I have a table with prefixes (here in csv format):
PREFIX,LABEL
A,Infectious diseases
B,Infectious diseases
C,Tumor
D1,Tumor
D2,Tumor
D31,Tumor
D32,Tumor
D33,Blood disorder
D4,Blood disorder
D5,Blood disorder
And I want to join it with this one:
AGE,DEATH_CODE
67,A02
85,D318
75,C007+X
62,D338
To get obviously:
AGE,LABEL
67,Infectious diseases
85,Tumor
75,Tumor
62,Blood disorder
I know how to do that with SQL and LIKE but not with tidyverse left_join or base R.
Dput of data
Table 1: CIM_CODES
structure(list(PREFIX = c("A", "B", "C", "D1", "D2", "D31", "D32",
"D33", "D4", "D5"), LABEL = c("Infectious diseases", "Infectious diseases",
"Tumor", "Tumor", "Tumor", "Tumor", "Tumor", "Blood disorder",
"Blood disorder", "Blood disorder")), row.names = c(NA, -10L), spec = structure(list(
cols = list(PREFIX = structure(list(), class = c("collector_character",
"collector")), LABEL = structure(list(), class = c("collector_character",
"collector"))), default = structure(list(), class = c("collector_guess",
"collector")), delim = ","), class = "col_spec"), problems = <pointer: 0x000002527d306190>, class = c("spec_tbl_df",
"tbl_df", "tbl", "data.frame"))
Table 2: DEATH_CAUSES
structure(list(AGE = c(67, 85, 75, 62), DEATH_CODE = c("A02",
"D318", "C007+X", "D338")), row.names = c(NA, -4L), spec = structure(list(
cols = list(AGE = structure(list(), class = c("collector_double",
"collector")), DEATH_CODE = structure(list(), class = c("collector_character",
"collector"))), default = structure(list(), class = c("collector_guess",
"collector")), delim = ","), class = "col_spec"), problems = <pointer: 0x0000025273898c60>, class = c("spec_tbl_df",
"tbl_df", "tbl", "data.frame"))
You could do a partial string match that has the lowest difference between the two columns:
library(tidyverse)
DEATH_CAUSES |>
mutate(LABEL = map_chr(DEATH_CODE,
~CIM_CODES$LABEL[
which.min(stringdist::stringdist(.x, CIM_CODES$PREFIX))
]))
#> # A tibble: 4 x 3
#> AGE DEATH_CODE LABEL
#> <dbl> <chr> <chr>
#> 1 67 A02 Infectious diseases
#> 2 85 D318 Tumor
#> 3 75 C007+X Tumor
#> 4 62 D338 Blood disorder
UPDATE
not using the stringdist package as requested.
library(tidyverse)
get_match <- function(code, prefix, target){
map(code, \(x){
map(prefix, \(y){
grepl(paste0("^", y), x)
})
}) |>
map_chr(\(z) target[unlist(z) |> which()] )
}
DEATH_CAUSES |>
mutate(LABEL = get_match(DEATH_CAUSES$DEATH_CODE,
CIM_CODES$PREFIX,
CIM_CODES$LABEL))
#> # A tibble: 4 x 3
#> AGE DEATH_CODE LABEL
#> <dbl> <chr> <chr>
#> 1 67 A02 Infectious diseases
#> 2 85 D318 Tumor
#> 3 75 C007+X Tumor
#> 4 62 D338 Blood disorder
EDIT
how to do this with a join:
library(tidyverse)
library(fuzzyjoin)
fuzzy_left_join(DEATH_CAUSES,
CIM_CODES,
by = c("DEATH_CODE" = "PREFIX"),
str_detect)
#> # A tibble: 4 x 4
#> AGE DEATH_CODE PREFIX LABEL
#> <dbl> <chr> <chr> <chr>
#> 1 67 A02 A Infectious diseases
#> 2 85 D318 D31 Tumor
#> 3 75 C007+X C Tumor
#> 4 62 D338 D33 Blood disorder
My code below, I used mysql:
select a.age, p.label
from prefix p
left join age a on a.death_code like CONCAT("%",p.prefix,"%");
You can refer here: how to use a like with a join in sql?
I am learning how to create a function in R, but I am struggling to understand how to write for loop. My understanding is that
for (item I list_items) {
do_something(itemn)
}
I would like to write a for loop to replace with 333 the cells that are equal with 123. So the item is 123 and the list of items is the df from sec1 till sec4.
Could somebody explain this to me, please? And how this can be included in a function?
