Question

在SQL中，你可以这样做一个语句：

SELECT *
FROM table
WHERE (var1, var2, var3, var4) IN (("var1-1", "var2-1", "var3-1", "var4-1"),
                                   ("var1-2", "var2-2", "var3-2", "var4-2"))

这意味着抓住所有行（var1 ==＆＃34; var1-1＆＃34; var2 ==＆＃34; var2-1＆＃34;和var3 ==＆＃34; var3-1＆＃ 34;和var4 ==＆＃34; var4-1＆＃34;）或（var1 ==＆＃34; var1-2＆＃34;和var2 ==＆＃34; var2-2＆＃34;和var3 == ＆＃34; var3-2＆＃34;和var4 ==＆＃34; var4-2＆＃34;）

有没有办法以编程方式在dbplyr中进行类似的查询？

所以例如假设我有一个tibble：

tribble(
    ~var1,     ~var2,    ~var3,    ~var4,
    "var1-1",  "var2-1", "var3-1", "var4-1",
    "var1-2",  "var2-2", "var3-2", "var4-2"
  )

我可以使用某种函数让dbplyr构建一个像上面那样的SQL语句吗？

Answer 1

1）使用inner_join：

library(dplyr)

# test data
v <- paste0("var", 1:4)
DF1 <- as.data.frame(t(outer(v, 1:3, paste, sep = "-")), stringsAsFactors = FALSE)
DF2 <- as.data.frame(t(outer(v, 2:4, paste, sep = "-")), stringsAsFactors = FALSE)

DF1 %>% inner_join(DF2)

，并提供：

Joining, by = c("V1", "V2", "V3", "V4")
# A tibble: 2 x 4
  V1     V2     V3     V4    
  <chr>  <chr>  <chr>  <chr> 
1 var1-2 var2-2 var3-2 var4-2
2 var1-3 var2-3 var3-3 var4-3

2）在基数R中，我们可以使用merge：

merge(DF1, DF2)

或intersect

intersect(DF1, DF2)

3）在dbplyr中：

library(dbplyr)

# set up backend using DF1 and DF2 from (1)
con <- DBI::dbConnect(RSQLite::SQLite(), path = ":memory:")
copy_to(con, DF1, "DF1")
copy_to(con, DF2, "DF2")

DF1_db <- tbl(con, "DF1")
DF2_db <- tbl(con, "DF2")
DF1_db %>% inner_join(DF2_db)

，并提供：

Joining, by = c("V1", "V2", "V3", "V4")
# Source:   lazy query [?? x 4]
# Database: sqlite 3.19.3 []
  V1     V2     V3     V4    
  <chr>  <chr>  <chr>  <chr> 
1 var1-2 var2-2 var3-2 var4-2
2 var1-3 var2-3 var3-3 var4-3

如果你有一个tibble和一个数据库表，你需要使用copy_to将tibble复制到数据库，或者将数据库表抓到R. inner_join不能混合源。

Answer 2

Using some advanced R programming with purrr and rlang, you should be able to create a single expression for the filter() that, I think, does the exact thing that you're asking, here's an example using mtcars. I recreated your tribble with data that would apply to the example. I also added inline comments to help explain what each step is doing:

library(dbplyr, warn.conflicts = FALSE)
library(dplyr, warn.conflicts = FALSE)
library(purrr, warn.conflicts = FALSE)
library(DBI, warn.conflicts = FALSE)
library(rlang, warn.conflicts = FALSE)

con <- DBI::dbConnect(RSQLite::SQLite(), path = ":dbname:")
db_mtcars <- copy_to(con, mtcars)

filters <- tribble(
  ~gear, ~carb,    
  4,     4,
  3,     1
)
# transpose() converts rows into lists entries
filter_expr <- transpose(filters) %>%
  # iterate through each row
  map(~{
    # iterate through each pair ie: gear == 4
    imap(.x, ~expr(!!sym(.y) == !!.x)) %>%
      # creates one call in the row by 
      # "collapsing" all pairs, separating them with &
      reduce(function(x, y) expr((!!x & !!y)))
    }) %>%
  # creates one call collapsing all row calls 
  # into a single one, separating them with |
  reduce(function(x, y ) expr(!!x | !! y))
# the resulting call
filter_expr
#> (gear == 4 & carb == 4) | (gear == 3 & carb == 1)

filtered_mtcars <- db_mtcars %>%
  # Use bang-bang (!!) to execute the new call
  filter(!! filter_expr)

filtered_mtcars
#> # Source:   lazy query [?? x 11]
#> # Database: sqlite 3.22.0 []
#>     mpg   cyl  disp    hp  drat    wt  qsec    vs    am  gear  carb
#>   <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1  21       6  160    110  3.9   2.62  16.5     0     1     4     4
#> 2  21       6  160    110  3.9   2.88  17.0     0     1     4     4
#> 3  21.4     6  258    110  3.08  3.22  19.4     1     0     3     1
#> 4  18.1     6  225    105  2.76  3.46  20.2     1     0     3     1
#> 5  19.2     6  168.   123  3.92  3.44  18.3     1     0     4     4
#> 6  17.8     6  168.   123  3.92  3.44  18.9     1     0     4     4
#> 7  21.5     4  120.    97  3.7   2.46  20.0     1     0     3     1

show_query(filtered_mtcars)
#> <SQL>
#> SELECT *
#> FROM `mtcars`
#> WHERE ((`gear` = 4.0 AND `carb` = 4.0) OR (`gear` = 3.0 AND `carb` = 1.0))

dbDisconnect(con)

dbplyr中使用列表列表

2 个答案: