I have a dataframe(df) that looks like below:
Objective: I want to create 52 DATAFRAMES, I don't know how to use it with dplyr
Assuming your dataframe is in variable df, try the following code:
library(dplyr)
columns_name = names(df) #names of column in your dataframe
df_list =list() #empty list to store output dataframes
#loop through columns of the original dataframe,
#selecting the first and i_th column and storing the resulting dataframe in a list
for (i in 1:(length(columns_name) -1)){
df_list[[i]] = df %>% select(columns_name[1],columns_name[i+1]) %>% filter_all(all_vars(!is.na(.)))
}
#access smaller dataframes using the following code
df_list[[1]]
df_list[[2]]
Try next code:
library(dplyr)
library(tidyr)
#Code
new <- df %>% pivot_longer(-1) %>%
group_by(name) %>%
filter(!is.na(value))
#List
List <- split(new,new$name)
#Set to envir
list2env(List,envir = .GlobalEnv)
Some data used:
#Data
df <- structure(list(id_unico = c("112172-1", "112195-1", "112257-1",
"112268-1", "112383-1", "112452-1", "112715-1", "112716-1", "112761-1",
"112989-1"), P101COD = c(NA, NA, NA, NA, NA, 411010106L, NA,
NA, 411010106L, NA), P102COD = c(421010102L, 421010102L, 421010102L,
421010102L, 421010102L, NA, 421010108L, 421010108L, NA, 421010102L
), P103COD = c(441010109L, 441010109L, 441010109L, 441010109L,
441010109L, 441010109L, 441010109L, 441010109L, 441010109L, 441010101L
), P110_52_COD = c(NA, 831020103L, 831020103L, NA, 831020103L,
NA, NA, NA, NA, NA)), class = "data.frame", row.names = c(NA,
-10L))
Related
I have a dataframe which contains many triplicate (3 columns set). And I have grouped the dataframe into each triplicate as a seperate group of list.
The example dataset is,
example_data <- structure(list(`1_3ng` = c(69648445400, 73518145600, NA, NA,
73529102400, 75481088000, NA, 73545910600, 74473949200, 77396199900
), `2_3ng` = c(71187990600, 70677690400, NA, 73675407400, 73215342700,
NA, NA, 69996254800, 69795686400, 76951318300), `3_3ng` = c(65032022000,
71248214000, NA, 72393058300, 72025550900, 71041067000, 73604692000,
NA, 73324202000, 75969608700), `4_7-5ng` = c(NA, 65845061600,
75009245100, 64021237700, 66960666600, 69055643600, NA, 64899540900,
NA, NA), `5_7-5ng` = c(65097201700, NA, NA, 69032126500, NA,
70189899800, NA, 74143529100, 69299087400, NA), `6_7-5ng` = c(71964413900,
69048485800, NA, 71281569700, 71167596500, NA, NA, 68389822800,
69322289200, NA), `7_10ng` = c(71420403700, 67552276500, 72888076300,
66491357100, NA, 68165019600, 70876631000, NA, 69174190100, 63782945300
), `8_10ng` = c(NA, 71179401200, 68959365100, 70570182700, 73032738800,
NA, 74807496700, NA, 71812102100, 73855098500), `9_10ng` = c(NA,
70403756100, NA, 70277421000, 69887731700, 69818871800, NA, 71353886700,
NA, 74115466700), `10_15ng` = c(NA, NA, 68487581700, NA, NA,
69056997400, NA, 67780479400, 66804467800, 72291939500), `11_15ng` = c(NA,
63599643700, NA, NA, 60752029700, NA, NA, 63403655600, NA, 64548492900
), `12_15ng` = c(NA, 67344750600, 61610182700, 67414425600, 65946654700,
66166118400, NA, 70830837700, 67288305700, 69911451300)), class = c("tbl_df",
"tbl", "data.frame"), row.names = c(NA, -10L)
And after grouping I got the four lists, since the above example dataset contains 4 groups. I have used the following R code for grouping the data,
grouping_data<-function(df){ #df= dataframe
df_col<-ncol(df) #calculates no. of columns in dataframe
groups<-sort(rep(0:((df_col/3)-1),3)) #creates user determined groups
id<-list() #creates empty list
for (i in 1:length(unique(groups))){
id[[i]]<-which(groups == unique(groups)[i])} #creates list of groups
names(id)<-paste0("id",unique(groups)) #assigns group based names to the list "id"
data<-list() #creates empty list
for (i in 1:length(id)){
data[[i]]<-df[,id[[i]]]} #creates list of dataframe columns sorted by groups
names(data)<-paste0("data",unique(groups)) #assigns group based names to the list "data"
return(data)}
group_data <-grouping_data(example_data)
Please suggest useful R code for do a particular function for all the lists at a same time.