Sample code:
structure(list(sec1 = c(1, 123, 1), sec2 = c(123, 1, 1), sec3 = c(123,
0, 0), sec4 = c(1, 123, 1)), spec = structure(list(cols = list(
sec1 = structure(list(), class = c("collector_double", "collector"
)), sec2 = structure(list(), class = c("collector_double",
"collector")), sec3 = structure(list(), class = c("collector_double",
"collector")), sec4 = structure(list(), class = c("collector_double",
"collector"))), default = structure(list(), class = c("collector_guess",
"collector")), delim = ","), class = "col_spec"), row.names = c(NA,
-3L), class = c("spec_tbl_df", "tbl_df", "tbl", "data.frame"))
We do not need a for loop here:
df[df==123]<-333
If we really need for loops:
for(i in 1:ncol(df)){
df[i][df[i]==123] <-333
}
output
df
# A tibble: 3 x 4
sec1 sec2 sec3 sec4
<dbl> <dbl> <dbl> <dbl>
1 1 333 333 1
2 333 1 0 333
3 1 1 0 1
Here's how it would work for one column of your data:
dat <- structure(list(sec1 = c(1, 123, 1),
sec2 = c(123, 1, 1),
sec3 = c(123, 0, 0),
sec4 = c(1, 123, 1)),
spec = structure(list(cols = list(
sec1 = structure(list(),
class = c("collector_double", "collector")),
sec2 = structure(list(),
class = c("collector_double","collector")),
sec3 = structure(list(),
class = c("collector_double", "collector")),
sec4 = structure(list(),
class = c("collector_double","collector"))),
default = structure(list(),
class = c("collector_guess","collector")),
delim = ","), class = "col_spec"),
row.names = c(NA,-3L), class =
c("spec_tbl_df", "tbl_df", "tbl", "data.frame"))
for(i in 1:nrow(dat)){
dat$sec1[i] <- ifelse(dat$sec1[i] == 123, 333, dat$sec1[i])
}
dat
#> sec1 sec2 sec3 sec4
#> 1 1 123 123 1
#> 2 333 1 0 123
#> 3 1 1 0 1
Created on 2022-01-31 by the reprex package (v2.0.1)
To replace all of them, using for loops, you could do a double loop over columns and rows.
for(j in names(dat)){
for(i in 1:nrow(dat)){
dat[[j]][i] <- ifelse(dat[[j]][i] == 123, 333, dat[[j]][i])
}
}
Of course, as others have identified, you certainly don't need a for loop to accomplish this.
in addition to DaveArmstrong Answer this would work for all rows and columns:
dat <- structure(list(sec1 = c(1, 123, 1), sec2 = c(123, 1, 1), sec3 = c(123,
0, 0), sec4 = c(1, 123, 1)), spec = structure(list(cols = list(
sec1 = structure(list(), class = c("collector_double", "collector"
)), sec2 = structure(list(), class = c("collector_double",
"collector")), sec3 = structure(list(), class = c("collector_double",
"collector")), sec4 = structure(list(), class = c("collector_double",
"collector"))), default = structure(list(), class = c("collector_guess",
"collector")), delim = ","), class = "col_spec"), row.names = c(NA,
-3L), class = c("spec_tbl_df", "tbl_df", "tbl", "data.frame"))
for(i in 1:nrow(dat)){
for(j in 1:ncol(dat)){
dat[i,j] <- ifelse(dat[i,j] == 123, 333, dat[i,j])
}
}
I need a chart of accounts to stay in order when new accounts are added or dropped in future years. This is because in Accounting the accounts are sorted by type (for example Asset, Liability Equity) but it is not explicit in the dataset. This is an example of the code that is putting new "Accounts" from Year2 and Year3 at the bottom.
