Related
I'm trying to plot a graph for a likert test using ggplot2 and I would like to have the percentages values appearing on the graph. I've created a df with all the averages and percentages so I could write it on the graph. It all seems to be working good, except the values are being plotted as if they were upsided or something.
This is the code I'm using
example <- structure(list(grupo = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("EJA",
"REG"), class = "factor"), nivel = structure(c(1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L
), .Label = c("CINCO", "DOZE", "NOVE"), class = "factor"), tipo = structure(c(1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 3L), .Label = c("COR", "PAD", "RES"), class = "factor"),
likert = structure(c(1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L), .Label = c("0",
"1", "2", "3"), class = c("ordered", "factor")), cnt = c(3L,
1L, 3L, 5L, 3L, 1L, 3L, 6L, 2L, 1L, 10L, 5L, 5L, 9L, 11L,
6L, 4L, 10L, 10L, 10L), freq = c(0.25, 0.083, 0.25, 0.417,
0.231, 0.077, 0.231, 0.462, 0.154, 0.077, 0.769, 0.167, 0.167,
0.3, 0.367, 0.2, 0.133, 0.333, 0.333, 0.333), prop = c(25,
8.3, 25, 41.7, 23.1, 7.7, 23.1, 46.2, 15.4, 7.7, 76.9, 16.7,
16.7, 30, 36.7, 20, 13.3, 33.3, 33.3, 33.3), proptext = c("25",
"8.3", "25", "41.7", "23.1", "7.7", "23.1", "46.2", "15.4",
"7.7", "76.9", "16.7", "16.7", "30", "36.7", "20", "13.3",
"33.3", "33.3", "33.3")), row.names = c(NA, -20L), groups = structure(list(
grupo = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("EJA",
"REG"), class = "factor"), nivel = structure(c(1L, 1L, 1L,
2L, 2L, 2L), .Label = c("CINCO", "DOZE", "NOVE"), class = "factor"),
tipo = structure(c(1L, 2L, 3L, 1L, 2L, 3L), .Label = c("COR",
"PAD", "RES"), class = "factor"), .rows = structure(list(
1:4, 5:8, 9:11, 12:15, 16:19, 20L), ptype = integer(0), class = c("vctrs_list_of",
"vctrs_vctr", "list"))), row.names = c(NA, -6L), class = c("tbl_df",
"tbl", "data.frame"), .drop = TRUE), class = c("grouped_df",
"tbl_df", "tbl", "data.frame"))
ggplot(example, aes(x=(interaction(grupo, nivel, tipo)),y=prop, fill=likert))+
geom_col()+
#scale_y_continuous(labels = percent)+
coord_flip() +
ggtitle("Testing")+
xlab("A, B, and C")+
ylab("%")+
geom_text(aes(label = proptext), size = 2, colour = "black")
Would someone have an idea of how could I solve it?
The geom_text may also require the x, y
library(dplyr)
library(tidyr)
library(ggplot2)
example %>%
unite(new, grupo, nivel, tipo, sep = ".") %>%
ggplot(aes(x=new, fill=likert))+
geom_col(aes(y= prop))+
geom_text(aes(x = new, y = prop, label = proptext),
position = position_stack(vjust = .5)) +
coord_flip() +
#scale_y_continuous(labels = percent)+
ggtitle("Testing")+
xlab("A, B, and C")+
ylab("%")
-output
I am having trouble getting my plots to work, I have multiple categorical variables by which I want to color by one, and facet by another. However, R keeps adding the "values" (I used melt) for the same variables together instead. It works when I only have one variable.
