Get the rows that include specific strings - r

I have a data like this
df<- structure(list(Groups = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L),
No = c(8L, 4L, 9L, 2L, 7L, 3L, 5L, 1L, 2L), NO1 = c(1L, 1L,
1L, 2L, 1L, 1L, 1L, 1L, 1L), Accessions = structure(c(6L,
5L, 1L, 3L, 2L, 7L, 4L, 9L, 8L), .Label = c("E9PCL5", "P00367",
"P05783", "P63104", "Q6DD88", "Q6FI13", "Q6P597-3", "Q7Z406-6",
"Q9BUA3"), class = "factor"), Accessions2 = structure(c(6L,
2L, 1L, 4L, 3L, 7L, 5L, 9L, 8L), .Label = c("B4DIW5; F8WA69; P56945; E9PCV2; F5GXA2; F5H855; E9PCL5; F5GXV6; F5H7Z0",
"F5GWF8; F5H6I7; Q6DD88", "P00367; B3KV55; B4DGN5; P49448; F5GYQ4; H0YFJ0; F8WA20",
"P05783; F8VZY9", "P63104; E7EX24; H0YB80; B0AZS6; B7Z2E6",
"Q16777; Q99878; F8WA69; H0YFX9; Q9BTM1; P20671; P0C0S8; Q6FI13",
"Q6P597-3; Q6P597-2; Q6P597", "Q7Z406-2; Q7Z406-6", "Q9BUA3"
), class = "factor"), NO3 = c(1L, 0L, 0L, 0L, 1L, 0L, 1L,
0L, 0L)), .Names = c("Groups", "No", "NO1", "Accessions",
"Accessions2", "NO3"), class = "data.frame", row.names = c(NA,
-9L))
I am trying to find those row that have specific strings in Accession2 column and then sum up the NO1
For example, I want to know F8WA69 and Q9BUA3 exist in which rows
So It it will be
Groups No NO1 Accessions Accessions2 NO3
1 8 1 Q6FI13 Q16777; Q99878; F8WA69; H0YFX9; Q9BTM1; P20671; P0C0S8; Q6FI13 1
1 9 1 E9PCL5 B4DIW5; F8WA69; P56945; E9PCV2; F5GXA2; F5H855; E9PCL5; F5GXV6; F5H7Z0 0
and
Groups No NO1 Accessions Accessions2 NO3
1 3 1 Q6P597-3 Q6P597-3; Q6P597-2; Q9BUA3 0
1 1 1 Q9BUA3 Q9BUA3 0
1 2 1 Q7Z406-6 Q7Z406-2; Q9BUA3 0
Then the sum up the NO1 for each of them
The first one is 2 and the second one is 3

You can use simple grepl or grep to find rows where ID is present.
For example:
grepl("F8WA69", df$Accessions2)
[1] TRUE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE
To subset your data use:
df[grepl("F8WA69", df$Accessions2), ]
And if you want to iterate over multiple ID's and sum NO1 you can use sapply:
sapply(c("F8WA69", "Q9BUA3"),
function(x) sum(df[grepl(x, df$Accessions2), ]$NO1))
F8WA69 Q9BUA3
2 1

