[R] How to filter data in R based on first column ID

Sun Jun 23 17:22:06 CEST 2019

Hi Rui,

Thanks for your help. but still I did not able to get the data.

> dput(head(data))

structure(list(`Root-1.S35.L001` = c(0, 0, 0, 0, 0, 0.0467945718296678

), `Root-10.S75.L001` = c(0, 0, 0, 0, 0, 0), `Root-13.S5.L001` = c(0,

0, 0, 0, 0, 0), `Root-14.S16.L001` = c(0, 0, 0, 0, 0, 0),
`Root-17.S26.L001` = c(0,

0, 0, 0, 0, 0), `Root-18.S36.L001` = c(0, 0, 0, 0, 0, 0),
`Root-19.S46.L001` = c(0,

0, 0, 0, 0, 0), `Root-22.S56.L001` = c(0, 0, 0, 0, 0, 0),
`Root-24.S66.L001` = c(0,

0, 0, 0, 0, 0), `Root-25.S76.L001` = c(0, 0, 0, 0, 0, 0), `Root-26.S6.L001`
= c(0,

0, 0, 0, 0, 0), `Root-27.S17.L001` = c(0.0293745480838756, 0,

0, 0, 0, 0), `Root-3.S45.L001` = c(0, 0, 0, 0, 0, 0), `Root-30.S27.L001` =
c(0,

0, 0, 0, 0, 0), `Root-32.S37.L001` = c(0, 0, 0, 0, 0, 0),
`Root-34.S47.L001` = c(0,

0, 0, 0, 0, 0), `Root-39.S57.L001` = c(0, 0, 0, 0, 0, 0), `Root-4.S55.L001`
= c(0,

0, 0, 0, 0, 0), `Root-40.S67.L001` = c(0.0189409882986783, 0,

0, 0, 0, 0), `Root-41.S77.L001` = c(0.0171320884015762, 0, 0,

0.0202470135654991, 0, 0), `Root-43.S7.L001` = c(0, 0, 0, 0,

0, 0), `Root-45.S18.L001` = c(0, 0, 0, 0, 0, 0), `Root-47.S28.L001` = c(0,

0, 0, 0, 0, 0), `Root-50.S38.L001` = c(0, 0, 0, 0, 0, 0),
`Root-51.S48.L001` = c(0,

0, 0, 0, 0, 0), `Root-54.S58.L001` = c(0.0080481457966323, 0,

0, 0, 0, 0), `Root-9.S65.L001` = c(0.00744125132082211, 0, 0,

0, 0, 0), Root.11.S5 = c(0, 0, 0, 0, 0, 0), Root.12.S16 = c(0,

0, 0, 0, 0, 0), Root.15.S26 = c(0, 0, 0, 0, 0, 0), Root.16.S36 = c(0,

0, 0, 0, 0, 0), Root.2.S35 = c(0, 0, 0, 0, 0, 0), Root.20.S46 = c(0,

0, 0, 0, 0, 0), Root.21.S56 = c(0, 0, 0, 0, 0, 0), Root.23.S66 = c(0,

0, 0, 0.0123632317487791, 0, 0), Root.28.S76 = c(0, 0, 0, 0,

0, 0), Root.29.S6 = c(0, 0, 0, 0, 0, 0), Root.31.S17 = c(0, 0,

0, 0, 0, 0), Root.33.S27 = c(0.0165520894254218, 0, 0, 0, 0,

0), Root.35.S37 = c(0, 0, 0, 0, 0, 0), Root.36.S47 = c(0,
0.00731421884142774,

0, 0, 0, 0), Root.37.S57 = c(0.00668627975394491, 0, 0,
0.00780065971293572,

0, 0), Root.38.S67 = c(0, 0, 0, 0, 0, 0), Root.42.S77 =
c(0.00368785956630772,

0, 0, 0, 0.00553178934946157, 0), Root.44.S7 = c(0, 0, 0.0306968177632252,

0, 0, 0), Root.46.S18 = c(0, 0, 0, 0, 0, 0), Root.48.S28 = c(0,

0, 0, 0, 0, 0), Root.49.S38 = c(0, 0.0133380016339052, 0, 0,

0, 0), Root.5.S45 = c(0, 0, 0, 0, 0, 0), Root.52.S48 = c(0, 0,

0, 0, 0, 0), Root.53.S58 = c(0, 0, 0, 0, 0, 0), Root.6.S55 =
c(0.0150072892547809,