Here is my plot with one variable
Here is my plot with two variables, you can see the adding that is happening
simple dataframe
Here is my code:
library(reshape2)
library(ggplot2)
test2 <- structure(list(SampleID = c(12.19, 12.22, 13.1, 12.19, 12.22,
13.1, 12.19, 12.22, 13.1, 12.19, 12.22, 13.1), patient = c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), type = structure(c(1L,
1L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 2L), .Label = c("L",
"T"), class = "factor"), timepoint = structure(c(1L, 2L, 2L,
1L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 2L), .Label = c("1", "2"), class = "factor"),
Group = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L), .Label = "D", class = "factor"), variable = structure(c(1L,
1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L), .Label = c("A",
"B", "C", "D", "E", "F", "G", "H", "I"), class = "factor"),
value = c(2L, 5L, 6L, 25L, 18L, 12L, 6L, 10L, 15L, 21L, 23L,
33L)), .Names = c("SampleID", "patient", "type", "timepoint",
"Group", "variable", "value"), row.names = c(NA, 12L), class = "data.frame")
ggplot(test2, aes(test2$variable, test2$value, fill=test2$timepoint)) +
geom_bar(stat="identity", position = "dodge") +
scale_fill_manual(values=c("rosybrown1", "steelblue2", "gray")) +
labs(x="Category", y="Count", title = paste0("Sample ", as.character(unique(test2$patient)) , " - " , as.character(unique(test2$Group)))) +
facet_wrap(~test2$type) +
theme(text = element_text(size=15),
axis.text.x = element_text(angle = 90, hjust = 1, vjust=.5, size = 7))
If I am understanding right, it looks like you just need to give the scales option to facet_wrap like so:
facet_wrap(~type, scales = "free_x")
I'm writing a function that attempts to add values in a single row of a data.frame in several columns at once:
require(stringr)
addPointsToKeyRow = function(df, keyRowNum, searchStringForPointColNames, pointsVector){
colsWithMatchingSearchResults = str_match(colnames(df), searchStringForPointColNames)
pointColNums = (which(!is.na(colsWithMatchingSearchResults)))
pointsVectorCleaned = pointsVector[!is.na(pointsVector)]
print(is.vector(pointsVectorCleaned)) #Returns TRUE
print(is.data.frame(pointsVectorCleaned)) #Returns FALSE
print(pointsVectorCleaned)
if(length(pointsVectorCleaned) == length(pointColNums)){
newDf = data.frame(df, stringsAsFactors = FALSE)
newDf[keyRowNum, pointColNums] = as.character(pointsVectorCleaned)
#for(i in 1:length(pointColNums)){
# newDf[keyRowNum,pointColNums[i]]=as.character(pointsVectorCleaned[i])
#}
print(newDf[keyRowNum,])
}
}
When I apply the function to my data (addPointsToKeyRow(finalDf, which(finalDf[,1]=="key"), "points_q", pointVals)), I get the following warnings:
In [<-.factor(*tmp*, iseq, value = "2") :
invalid factor level, NA generated
I've looked for the error on SO and other sites, and the recommendation always seems to be to make sure your data.frame has stringsAsFactors = FALSE.
I think my issue might be that when I subset the data.frame (newDf[keyRowNum, pointColNums]), it no longer keeps stringsAsFactors = FALSE.
Regardless of whether that's the issue or not, I'd very much welcome some help solving this weird issue. Many thanks in advance!
For the sake of an example, let's say df is:
df = structure(list(first = structure(c(7L, 9L, 5L, 4L, 10L, 2L, 3L,
6L, 1L, 8L), .Label = c("autumn", "spring", "summer", "winter",
"july", "betty", "november", "echo", "victor", "tango"), class = "factor"),
last = structure(c(6L, 2L, 4L, 5L, 1L, 8L, 3L, 9L, 10L, 7L
), .Label = c("brummett1", "do", "drorbaugh", "galeno", "gerber",
"key", "lyons", "pecsok", "perezfranco", "swatt"), class = "factor"),
question1 = structure(c(1L, 1L, 1L, 4L, 6L, 2L, 5L, 3L, 5L,
5L), .Label = c("0", "0.25", "1:02:01", "1:2 50%", "2-Jan",
"50%"), class = "factor"), points_q1 = structure(c(1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "", class = "factor"),
question2 = structure(c(8L, 10L, 6L, 5L, 2L, 3L, 7L, 1L,
4L, 9L), .Label = c(" a | b; A| Aa | Ab; b| ab | bb; the possibility that the offspring will be heterozygous is about 25%. The same goes for the homozygous recessive it is a 1:1:1:1",
"1/4 heterozygous for \xf1a\xee and 0 recessive for \xf1b\xee",
"16-Mar", "2-Jan", "3:1 25%", "4-Jan", "Male=aabb Female=AAbb Heterozygous is going to be 1/2. Homozygous is going to be 1/4.",
"possible offspring genotypes (each with probability of 0.25): AABb AaBb AAbb Aabb. Question is asking about probability of Aabb_ which is 0.25.",
"The square shows Ab Ab_ Bb Bb so 50% or 1/2. ", "Xa Yb (father) crossed with XA Xb (mother) = 1/2 "
), class = "factor"), points_q2 = structure(c(1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "", class = "factor"),
question3 = structure(c(4L, 5L, 3L, 5L, 5L, 5L, 7L, 2L, 6L,
1L), .Label = c("Codominance", "coheritance", "incomplete dominance",