Related

Frequency of one dataframe rows from another dataframe

Can someone help me how to count from another dataframe?
df1(out)
structure(list(Item = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L), class = "factor", .Label = "0S1576"), LC = structure(c(1L,
1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L), class = "factor", .Label = c("MW92",
"OY01", "RM11")), Fiscal.Month = c("2019-M06", "2019-M07", "2019-M06",
"2019-M07", "2019-M08", "2019-M09", "2019-M06", "2019-M07", "2019-M08"
)), row.names = c(NA, -9L), class = "data.frame")
df2(tempdf)
structure(list(Item = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "0S1576", class = "factor"),
LC = structure(c(1L, 1L, 1L, 1L, 2L, 3L, 4L, 6L, 5L, 1L,
2L, 2L, 3L, 3L), .Label = c("MW92", "OY01", "RM11", "RS11",
"WK14", "WK15"), class = "factor"), Fiscal.Month = structure(c(1L,
2L, 3L, 4L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("2019-M06",
"2019-M07", "2019-M08", "2019-M09"), class = "factor"), fcst = c(22L,
21L, 20L, 19L, 12L, 10L, 10L, 12L, 10L, 12L, 10L, 10L, 10L,
10L)), row.names = c(NA, -14L), class = "data.frame")
I want to count the frequency of Item,LC,Fiscal.month of df1 from df2
You can count using table and merge df1 with df2 by using factor and you need interaction as you use more than one column to merge.
table(factor(interaction(df2[c("Item","LC","Fiscal.Month")]), levels=interaction(df1)))
#0S1576.MW92.2019-M06 0S1576.MW92.2019-M07 0S1576.OY01.2019-M06
# 2 1 3
#0S1576.OY01.2019-M07 0S1576.OY01.2019-M08 0S1576.OY01.2019-M09
# 0 0 0
#0S1576.RM11.2019-M06 0S1576.RM11.2019-M07 0S1576.RM11.2019-M08
# 3 0 0
Or a speed improved version using match and tabulate:
(df1$freq <- tabulate(match(interaction(df2[c("Item","LC","Fiscal.Month")]), interaction(df1)), nrow(df1)))
#[1] 2 1 3 0 0 0 3 0 0
Or sometimes even faster using fastmatch:
library(fastmatch)
df1$freq <- tabulate(fmatch(interaction(df2[c("Item","LC","Fiscal.Month")]), interaction(df1)), nrow(df1))

Large data set cleaning: How to fill in missing data based on multiple categories and searching by row order

