summarize and spread by almost identical strings - r

Question

I started with several raw df's with similar items ,cleaned and merged to a long format which i later combine to wide format using dplyr... However, i'm left with duplicates because i'm dealing with almost identical strings, can anyone please suggest an easier way to remove the duplicates while spreading my data.
here is a sample of my code
library(tidyverse)
library(readxl)
library(reprex)
all_data_final_wider<-all_data_final %>%
mutate(cases = case_when(cases=='X' ~ 'x', cases=='x' ~ 'x'))%>%
group_by(Species) %>%
mutate(row = row_number()) %>%
tidyr::pivot_wider(names_from = location, values_from =cases)%>%
select(-row)
and below is a dput of my sample data
structure(list(`Wall type (Kaminski 2014)` = c("", "", "hyaline",
"hyaline", "hyaline", "hyaline", "", "hyaline", "", "hyaline",
"hyaline", "", "", "porcelaneous (imperforate)", "porcelaneous (imperforate)",
"porcelaneous (imperforate)", "porcelaneous (imperforate)", "porcelaneous (imperforate)",
"", "", "", "", "", "", "", "", "", "porcelaneous (imperforate)",
"porcelaneous (imperforate)", "porcelaneous (imperforate)", "porcelaneous (imperforate)",
"porcelaneous (imperforate)", "porcelaneous (imperforate)", "porcelaneous (imperforate)",
"", "", "", "", "", "", "porcelaneous (imperforate)", "", "",
"", "porcelaneous (imperforate)", "", "", "", "", ""), Order = c("",
"", "Rotaliida", "Rotaliida", "Rotaliida", "Rotaliida", "", "Rotaliida",
"", "Rotaliida", "Rotaliida", "", "", "Miliolida", "Miliolida",
"Miliolida", "Miliolida", "Miliolida", "Miliolida", "", "", "",
"", "", "", "", "", "Miliolida", "Miliolida", "Miliolida", "Miliolida",
"Miliolida", "Miliolida", "Miliolida", "", "", "", "", "", "",
"Miliolida", "", "", "", "Miliolida", "", "", "", "", ""), Superfamily = c("",
"", "Planorbulinoidea", "Acervulinoidea", "Acervulinoidea", "Acervulinoidea",
"", "Acervulinoidea", "Acervulinoidea ", "Acervulinoidea", "Acervulinoidea",
"Milioloidea", "Milioloidea", "Milioloidea", "Milioloidea", "Milioloidea",
"Milioloidea", "Milioloidea", "", "", "", "", "", "", "", "",
"", "Milioloidea", "Milioloidea", "Milioloidea", "Milioloidea",
"Milioloidea", "Milioloidea", "Milioloidea", "", "", "", "",
"", "", "Milioloidea", "", "", "", "Milioloidea", "", "", "",
"", ""), Family = c("", "", "Planorbulinidae", "Acervulinoidae",
"Acervulinoidae", "Acervulinoidae", "", "Acervulinoidae", "Acervulinidae",
"Acervulinoidae", "Acervulinoidae", "Cribrolinoididae", "Cribrolinoididae",
"Cribrolinoididae", "Cribrolinoididae", "Hauerinidae", "Hauerinidae",
"Hauerinidae", "Hauerinidae", "", "", "", "", "", "", "", "",
"Cribrolinoididae", "Cribrolinoididae", "Cribrolinoididae", "Cribrolinoididae",
"Cribrolinoididae", "Cribrolinoididae", "Cribrolinoididae", "",
"", "", "", "", "", "Cribrolinoididae", "", "", "", "Cribrolinoididae",
"", "", "", "", ""), Genus = c("", "", "?Planorbulina", "Acervulina",
"Acervulina", "Acervulina", "", "Acervulina", "Acervulina", "Acervulina",
"Acervulina", "Adelosina", "Adelosina", "Adelosina", "Adelosina",
"Adelosina", "Adelosina", "Adelosina", "Quinqueloculina", "",
"", "", "", "", "", "", "", "Adelosina", "Adelosina", "Adelosina",
"Adelosina", "Adelosina", "Adelosina", "Adelosina", "", "", "",
"", "", "", "Adelosina", "", "", "", "Adelosina", "Adelosina",
"Adelosina", "", "", ""), Species = c("", "", "?Planorbulina sp . 1",
"Acervulina cf. A. mahabethi", "Acervulina cf. A. mahabeti",