0, 0, 0, 0, 0), Root.7.S65 = c(0, 0, 0, 0, 0, 0), Root.8.S75 = c(0,

0, 0, 0.0062986835751328, 0, 0)), row.names =
c("71f84e7910006f22684121564206e8ca",

"03b167b9f86f2519b4263b4125377eed", "54e204fb99c80764e964456dadd6a0e5",

"55cd1fc570879d645bbf7a3642e9b0a8", "65f5c31e12c277aec319e2096463f9d2",

"7bed62f0fef250fd831dcf13bf43f4fc"), class = "data.frame")

> i <- row.names(data) %in% otu.list

> data[i, ]

 [1] Root-1.S35.L001  Root-10.S75.L001 Root-13.S5.L001  Root-14.S16.L001

 [5] Root-17.S26.L001 Root-18.S36.L001 Root-19.S46.L001 Root-22.S56.L001

 [9] Root-24.S66.L001 Root-25.S76.L001 Root-26.S6.L001  Root-27.S17.L001

[13] Root-3.S45.L001  Root-30.S27.L001 Root-32.S37.L001 Root-34.S47.L001

[17] Root-39.S57.L001 Root-4.S55.L001  Root-40.S67.L001 Root-41.S77.L001

[21] Root-43.S7.L001  Root-45.S18.L001 Root-47.S28.L001 Root-50.S38.L001

[25] Root-51.S48.L001 Root-54.S58.L001 Root-9.S65.L001  Root.11.S5

[29] Root.12.S16      Root.15.S26      Root.16.S36      Root.2.S35

[33] Root.20.S46      Root.21.S56      Root.23.S66      Root.28.S76

[37] Root.29.S6       Root.31.S17      Root.33.S27      Root.35.S37

[41] Root.36.S47      Root.37.S57      Root.38.S67      Root.42.S77

[45] Root.44.S7       Root.46.S18      Root.48.S28      Root.49.S38

[49] Root.5.S45       Root.52.S48      Root.53.S58      Root.6.S55

[53] Root.7.S65       Root.8.S75

<0 rows> (or 0-length row.names)

Thanks

On Sun, Jun 23, 2019 at 4:20 PM Yogesh Gupta <nabiyogesh using gmail.com> wrote:

