[R] finding duplicates in a data frame

[Rui Barradas]

Hello,

Thanks! Now we can see that your df1 only has one column, your dataset 
was messed up in some previous step. So, it needs to be transformed into 
a 3 columns data.frame first. Then use merge().



x <- levels(df1$new.col.ppm.p..freq.p.)[df1$new.col.ppm.p..freq.p.]
x <- t(sapply(x, function(xx) strsplit(xx, " ")))
x <- data.frame(do.call(rbind, x), stringsAsFactors=FALSE)
names(x) <- names(df2)
x$ppm.p. <- as.numeric(x$ppm.p.)
x$freq.p. <- as.numeric(x$freq.p.)
str(x)
'data.frame':   30 obs. of  3 variables:
  $ new.col: chr  "1_3_diaminopropane" "1_3_diaminopropane" 
"1_3_diaminopropane" "1_3_diaminopropane" ...
  $ ppm.p. : num  3.14 3.14 3.14 3.13 3.12 ...
  $ freq.p.: num  5.68 6.65 8.01 9.64 298.24 ...

# If the output is like above, it's ok to merge the two dfs
merge(x, df2, by.x=c("ppm.p.", "freq.p."), by.y=c("ppm.p.", "freq.p."))


If you want it's also ok to rename 'x' as 'df1', with df1 <- x

If this doesn't do it, say something.