"Acervulina inhaerens", "Acervulina inhaerens ", "Acervulina mabahethi",
"Acervulina mabahethi ", "Acervulina sp. 01", "Acervulina sp. 01",
"Adelosina bicornis ", "Adelosina bicornis ", "Adelosina carinatastriata",
"Adelosina carinatastriata", "Adelosina carinatastriata", "Adelosina carinatastriata",
"Adelosina carinatastriata", "Adelosina carinatastriata", "Adelosina carinatastriata ",
"Adelosina carinatastriata ", "Adelosina carinatastriata ", "Adelosina carinatastriata ",
"Adelosina carinatastriata ", "Adelosina carinatastriata ", "Adelosina carinatastriata ",
"Adelosina carinatastriata ", "Adelosina cf. A. mediterranensis",
"Adelosina crassicarinata", "Adelosina crassicarinata", "Adelosina crassicarinata",
"Adelosina crassicarinata", "Adelosina dagornae", "Adelosina dagornae",
"Adelosina dagornae", "Adelosina dagornae", "Adelosina dagornae",
"Adelosina dagornae", "Adelosina dagornae", "Adelosina dagornae",
"Adelosina echinata", "Adelosina echinata ", "Adelosina echinata ",
"Adelosina echinata ", "Adelosina honghensis", "Adelosina honghensis",
"Adelosina honghensis", "Adelosina honghensis ", "Adelosina honghensis ",
"Adelosina honghensis "), authority = c("Haynesina sp.", "Haynesina sp.",
"d'Orbigny, 1826", " Said, 1949 ", "", "Schulze, 1854", "Schulze, 1854",
" Said, 1949 ", "Said, 1949 ", "Schultze, 1854", "", "Walker & Jacob, 1798 ",
"Walker & Jacob, 1798 ", " Wiesner, 1923 ", " Wiesner, 1923 ",
" Wiesner, 1923 ", " Wiesner, 1923 ", " Wiesner, 1923 ", "Wiesner, 1923",
"Wiesner 1923 ", "Wiesner 1923 ", "Wiesner 1923 ", "Wiesner 1923 ",
"Wiesner 1923 ", "Wiesner 1923 ", "Wiesner 1923 ", "Wiesner 1923 ",
" Le Calvez & Le Calvez, 1958 ", "", "", "", "", "", "", "Levi et al. 1990 ",
"Levi et al. 1990 ", "Levi et al. 1990 ", "Levi et al. 1990 ",
"Levi et al. 1990 ", "Levi et al. 1990 ", "", "d'Orbigny, 1826",
"d'Orbigny, 1826", "d'Orbigny, 1826", "", "", "", "Lak, 1982",
"Lak, 1982", "Lak, 1982"), location = c(" Parkar and Gischler 2015 ",
"Present study", "Cherif et al. 1997", "Amao et al. 2016 PG",
"Amao_et_al_2019_Persian_Gulf_paper", "Murray 1965", " Shublak 1977 ",
"Parker and Gischler 2015", " Parkar and Gischler 2015 ", "Amao et al. 2016 PG",
"Amao_et_al_2019_Persian_Gulf_paper", " Shublak 1977 ", "Khader 2020 ",
"Al-Zamel et al 1996", "Al-Zamel et al 2009", "Parker and Gischler 2015",
"Amao et al. 2016 MP", "Amao et al. 2016 Salwa", "Amao_et_al_2019_baseline_paper",
"Al-Zamel et al. 1996 ", "Khader 1997 ", " Cherif et al. 1997 ",
"Al-Ghadban 2000 ", "Al-Zamel et al. 2009 ", "Al-Theyabi 2012b ",
"Al-Enezi et al. 2019 ", "Khader 2020 ", "Amao et al. 2016 MP",
"Al-Zamel et al 1996", "Cherif et al. 1997", "Al-Zamel & Cherif 1998",
"Al-Enezi & Frontalini 2015", "Al-Zamel et al 2009", "Al-Enezi & Frontalini 2015",
"Khader 1997 ", "Al-Ghadban 2000 ", "Al-Zamel et al. 2009 ",
"Al-Ammar 2011 ", "Al-Enezi and Frontalini 2015 ", "Khader 2020 ",
"Cherif et al. 1997", "Al-Shuaibi 1997 ", "Al-Ghadban 2000 ",
"Khader 2020 ", "Cherif et al. 1997", "Clark and Keiji 1975",
"Nabavi 2014", " Cherif et al. 1997 ", "Al-Ghadban 2000 ",
"Khader 2020 "), cases = c("X", "X", "x", "x", "x", "x", "X",
"x", "X", "x", "x", "X", "X", "x", "x", "x", "x", "x", "x", "X",
"X", "X", "X", "X", "X", "X", "X", "x", "x", "x", "x", "x", "x",
"x", "X", "X", "X", "X", "X", "X", "x", "X", "X", "X", "x", "x",
"x", "X", "X", "X")), row.names = c(NA, -50L), class = c("tbl_df",
"tbl", "data.frame"))
At the moment, my result look like Before but my target is After
Thank you in anticipation for your help.