XYZCompany_Consolidated <- XYZCompany_Year1 %>%
full_join(XYZCompany_Year2 by = "Account") %>%
full_join(XYZCompany_Year3, by = "Account")
Example: This picture is just to give a simplified example. The highlight in orange is where the new accounts are going and to the right is the code i'm using, and the green is what I'm trying to achieve
Perhaps I'm overthinking this problem but I find it hard to solve. Let's define some data first:
df_year1 <- structure(list(Account = c("Cash", "Accounts", "Loan1", "Auto",
"JaneDoe"), Year_1 = c(100, 1000, 20, 300, 500)), class = c("spec_tbl_df",
"tbl_df", "tbl", "data.frame"), row.names = c(NA, -5L), spec = structure(list(
cols = list(Account = structure(list(), class = c("collector_character",
"collector")), Year_1 = structure(list(), class = c("collector_double",
"collector"))), default = structure(list(), class = c("collector_guess",
"collector")), skip = 1L), class = "col_spec"))
df_year2 <- structure(list(Account = c("Cash", "Accounts", "Loan1", "Auto",
"Laptop", "JaneDoe"), Year_2 = c(80, 1200, 50, 300, 500, 0)), class = c("spec_tbl_df",
"tbl_df", "tbl", "data.frame"), row.names = c(NA, -6L), spec = structure(list(
cols = list(Account = structure(list(), class = c("collector_character",
"collector")), Year_2 = structure(list(), class = c("collector_double",
"collector"))), default = structure(list(), class = c("collector_guess",
"collector")), skip = 1L), class = "col_spec"))
df_year3 <- structure(list(Account = c("Cash", "Accounts", "Loan1", "Auto",
"Rent", "JaneDoe"), Year_3 = c(80, 1200, 50, 300, 1000, 0)), class = c("spec_tbl_df",
"tbl_df", "tbl", "data.frame"), row.names = c(NA, -6L), spec = structure(list(
cols = list(Account = structure(list(), class = c("collector_character",
"collector")), Year_3 = structure(list(), class = c("collector_double",
"collector"))), default = structure(list(), class = c("collector_guess",
"collector")), skip = 1L), class = "col_spec"))
Those are similar to the data shown in the OP's picture, e.g. df_year1 looks like
# A tibble: 5 x 2
Account Year_1
<chr> <dbl>
1 Cash 100
2 Accounts 1000
3 Loan1 20
4 Auto 300
5 JaneDoe 500
Next we transform those data a little bit, namely
library(dplyr)
library(tidyr)
df_y1 <- df_year1 %>%
mutate(Year = 1,
no = row_number()) %>%
rename(value = Year_1)
which returns
# A tibble: 5 x 4
Account value Year no
<chr> <dbl> <dbl> <int>
1 Cash 100 1 1
2 Accounts 1000 1 2
3 Loan1 20 1 3
4 Auto 300 1 4
5 JaneDoe 500 1 5
The new column no stores the account's original position, column Year stores the chart's year. All three data.frames are processed like this, so we get df_y1, df_y2, df_y3.
Finally we bind them together
bind_rows(df_y1, df_y2, df_y3) %>%
mutate(num_years = max(Year)) %>%
group_by(Account) %>%
mutate(rank = sum((num_years - n() + 1) * no), .keep = "unused") %>%
pivot_wider(names_from = Year) %>%
arrange(rank) %>%
select(-rank) %>%
ungroup()
and calculate a rank for each account. The accounts are ordered by this rank. As a result, we get
# A tibble: 7 x 4
Account Year_1 Year_2 Year_3
<chr> <dbl> <dbl> <dbl>
1 Cash 100 80 80
2 Accounts 1000 1200 1200
3 Loan1 20 50 50
4 Auto 300 300 300
5 Laptop NA 500 NA
6 Rent NA NA 1000
7 JaneDoe 500 0 0
Note
I believe, there are better approaches, but at least this works for the example data.
I'm not sure about the calculated rank's stability. Take care.
I am trying to get the first value of the next group in r to estimate a ratio. I have created a group based on the type column in my the df. Then estimated some influence factors using the sample position within the group. Finally, I am trying to estimate a ratio like this: RRF=response/(F1*first(response)+(F2*??????)) where the F1*first(response) is the cal in the group but I don't know how to call the first value of the next group to finish the ratio. Can someone help with this? This is my code and my data:
library(dplyr)
conc_zero_test <- zero_test %>%
gather(gas, response, -time,-type)%>%
group_by(group = cumsum(type == "current_std"),gas)%>%
mutate(X1= row_number()-1, #estimates the position of the sample within the group -1 removes std
F1=1-(X1/n()), #relative factor influence of the cal in the current group
F2=1-F1, #relative factor influence of the cal in the next group
RRF=response/(F1*first(response)+(F2*????))