This is my first StackOverflow post, so I hope that it isn't too difficult to understand.
I have a large dataset (~14,000) rows of bird observations. These data were collected by standing in one place (point) and counting birds that you see within 3 minutes. Within each point-count a new bird observation becomes a new row, so that there are many repeated dates, times, sites, and point (specific location within a site). Again, each point count is 3 minutes long. So if you see a yellow warbler (coded as YEWA) during minute 1, then it will be associated with MINUTE=1 for that specific point count (date, site, point, and time). ID=observer intials and Number=number of birds spotted (not necessarily important here).
However, if NO BIRDS are seen, then a "NOBI" goes into the dataset for that specific minute. Thus, if there are NOBI for an entire 3 minute point count, their will be three rows with the same date, site, point, and time, and "NOBI" in the "BIRD" column for each of the three rows.
So I have TWO main problems. The first is that some observers entered "NOBI" once for all three minutes, instead of three times (once per minute). Anywhere where "MINUTE"
has been left blank (becoming NA), AND "BIRD"="NOBI", I need to add three rows of data, all with the same values for all columns except "MINUTE", which should be 1, 2, and 3 for the respective rows.
If it looks like this:
ID DATE SITE POINT TIME MINUTE BIRD NUMBER
1 BS 5/9/2018 CW2 U125 7:51 NA NOBI NA
2 BS 5/9/2018 CW1 D250 8:12 1 YEWA 2
3 BS 5/9/2018 CW1 D250 8:12 2 NOBI NA
4 BS 5/9/2018 CW1 D250 8:12 3 LABU 1
It should look like this instead:
ID DATE SITE POINT TIME MINUTE BIRD NUMBER
1 BS 5/9/2018 CW2 U125 7:51 1 NOBI NA
2 BS 5/9/2018 CW2 U125 7:51 2 NOBI NA
3 BS 5/9/2018 CW2 U125 7:51 3 NOBI NA
4 BS 5/9/2018 CW1 D250 8:12 1 YEWA 2
5 BS 5/9/2018 CW1 D250 8:12 2 NOBI NA
6 BS 5/9/2018 CW1 D250 8:12 3 LABU 1
note: If you are wanting to enter some of this data into your R console, I included some at the end of this post using dput, which should be easier to enter than copy-and-pasting the above
I have made failed attempts at reproducing if statements with multiple conditions (based on:
R multiple conditions in if statement & Ifelse in R with multiple categorical conditions) I tried writing this many ways, including with piping from dplyr, but see below for one example of some code, notes, and error messages.
>if(PC$BIRD == "NOBI" & PC$MINUTE==NA){PC$Fix<-TRUE}
Error in if (PC$BIRD == "NOBI" & PC$MINUTE == NA) { :
missing value where TRUE/FALSE needed
In addition: Warning message:
In if (PC$BIRD == "NOBI" & PC$MINUTE == NA) { :
the condition has length > 1 and only the first element will be used
## Then I need to do something like this:
>if(PC$Fix<-TRUE){duplicate(row where Fix==TRUE, times=2)} #I know this isn't
### even close, but I want the row to be replicated two more times so
### that there are 3 total rows witht he same values
### Fix indicates that a fix is needed in this example
# Then somehow I need to assign a 1 to PC$MINUTE for the first row (original row),
# a 2 to the next row (with other values from other columns being the same), and a 3
# to the last duplicated row (still other values from other columns being the same)
The second problem, which seems more difficult to me is to search the dataset in order or perhaps by DATE,SITE,POINT, and TIME in some way. The minute values should always go from 1... to 2... to 3, and then back to 1 for the next set of date, time, site, and point. That is, each point count should have all values 1:3. However, one count may have multiple sightings in MINUTE=1 so that there are 5 or 6 (or 20) MINUTE=1 before MINUTE=2. BUT, again, some observers in this dataset simply left a row out when there was NO BIRDS (NOBI), instead of writing a row with BIRD="NOBI" for each MINUTE. That is if the dataset goes:
ID DATE SITE POINT TIME MINUTE BIRD NUMBER
...
4 BS 5/9/2018 CW2 U125 7:54 1 AMRO 1
5 BS 5/9/2018 CW2 U125 7:54 1 SPTO 1
6 BS 5/9/2018 CW2 U125 7:57 1 AMRO 1
7 BS 5/9/2018 CW2 U125 7:57 1 SPTO 1
8 BS 5/9/2018 CW2 U125 7:57 1 AMCR 3
9 BS 5/9/2018 CW2 U125 7:57 2 SPTO 1
10 BS 5/9/2018 CW2 U125 7:57 2 HOWR 1
11 BS 5/9/2018 CW2 U125 7:57 3 UNBI 1
We can see that the 7:57 point count time is complete (there are MINUTE values of 1:3). However, the 7:54 point count time stops at MINUTE=1. Meaning, I need to enter two more rows underneath that have all of the same DATE,SITE,POINT,TIME information, but with MINUTE=2 and BIRD="NOBI" for the first added row and MINUTE=3 and BIRD="NOBI" for the second added row. So it should look like this:
ID DATE SITE POINT TIME MINUTE BIRD NUMBER
...
4 BS 5/9/2018 CW2 U125 7:54 1 AMRO 1
5 BS 5/9/2018 CW2 U125 7:54 1 SPTO 1
6 BS 5/9/2018 CW2 U125 7:54 2 NOBI NA
7 BS 5/9/2018 CW2 U125 7:54 3 NOBI NA
8 BS 5/9/2018 CW2 U125 7:57 1 AMRO 1
9 BS 5/9/2018 CW2 U125 7:57 1 SPTO 1
10 BS 5/9/2018 CW2 U125 7:57 1 AMCR 3
11 BS 5/9/2018 CW2 U125 7:57 2 SPTO 1
12 BS 5/9/2018 CW2 U125 7:57 2 HOWR 1
13 BS 5/9/2018 CW2 U125 7:57 3 UNBI 1
Lastly, I understand that this is a long and complicated question, and I may not have articulated it very well. Please let me know if there is any clarification needed, and I would be happy to hear any advice, even if it doesn't fully answer my problems. Thank you in advance!
Everything below this line is only useful for you if you want to enter a sample of my data into R