"Incomplete dominance", "Incomplete dominance ", "Incomplete dominance. ",
"Independent Assortment"), class = "factor"), points_q3 = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "", class = "factor"),
question4 = structure(c(3L, 4L, 2L, 3L, 6L, 3L, 7L, 1L, 5L,
4L), .Label = c("", "co-dominance", "Codominance", "Codominance ",
"Codominance. ", "Codominant ", "Independent Assortment? (Wrong)"
), class = "factor"), points_q4 = structure(c(1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "", class = "factor"),
question5 = structure(c(2L, 10L, 6L, 4L, 5L, 3L, 8L, 1L,
7L, 9L), .Label = c(" X | Y; X| XX | XY; x| Xx | xY; the percentage will be 25 % or 1/4 the same applies to the son ",
"0 for daughter_ because male can only give non-colorblind X chromosome (because he's not colorblind an only has one X chromosome). 0.25 for both son and colorblind.",
"0.25", "25% for son and 25% for daughter", "25% for the son and 25% for the daughter ",
"4-Jan", "50%", "Father=XY Mother=X2Y Therefore_ by using the punnet square_ I was able to show/understand that the probability of them having a son AND him being colorblind is 1/4.",
"To have a son or daughter is 50/50. To have a colorblind daughter is .25 whereas to have a colorblind son is .75 because it is carried on the X chromosome and the son is much more likely to inherit this because he has less x to work with",
"XcY (father) XC Xc (mother) Daughter is 1/4 son 1/4"), class = "factor"),
points_q5 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L), .Label = "", class = "factor"), question6 = structure(c(3L,
6L, 7L, 8L, 5L, 2L, 10L, 9L, 4L, 1L), .Label = c("Chromatids ",
"Chromosomes (diploids)", "homologous chromosome pairs",
"Homologous chromosome pairs are being separated. ", "Homologous chromosomes ",
"Homologous pairs ", "homologous pairs of chromosomes", "Homologus Chromosomes ",
"sister chromatids ", "Sister Chromatids?"), class = "factor"),
points_q6 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L), .Label = "", class = "factor"), question7 = structure(c(6L,
8L, 5L, 7L, 8L, 2L, 3L, 1L, 9L, 4L), .Label = c("", "Chromatids (haploids)",
"Daughter Chromosomes?", "One cell to 2", "sister chromatids",
"Sister chromatids", "Sister Chromatids", "Sister chromatids ",
"Sister chromatids within daughter cells are separating. "
), class = "factor"), points_q7 = structure(c(1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "", class = "factor"),
question8 = structure(c(1L, 4L, 1L, 2L, 4L, 2L, 3L, 6L, 5L,
3L), .Label = c("sister chromatids", "Sister chromatids",
"Sister Chromatids", "Sister chromatids ", "Sister chromatids are held together by the centromeres. In prophase chromosomes become visible. During metaphase chromosomes attach to spindles. During Anaphase the chromosomes are split apart and in telophase the cells start to create cleavage. ",
"sisters chromatides"), class = "factor"), points_q8 = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "", class = "factor"),
question9 = structure(c(2L, 4L, 1L, 3L, 4L, 3L, 3L, 2L, 5L,
3L), .Label = c("prohase ", "prophase", "Prophase", "Prophase ",
"They condense during prophase before the rest of the phases. "
), class = "factor"), points_q9 = structure(c(1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "", class = "factor"),
question10 = structure(c(1L, 3L, 1L, 2L, 3L, 2L, 2L, 1L,
4L, 2L), .Label = c("anaphase", "Anaphase", "Anaphase ",
"During anaphase. "), class = "factor"), points_q10 = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "", class = "factor"),
question11 = structure(c(3L, 4L, 3L, 4L, 4L, 4L, 4L, 3L,
1L, 2L), .Label = c("During prophase. ", "Telephase ", "telophase",
"Telophase"), class = "factor"), points_q11 = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "", class = "factor"),
question12 = structure(c(1L, 3L, 1L, 2L, 3L, 2L, 3L, 1L,
4L, 2L), .Label = c("metaphase", "Metaphase", "Metaphase ",
"Metaphase. "), class = "factor"), points_q12 = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "", class = "factor"),
question13 = structure(c(1L, 4L, 1L, 4L, 2L, 4L, 2L, 5L,
3L, 6L), .Label = c("centromere", "Centromere", "Centromere. ",
"Centromeres", "centromeres ", "Cleavage"), class = "factor"),
points_q13 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L), .Label = "", class = "factor")), .Names = c("first",
"last", "question1", "points_q1", "question2", "points_q2", "question3",
"points_q3", "question4", "points_q4", "question5", "points_q5",
"question6", "points_q6", "question7", "points_q7", "question8",
"points_q8", "question9", "points_q9", "question10", "points_q10",
"question11", "points_q11", "question12", "points_q12", "question13",
"points_q13"), row.names = c(NA, -10L), class = "data.frame")
which(finalDf[,1]=="key") is 1.