For example the below function I have done by following way,
#VSN Normalization
vsnNorm <- function(dat) {
dat<-as.data.frame(dat)
vsnNormed <- suppressMessages(vsn::justvsn(as.matrix(dat)))
colnames(vsnNormed) <- colnames(dat)
row.names(vsnNormed) <- rownames(dat)
return(as.matrix(vsnNormed))
}
And I have tried like below,
vsn.dat0 <- vsnNorm(group_data$data0)
vsn.dat1 <- vsnNorm(group_data$data1)
vsn.dat2 <- vsnNorm(group_data$data2)
vsn.dat3 <- vsnNorm(group_data$data3)
vsn.dat <- cbind (vsn.dat0,vsn.dat1,vsn.dat2,vsn.dat3)
It is working well.
But the dataset triplicate (3 columns set) value may be change from dataset to dataset. And calling all the lists everytime become will be tedious.
So kindly share some codes which will call all the resulted lists for performing a function and combine the result as a single file.
Thank you in advance.
The shortcut you are looking for is:
vsn.dat <- do.call("rbind", lapply(group_data, vsnNorm))
I have a data structure, it looks as such in the dput form:
test_df <- structure(list(dob = structure(c(-25932, -25932, -25932, -25932,
-25932, -25932, -25932, -25932, -25932, -25932, -25932, -25932,
-25932, -25932, -16955, -13514, -12968, -12419, -12237, -11537,
-10168, -9742, -9376, -9131, -8766, -8676, -8462, -8189, -8036,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA), class = "Date")), class = "data.frame", row.names = c(NA,
-45L))
This should produce a variable with 45 rows.
If I then run:
test_include <- test_df %>% filter(dob == '1899-01-01')
This returns the proper amount of rows, which would be 14.
But if I do the opposite of this and filter for all rows that DO NOT equal '1899-01-01' it returns a weird result:
test_exclude <- test_df %>% filter(dob != '1899-01-01')
Instead of returning 31 rows (45 - 14), it returns 15 rows, which makes no sense.
Does anyone have a solution and explanation as to why it is doing this?
Basically, != does not get NA, check this post for more information, but here is an example with your data
library(dplyr)
library(lubridate)
> test_df %>% filter(dob == ymd('1899-01-01')) %>% nrow()
[1] 14
> test_df %>% filter(dob != ymd('1899-01-01')) %>% nrow()
[1] 15
> test_df %>% filter(is.na(dob)) %>% nrow()
[1] 16
> test_df %>% filter(dob != ymd('1899-01-01') | is.na(dob)) %>% nrow()
[1] 31
I have the following data frame, each row containing four dates ("y") and four measurements ("x"):
df = structure(list(x1 = c(69.772808673525, NA, 53.13125414839,
17.3033274666411,
NA, 38.6120670385487, 57.7229000792707, 40.7654208618078, 38.9010405201831,
65.7108936694177), y1 = c(0.765671296296296, NA, 1.37539351851852,
0.550277777777778, NA, 0.83037037037037, 0.0254398148148148,
0.380671296296296, 1.368125, 2.5250462962963), x2 = c(81.3285388496182,
NA, NA, 44.369872853302, NA, 61.0746827226573, 66.3965114460601,
41.4256874481852, 49.5461413070349, 47.0936997726146), y2 =
c(6.58287037037037,
NA, NA, 9.09377314814815, NA, 7.00127314814815, 6.46597222222222,
6.2462962962963, 6.76976851851852, 8.12449074074074), x3 = c(NA,
60.4976916064608, NA, 45.3575294731303, 45.159758146854, 71.8459173097114,
NA, 37.9485456227131, 44.6307631013742, 52.4523342186143), y3 = c(NA,
12.0026157407407, NA, 13.5601157407407, 16.1213657407407, 15.6431018518519,
NA, 15.8986805555556, 13.1395138888889, 17.9432638888889), x4 = c(NA,
NA, NA, 57.3383407228293, NA, 59.3921356160536, 67.4231673171527,
31.853845252547, NA, NA), y4 = c(NA, NA, NA, 18.258125, NA,
19.6074768518519,
20.9696527777778, 23.7176851851852, NA, NA)), class = c("tbl_df",
"tbl", "data.frame"), row.names = c(NA, -10L))
I would like to create an additional column containing the slope of all the y's versus all the x's, for each row (each row is a patient with these 4 measurements).
Here is what I have so far:
df <- df %>% mutate(Slope = lm(vars(starts_with("y") ~
vars(starts_with("x"), data = .)
I am getting an error:
invalid type (list) for variable 'vars(starts_with("y"))'...
What am I doing wrong, and how can I calculate the rowwise slope?
You are using a tidyverse syntax but your data is not tidy...
Maybe you should rearrange your data.frame and rethink the way you store your data.