structure(list(time = structure(c(1564468200, 1564475400, 1564484400,
1564486200, 1564493400, 1564497000, 1564498800, 1564506000, 1564509600,
1564511400, 1564518600, 1564522200, 1564524000, 1564527600, 1564531200
), class = c("POSIXct", "POSIXt"), tzone = "UTC"), type = c("current_std",
"n2", "n2", "current_std", "n2", "-", "current_std", "-", "n2",
"current_std", "n2", "-", "current_std", "-", "-"), ben = c(2293951.5,
12703.1, 6392.7, 1762512.6, 10748.4, 25468.3, 1597679, 24400.4,
6019.4, 1510760.2, 10329.1, 29292.6, 1495942.8, 61227.5, 25379.5
), xyl = c(210975.6, 4482, 2910.8, 127612.4, 3792.6, 10295.7,
113439.1, 10628.8, 2064.3, 107134.3, 3764.1, 10380.6, 107353.6,
23639.1, 10317.4), cym = c(546894.5, 12202.6, 8400.8, 302091.6,
11072.2, 16349.2, 291637.5, 18891.8, 6500.7, 276997.5, 10821.2,
18672, 274149.4, 61379.2, 19254.7), isop = c(397288.2, 0, 0,
239779.9, 0, 1364.8, 199081.5, 1511.2, 0, 179364, 0, 1318.4,
174450.7, 7137.5, 9567), macr = c(221195.8, 0, 0, 138806.3, 0,
0, 116644, 0, 0, 108893.3, 0, 0, 105689, 4325.4, 0), pin = c(50795.3,
0, 0, 28436, 0, 1020.1, 26482.9, 925.2, 0, 27394.1, 0, 989.7,
24344.6, 1414.7, 736.3), tmb = c(9314.5, 0, 0, 5798, 0, 0, 5136.4,
2252.5, 0, 4542.9, 0, 0, 4398.4, 3794.4, 2186.3), tol = c(880567.1,
7430.6, 4225.5, 569616.2, 6091.8, 65642.6, 495780.5, 52129.9,
3226, 456079.6, 5874, 34725.9, 453944.8, 56594.4, 66148.1), mvk = c(169036.8,
0, 0, 108738, 0, 0, 56712.5, 0, 0, 79148.9, 0, 0, 64065, 0, 0
), euc = c(12815.2, 0, 0, 8012.6, 0, 0, 5411.8, 0, 0, 5839.9,
0, 491.7, 5450.7, 1990.8, 500.7)), class = c("spec_tbl_df", "tbl_df",
"tbl", "data.frame"), row.names = c(NA, -15L), spec = structure(list(
cols = list(time = structure(list(format = ""), class = c("collector_datetime",
"collector")), type = structure(list(), class = c("collector_character",
"collector")), ben = structure(list(), class = c("collector_double",
"collector")), xyl = structure(list(), class = c("collector_double",
"collector")), cym = structure(list(), class = c("collector_double",
"collector")), isop = structure(list(), class = c("collector_double",
"collector")), macr = structure(list(), class = c("collector_double",
"collector")), pin = structure(list(), class = c("collector_double",
"collector")), tmb = structure(list(), class = c("collector_double",
"collector")), tol = structure(list(), class = c("collector_double",
"collector")), mvk = structure(list(), class = c("collector_double",
"collector")), euc = structure(list(), class = c("collector_double",
"collector"))), default = structure(list(), class = c("collector_guess",
"collector")), skip = 2), class = "col_spec"))
Example of expected output
time type gas response group X1 F1 F2 RRF
<dttm> <chr> <chr> <dbl> <int> <dbl> <dbl> <dbl> <dbl>
1 2019-07-30 06:30:00 current_std ben 2293952. 1 0 1 0 1
2 2019-07-30 08:30:00 n2 ben 12703. 1 1 0.667 0.333 0.006005
3 2019-07-30 11:00:00 n2 ben 6393. 1 2 0.333 0.667 0.003962
I would use a self-join to get the first response of the next group:
library(tidyverse)