pointVals is c(NA, "2", "2", "2", "2", "2", "2", "2", "1", "1", "1", "1",
"1", "1")
For clarification, I'd want the final table to look something like:
First Last question1 points_q1 question2 points_q2 etc.
key key 0 2 "possible_offspring_genotypes..." 1 etc.
I have reduced your function based on my understanding , let me know if it gives what you want or if I have misunderstood something
addPointsToKeyRow = function(df, keyRowNum, searchString, pointsVector) {
#Find columns which has searchString in it
cols <- grepl(searchString, colnames(df))
#Check if the columns with searchString and length of pointsVector is the same
if (sum(cols) == length(pointsVector)) {
#Assign the value
df[keyRowNum,cols] <- pointsVector
}
#Return the updated dataframe
df
}
#Convert all the variables in the column from factor to character
df[] <- lapply(df, as.character)
#define the values to be replaced
pointVals <- c("2", "2", "2", "2", "2", "2", "2", "1", "1", "1", "1","1", "1")
#Call the function
df <- addPointsToKeyRow(df, 1, "points_q", pointsval)
#Check the dataframe
df
I have a dataset with 10 columns and out of them 10, 3 are of interest to create a new indicator feature. The features are "pT", "pN", & "M" and they all take different values. Off all the values that these 3 features take, there are a toal of 9 unique combinations that needs to be captures in the new variable.
PATHOT PATHON PATHOM
1 pT2 pN1 M0
4 pT1 pN1 M0
13 pT3 pN1 M0
161 pT1 *pN2 M0
391 pT1 pN1 *M1
810 *pTIS pN1 M0
948 pT3 *pN2 M0
1043 pT2 pN1 *M1
1067 *pT4 pN1 M0
For example, the new variable will have value "1" when PATHOT=pT2, PATHON=pN1 & PATHOM=M0 and so on upto value 9. I have completed the task but after spending almost 20 lines of code involving vectorised operation for all unique combinations.
diag3_bs$sfd[diag3_bs$pathot=="pT2" & diag3_bs$pathon=="pN1" &
diag3_bs$pathom=="M0"] <- 1
diag3_bs$sfd[diag3_bs$pathot=="pT1" & diag3_bs$pathon=="pN1" &
diag3_bs$pathom=="M0"] <- 2
diag3_bs$sfd[diag3_bs$pathot=="pT3" & diag3_bs$pathon=="pN1" &
diag3_bs$pathom=="M0"] <- 3... so on upto 9.
I want to ask if there is a better more automated way of getting the same result?
dput(data.frame) is given below
structure(list(F_STATUS = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L), .Label = "Y", class = "factor"), EVENT_ID = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "BASELINE", class =
"factor"),
PAG_NAME = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L), .Label = "BR2", class = "factor"), PTSIZE = c(3, 4,
2.7, 2, 0.9, 3, 3, 0.9, 3, 4.5), PTSIZE_U = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "CM", class = "factor"),
PT_SYM = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L), .Label = c("", "-", "<", ">"), class = "factor"), PATHOT = structure(c(4L,
4L, 4L, 3L, 3L, 4L, 4L, 3L, 4L, 4L), .Label = c("*pT4", "*pTIS",
"pT1", "pT2", "pT3"), class = "factor"), PATHON = structure(c(2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("*pN2", "pN1"
), class = "factor"), PATHOM = structure(c(2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L), .Label = c("*M1", "M0"), class = "factor"),
RSUBJID = 901000:901009, RUSUBJID = structure(1:10, .Label = c(
"000301-000-901-251", "000301-000-901-252", "000301-000-901-253",
"000301-000-901-254", "000301-000-901-255", "000301-000-901-256",
"000301-000-901-257", "000301-000-901-258", "000301-000-901-259",
"000301-000-901-260", "000301-000-901-261", "000301-000-901-262")
, class = "factor")), .Names = c("F_STATUS", "EVENT_ID", "PAG_NAME", "PTSIZE", "PTSIZE_U", "PT_SYM", "PATHOT",
"PATHON", "PATHOM", "RSUBJID", "RUSUBJID"), row.names = c(NA, 10L),
class = "data.frame")
Thanks.