To enter my data into R console, copy and paste everything from "structure" function to end of code to enter it as dataframe in R console with code: dataframe<-structure(list...
See Example of using dput() for help.
PC<-read.csv("PC.csv") ### ORIGINAL FILE
dput(PC)
structure(list(ID = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "BS", class = "factor"),
DATE = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "5/9/2018", class = "factor"),
SITE = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "CW2", class = "factor"),
POINT = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("M", "U125"), class = "factor"),
TIME = structure(c(8L, 8L, 8L, 9L, 9L, 10L, 10L, 10L, 10L,
10L, 10L, 11L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 4L, 4L, 4L,
4L, 5L, 5L, 5L, 5L, 5L, 5L, 6L, 7L), .Label = c("6:48", "6:51",
"6:54", "6:57", "7:12", "7:15", "7:18", "7:51", "7:54", "7:57",
"8:00"), class = "factor"), MINUTE = c(1L, 2L, 3L, 1L, 1L,
1L, 1L, 1L, 2L, 2L, 3L, 1L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 1L,
1L, 1L, 2L, 3L, 1L, 1L, 1L, 2L, 3L, 3L, NA, NA), BIRD = structure(c(6L,
6L, 6L, 2L, 7L, 2L, 7L, 1L, 7L, 5L, 8L, 8L, 6L, 6L, 6L, 6L,
6L, 6L, 7L, 7L, 7L, 7L, 6L, 8L, 3L, 7L, 9L, 5L, 4L, 2L, 6L,
6L), .Label = c("AMCR", "AMRO", "BRSP", "DUFL", "HOWR", "NOBI",
"SPTO", "UNBI", "VESP"), class = "factor"), NUMBER = c(NA,
NA, NA, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, NA, NA, NA, NA,
NA, NA, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, NA,
NA)), class = "data.frame", row.names = c(NA, -32L))
PCc<-read.csv("PC_Corrected.csv") #### WHAT I NEED MY DATABASE TO LOOK LIKE
dput(PCc)
structure(list(ID = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L), .Label = "BS", class = "factor"), DATE = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "5/9/2018", class = "factor"),
SITE = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L), .Label = "CW2", class = "factor"), POINT = structure(c(2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("M",
"U125"), class = "factor"), TIME = structure(c(8L, 8L, 8L,
9L, 9L, 9L, 9L, 10L, 10L, 10L, 10L, 10L, 10L, 11L, 11L, 11L,
1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 5L,
5L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 7L, 7L, 7L), .Label = c("6:48",
"6:51", "6:54", "6:57", "7:12", "7:15", "7:18", "7:51", "7:54",
"7:57", "8:00"), class = "factor"), MINUTE = c(1L, 2L, 3L,
1L, 1L, 2L, 3L, 1L, 1L, 1L, 2L, 2L, 3L, 1L, 2L, 3L, 1L, 2L,
3L, 1L, 2L, 3L, 1L, 1L, 2L, 3L, 1L, 1L, 2L, 3L, 1L, 1L, 1L,
2L, 3L, 3L, 1L, 2L, 3L, 1L, 2L, 3L), BIRD = structure(c(6L,
6L, 6L, 2L, 7L, 6L, 6L, 2L, 7L, 1L, 7L, 5L, 8L, 8L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 7L, 7L, 6L, 6L, 7L, 7L, 6L, 8L, 3L,
7L, 9L, 5L, 4L, 2L, 6L, 6L, 6L, 6L, 6L, 6L), .Label = c("AMCR",
"AMRO", "BRSP", "DUFL", "HOWR", "NOBI", "SPTO", "UNBI", "VESP"
), class = "factor"), NUMBER = c(NA, NA, NA, 1L, 1L, NA,
NA, 1L, 1L, 1L, 1L, 1L, 1L, 1L, NA, NA, NA, NA, NA, NA, NA,
NA, 1L, 1L, NA, NA, 1L, 1L, NA, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
NA, NA, NA, NA, NA, NA)), class = "data.frame", row.names = c(NA,
-42L))
Here's a way to do it using dplyr and tidyr from the tidyverse meta-package.
# Step one - identify missing rows.
# For each DATE, SITE, POINT, TIME, count how many of each minute
library(tidyverse)
# Convert factors to character to make later joining simpler,
# and fix missing ID's by assuming prior line should be used,
# and make NOBI rows have a count of NA
PC_2_clean <- PC %>%
mutate_if(is.factor, as.character) %>%
fill(ID, .direction = "up") %>%
mutate(NUMBER = if_else(BIRD == "NOBI", NA_integer_, NUMBER))
# Create a wide table with spots for each minute. Missing will
# show up as NA's
# All the NA's here in the 1, 2, and 3 columns represent
# missing minutes that we should add.
PC_3_NA_find <- PC_2_clean %>%
count(ID, DATE, SITE, POINT, TIME, MINUTE) %>%
spread(MINUTE, n)
PC_3_NA_find
# A tibble: 11 x 9
# ID DATE SITE POINT TIME `1` `2` `3` `<NA>`
# <chr> <chr> <chr> <chr> <chr> <int> <int> <int> <int>
# 1 BS 5/9/2018 CW2 M 7:12 3 1 2 NA
# 2 BS 5/9/2018 CW2 M 7:15 NA NA NA 1
# 3 BS 5/9/2018 CW2 M 7:18 NA NA NA 1
# 4 BS 5/9/2018 CW2 U125 6:48 1 1 1 NA
# 5 BS 5/9/2018 CW2 U125 6:51 1 1 1 NA
# 6 BS 5/9/2018 CW2 U125 6:54 2 NA NA NA
# 7 BS 5/9/2018 CW2 U125 6:57 2 1 1 NA
# 8 BS 5/9/2018 CW2 U125 7:51 1 1 1 NA
# 9 BS 5/9/2018 CW2 U125 7:54 2 NA NA NA
# 10 BS 5/9/2018 CW2 U125 7:57 3 2 1 NA
# 11 BS 5/9/2018 CW2 U125 8:00 1 NA NA NA
# Take the NA minute entries and make the desired line for each
PC_4_rows_to_add <- PC_3_NA_find %>%
gather(MINUTE, count, `1`:`3`) %>%
filter(is.na(count)) %>%
select(-count, -`<NA>`) %>%
mutate(MINUTE = as.integer(MINUTE),
BIRD = "NOBI",
NUMBER = NA_integer_)
# Add these lines to the original, remove the NA minute rows
# (these have been replaced with minute rows), and sort
PC_5_with_NOBIs <- PC_2_clean %>%
bind_rows(PC_4_rows_to_add) %>%
filter(MINUTE != "NA") %>%
arrange(ID, DATE, SITE, POINT, TIME, MINUTE, BIRD)
# Check result
PC_5_with_NOBIs %>%
count(ID, DATE, SITE, POINT, TIME, MINUTE) %>%
spread(MINUTE, n)
PC_5_with_NOBIs
# Now to confirm it matches your desired output.
# Note, I convert to character to avoid mismatches between factors
PCc_char <- PCc %>%
mutate_if(is.factor, as.character) %>%
arrange(ID, DATE, SITE, POINT, TIME, MINUTE, BIRD)
identical(PC_5_with_NOBIs, PCc_char)
# [1] TRUE

