I have a 2 dimensional data set (matrix/data frame) that looks like this
779 482 859 1156
maxs 56916.00 78968.00 51156.00 44827.01
Means+Stdv 41784.70 64440.83 38319.10 42767.14
Mean_Cost 31863.18 44407.40 29365.78 38711.29
Means_Stdv 21941.66 24373.97 20412.45 34655.43
mins 21088.00 13768.00 24132.00 31452.00
The 779, 489,859, 1156 are values that I want to draw on the x-axis
The rest of the values on the column are values that correpond to each x
Now I want to plot the entire data set, so that I have a graph with the the following points
(779,56916) , (779, 41784)......
(482,78968) , (482, 64440)..... and so on
The way I did it so far is like this (it gives me the plot I am looking for)
plot(colnames(resultsSummary),resultsSummary[1,],ylim=c(0,80000),pch=6)
points(colnames(resultsSummary),resultsSummary[2,],pch=3)
points(colnames(resultsSummary),resultsSummary[3,])
and so on..... plotting row by row
I am sure there is a better way to do it, but I dont know how, any suggestions?
DF <- read.table(text=" 779 482 859 1156
maxs 56916.00 78968.00 51156.00 44827.01
Means+Stdv 41784.70 64440.83 38319.10 42767.14
Mean_Cost 31863.18 44407.40 29365.78 38711.29
Means_Stdv 21941.66 24373.97 20412.45 34655.43
mins 21088.00 13768.00 24132.00 31452.00",
header=TRUE, check.names=FALSE)
m <- as.matrix(DF)
matplot(as.integer(colnames(m)),
t(m), pch=seq_len(ncol(m)))
Following also works:
ddf = structure(list(var = structure(c(1L, 4L, 2L, 3L, 5L), .Label = c("maxs",
"Mean_Cost", "Means_Stdv", "Means+Stdv", "mins"), class = "factor"),
X779 = c(56916, 41784.7, 31863.18, 21941.66, 21088), X482 = c(78968,
64440.83, 44407.4, 24373.97, 13768), X859 = c(51156, 38319.1,
29365.78, 20412.45, 24132), X1156 = c(44827.01, 42767.14,
38711.29, 34655.43, 31452)), .Names = c("var", "X779", "X482",
"X859", "X1156"), class = "data.frame", row.names = c(NA, -5L
))
ddf
var X779 X482 X859 X1156
1 maxs 56916.00 78968.00 51156.00 44827.01
2 Means+Stdv 41784.70 64440.83 38319.10 42767.14
3 Mean_Cost 31863.18 44407.40 29365.78 38711.29
4 Means_Stdv 21941.66 24373.97 20412.45 34655.43
5 mins 21088.00 13768.00 24132.00 31452.00
ddf[6,2:5]=as.numeric(substr(names(ddf)[2:5],2,4))
ddf2 = data.frame(t(ddf))
ddf2 = ddf2[-1,]
mm = melt(ddf2, id='X6')
ggplot(mm)+geom_point(aes(x=X6, y=value, color=variable))
Related
I have a list that's 1314 element long. Each element is a data frame consisting of two rows and four columns.
Game.ID Team Points Victory
1 201210300CLE CLE 94 0
2 201210300CLE WAS 84 0
I would like to use the lapply function to compare points for each team in each game, and change Victory to 1 for the winning team.
I'm trying to use this function:
test_vic <- lapply(all_games, function(x) {if (x[1,3] > x[2,3]) {x[1,4] = 1}})
But the result it produces is a list 1314 elements long with just the Game ID and either a 1 or a null, a la:
$`201306200MIA`
[1] 1
$`201306160SAS`
NULL
How can I fix my code so that each data frame maintains its shape. (I'm guessing solving the null part involves if-else, but I need to figure out the right syntax.)
Thanks.
Try
lapply(all_games, function(x) {x$Victory[which.max(x$Points)] <- 1; x})
Or another option would be to convert the list to data.table by using rbindlist and then do the conversion
library(data.table)
rbindlist(all_games)[,Victory:= +(Points==max(Points)) ,Game.ID][]
data
all_games <- list(structure(list(Game.ID = c("201210300CLE",
"201210300CLE"
), Team = c("CLE", "WAS"), Points = c(94L, 84L), Victory = c(0L,
0L)), .Names = c("Game.ID", "Team", "Points", "Victory"),
class = "data.frame", row.names = c("1",
"2")), structure(list(Game.ID = c("201210300CME", "201210300CME"
), Team = c("CLE", "WAS"), Points = c(90, 92), Victory = c(0L,
0L)), .Names = c("Game.ID", "Team", "Points", "Victory"),
row.names = c("1", "2"), class = "data.frame"))
You could try dplyr:
library(dplyr)
all_games %>%
bind_rows() %>%
group_by(Game.ID) %>%
mutate(Victory = row_number(Points)-1)
Which gives:
#Source: local data frame [4 x 4]
#Groups: Game.ID
#
# Game.ID Team Points Victory
#1 201210300CLE CLE 94 1
#2 201210300CLE WAS 84 0
#3 201210300CME CLE 90 0
#4 201210300CME WAS 92 1
I have a data frame that has annual data for population by MSA. They are organized as follows:
MSA FIPS x1969 x1970 x1971 .... x2012
Akron 123 12 14 17 .... 22
Miami 234 23 20 24 .... 29
etc.