Here is how to do it in a quick and dirty way (at least if I understood your explanations correctly):
df <- merge(reshape(df[,(1:4)*2-1], dir="long", varying = list(1:4), v.names = "x", idvar = "patient"),
reshape(df[,(1:4)*2], dir="long", varying = list(1:4), v.names = "y", idvar = "patient"))
df$patient <- factor(df$patient)
Then you could loop over the patients, perform a linear regression and get the slopes as a vector:
sapply(levels(df$patient), function(pat) {
coef(lm(y~x,df[df$patient==pat,],na.action = "na.omit"))[2]
})
Missing_Values = data.frame(colSums(is.na(train)))
Missing_Values_per = data.frame(colMeans(is.na(train))) * 100
data.frame(Column_Name = names(train))
i need to create the data frame using these three variables ,could someone help on this
try this:
library(tidyverse)
train <- tibble(a = c(NA, 1, 4, NA, NA),
b = c(6, NA, NA, NA, NA))
train %>%
gather(column_name, v) %>%
group_by(column_name) %>%
summarize(missing_values = sum(is.na(v)),
missing_values_per = mean(is.na(v)) * 100)
Variables are mistakenly being entered into multiple columns eg: "aaa_1", "aaa_2" and "aaa_3", or "ccc_1, "ccc_2", and "ccc_3"). Need to create single new columns (eg "aaa", or "ccc"). Some variables are currently in a single column though ("hhh_1"), but more columns may be added (hhh_2 etc).
This is what I got:
aaa_1 <- c(43, 23, 65, NA, 45)
aaa_2 <- c(NA, NA, NA, NA, NA)
aaa_3 <- c(NA, NA, 92, NA, 82)
ccc_1 <- c("fra", NA, "spa", NA, NA)
ccc_2 <- c(NA, NA, NA, "wez", NA)
ccc_3 <- c(NA, "ija", NA, "fda", NA)
ccc_4 <- c(NA, NA, NA, NA, NA)
hhh_1 <- c(183, NA, 198, NA, 182)
dataf1 <- data.frame(aaa_1,aaa_2,aaa_3,ccc_1,ccc_2, ccc_3,ccc_4,hhh_1)
This is what I want:
aaa <- c(43, 23, NA, NA, NA)
ccc <- c("fra", "ija", "spa", NA, NA)
hhh <- c(183, NA, 198, NA, 182)
dataf2 <- data.frame(aaa,ccc,hhh)
General solution needed as there are ~100 variables (eg "aaa", "hhh", "ccc", "ttt", "eee", "hhh"etc).
Thanks!
This is a base solution, i.e. no packages.
First define get_only which when given a list converts it to a data.frame and applies get_only to each row. When given a vector it returns the single non-NA in it or NA if there is not only one.
Define root to be the column names without the suffixes.
Convert the data frame to a list of columns, group them by root and apply get_only to each such group.
Finally, convert the resulting list to a data frame.
get_only <- function(x) UseMethod("get_only")
get_only.list <- function(x) apply(data.frame(x), 1, get_only)
get_only.default <- function(x) if (sum(!is.na(x)) == 1) na.omit(x) else NA
root <- sub("_.*", "", names(dataf1))
as.data.frame(lapply(split(as.list(dataf1), root), FUN = get_only))
giving:
age country hight
1 43 fra 183
2 23 ija NA
3 NA spa 198
4 NA <NA> NA
5 NA <NA> 182
We may try with splitstackshape
library(splitstackshape)
nm1 <- sub("_\\d+", "", names(dataf1))
tbl <- table(nm1) > 1
merged.stack(dataf1, var.stubs = names(tbl)[tbl], sep="_")
I'm not sure your example is right. For example in the third row you've got values for both age_1 and age_3, then in the desired output NA for that row.
If I've understood what you're trying to do though, it will be much easier if you transpose columns to rows, fix them and then transpose back again. Try this as a start point using the 'tidyverse' of dplyr and tidyr.
library(tidyverse)
library(stringr)
age_1 <- c(43, 23, 65, NA, 45)
age_2 <- c(NA, NA, NA, NA, NA)
age_3 <- c(NA, NA, 92, NA, 82)
country_1 <- c("fra", NA, "spa", NA, NA)
country_2 <- c(NA, NA, NA, "wez", NA)
country_3 <- c(NA, "ija", NA, "fda", NA)
country_4 <- c(NA, NA, NA, NA, NA)
hight_1 <- c(183, NA, 198, NA, 182)
dataf1 <- data.frame(age_1,age_2,age_3,country_1,country_2, country_3,country_4,hight_1)
data <- dataf1 %>%
mutate(row_num = row_number()) %>% #create a row number to track values
gather(key, value, -row_num) %>% #flatten your data
drop_na() %>% #drop na rows
mutate(key = str_replace(key, "_.", "")) %>% #remove the '_x' part of names
group_by(row_num) %>%
top_n(1) %>%
spread(key, value) #pivot back to columns
For your example you need the group_by() and top_n() lines to make it run because you've got multiple values in the same row. If you only have one value (as I think you should?) then you can remove these two lines. It will be better without them because then it won't run if your data is wrong.
Edit following comment below. This will make any duplicated entries NA.
data <- dataf1 %>%
mutate(row_num = row_number()) %>% #create a row number to track values
gather(key, value, -row_num) %>% #flatten your data
drop_na() %>% #drop na rows
mutate(key = str_replace(key, "_.", "")) %>% #remove the '_x' part of names
group_by(row_num, key) %>%
mutate(count = n()) %>% #count how many entries for each row/key combo
mutate(value = ifelse(count > 1, NA, value)) %>% #set NA for rows with duplicates
drop_na() %>%
spread(key, value) %>% #pivot back to columns
select(-count) #drop the `count` variable