.1, 0.04, NA), i_ratiolg = c(6.97758534115885,
12.2123599359707, 5.94174346250788, 15.4708268534328, 4.73452704479705,
4.273153701824, NA, 19.743162154619, 5.26497282374256, NA
)), row.names = c(NA, -10L), class = c("tbl_df", "tbl", "data.frame"
))
The df looks like:
paciente grupo_int_v00 time peso1 cintura1 tasis2_e tadias2_e
<dbl> <fct> <fct> <dbl> <dbl> <dbl> <dbl>
1 6163 A 66 76.3 104. 145 64
2 6553 A 01 95.4 120 137 61
3 6357 B 01 104. 116 123 76
4 6331 B 00 82.1 104 153 75
5 6228 A 01 103. 120. 131 65
6 6280 B 01 77.6 104 147 84
split(df, df$grupo_int_v00) %>% list2env(envir = globalenv())
I am generating dfs with the name of the grupo_int_v00, now imagine I want to set my name of the df, how can I do that? Because my grupo_int_v00 here is A or B, but usually are numbers, and I don’t want them to be numbers, I want them to be group_A , group_B, group_C …
Not sure if you can provide with dplyr option (group_split and set_names or similar)
Thank you
>Solution :
You can change the names with paste + set_names:
library(magrittr)
split(df, df$grupo_int_v00) %>%
set_names(paste("group", names(.), sep = "_"))
The base R alternative is:
spl <- split(df, df$grupo_int_v00)
names(spl) <- paste("group", names(spl), sep = "_")
An even shorter alternative is to add the paste call in the split function:
split(df, ~ paste0("group_", grupo_int_v00))
output
> spl
$group_A
# A tibble: 6 × 30
paciente grupo_i…¹ time peso1 cintu…² tasis…³ tadia…⁴ p17_t…⁵ geaf_…⁶ glucosa albumi coltot
<dbl> <fct> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 6163 A 66 76.3 104. 145 64 12 1678. 273 4.15 137
2 6553 A 01 95.4 120 137 61 3 1399. 149 4.75 174
3 6228 A 01 103. 120. 131 65 8 4876. 101 4.64 211
4 6383 A 01 76 NA NA NA 9 1762. NA NA NA
5 6198 A 01 88.3 110 147 76 7 3189. 125 4.71 192
6 6316 A 01 64 104 121 59 12 7193. 104 4.33 281
# … with 18 more variables: hdl <dbl>, ldl_calc <dbl>, trigli <dbl>, hba1c <dbl>,
# i_hucpeptide <dbl>, i_hughrelin <dbl>, i_hugip <dbl>, i_huglp1 <dbl>, i_huglucagon <dbl>,
# i_huinsulin <dbl>, i_huleptin <dbl>, i_hupai1 <dbl>, i_huresistin <dbl>,
# i_huvisfatin <dbl>, col_rema <dbl>, homa <dbl>, i_pcr <dbl>, i_ratiolg <dbl>, and
# abbreviated variable names ¹grupo_int_v00, ²cintura1, ³tasis2_e, ⁴tadias2_e, ⁵p17_total,
# ⁶geaf_tot
# ℹ Use `colnames()` to see all variable names
$group_B
# A tibble: 4 × 30
paciente grupo_i…¹ time peso1 cintu…² tasis…³ tadia…⁴ p17_t…⁵ geaf_…⁶ glucosa albumi coltot
<dbl> <fct> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 6357 B 01 104. 116 123 76 9 1566. 96 4.59 252
2 6331 B 00 82.1 104 153 75 6 587. 115 4.83 270
3 6280 B 01 77.6 104 147 84 10 3776. 94 4.49 164
4 6148 B 01 101 119 131 96 9 1678. 107 4.09 234
# … with 18 more variables: hdl <dbl>, ldl_calc <dbl>, trigli <dbl>, hba1c <dbl>,
# i_hucpeptide <dbl>, i_hughrelin <dbl>, i_hugip <dbl>, i_huglp1 <dbl>, i_huglucagon <dbl>,
# i_huinsulin <dbl>, i_huleptin <dbl>, i_hupai1 <dbl>, i_huresistin <dbl>,
# i_huvisfatin <dbl>, col_rema <dbl>, homa <dbl>, i_pcr <dbl>, i_ratiolg <dbl>, and
# abbreviated variable names ¹grupo_int_v00, ²cintura1, ³tasis2_e, ⁴tadias2_e, ⁵p17_total,
# ⁶geaf_tot
# ℹ Use `colnames()` to see all variable names