I need to reshape the data into
MSA FIPS Year Data
Akron 123 1969 12
Akron 123 1970 14
Akron 123 1971 17
...
I can do this using "melt", but I also want to interpolate these annual data to include quarterly data points for the full time series. So, how best to create the quarterly (interpolated) matrix on the fly?
I can do this using a loop over the rows of the first matrix above and then use melt to reshape the new data, but I've been asked to slap myself anytime I catch myself building explicitly coded loops.
I've been tinkering with "apply", but it creates a list of lists -- which would then require assembling the final data frame.
I can feel a simple solution must be out there.
Thanks, Chris.
May be you could try td from tempdisagg
library(tempdisagg)
library(reshape2)
library(zoo)
dM <- transform(melt(df, id.var=c('MSA', 'FIPS')),
variable=as.numeric(gsub('^x', '', variable)))
res <- lapply(split(dM, dM$MSA), function(x) {
val <- ts(x$value, start=x$variable[1], end=x$variable[nrow(x)])
val2 <-predict(td(val~1, to='quarterly', method='uniform'))
#change the options as needed
data.frame(yearQtr= as.yearqtr(time(val2)), val=val2)})
data
df <- structure(list(MSA = c("Akron", "Miami"), FIPS = c(123L, 234L
), x1969 = c(12L, 23L), x1970 = c(14L, 20L), x1971 = c(17L, 24L
)), .Names = c("MSA", "FIPS", "x1969", "x1970", "x1971"), class = "data.frame",
row.names = c(NA, -2L))
This builds on #akrun earlier:
#His data frame build:
df <- structure(list(MSA = c("Akron", "Miami"), FIPS = c(123L, 234L),
x1969 = c(12L, 23L), x1970 = c(14L, 20L), x1971 = c(17L, 24L)),
.Names = c("MSA", "FIPS", "x1969", "x1970", "x1971"), class = "data.frame",
row.names = c(NA, -2L))
#His set up:
dM <- transform(melt(df, id.var=c('MSA', 'FIPS')),
variable=as.numeric(gsub('^x', '', variable)))
#My variation on his lapply:
res <- lapply(split(dM, dM$MSA), function(x) {
xseq=seq(min(x$variable),max(x$variable),by=.25)
val <- approx(x$variable,x$value,xout=xseq)
data.frame(yearQtr=xseq,val=val$y)})
df.new <- do.call(rbind.data.frame,res)
It's not quite perfect, but I'll get back to it later. We're close. Thank you #akrun
I have 2 dataframe sharing the same rows IDs but with different columns
Here is an example
chrom coord sID CM0016 CM0017 CM0018
7 10 3178881 SP_SA036,SP_SA040 0.000000000 0.000000000 0.0009923
8 10 38894616 SP_SA036,SP_SA040 0.000434783 0.000467464 0.0000970
9 11 104972190 SP_SA036,SP_SA040 0.497802888 0.529319536 0.5479003
and
chrom coord sID CM0001 CM0002 CM0003
4 10 3178881 SP_SA036,SA040 0.526806527 0.544927536 0.565610860
5 10 38894616 SP_SA036,SA040 0.009049774 0.002849003 0.002857143
6 11 104972190 SP_SA036,SA040 0.451612903 0.401617251 0.435318275
I am trying to create a composite boxplot figure where I have in x axis the chrom and coord combined (so 3 points) and for each x value 2 boxplots side by side corresponding to the two dataframes ?
What is the best way of doing this ? Should I merge the two dataframes together somehow in order to get only one and loop over the boxplots rendering by 3 columns ?
Any idea on how this can be done ?
