У меня есть два следующих набора данных:
DT1 <- structure(list(Province = c(1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2,
2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3), Year = c(2000,
2000, 2000, 2001, 2001, 2001, 2002, 2002, 2002, 2000, 2000, 2000,
2001, 2001, 2001, 2002, 2002, 2002, 2000, 2000, 2000, 2001, 2001,
2001, 2002, 2002, 2002), Municipality = c("Something", "Anything",
"Nothing", "Something", "Anything", "Nothing", "Something", "Anything",
"Nothing", "Something", "Anything", "Nothing", "Something", "Anything",
"Nothing", "Something", "Anything", "Nothing", "Something", "Anything",
"Nothing", "Something", "Anything", "Nothing", "Something", "Anything",
"Nothing"), Values = c(0.59, 0.58, 0.66, 0.53, 0.94, 0.2, 0.86,
0.85, 0.99, 0.59, 0.58, 0.66, 0.53, 0.94, 0.2, 0.86, 0.85, 0.99,
0.59, 0.58, 0.66, 0.53, 0.94, 0.2, 0.86, 0.85, 0.99)), row.names = c(NA,
-27L), class = c("tbl_df", "tbl", "data.frame"))
DT2 <- structure(list(Province = c(1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2,
2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 3), Year = c(2000,
2000, 2000, 2001, 2001, 2001, 2002, 2002, 2002, 2000, 2000, 2000,
2001, 2001, 2001, 2002, 2002, 2002, 2000, 2000, 2000, 2001, 2001,
2001, 2002, 2002, 2002), Municipality = c("Some", "Anything",
"Nothing", "Someth.", "Anything", "Not", "Something", "Anything",
"None", "Some", "Anything", "Nothing", "Someth.", "Anything",
"Not", "Something", "Anything", "None", "Some", "Anything", "Nothing",
"Someth.", "Anything", "Not", "Something", "Anything", "None"
), `Other Values` = c(0.41, 0.42, 0.34, 0.47, 0.0600000000000001,
0.8, 0.14, 0.15, 0.01, 0.41, 0.42, 0.34, 0.47, 0.0600000000000001,
0.8, 0.14, 0.15, 0.01, 0.41, 0.42, 0.34, 0.47, 0.0600000000000001,
0.8, 0.14, 0.15, 0.01)), row.names = c(NA, -27L), class = c("tbl_df",
"tbl", "data.frame"))
Я пытаюсь сопоставить их следующим образом, предложенным в этом ссылка, автор Артур Йип.
library(fuzzyjoin); library(dplyr);
stringdist_join(DT1, DT2,
by = "Municipality",
mode = "left",
ignore_case = TRUE,
method = "jw",
max_dist = 10,
distance_col = "dist") %>%
group_by(Municipality.x) %>%
top_n(1, -dist)
Проблема в том, что код полностью «поджаривает» мой компьютер, поэтому я хотел бы разбить код на группы, чтобы ограничить количество сравнений строк. Я пытался:
library(fuzzyjoin); library(dplyr);
stringdist_join(DT1, DT2,
by = c("Municipality","Year", "State"),
mode = "left",
ignore_case = TRUE,
method = "jw",
max_dist = 10,
distance_col = "dist") %>%
group_by(Municipality.x) %>%
top_n(1, -dist)
stringdist_join(DT1, DT2,
by = "Municipality",
mode = "left",
ignore_case = TRUE,
method = "jw",
max_dist = 10,
distance_col = "dist") %>%
group_by(Municipality, Year, Province) %>%
top_n(1, -dist)
Но оба дают мне следующие соответствующие ошибки:
Error: All columns in a tibble must be vectors.
x Column `col` is NULL.
Run `rlang::last_error()` to see where the error occurred.
А также:
Error: Must group by variables found in `.data`.
* Column `Municipality` is not found.
* Column `Year` is not found.
* Column `Province` is not found.
Run `rlang::last_error()` to see where the error occurred.
Как правильно это сделать?
