I have two data frames
df1 <- structure(list(g1 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("A", "B"), class = "factor"), g2 = structure(c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L), .Label = c("a", "b", "c"), class = "factor"), val1 = 1:20, val2 = c(1L, 2L, 3L, 4L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 4L, 1L, 2L, 3L)), .Names = c("g1", "g2", "val1", "val2"), row.names = c(NA, -20L), class = "data.frame")
df2 <- structure(list(g1 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("A", "B"), class = "factor"), g2 = structure(c(1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L), .Label = c("a", "b", "c"), class = "factor"), val3 = c(5L, 6L, 7L, 3L, 4L, 5L, 2L, 3L, 4L, 8L, 9L, 10L, 4L, 5L, 6L, 5L, 6L)), .Names = c("g1", "g2", "val3"), row.names = c(NA, -17L), class = "data.frame")
> df1
g1 g2 val1 val2
1 A a 1 1
2 A a 2 2
3 A a 3 3
4 A a 4 4
5 A b 5 1
6 A b 6 2
7 A b 7 3
8 A c 8 1
9 A c 9 2
10 A c 10 3
11 B a 11 1
12 B a 12 2
13 B a 13 3
14 B b 14 1
15 B b 15 2
16 B b 16 3
17 B b 17 4
18 B c 18 1
19 B c 19 2
20 B c 20 3
> df2
g1 g2 val3
1 A a 5
2 A a 6
3 A a 7
4 A b 3
5 A b 4
6 A b 5
7 A c 2
8 A c 3
9 B c 4
10 B a 8
11 B a 9
12 B a 10
13 B b 4
14 B b 5
15 B b 6
16 B c 5
17 B c 6
My aim is to rescale df1$val2 to take values between the min and max values of df2$val3 within the respective groups.
I tried this:
library(dplyr)
df1 <- df1 %.% group_by(g1, g2) %.% mutate(rescaled=(max(df2$val3)-min(df2$val3))*(val2-min(val2))/(max(val2)-min(val2))+min(df2$val3))
But the output is different from what I expect. The problem is that I can neither cbind nor merge the two data frames due to their different lengths. Any hints?
Does this work?
library(plyr)
df3 <- ddply(df2, .(g1, g2), summarize, max.val=max(val3), min.val=min(val3))
merged.df <- merge(df1, df3, by=c("g1", "g2"), all.x=TRUE)
## Now rescale merged.df$val2 as desired
Related
How can i remove rows with any same value that is in another column of the same row? For example,
df<-structure(list(V1 = c(1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L,
2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L,
3L), V2 = c(1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 2L,
2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L), V3 = c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L)), row.names = c(NA, -27L
), class = "data.frame")
##Top three rows
V1 V2 V3
1 1 1 1
2 2 1 1
3 3 1 1
4 1 2 1
5 2 2 1
6 3 2 1
7 1 3 1
8 2 3 1
In the following case (only showing 8 rows), I would remove every row accept rows 6 and 8 since they do not have any duplicate values in any column of the same row. I'm preferably looking for a data.table solution since I have a much larger dataframe.
You may use anyDuplicated for each row.
library(data.table)
setDT(df)
df[apply(df, 1, anyDuplicated) == 0]
# V1 V2 V3
#1: 3 2 1
#2: 2 3 1
#3: 3 1 2
#4: 1 3 2
#5: 2 1 3
#6: 1 2 3
An option using pairwise combn on the columns to check if there are equal values
df[!Reduce(`|`, combn(df, 2, FUN = function(x)
x[[1]] == x[[2]], simplify = FALSE))]
V1 V2 V3
1: 3 2 1
2: 2 3 1
3: 3 1 2
4: 1 3 2
5: 2 1 3
6: 1 2 3
Hello for my work I creates a ggplot2 heatmap.
here are the data
structure(list(label = structure(c(4L, 5L, 7L, 2L, 3L, 6L, 8L,
1L, 4L, 5L, 7L, 2L, 3L, 6L, 8L, 1L, 4L, 5L, 7L, 2L, 3L, 6L, 8L,
1L), .Label = c("SP1", "SP2", "SP3", "SP4", "SP5", "SP6", "SP7",
"SP8"), class = "factor"), Categories = structure(c(1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L), .Label = c("VAR1", "VAR2", "VAR3"), class = "factor"),
Value = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 3L,
3L, 3L, 3L, 2L, 1L, 1L, 2L, 3L, 3L, 3L, 3L, 3L, 1L, 1L), .Label = c("<NA>",
"A", "B"), class = "factor")), class = "data.frame", row.names = c(NA,
-24L))
as you can see there is a specific order of labels :
1 - SP4
2 - SP5
3 - SP7
...