Answer 1

As #hendrikvanb points our, your duplicate output rows are not only due to strings, but also incomplete data and slight differences in some of your input strings. Even if two strings contain the same information for a human reader, R treats them as different unless every single character is the same. Once we resolve this the solution is much easier.
Step 1: ensure entries with similar names have the same name
The following code begins with some simple tidying (removing excess white space, making everything lower case). It then searches your table for text that is similar and for every pair asks if you want to replace one with the other.
E.g. if you dataset contains "levi et al. 1990" and "levi et al 1990" one with a full stop and the other without, you will receive a message:
Do you want to replace "levi et al. 1990" with "levi et al 1990"?
You will also be asked the same question in reverse order. If you click 'yes' then all instances of the first will be replaced by the second in your database.
library(dplyr)
library(tidyr)
# standardise
standardized <- all_data_final %>%
rename(walltype = `Wall type (Kaminski 2014)`) %>% # first column in example data has odd name
mutate_all(as.character) %>% # ensures all columns are string not factor
mutate_all(trimws) %>% # leading and trailing white space
mutate_all(function(x){gsub(" +"," ",x)}) %>% # remove internal duplicate spaces
mutate_all(tolower) %>% # cast everything to lower
mutate(row = row_number())
# prompt user to merge text that is very close together
tollerance = 2
cols <- c("walltype", "Order", "Superfamily", "Family", "Genus", "Species", "authority", "location")
for(col in cols){
unique_vals = standardized[[col]] %>% unique() %>% sort()
for(val in unique_vals){
for(val2 in unique_vals){
# check if text strings are within edit distance of each other
if(adist(val, val2) > 0 & adist(val, val2) <= tollerance){
msg = paste0("Do you want [", val, "] replaced with [", val2, "] ?")
ans = FALSE
ans = askYesNo(msg) # ask user for every pair of close values
if(ans)
standardized <- mutate_all(standardized, function(x){ifelse(x == val, val2, x)})
}
}
}
}
You can control the sensitivity of this check by adjusting the tollerance parameter. You can think of it as the number of characters between the correct text and a spelling mistake.
Step 2: keep category text information where available
The goal here is to ensure that if one record of the species has an order, family, genus, or authority then this appears on the final table. We can do this by asking for the maximum order/family/genus per species.
When working with text, max returns the last record alphabetically. Blank or white space gets sorted to the top first, hence we must use max as min will return empty text fields.
The code for this is merged into step 3.
Step 3: keep case mark where available
By converting the case column to numeric, we can summarise across cases looking for a maximum value of 1. In some cases NA or NULL gets treated as -Inf so we also handle this.
The following code resolves step 2 and 3 in the same summarise_all statement.
# collapse
final_result <- standardized %>%
mutate(cases = ifelse(!is.na(cases), 1, 0)) %>%
pivot_wider(names_from = location, values_from = cases) %>%
group_by(Species) %>%
summarise_all(max, na.rm = TRUE) %>% # hack, ideally we'd handle strings and numbers differently
mutate_all(function(x){ifelse(is.infinite(x), NA, x)}) # gets rid of -Inf caused by summarise_all
Here is the dput output I get from this code:
structure(list(Species = c("", "?planorbulina sp . 1", "acervulina cf. a. mahabethi",
"acervulina inhaerens", "acervulina mabahethi", "acervulina sp. 01",
"adelosina bicornis", "adelosina carinatastriata", "adelosina cf. a. mediterranensis",
"adelosina crassicarinata", "adelosina dagornae", "adelosina echinata",
"adelosina honghensis"), walltype = c("", "hyaline", "hyaline",
"hyaline", "hyaline", "hyaline", "", "porcelaneous (imperforate)",
"porcelaneous (imperforate)", "porcelaneous (imperforate)", "porcelaneous (imperforate)",
"porcelaneous (imperforate)", "porcelaneous (imperforate)"),
Order = c("", "rotaliida", "rotaliida", "rotaliida", "rotaliida",