I tried to edit the data so it didn't throw an error on input. Also created a version of that tabulation of possible combinations:
stg_tbl <- structure(list(PATHOT = structure(c(4L, 3L, 5L, 3L, 3L, 2L, 5L,
4L, 1L), .Label = c("*pT4", "*pTIS", "pT1", "pT2", "pT3"), class = "factor"),
PATHON = structure(c(2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 2L), .Label = c("*pN2",
"pN1"), class = "factor"), PATHOM = structure(c(2L, 2L, 2L,
2L, 1L, 2L, 2L, 1L, 2L), .Label = c("*M1", "M0"), class = "factor")), .Names = c("PATHOT",
"PATHON", "PATHOM"), class = "data.frame", row.names = c("1",
"4", "13", "161", "391", "810", "948", "1043", "1067"))
Make a vector of text-equivalents of the categories:
stg_lbls <- with(stg_tbl, paste(PATHOT, PATHON, PATHOM, sep="_") )
Then the as.numeric values of a factor created using those levels will be the desired result:
dat$stg <- with(dat, factor( paste(PATHOT, PATHON, PATHOM, sep="_"), levels=stg_lbls))
as.numeric(dat$stg)
#[1] 1 1 1 2 2 1 1 2 1 1
You can just assign those values in the usual way:
dat$sfd <- as.numeric(dat$stg)
I made some new data, that should be useful for your problem.
k<-expand.grid(data.frame(a=letters[1:3],b=letters[4:6],c=letters[7:9]))
library(dplyr)
k %>% mutate(groups=paste0(a,b,c))->k2
k2$groups<-as.numeric(factor(k2$groups))
k2
It's crude, and you're not picking which combination get's which numbers, so it'd take some digging afterwards, but it's quick.
I have this dataframe.
dput(EF_Lat_Am)
structure(list(V1 = structure(c(4L, 3L, 5L, 6L, 1L, 2L, 7L, 8L,
4L, 3L, 5L, 6L, 1L, 2L, 7L, 8L), .Label = c("Crop Agriculture",
"Mining", "Mixed Agriculture", "Other land use", "Pasture", "Tree crops",
"Urban", "Water"), class = "factor"), V2 = structure(c(1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "Emission Factor", class = "factor"),
V3 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L), .Label = c("2000", "2005"), class = "factor"),
V4 = c(77.0109486116396, 69.2454348145657, 73.684103657833,
71.0430911289891, 43.136201172115, 117.358146800995, 77.4653952935238,
89.0966064142874, 71.8286578413912, 67.9099357961953, 76.7438444998728,
67.4818461466729, 50.6468079101972, 117.799797611894, 78.7347377710757,
81.3020943196897)), .Names = c("V1", "V2", "V3", "V4"), row.names = c(NA,
16L), class = "data.frame")
As you can see for the years 2000 and 2005, I have an emission factor value for each type of land use. I want to plot an histogram with the type of land use in the x axis and the emission factors in the y axis. In addition, for each land use I want the bars for the two years to be adjacents. I also want a legend showing for which years correspond the bars (either 2000 or 2005). Thanks for your help.
Here is the answer.
ggplot(EF_Lat_Am, aes(x=V1, y = V4, fill=V3, width=.85)) + geom_bar(position="dodge", stat="identity") +
labs(x = "", y = "EF (T/ha)") +
theme(axis.text=element_text(size=16),axis.title=element_text(size=20),
legend.title=element_text(size=20, face='bold'),legend.text=element_text(size=20), axis.line = element_line(colour = "black")) +
scale_fill_grey("Period") + scale_y_continuous(limits=c(0,120)) + theme_classic(base_size = 20, base_family = "")