7 - SP8
8 - SP1
here is the df :
> table
label Categories Value
1 SP4 VAR1 <NA>
2 SP5 VAR1 <NA>
3 SP7 VAR1 <NA>
4 SP2 VAR1 <NA>
5 SP3 VAR1 <NA>
6 SP6 VAR1 <NA>
7 SP8 VAR1 <NA>
8 SP1 VAR1 <NA>
9 SP4 VAR2 A
10 SP5 VAR2 B
11 SP7 VAR2 B
12 SP2 VAR2 B
13 SP3 VAR2 B
14 SP6 VAR2 A
15 SP8 VAR2 <NA>
16 SP1 VAR2 <NA>
17 SP4 VAR3 A
18 SP5 VAR3 B
19 SP7 VAR3 B
20 SP2 VAR3 B
21 SP3 VAR3 B
22 SP6 VAR3 B
23 SP8 VAR3 <NA>
24 SP1 VAR3 <NA>
so I'm expecting to see the same row order if I do a heatmap with ggplot, but instead I get this order:
I used the code :
ggplot(mod_mat_gen_env, aes(x=Categories, y=label))+
geom_tile(aes(fill=Value))
One option is to refactor it in your data.frame, or you can provide the order using limits= option in scale_y_discrete()
df$Value = replace(as.character(df$Value),df$Value=="<NA>",NA)
list_correct_order=c("SP4","SP5","SP7","SP2","SP3","SP6","SP8","SP1")
ggplot(df, aes(x=Categories, y=label))+
geom_tile(aes(fill=Value)) +
scale_y_discrete(limits=rev(list_correct_order))
I have a data, as an example I show below
a = rep(1:5, each=3)
b = rep(c("a","b","c","a","c"), each = 3)
df = data.frame(a,b)
I want to select all the rows that have the "a"
I tried to do it with
df[df$a %in% a,]
Can someone give me an idea how to get them out?
df2<- structure(list(V1 = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), V2 = structure(c(1L,
2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 1L, 2L, 3L, 4L,
5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L), .Label = c("B02", "B03",
"B04", "B05", "B06", "B07", "C02", "C03", "C04", "C05", "C06",
"C07"), class = "factor")), .Names = c("V1", "V2"), class = "data.frame", row.names = c(NA,
-24L))
I want to select specific rows that start with B but not all of them and just 02, 03, 04, 05
1 B02
1 B03
1 B04
1 B05
2 B02
2 B03
2 B04
2 B05
I also want to have the original data without them too
We need to check the 'b' column
df[df$b %in% 'a',]
For the updated question with 'df2', we can use paste to create the strings 'B02' to 'B05' and use %in% to subset
df2[df2$V2 %in% paste0("B0", 2:5),]
Or another option is grep
df2[grep("^B0[2-5]$", df2$V2),]
> df
a b
1 1 a
2 1 a
3 1 a
4 2 b
5 2 b
6 2 b
7 3 c
8 3 c
9 3 c
10 4 a
11 4 a
12 4 a
13 5 c
14 5 c
15 5 c
This basically says:
For all columns in df choose rows that have value equal to a
> rows_with_a<-df[df$b=='a', ]
> rows_with_a
a b
1 1 a
2 1 a
3 1 a
10 4 a
11 4 a
12 4 a
How would you go about creating the graph below in R? I want to show the duration of different treatments for different patients.