"rotaliida", "", "miliolida", "miliolida", "miliolida", "miliolida",
"miliolida", "miliolida"), Superfamily = c("", "planorbulinoidea",
"acervulinoidea", "acervulinoidea", "acervulinoidea", "acervulinoidea",
"milioloidea", "milioloidea", "milioloidea", "milioloidea",
"milioloidea", "milioloidea", "milioloidea"), Family = c("",
"planorbulinidae", "acervulinidae", "acervulinidae", "acervulinidae",
"acervulinidae", "cribrolinoididae", "hauerinidae", "cribrolinoididae",
"cribrolinoididae", "cribrolinoididae", "cribrolinoididae",
"cribrolinoididae"), Genus = c("", "?planorbulina", "acervulina",
"acervulina", "acervulina", "acervulina", "adelosina", "quinqueloculina",
"adelosina", "adelosina", "adelosina", "adelosina", "adelosina"
), authority = c("haynesina sp.", "d'orbigny, 1826", "said, 1949",
"schultze, 1854", "said, 1949", "schultze, 1854", "walker & jacob, 1798",
"wiesner 1923", "le calvez & le calvez, 1958", "", "levi et al. 1990",
"d'orbigny, 1826", "lak, 1982"), row = c(2L, 3L, 5L, 7L,
9L, 11L, 13L, 27L, 28L, 32L, 40L, 44L, 50L), `parkar and gischler 2015` = c(1,
NA, NA, NA, 1, NA, NA, 1, NA, NA, NA, NA, NA), `present study` = c(1,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA), `cherif et al. 1997` = c(NA,
1, NA, NA, NA, NA, NA, 1, NA, 1, NA, 1, 1), `amao et al. 2016 mp` = c(NA,
NA, 1, NA, NA, 1, NA, 1, 1, NA, NA, NA, NA), amao_et_al_2019_persian_gulf_paper = c(NA,
NA, 1, NA, NA, 1, NA, NA, NA, NA, NA, NA, NA), `murray 1965` = c(NA,
NA, NA, 1, NA, NA, NA, NA, NA, NA, NA, NA, NA), `shublak 1977` = c(NA,
NA, NA, 1, NA, NA, 1, NA, NA, NA, NA, NA, NA), `khader 2020` = c(NA,
NA, NA, NA, NA, NA, 1, 1, NA, NA, 1, 1, 1), `al-zamel et al 1996` = c(NA,
NA, NA, NA, NA, NA, NA, 1, NA, 1, NA, NA, NA), `al-zamel et al 2009` = c(NA,
NA, NA, NA, NA, NA, NA, 1, NA, NA, 1, NA, NA), `amao et al. 2016 salwa` = c(NA,
NA, NA, NA, NA, NA, NA, 1, NA, NA, NA, NA, NA), amao_et_al_2019_baseline_paper = c(NA,
NA, NA, NA, NA, NA, NA, 1, NA, NA, NA, NA, NA), `khader 1997` = c(NA,
NA, NA, NA, NA, NA, NA, 1, NA, NA, 1, NA, NA), `al-ghadban 2000` = c(NA,
NA, NA, NA, NA, NA, NA, 1, NA, NA, 1, 1, 1), `al-theyabi 2012b` = c(NA,
NA, NA, NA, NA, NA, NA, 1, NA, NA, NA, NA, NA), `al-enezi et al. 2019` = c(NA,
NA, NA, NA, NA, NA, NA, 1, NA, NA, NA, NA, NA), `al-zamel & cherif 1998` = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, 1, NA, NA, NA), `al-enezi & frontalini 2015` = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, 1, 1, NA, NA), `al-ammar 2011` = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, 1, NA, NA), `al-enezi and frontalini 2015` = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, 1, NA, NA), `al-shuaibi 1997` = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 1, NA), `clark and keiji 1975` = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 1), `nabavi 2014` = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 1)), class = c("tbl_df",
"tbl", "data.frame"), row.names = c(NA, -13L))

Answer 2

...even if you decide to use just the species column ignoring every other column.e. Species, location and cases to pivot wide, it still doesn't help.
Actually, with minimal wrangling, it does help.
This is more complex than your comment appear to suggest.
I don't believe it is:
# load libraries
library(tidyverse)
# define data using the structure posted in the initial question
# create all_data_final_wider by taking all_data_final %>% remove all
# leading/trailing white space %>% convert cases column to lowercase %>% select
# columns to retain %>% remove exact duplicates %>% pivot from long to wide
all_data_final_wider <- all_data_final %>%
mutate_all(str_squish) %>%
mutate(cases = str_to_lower(cases)) %>%
select(Species, location, cases) %>%
distinct() %>%
pivot_wider(names_from = location, values_from = cases)
# prove that there are as many rows in all_data_final_wider as there are
# distinct spellings of the Species column
nrow(all_data_final_wider) == length(unique(all_data_final_wider$Species))
#> [1] TRUE
So I stand by my comments:
You'll need to fix these and all other inconsistencies in the input data if you expect to get sensible results from pivot_wider()