> Hi Rui,
>
> Thanks for your help. but still I did able to get the data.
>
> > dput(head(data))
>
> structure(list(`Root-1.S35.L001` = c(0, 0, 0, 0, 0, 0.0467945718296678
>
> ), `Root-10.S75.L001` = c(0, 0, 0, 0, 0, 0), `Root-13.S5.L001` = c(0,
>
> 0, 0, 0, 0, 0), `Root-14.S16.L001` = c(0, 0, 0, 0, 0, 0),
> `Root-17.S26.L001` = c(0,
>
> 0, 0, 0, 0, 0), `Root-18.S36.L001` = c(0, 0, 0, 0, 0, 0),
> `Root-19.S46.L001` = c(0,
>
> 0, 0, 0, 0, 0), `Root-22.S56.L001` = c(0, 0, 0, 0, 0, 0),
> `Root-24.S66.L001` = c(0,
>
> 0, 0, 0, 0, 0), `Root-25.S76.L001` = c(0, 0, 0, 0, 0, 0),
> `Root-26.S6.L001` = c(0,
>
> 0, 0, 0, 0, 0), `Root-27.S17.L001` = c(0.0293745480838756, 0,
>
> 0, 0, 0, 0), `Root-3.S45.L001` = c(0, 0, 0, 0, 0, 0), `Root-30.S27.L001` =
> c(0,
>
> 0, 0, 0, 0, 0), `Root-32.S37.L001` = c(0, 0, 0, 0, 0, 0),
> `Root-34.S47.L001` = c(0,
>
> 0, 0, 0, 0, 0), `Root-39.S57.L001` = c(0, 0, 0, 0, 0, 0),
> `Root-4.S55.L001` = c(0,
>
> 0, 0, 0, 0, 0), `Root-40.S67.L001` = c(0.0189409882986783, 0,
>
> 0, 0, 0, 0), `Root-41.S77.L001` = c(0.0171320884015762, 0, 0,
>
> 0.0202470135654991, 0, 0), `Root-43.S7.L001` = c(0, 0, 0, 0,
>
> 0, 0), `Root-45.S18.L001` = c(0, 0, 0, 0, 0, 0), `Root-47.S28.L001` = c(0,
>
> 0, 0, 0, 0, 0), `Root-50.S38.L001` = c(0, 0, 0, 0, 0, 0),
> `Root-51.S48.L001` = c(0,
>
> 0, 0, 0, 0, 0), `Root-54.S58.L001` = c(0.0080481457966323, 0,
>
> 0, 0, 0, 0), `Root-9.S65.L001` = c(0.00744125132082211, 0, 0,
>
> 0, 0, 0), Root.11.S5 = c(0, 0, 0, 0, 0, 0), Root.12.S16 = c(0,
>
> 0, 0, 0, 0, 0), Root.15.S26 = c(0, 0, 0, 0, 0, 0), Root.16.S36 = c(0,
>
> 0, 0, 0, 0, 0), Root.2.S35 = c(0, 0, 0, 0, 0, 0), Root.20.S46 = c(0,
>
> 0, 0, 0, 0, 0), Root.21.S56 = c(0, 0, 0, 0, 0, 0), Root.23.S66 = c(0,
>
> 0, 0, 0.0123632317487791, 0, 0), Root.28.S76 = c(0, 0, 0, 0,
>
> 0, 0), Root.29.S6 = c(0, 0, 0, 0, 0, 0), Root.31.S17 = c(0, 0,
>
> 0, 0, 0, 0), Root.33.S27 = c(0.0165520894254218, 0, 0, 0, 0,
>
> 0), Root.35.S37 = c(0, 0, 0, 0, 0, 0), Root.36.S47 = c(0,
> 0.00731421884142774,
>
> 0, 0, 0, 0), Root.37.S57 = c(0.00668627975394491, 0, 0,
> 0.00780065971293572,
>
> 0, 0), Root.38.S67 = c(0, 0, 0, 0, 0, 0), Root.42.S77 =
> c(0.00368785956630772,
>
> 0, 0, 0, 0.00553178934946157, 0), Root.44.S7 = c(0, 0, 0.0306968177632252,
>
> 0, 0, 0), Root.46.S18 = c(0, 0, 0, 0, 0, 0), Root.48.S28 = c(0,
>
> 0, 0, 0, 0, 0), Root.49.S38 = c(0, 0.0133380016339052, 0, 0,
>
> 0, 0), Root.5.S45 = c(0, 0, 0, 0, 0, 0), Root.52.S48 = c(0, 0,
>
> 0, 0, 0, 0), Root.53.S58 = c(0, 0, 0, 0, 0, 0), Root.6.S55 =
> c(0.0150072892547809,
>
> 0, 0, 0, 0, 0), Root.7.S65 = c(0, 0, 0, 0, 0, 0), Root.8.S75 = c(0,
>
> 0, 0, 0.0062986835751328, 0, 0)), row.names =
> c("71f84e7910006f22684121564206e8ca",
>
> "03b167b9f86f2519b4263b4125377eed", "54e204fb99c80764e964456dadd6a0e5",
>
> "55cd1fc570879d645bbf7a3642e9b0a8", "65f5c31e12c277aec319e2096463f9d2",
>
> "7bed62f0fef250fd831dcf13bf43f4fc"), class = "data.frame")
>
>
> > i <- row.names(data) %in% otu.list
>
> > data[i, ]
>
>  [1] Root-1.S35.L001  Root-10.S75.L001 Root-13.S5.L001  Root-14.S16.L001
>
>  [5] Root-17.S26.L001 Root-18.S36.L001 Root-19.S46.L001 Root-22.S56.L001
>
>  [9] Root-24.S66.L001 Root-25.S76.L001 Root-26.S6.L001  Root-27.S17.L001
>