Rui Barradas
Em 13-06-2012 13:45, Sathya Priya escreveu:
> *>dput(head(df1, 30))*
> structure(list(new.col.ppm.p..freq.p. = structure(c(22L, 21L,
> 20L, 19L, 18L, 17L, 16L, 15L, 14L, 13L, 12L, 11L, 10L, 9L, 8L,
> 7L, 6L, 5L, 4L, 3L, 2L, 1L, 24L, 23L, 26L, 25L, 90L, 89L, 88L,
> 87L), .Label = c("1_3_diaminopropane -0.00533455 7.32726",
> "1_3_diaminopropane 0.00021588 103.234",
> "1_3_diaminopropane 0.00655923 7.6155", "1_3_diaminopropane 2.04634
> 32.1115",
> "1_3_diaminopropane 2.0618 72.4135", "1_3_diaminopropane 2.06497 49.6692",
> "1_3_diaminopropane 2.07251 47.5652", "1_3_diaminopropane 2.07727 135.629",
> "1_3_diaminopropane 2.08242 51.5292", "1_3_diaminopropane 2.09312 79.8969",
> "1_3_diaminopropane 2.10859 37.0658", "1_3_diaminopropane 3.07912 5.6996",
> "1_3_diaminopropane 3.0807 7.47272", "1_3_diaminopropane 3.08943 308.2",
> "1_3_diaminopropane 3.09617 44.1467", "1_3_diaminopropane 3.10528 337.852",
> "1_3_diaminopropane 3.1152 44.6212", "1_3_diaminopropane 3.12075 298.243",
> "1_3_diaminopropane 3.13383 9.64184", "1_3_diaminopropane 3.13541 8.0142",
> "1_3_diaminopropane 3.137 6.65388", "1_3_diaminopropane 3.13859 5.67516",
> "1_3_dimethylurea 2.66393 39.238", "1_3_dimethylurea 4.80643 88.4026",
> "1_amino_1_phenylmethyl_phosphonic_acid 4.81412 105.11",
> "1_amino_1_phenylmethyl_phosphonic_acid 7.44687 7.1684",
> "2_3_diphospho_D_glyceric_acid 0.000156828 127.55",
> "2_3_diphospho_D_glyceric_acid 1.12848 35.0817",
> "2_3_diphospho_D_glyceric_acid 1.13681 45.9263",
> "2_3_diphospho_D_glyceric_acid 1.14513 64.8014",
> "2_3_diphospho_D_glyceric_acid 1.15306 116.661",
> "2_3_diphospho_D_glyceric_acid 1.1598 115.19",
> "2_3_diphospho_D_glyceric_acid 1.1709 102.384",
> "2_3_diphospho_D_glyceric_acid 1.17764 140.963",
> "2_3_diphospho_D_glyceric_acid 1.18478 115.727",
> "2_3_diphospho_D_glyceric_acid 1.19548 62.2725",
> "2_3_diphospho_D_glyceric_acid 1.20262 74.4761",
> "2_3_diphospho_D_glyceric_acid 1.20936 48.6332",
> "2_3_diphospho_D_glyceric_acid 1.21808 10.5804",
> "2_3_diphospho_D_glyceric_acid 1.22482 6.26529",
> "2_3_diphospho_D_glyceric_acid 1.27239 64.2389",
> "2_3_diphospho_D_glyceric_acid 1.27834 93.7896",
> "2_3_diphospho_D_glyceric_acid 1.29737 211.264",
> "2_3_diphospho_D_glyceric_acid 1.30371 298.131",
> "2_3_diphospho_D_glyceric_acid 1.32076 616.226",
> "2_3_diphospho_D_glyceric_acid 1.32671 503.942",
> "2_3_diphospho_D_glyceric_acid 1.33107 662.735",
> "2_3_diphospho_D_glyceric_acid 1.33741 593.161",
> "2_3_diphospho_D_glyceric_acid 1.35208 290.138",
> "2_3_diphospho_D_glyceric_acid 1.35724 310.132",
> "2_3_diphospho_D_glyceric_acid 1.36992 38.1639",
> "2_3_diphospho_D_glyceric_acid 1.38182 93.7426",
> "2_3_diphospho_D_glyceric_acid 1.62604 191.929",
> "2_3_diphospho_D_glyceric_acid 1.6522 179.805",
> "2_3_diphospho_D_glyceric_acid 1.77788 274.143",
> "2_3_diphospho_D_glyceric_acid 1.78462 294.731",
> "2_3_diphospho_D_glyceric_acid 1.79572 410.836",
> "2_3_diphospho_D_glyceric_acid 1.80167 361.596",
> "2_3_diphospho_D_glyceric_acid 1.82585 30.7865",
> "2_3_diphospho_D_glyceric_acid 1.95311 34.917",
> "2_3_diphospho_D_glyceric_acid 1.95787 30.7119",
> "2_3_diphospho_D_glyceric_acid 1.97849 465.916",
> "2_3_diphospho_D_glyceric_acid 1.99395 300.192",
> "2_3_diphospho_D_glyceric_acid 3.10007 55.6859",
> "2_3_diphospho_D_glyceric_acid 3.108 92.3526",
> "2_3_diphospho_D_glyceric_acid 3.12148 159.122",
> "2_3_diphospho_D_glyceric_acid 3.12981 193.855",
> "2_3_diphospho_D_glyceric_acid 3.13813 121.311",
> "2_3_diphospho_D_glyceric_acid 3.14289 114.087",
> "2_3_diphospho_D_glyceric_acid 3.15121 92.128",
> "2_3_diphospho_D_glyceric_acid 3.96911 17.9823",
> "2_3_diphospho_D_glyceric_acid 3.97823 36.9309",
> "2_3_diphospho_D_glyceric_acid 3.99052 57.8175",
> "2_3_diphospho_D_glyceric_acid 3.99964 100.939",
> "2_3_diphospho_D_glyceric_acid 4.00876 61.2461",
> "2_3_diphospho_D_glyceric_acid 4.01232 60.9695",
> "2_3_diphospho_D_glyceric_acid 4.01906 70.3493",
> "2_3_diphospho_D_glyceric_acid 4.02144 66.5612",
> "2_3_diphospho_D_glyceric_acid 4.02858 58.5852",
> "2_3_diphospho_D_glyceric_acid 4.03373 24.3897",
> "2_3_diphospho_D_glyceric_acid 4.04047 22.4084",
> "2_3_diphospho_D_glyceric_acid 4.04325 23.3606",
> "2_3_diphospho_D_glyceric_acid 4.04999 17.279",
> "2_3_diphospho_D_glyceric_acid 4.4853 22.1747",
> "2_3_diphospho_D_glyceric_acid 4.49164 44.5942",
> "2_3_diphospho_D_glyceric_acid 4.49799 25.3894",
> "2_3_diphospho_D_glyceric_acid 4.50076 35.5218",
> "2_3_diphospho_D_glyceric_acid 4.51028 44.1328",
> "2_3_diphospho_D_glyceric_acid 4.51622 21.4894",
> "2_3_diphospho_D_glyceric_acid 4.5186 18.3831",
> "2_amino_5_ethyl_1_3_4_thiadiazole 0.000156828 127.55",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.12848 35.0817",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.13681 45.9263",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.14513 64.8014",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.15306 116.661",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.1598 115.19",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.1709 102.384",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.17764 140.963",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.18478 115.727",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.19548 62.2725",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.20262 74.4761",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.20936 48.6332",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.21808 10.5804",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.22482 6.26529",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.27239 64.2389",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.27834 93.7896",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.29737 211.264",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.30371 298.131",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.32076 616.226",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.32671 503.942",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.33107 662.735",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.33741 593.161",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.35208 290.138",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.35724 310.132",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.36992 38.1639",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.38182 93.7426",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.62604 191.929",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.6522 179.805",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.77788 274.143",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.78462 294.731",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.79572 410.836",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.80167 361.596",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.82585 30.7865",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.95311 34.917",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.95787 30.7119",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.97849 465.916",
> "2_amino_5_ethyl_1_3_4_thiadiazole 1.99395 300.192",
> "2_amino_5_ethyl_1_3_4_thiadiazole 3.10007 55.6859",
> "2_amino_5_ethyl_1_3_4_thiadiazole 3.108 92.3526",
> "2_amino_5_ethyl_1_3_4_thiadiazole 3.12148 159.122",
> "2_amino_5_ethyl_1_3_4_thiadiazole 3.12981 193.855",
> "2_amino_5_ethyl_1_3_4_thiadiazole 3.13813 121.311",
> "2_amino_5_ethyl_1_3_4_thiadiazole 3.14289 114.087",
> "2_amino_5_ethyl_1_3_4_thiadiazole 3.15121 92.128",
> "2_amino_5_ethyl_1_3_4_thiadiazole 3.96911 17.9823",
> "2_amino_5_ethyl_1_3_4_thiadiazole 3.97823 36.9309",
> "2_amino_5_ethyl_1_3_4_thiadiazole 3.99052 57.8175",
> "2_amino_5_ethyl_1_3_4_thiadiazole 3.99964 100.939",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.00876 61.2461",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.01232 60.9695",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.01906 70.3493",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.02144 66.5612",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.02858 58.5852",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.03373 24.3897",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.04047 22.4084",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.04325 23.3606",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.04999 17.279",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.4853 22.1747",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.49164 44.5942",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.49799 25.3894",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.50076 35.5218",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.51028 44.1328",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.51622 21.4894",
> "2_amino_5_ethyl_1_3_4_thiadiazole 4.5186 18.3831"
> ), class = "factor")), .Names = "new.col.ppm.p..freq.p.", row.names = c(NA,
> 30L), class = "data.frame")
>>   dput(head(df2, 30))
> structure(list(new.col = structure(c(1L, 1L), .Label = "unknown", class =
> "factor"),
>      ppm.p. = c(7.44687, 4.81412), freq.p. = c(7.1684, 105.11)), .Names =
> c("new.col",
> "ppm.p.", "freq.p."), row.names = 1:2, class = "data.frame")
>