The problem is that the two dataframes have the same number of rows but can differ in number of columns
> dim(A)
[1] 99 20
> dim(B)
[1] 99 28
I was thinking about transposing the dataframe in order to get the same number of column but got lost on how to this properly
Thanks in advance
UPDATE
This is what I tried to do
I merged chrom and coord columns together to create a single ID
I used reshape t melt the dataframes
I merged the 2 melted dataframe into a single one
the head looks like this
I have two variable A2 and A4 corresponding to the 2 dataframes
then I created a boxplot such using this
ggplot(A2A4, aes(factor(combine), value)) +geom_boxplot(aes(fill = factor(variable)))
I think it solved my problem but the boxplot looks very busy with 99 x values with 2 boxplots each
So if these are your input tables
d1<-structure(list(chrom = c(10L, 10L, 11L),
coord = c(3178881L, 38894616L, 104972190L),
sID = structure(c(1L, 1L, 1L), .Label = "SP_SA036,SP_SA040", class = "factor"),
CM0016 = c(0, 0.000434783, 0.497802888), CM0017 = c(0, 0.000467464,
0.529319536), CM0018 = c(0.0009923, 9.7e-05, 0.5479003)), .Names = c("chrom",
"coord", "sID", "CM0016", "CM0017", "CM0018"), class = "data.frame", row.names = c("7",
"8", "9"))
d2<-structure(list(chrom = c(10L, 10L, 11L), coord = c(3178881L,
38894616L, 104972190L), sID = structure(c(1L, 1L, 1L), .Label = "SP_SA036,SA040", class = "factor"),
CM0001 = c(0.526806527, 0.009049774, 0.451612903), CM0002 = c(0.544927536,
0.002849003, 0.401617251), CM0003 = c(0.56561086, 0.002857143,
0.435318275)), .Names = c("chrom", "coord", "sID", "CM0001",
"CM0002", "CM0003"), class = "data.frame", row.names = c("4",
"5", "6"))
Then I would combine and reshape the data to make it easier to plot. Here's what i'd do
m1<-melt(d1, id.vars=c("chrom", "coord", "sID"))
m2<-melt(d2, id.vars=c("chrom", "coord", "sID"))
dd<-rbind(cbind(m1, s="T1"), cbind(m2, s="T2"))
mm$pos<-factor(paste(mm$chrom,mm$coord,sep=":"),
levels=do.call(paste, c(unique(dd[order(dd[[1]],dd[[2]]),1:2]), sep=":")))
I first melt the two input tables to turn columns into rows. Then I add a column to each table so I know where the data came from and rbind them together. And finally I do a bit of messy work to make a factor out of the chr/coord pairs sorted in the correct order.
With all that done, I'll make the plot like
ggplot(mm, aes(x=pos, y=value, color=s)) +
geom_boxplot(position="dodge")
and it looks like
I imagine that there's some way to do this with sqldf, though I'm not familiar with the syntax of that package enough to get this to work. Here's the issue:
I have two data frames, each of which describe genomic regions and contain some other data. I have to combine the two if the region described in the one df falls within the region of the other df.
One df, g, looks like this (though my real data has other columns)
start_position end_position
1 22926178 22928035
2 22887317 22889471
3 22876403 22884442
4 22862447 22866319
5 22822490 22827551
And another, l, looks like this (this sample has a named column)
name start end
101 GRMZM2G001024 11149187 11511198
589 GRMZM2G575546 24382534 24860958
7859 GRMZM2G441511 22762447 23762447
658 AC184765.4_FG005 26282236 26682919
14 GRMZM2G396835 10009264 10402790
I need to merge the two dataframes if the values from the start_position OR end_position columns in g fall within the start-end range in l, returning only the columns in l that have a match. I've been trying to get findInterval() to do the job, but haven't been able to return a merged DF. Any ideas?
My data:
g <- structure(list(start_position = c(22926178L, 22887317L, 22876403L,
22862447L, 22822490L), end_position = c(22928035L, 22889471L,
22884442L, 22866319L, 22827551L)), .Names = c("start_position",
"end_position"), row.names = c(NA, 5L), class = "data.frame")
l <- structure(list(name = structure(c(2L, 12L, 9L, 1L, 8L), .Label = c("AC184765.4_FG005",
"GRMZM2G001024", "GRMZM2G058655", "GRMZM2G072028", "GRMZM2G157132",
"GRMZM2G160834", "GRMZM2G166507", "GRMZM2G396835", "GRMZM2G441511",
"GRMZM2G442645", "GRMZM2G572807", "GRMZM2G575546", "GRMZM2G702094"
), class = "factor"), start = c(11149187L, 24382534L, 22762447L,
26282236L, 10009264L), end = c(11511198L, 24860958L, 23762447L,
26682919L, 10402790L)), .Names = c("name", "start", "end"), row.names = c(101L,
589L, 7859L, 658L, 14L), class = "data.frame")
I have the following table ordered group by first, second and name.