Taking the frequency of three different columns [duplicate]

This question already has answers here:
Count number of rows within each group
(17 answers)
Closed 5 years ago.
I have a dataframe like this:
df <- structure(list(col1 = structure(c(1L, 1L, 2L, 3L, 1L, 3L, 1L,
3L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 4L), .Label = c("stock1",
"stock2", "stock3", "stock4"), class = "factor"), col2 = structure(c(4L,
5L, 7L, 6L, 5L, 5L, 5L, 6L, 6L, 8L, 8L, 4L, 3L, 3L, 1L, 2L, 3L
), .Label = c("comapny1", "comapny1+comapny4", "comapny4", "company1",
"company2", "company2+company1", "company3", "company4"), class = "factor"),
col3 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 2L), .Label = c("predictor1", "predictor2"
), class = "factor")), .Names = c("col1", "col2", "col3"), class = "data.frame", row.names = c(NA,
-17L))
I would like to take the frequency from the three columns.
Expected output
df2 <- structure(list(col1 = structure(c(1L, 1L, 1L, 2L, 4L, 1L, 1L,
3L, 3L, 1L, 2L, 1L), .Label = c("stock1", "stock2", "stock3",
"stock4"), class = "factor"), col2 = structure(c(1L, 2L, 3L,
3L, 3L, 4L, 5L, 5L, 6L, 6L, 7L, 8L), .Label = c("comapany1",
"comapany1+comapany4", "comapany4", "company1", "company2", "company2+company1",
"company3", "company4"), class = "factor"), col3 = structure(c(2L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("predictor1",
"predictor2"), class = "factor"), frequency = c(1L, 1L, 1L, 1L,
1L, 2L, 3L, 1L, 2L, 1L, 1L, 2L)), .Names = c("col1", "col2",
"col3", "frequency"), class = "data.frame", row.names = c(NA,
-12L))
How is it possible to make it?
We can use count
library(dplyr)
count(df, col1, col2, col3)
# A tibble: 12 x 4
# col1 col2 col3 n
# <fctr> <fctr> <fctr> <int>
# 1 stock1 comapny1 predictor2 1
# 2 stock1 comapny1+comapny4 predictor2 1
# 3 stock1 comapny4 predictor2 1
# 4 stock1 company1 predictor1 2
# 5 stock1 company2 predictor1 3
# 6 stock1 company2+company1 predictor1 1
# 7 stock1 company4 predictor1 2
# 8 stock2 comapny4 predictor2 1
# 9 stock2 company3 predictor1 1
#10 stock3 company2 predictor1 1
#11 stock3 company2+company1 predictor1 2
#12 stock4 comapny4 predictor2 1
Or with data.table
library(data.table)
setDT(df)[, .N, .(col1, col2, col3)]