# the OPs example data (long!)
zero_test <-
structure(
list(
time = structure(
c(
1564468200,
1564475400,
1564484400,
1564486200,
1564493400,
1564497000,
1564498800,
1564506000,
1564509600,
1564511400,
1564518600,
1564522200,
1564524000,
1564527600,
1564531200
),
class = c("POSIXct", "POSIXt"),
tzone = "UTC"
),
type = c(
"current_std",
"n2",
"n2",
"current_std",
"n2",
"-",
"current_std",
"-",
"n2",
"current_std",
"n2",
"-",
"current_std",
"-",
"-"
),
ben = c(
2293951.5,
12703.1,
6392.7,
1762512.6,
10748.4,
25468.3,
1597679,
24400.4,
6019.4,
1510760.2,
10329.1,
29292.6,
1495942.8,
61227.5,
25379.5
),
xyl = c(
210975.6,
4482,
2910.8,
127612.4,
3792.6,
10295.7,
113439.1,
10628.8,
2064.3,
107134.3,
3764.1,
10380.6,
107353.6,
23639.1,
10317.4
),
cym = c(
546894.5,
12202.6,
8400.8,
302091.6,
11072.2,
16349.2,
291637.5,
18891.8,
6500.7,
276997.5,
10821.2,
18672,
274149.4,
61379.2,
19254.7
),
isop = c(
397288.2,
0,
0,
239779.9,
0,
1364.8,
199081.5,
1511.2,
0,
179364,
0,
1318.4,
174450.7,
7137.5,
9567
),
macr = c(
221195.8,
0,
0,
138806.3,
0,
0,
116644,
0,
0,
108893.3,
0,
0,
105689,
4325.4,
0
),
pin = c(
50795.3,
0,
0,
28436,
0,
1020.1,
26482.9,
925.2,
0,
27394.1,
0,
989.7,
24344.6,
1414.7,
736.3
),
tmb = c(
9314.5,
0,
0,
5798,
0,
0,
5136.4,
2252.5,
0,
4542.9,
0,
0,
4398.4,
3794.4,
2186.3
),
tol = c(
880567.1,
7430.6,
4225.5,
569616.2,
6091.8,
65642.6,
495780.5,
52129.9,
3226,
456079.6,
5874,
34725.9,
453944.8,
56594.4,
66148.1
),
mvk = c(169036.8,
0, 0, 108738, 0, 0, 56712.5, 0, 0, 79148.9, 0, 0, 64065, 0, 0),
euc = c(
12815.2,
0,
0,
8012.6,
0,
0,
5411.8,
0,
0,
5839.9,
0,
491.7,
5450.7,
1990.8,
500.7
)
),
class = c("spec_tbl_df", "tbl_df",
"tbl", "data.frame"),
row.names = c(NA,-15L),
spec = structure(list(
cols = list(
time = structure(list(format = ""), class = c("collector_datetime",
"collector")),
type = structure(list(), class = c("collector_character",
"collector")),
ben = structure(list(), class = c("collector_double",
"collector")),
xyl = structure(list(), class = c("collector_double",
"collector")),
cym = structure(list(), class = c("collector_double",
"collector")),
isop = structure(list(), class = c("collector_double",
"collector")),
macr = structure(list(), class = c("collector_double",
"collector")),
pin = structure(list(), class = c("collector_double",
"collector")),
tmb = structure(list(), class = c("collector_double",
"collector")),
tol = structure(list(), class = c("collector_double",
"collector")),
mvk = structure(list(), class = c("collector_double",
"collector")),
euc = structure(list(), class = c("collector_double",
"collector"))
),
default = structure(list(), class = c("collector_guess",
"collector")),
skip = 2
), class = "col_spec")
)
temp1 <- zero_test %>%
gather(gas, response, -time,-type) %>%
group_by(group = cumsum(type == "current_std"), gas) %>%
mutate(X1= row_number()-1, #estimates the position of the sample within the group -1 removes std
F1=1-(X1/n()), #relative factor influence of the cal in the current group
F2=1-F1,
first_response = first(response)) %>%
ungroup
conc_zero_test <- temp1 %>%
left_join(y = {temp1 %>%
mutate(group = group - 1) %>%
select(gas, group, first_response_next = first_response) %>%
distinct},
by = c("gas", "group")) %>%
mutate(RRF = response / ((F1 * first_response) + (F2 * first_response_next)))
conc_zero_test
#> # A tibble: 150 x 11
#> time type gas response group X1 F1 F2
#> <dttm> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 2019-07-30 06:30:00 curr… ben 2293952. 1 0 1 0
#> 2 2019-07-30 08:30:00 n2 ben 12703. 1 1 0.667 0.333
#> 3 2019-07-30 11:00:00 n2 ben 6393. 1 2 0.333 0.667
#> 4 2019-07-30 11:30:00 curr… ben 1762513. 2 0 1 0
#> 5 2019-07-30 13:30:00 n2 ben 10748. 2 1 0.667 0.333
#> 6 2019-07-30 14:30:00 - ben 25468. 2 2 0.333 0.667
#> 7 2019-07-30 15:00:00 curr… ben 1597679 3 0 1 0
#> 8 2019-07-30 17:00:00 - ben 24400. 3 1 0.667 0.333
#> 9 2019-07-30 18:00:00 n2 ben 6019. 3 2 0.333 0.667
#> 10 2019-07-30 18:30:00 curr… ben 1510760. 4 0 1 0
#> # … with 140 more rows, and 3 more variables: first_response <dbl>,
#> # first_response_next <dbl>, RRF <dbl>
Created on 2020-08-16 by the reprex package (v0.3.0)