> [13] Root-3.S45.L001  Root-30.S27.L001 Root-32.S37.L001 Root-34.S47.L001
>
> [17] Root-39.S57.L001 Root-4.S55.L001  Root-40.S67.L001 Root-41.S77.L001
>
> [21] Root-43.S7.L001  Root-45.S18.L001 Root-47.S28.L001 Root-50.S38.L001
>
> [25] Root-51.S48.L001 Root-54.S58.L001 Root-9.S65.L001  Root.11.S5
>
> [29] Root.12.S16      Root.15.S26      Root.16.S36      Root.2.S35
>
> [33] Root.20.S46      Root.21.S56      Root.23.S66      Root.28.S76
>
> [37] Root.29.S6       Root.31.S17      Root.33.S27      Root.35.S37
>
> [41] Root.36.S47      Root.37.S57      Root.38.S67      Root.42.S77
>
> [45] Root.44.S7       Root.46.S18      Root.48.S28      Root.49.S38
>
> [49] Root.5.S45       Root.52.S48      Root.53.S58      Root.6.S55
>
> [53] Root.7.S65       Root.8.S75
>
> <0 rows> (or 0-length row.names)
>
>
> Thanks
>
> Yogesh
>
>
>
> On Sun, Jun 23, 2019 at 3:34 PM Rui Barradas <ruipbarradas using sapo.pt> wrote:
>
>> Hello,
>>
>> Please always cc the list.
>>
>> The data you have posted has the values you want to match as
>> *row.names*, not as the first column values.
>>
>> This is why it is important to follow the posting guide and post
>> datasets as it suggests, in dput() format.
>>
>> dput(head(data))    # post the output of this
>>
>>
>> In the mean time, try
>>
>> i <- row.names(data) %in% otu.list
>> data[i, ]
>>
>>
>> Also, dim(i) doesn't make sense, it's a vector and in R it's not
>> expected to have a dim attribute. What would have made sense would have
>> been
>>
>> length(i)
>> sum(i)
>>
>>
>> Hope this helps,
>>
>> Rui Barradas
>>
>>
>> Às 11:41 de 23/06/19, Yogesh Gupta escreveu:
>> > Hi Rui,
>> >
>> > I used the code as you suggested , it is not giving the row values,
>> only
>> > showing the header of rows.
>> >
>> >> head(data)
>> >
>> >                                   Root-1.S35.L001 Root-10.S75.L001
>> >
>> > 71f84e7910006f22684121564206e8ca      0.00000000                0
>> >
>> > 03b167b9f86f2519b4263b4125377eed      0.00000000                0
>> >
>> > 54e204fb99c80764e964456dadd6a0e5      0.00000000                0
>> >
>> > 55cd1fc570879d645bbf7a3642e9b0a8      0.00000000                0
>> >
>> > 65f5c31e12c277aec319e2096463f9d2      0.00000000                0
>> >
>> > 7bed62f0fef250fd831dcf13bf43f4fc      0.04679457                0
>> >
>> >
>> > .....................................................
>> >
>> >
>> >> head(otu.list)
>> >
>> >    9d94ce7d60e59034941e3a12bc37865e
>> >
>> > 1 8e60d301122d7aa359eb6b0b00f37f62
>> >
>> > 2 bfad6370d28182cc6304844e9bec7fb6
>> >
>> > 3 088571139af8e0a63fb6652df8a7438b
>> >
>> > 4 ccd70d57890f276a542ef4b5e5142d4c
>> >
>> > 5 cab4ca278af34bf722e0c7cb3219370b
>> >
>> > 6 72f30f3780145f16ac882eb8e2d189a5
>> >
>> >
>> > ....................................
>> >
>> >
>> >> i <- data[[1]] %in% otu.list
>> >
>> >> dim(i)
>> >
>> > NULL
>> >
>> >> data[i, ]
>> >
>> >   [1] Root-1.S35.L001  Root-10.S75.L001 Root-13.S5.L001
>> Root-14.S16.L001
>> >
>> >   [5] Root-17.S26.L001 Root-18.S36.L001 Root-19.S46.L001
>> Root-22.S56.L001
>> >
>> >   [9] Root-24.S66.L001 Root-25.S76.L001 Root-26.S6.L001
>> Root-27.S17.L001
>> >
>> > [13] Root-3.S45.L001  Root-30.S27.L001 Root-32.S37.L001 Root-34.S47.L001
>> >