Getting missing values in aggregate function

I have following data with peculiar missing values situation (all values of vnum1 for vcat1==3 are missing):
> head(mydf)
vnum1 vcat1
1 -0.1624229 1
2 0.2465567 1
3 NA 3
4 0.7067778 2
5 NA 3
6 -0.2241726 4
> dput(mydf)
structure(list(vnum1 = c(-0.162422853864248, 0.246556718176803,
NA, 0.706777793886275, NA, -0.224172615208867, 0.0545850414695318,
NA, NA, -1.94778020954922, 1.89581259201036, 0.901973743223488,
-0.31255172156186, -1.67311124367419, 0.491316838004494, NA,
-0.699315343799762, 0.668020448193884, 1.45492995320554, 1.17747976289091,
-0.65137204397438, 1.78678696473193, 2.58978935829221, NA, 1.26534157843481,
0.629748102812663, 0.246596558590885, 0.968707124353133, 0.108668693948881,
-0.219419917000748, 2.25307417017233, -0.626124211646445, -1.16298694223082,
-1.23524906047676, -2.34636152907898, NA, 0.408667368960836,
0.272596114054819, 0.747455245383144, -0.745843219461836, -0.0966351379737077,
1.44803320811527, -1.5434982335725, -0.782902668540696, -0.448286848257394,
NA, 0.168327130336994, -0.493721325506037, 0.397253883862878,
1.57070527855864), vcat1 = structure(c(1L, 1L, 3L, 2L, 3L, 4L,
4L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 4L, 3L, 4L, 4L, 4L, 1L, 2L, 4L,
1L, 3L, 2L, 4L, 2L, 1L, 4L, 2L, 2L, 4L, 2L, 1L, 1L, 3L, 1L, 4L,
4L, 4L, 4L, 2L, 4L, 1L, 4L, 3L, 1L, 4L, 4L, 1L), .Label = c("1",
"2", "3", "4"), class = "factor")), .Names = c("vnum1", "vcat1"
), row.names = c(NA, 50L), class = "data.frame")
If I use tapply, I clearly see the missing category:
> with(mydf,tapply(vnum1, vcat1, mean))
1 2 3 4
0.09172749 0.48575555 NA 0.09632024
But it is totally ignored in aggregate function:
> aggregate(vnum1~vcat1, mydf, mean)
vcat1 vnum1
1 1 0.09172749
2 2 0.48575555
3 4 0.09632024
I want to get it in aggregate function also. How can I do it? Thanks.
In the formula method, use na.action = NULL to keep the NA result.
aggregate(vnum1 ~ vcat1, mydf, mean, na.action = NULL)
# vcat1 vnum1
# 1 1 0.09172749
# 2 2 0.48575555
# 3 3 NA
# 4 4 0.09632024
You could have also used the data frame method and not have this worry.
with(mydf, aggregate(list(vnum1 = vnum1), list(vcat1 = vcat1), mean))