Mock data here:
Start Day Stop Day
Patient 1 Drug 1 1 3
Drug 2 2 5
Drug 3 3 8
Patient 2 Drug 1 2 4
Drug 2 2 5
Drug 3 1 6
Patient 3 Drug 1 4 7
Drug 2 3 8
Drug 3 5 6
Your graph can be generated using geom_segment in the ggplot2 package:
df <- structure(list(Patient = structure(c(1L, 1L, 1L, 2L, 2L, 2L,
3L, 3L, 3L), .Label = c("Patient1", "Patient2", "Patient3"), class = "factor"),
Drug = structure(c(1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L), .Label = c("Drug1",
"Drug2", "Drug3"), class = "factor"), StartDay = c(1L, 2L,
3L, 2L, 2L, 1L, 4L, 3L, 5L), StopDay = c(3L, 5L, 8L, 4L,
5L, 6L, 7L, 8L, 6L)), .Names = c("Patient", "Drug", "StartDay",
"StopDay"), class = "data.frame", row.names = c(NA, -9L))
df$Drug <- factor(df$Drug, levels(df$Drug)[c(3,2,1)])
library(ggplot2)
ggplot(data=df, aes(color=Drug))+
geom_segment(aes(x=StartDay, xend=StopDay, y=Drug, yend=Drug),lwd=12)+
facet_grid(Patient~.)+xlab("Days")
Suppose I have data which looks like this
Id Name Price sales Profit Month Category Mode Supplier
1 A 2 5 8 1 X K John
1 A 2 6 9 2 X K John
1 A 2 5 8 3 X K John
2 B 2 4 6 1 X L Sam
2 B 2 3 4 2 X L Sam
2 B 2 5 7 3 X L Sam
3 C 2 5 11 1 X M John
3 C 2 5 11 2 X L John
3 C 2 5 11 3 X K John
4 D 2 8 10 1 Y M John
4 D 2 8 10 2 Y K John
4 D 2 5 7 3 Y K John
5 E 2 5 9 1 Y M Sam
5 E 2 5 9 2 Y L Sam
5 E 2 5 9 3 Y M Sam
6 F 2 4 7 1 Z M Kyle
6 F 2 5 8 2 Z L Kyle
6 F 2 5 8 3 Z M Kyle
if I apply table function, it will just combines are the rows and result will be
K L M
X 4 4 1
Y 2 1 3
Z 0 1 2
Now what if I want not the sum of all rows but only sum of those rows with Unique Id
so it looks like
K L M
X 2 2 1
Y 1 1 2
Z 0 1 1
Thanks
If df is your data.frame:
# Subset original data.frame to keep columns of interest
df1 <- df[,c("Id", "Category", "Mode")]
# Remove duplicated rows
df1 <- df1[!duplicated(df1),]
# Create table
with(df1, table(Category, Mode))
# Mode
# Category K L M
# X 2 2 1
# Y 1 1 2
# Z 0 1 1
Or in one line using unique
table(unique(df[c("Id", "Category", "Mode")])[-1])
df <- structure(list(Id = c(1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 4L,
4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L), Name = structure(c(1L, 1L, 1L,
2L, 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L), .Label = c("A",
"B", "C", "D", "E", "F"), class = "factor"), Price = c(2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L
), sales = c(5L, 6L, 5L, 4L, 3L, 5L, 5L, 5L, 5L, 8L, 8L, 5L,
5L, 5L, 5L, 4L, 5L, 5L), Profit = c(8L, 9L, 8L, 6L, 4L, 7L, 11L,
11L, 11L, 10L, 10L, 7L, 9L, 9L, 9L, 7L, 8L, 8L), Month = c(1L,
2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L,
3L), Category = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L), .Label = c("X", "Y", "Z"
), class = "factor"), Mode = structure(c(1L, 1L, 1L, 2L, 2L,
2L, 3L, 2L, 1L, 3L, 1L, 1L, 3L, 2L, 3L, 3L, 2L, 3L), .Label = c("K",
"L", "M"), class = "factor"), Supplier = structure(c(1L, 1L,
1L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 3L, 3L, 3L, 2L, 2L, 2L
), .Label = c("John", "Kyle", "Sam"), class = "factor")), .Names = c("Id",
"Name", "Price", "sales", "Profit", "Month", "Category", "Mode",
"Supplier"), class = "data.frame", row.names = c(NA, -18L))
We can try
library(data.table)
dcast(unique(setDT(df1[c('Category', 'Mode', 'Id')])),
Category~Mode, value.var='Id', length)
# Category K L M
#1: X 2 2 1
#2: Y 1 1 2
#3: Z 0 1 1
Or with dplyr
library(dplyr)
df1 %>%
distinct(Id, Category, Mode) %>%
group_by(Category, Mode) %>%
tally() %>%
spread(Mode, n, fill=0)
# Category K L M
# (chr) (dbl) (dbl) (dbl)
#1 X 2 2 1
#2 Y 1 1 2
#3 Z 0 1 1
Or as #David Arenburg suggested, a variant of the above is
df1 %>%
distinct(Id, Category, Mode) %>%
select(Category, Mode) %>%
table()