>> > [17] Root-39.S57.L001 Root-4.S55.L001  Root-40.S67.L001 Root-41.S77.L001
>> >
>> > [21] Root-43.S7.L001  Root-45.S18.L001 Root-47.S28.L001 Root-50.S38.L001
>> >
>> >
>> > .............
>> >
>> >
>> > Could you please suggest how I can get the row values along with the
>> harder?
>> >
>> >
>> > Kind Regards
>> >
>> > Yogesh
>> >
>> >
>> >
>> >
>> > *Yogesh Gupta*
>> > *Research Fellow*
>> > *Institute for Global Food Security*
>> > *Queen's University*
>> > *Belfast, UK*
>> >
>> >
>> >
>> > On Fri, Jun 21, 2019 at 9:29 PM Rui Barradas <ruipbarradas using sapo.pt
>> > <mailto:ruipbarradas using sapo.pt>> wrote:
>> >
>> >     Hello,
>> >
>> >     Please don't post in HTML like the posting guide asks you to, the
>> data
>> >     is unreadable.
>> >
>> >     Not tested:
>> >
>> >     i <- data[[1]] %in% ID.list
>> >     data[i, ]
>> >
>> >
>> >     That's it.
>> >
>> >     Hope this helps,
>> >
>> >     Rui Barradas
>> >
>> >     Às 21:09 de 21/06/19, Yogesh Gupta escreveu:
>> >      > Hi,
>> >      >
>> >      > I do need to filter data based on first column could you please
>> >     suggest ,
>> >      > How I can do it in R.
>> >      >
>> >      >
>> >      >
>> >      >
>> >      >
>> >      >
>> >      >
>> >      > head(data)
>> >      >
>> >      >
>> >      >
>> >      > Root-1.S35.L001 Root-10.S75.L001 Root-13.S5.L001 Root-14.S16.L001
>> >      > Root-17.S26.L001
>> >      > 719e20e1e3d19fbc5dd50844c6d29a8f 0.049304262 0 0 0 0.033765858
>> >      > bfffa74c0971b30ccf3b19f65911801f 0 0 0.017210717 0 0
>> >      > 80087a003188288a9b0e3990d72113e3 0 0 0 0.010248632 0
>> >      > aed34f36d535976c247278bec289fd12 0.580694642 0.113445793
>> 0.56221674
>> >      > 0.06764097 0.525782644
>> >      > 42df8f30203380e9a604cb5c4000411b 0 0 0 0.004099453 0
>> >      > d47199c9d9c5417c7cb82ff4159cf497 0 0.019729703 0 0 0
>> >      > 6272cdc38bd517a77ba3887619c36b9f 0 0 0 0.016397811 0.019294776
>> >      > 62a5c6f5e0adda662739a7ac521ea790 0.076695519 0 0.271546861
>> >     0.254166069
>> >      > 0.463074623
>> >      > 3b5d8860f6a03668df80d364e9591bab 0.125999781 0.019729703
>> 0.061193659
>> >      > 0.038944801 0.02411847
>> >      >
>> >      > I need to extract data for the below IDs
>> >      >
>> >      > head(ID.list)
>> >      >
>> >      > 719e20e1e3d19fbc5dd50844c6d29a8f
>> >      > bfffa74c0971b30ccf3b19f65911801f
>> >      > 62a5c6f5e0adda662739a7ac521ea790
>> >      >
>> >      > I will be tankful for your help.
>> >      >
>> >      > Thanks
>> >      > Yogesh
>> >      >
>> >      > *Yogesh Gupta*
>> >      > *Research Fellow*
>> >      > *Institute for Global Food Security*
>> >      > *Queen's University*
>> >      > *Belfast, UK*
>> >      >
>> >      >       [[alternative HTML version deleted]]
>> >      >
>> >      > ______________________________________________
>> >      > R-help using r-project.org <mailto:R-help using r-project.org> mailing list
>> >     -- To UNSUBSCRIBE and more, see
>> >      > https://stat.ethz.ch/mailman/listinfo/r-help
>> >      > PLEASE do read the posting guide
>> >     http://www.R-project.org/posting-guide.html
>> >      > and provide commented, minimal, self-contained, reproducible
>> code.
>> >      >
>> >
>>
>

	[[alternative HTML version deleted]]