Merge / match two variables with one group of variables from another dataframe

I have two data.frames df.1 and df.2 that I would merge or otherwise select data from to create a new data.frame. df.1 contains information about each individual (ID), sampling event (Event), Site and sample number (Sample). The tricky part for me is that Site and the corresponding Sample for each ID-Event pairing is different. For example, F3-3 has Site "plum" for Sample "1" and M6-3 has Site "pear" for Sample "1".
df.2 has Sample1 and Sample2 which corresponds to the Sample information in df.1 by way of the ID-Event pairing.
I'd like to match/merge the information between these two data.frames. Essentially, get the "word" from Site in df.1 that matches the Sample number. An example (df.3) is below.
Each ID-Event pairing will only have one Site and corresponding Sample (e.g. "Apple" will correspond to "1" not to "1" and "4"). I know I could use merge if I was only matching, for example, Sample1 or Sample2 I am not sure how to do this with both to populate Site1 and Site2 with the correctly matched word.
df.1 <- structure(list(ID = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("F1",
"F3", "M6"), class = "factor"), Sex = structure(c(1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L), .Label = c("F", "M"), class = "factor"), Event = c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L,
4L, 4L, 4L, 4L), Site = structure(c(1L, 3L, 9L, 7L, 8L, 10L,
2L, 6L, 4L, 5L, 1L, 9L, 7L, 8L, 10L, 5L, 10L, 2L, 6L, 4L, 5L,
1L, 9L, 2L, 6L, 4L, 5L, 1L, 8L, 3L, 10L, 4L, 2L, 6L, 4L, 5L,
1L), .Label = c("Apple", "Banana", "Grape", "Guava", "Kiwi",
"Mango", "Orange", "Peach", "Pear", "Plum"), class = "factor"),
Sample = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 1L, 2L,
3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L,
6L, 7L, 8L, 9L, 10L, 1L, 2L, 3L, 4L, 5L)), .Names = c("ID",
"Sex", "Event", "Site", "Sample"), class = "data.frame", row.names = c(NA,
-37L))
#
df.2 <- structure(list(Sample1 = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 2L, 2L), Sample2 = c(2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L,
3L, 4L, 5L), V1 = c(0.12, 0.497, 0.715, 0, 0.001, 0, 0.829, 0,
0, 0.001, 0, 0.829), V2 = c(0.107, 0.273, 0.595, 0, 0.004, 0,
0.547, 0.001, 0.001, 0.107, 0.273, 0.595), ID = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L), .Label = c("F1",
"M6"), class = "factor"), Sex = structure(c(1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 2L, 2L, 2L), .Label = c("F", "M"), class = "factor"),
Event = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 3L, 3L, 3L)), .Names = c("Sample1",
"Sample2", "V1", "V2", "ID", "Sex", "Event"), class = "data.frame", row.names = c(NA,
-12L))
#
df.3 <- structure(list(Sample1 = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 2L, 2L), Sample2 = c(2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L,
3L, 4L, 5L), V1 = c(0.12, 0.497, 0.715, 0, 0.001, 0, 0.829, 0,
0, 0.001, 0, 0.829), V2 = c(0.107, 0.273, 0.595, 0, 0.004, 0,
0.547, 0.001, 0.001, 0.107, 0.273, 0.595), Site1 = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L), .Label = c("Apple",
"Banana"), class = "factor"), Site2 = structure(c(2L, 8L, 6L,
7L, 9L, 1L, 5L, 3L, 4L, 5L, 3L, 4L), .Label = c("Banana", "Grape",
"Guava", "Kiwi", "Mango", "Orange", "Peach", "Pear", "Plum"), class = "factor"),
ID = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L), .Label = c("F1", "M6"), class = "factor"), Sex = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L), .Label = c("F",
"M"), class = "factor"), Event = c(1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 3L, 3L, 3L)), .Names = c("Sample1", "Sample2",
"V1", "V2", "Site1", "Site2", "ID", "Sex", "Event"), class = "data.frame", row.names = c(NA, -12L))
Two merges should do it:
first <- merge(df.2, unique(df.1[,3:5]), by.x=c("Sample1","Event"), by.y=c("Sample","Event"), all.x=TRUE)
second <- merge(first, unique(df.1[,3:5]),by.x=c("Sample2","Event"), by.y=c("Sample","Event"), all.x=TRUE)
print(second)
Sample2 Event Sample1 V1 V2 ID Sex Site.x Site.y
1 10 1 1 0.000 0.001 F1 F Apple Kiwi
2 2 1 1 0.120 0.107 F1 F Apple Grape
3 3 1 1 0.497 0.273 F1 F Apple Pear
4 3 3 2 0.001 0.107 M6 M Banana Mango
5 4 1 1 0.715 0.595 F1 F Apple Orange
6 4 3 2 0.000 0.273 M6 M Banana Guava
7 5 1 1 0.000 0.000 F1 F Apple Peach
8 5 3 2 0.829 0.595 M6 M Banana Kiwi
9 6 1 1 0.001 0.004 F1 F Apple Plum
10 7 1 1 0.000 0.000 F1 F Apple Banana
11 8 1 1 0.829 0.547 F1 F Apple Mango
12 9 1 1 0.000 0.001 F1 F Apple Guava

Resources