myData <- structure(list(first = c(120L, 120L, 126L, 126L, 126L, 132L, 132L), second = c(1.33, 1.33, 0.36, 0.37, 0.34, 0.46, 0.53),
Name = structure(c(5L, 5L, 3L, 3L, 4L, 1L, 2L), .Label = c("Benzene",
"Ethene._trichloro-", "Heptene", "Methylamine", "Pentanone"
), class = "factor"), Area = c(699468L, 153744L, 32913L,
4948619L, 83528L, 536339L, 105598L), Sample = structure(c(3L,
2L, 3L, 3L, 3L, 1L, 1L), .Label = c("PO1:1", "PO2:1", "PO4:1"
), class = "factor")), .Names = c("first", "second", "Name",
"Area", "Sample"), class = "data.frame", row.names = c(NA, -7L))
Within each group I want to extract the area that correspond to the specific sample. Several groups don´t have areas from the samples, so if the sample is´nt detected it should return "NA".Ideally, the final output should be a column for each sample.
I have tried the ifelse function to create one column to each sample:
PO1<-ifelse(myData$Sample=="PO1:1",myData$Area, "NA")
However this doesn´t takes into account the group distribution. I want to do this, but within the group. Within each group (a group as equal value for first, second and Name columns) if sample=PO1:1, Area, else NA.
For the first group:
structure(list(first = c(120L, 120L), second = c(1.33, 1.33),
Name = structure(c(1L, 1L), .Label = "Pentanone", class = "factor"),
Area = c(699468L, 153744L), Sample = structure(c(2L, 1L), .Label = c("PO2:1",
"PO4:1"), class = "factor")), .Names = c("first", "second", "Name",
"Area", "Sample"), class = "data.frame", row.names = c(NA, -2L))
The output should be:
structure(list(PO1.1 = NA, PO2.1 = 153744L, PO3.1 = NA, PO4.1 = 699468L), .Names =c("PO1.1", "PO2.1", "PO3.1", "PO4.1"), class = "data.frame", row.names = c(NA, -1L))
Any suggestion?
As in the example in the quesiton, I am assuming Sample is a factor. If this is not the case, consider making it such.
First, lets clean up the column Sample to make it a legal name, or else it might cause errors
levels(myData$Sample) <- make.names(levels(myData$Sample))
## DEFINE THE CUTS##
# Adjust these as necessary
#--------------------------
max.second <- 3 # max & nin range of myData$second
min.second <- 0 #
sprd <- 0.15 # with spread for each group
#--------------------------
# we will cut the myData$second according to intervals, cut(myData$second, intervals)
intervals <- seq(min.second, max.second, sprd*2)
# Next, lets create a group column to split our data frame by
myData$group <- paste(myData$first, cut(myData$second, intervals), myData$Name, sep='-')
groups <- split(myData, myData$group)
samples <- levels(myData$Sample) ## I'm assuming not all samples are present in the example. Manually adjusting with: samples <- sort(c(samples, "PO3.1"))
# Apply over each group, then apply over each sample
myOutput <-
t(sapply(groups, function(g) {
#-------------------------------
# NOTE: If it's possible that within a group there is more than one Area per Sample, then we have to somehow allow for thi. Hence the "paste(...)"
res <- sapply(samples, function(s) paste0(g$Area[g$Sample==s], collapse=" - ")) # allowing for multiple values
unlist(ifelse(res=="", NA, res))
## If there is (or should be) only one Area per Sample, then remove the two lines aboce and uncomment the two below:
# res <- sapply(samples, function(s) g$Area[g$Sample==s]) # <~~ This line will work when only one value per sample
# unlist(ifelse(res==0, NA, res))
#-------------------------------
}))
# Cleanup names
rownames(myOutput) <- paste("Group", 1:nrow(myOutput), sep="-") ## or whichever proper group name
# remove dummy column
myData$group <- NULL
Results
myOutput
PO1.1 PO2.1 PO3.1 PO4.1
Group-1 NA "153744" NA "699468"
Group-2 NA NA NA "32913 - 4948619"
Group-3 NA NA NA "83528"
Group-4 "536339" NA NA NA
Group-5 "105598" NA NA NA
You cannot really expect R to intuit that there is a fourth factor level between PO2 and PO4 , now can you.
> reshape(inp, direction="wide", idvar=c('first','second','Name'), timevar="Sample")
first second Name Area.PO4:1 Area.PO2:1 Area.PO1:1
1 120 1.3 Pentanone 699468 153744 NA
3 126 0.4 Heptene 32913 NA NA
4 126 0.4 Heptene 4948619 NA NA
5 126 0.3 Methylamine 83528 NA NA
6 132 0.5 Benzene NA NA 536339
7 132 0.5 Ethene._trichloro- NA NA 105598