r - 在 SQLite 中使用子查询更新表

Question

我想使用 ALTER TABLE 和 UPDATE 语句向我的表中添加一列，而不是重新创建整个表。

在我的 UPDATE 语句中使用子查询时，我没有得到预期的输出。

构建可重现的数据

library(dplyr)
library(dbplyr)
library(DBI)
con <- DBI::dbConnect(RSQLite::SQLite(), path = ":memory:")
copy_to(con, iris[c(1,2,51),],"iris")

tbl(con,"iris")
# # Source:   table<iris> [?? x 5]
# # Database: sqlite 3.19.3 []
#   Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
#          <dbl>       <dbl>        <dbl>       <dbl>      <chr>
# 1          5.1         3.5          1.4         0.2     setosa
# 2          4.9         3.0          1.4         0.2     setosa
# 3          7.0         3.2          4.7         1.4 versicolor

在单独的表中创建新列

DBI::dbSendQuery(con, "CREATE TABLE new_table AS SELECT t2.new_col from
                 iris t1 inner join 
                 (SELECT Species, sum(`Sepal.Width`) as new_col FROM iris GROUP BY Species) t2
                 on t1.Species = t2.Species")

tbl(con,"new_table")
# # Source:   table<new_table> [?? x 1]
# # Database: sqlite 3.19.3 []
#   new_col
#     <dbl>
# 1     6.5
# 2     6.5
# 3     3.2

在旧表中创建新列

DBI::dbSendQuery(con, "ALTER TABLE iris ADD COLUMN new_col DOUBLE")

尝试从 new_table 那里插入新列

DBI::dbSendQuery(con, "UPDATE iris SET new_col = (SELECT new_col FROM new_table)")

tbl(con,"iris")
# # Source:   table<iris> [?? x 6]
# # Database: sqlite 3.19.3 []
#   Sepal.Length Sepal.Width Petal.Length Petal.Width    Species new_col
#          <dbl>       <dbl>        <dbl>       <dbl>      <chr>   <dbl>
# 1          5.1         3.5          1.4         0.2     setosa     6.5
# 2          4.9         3.0          1.4         0.2     setosa     6.5
# 3          7.0         3.2          4.7         1.4 versicolor     6.5

如您所见，我的 new_col 仅包含值 6.5，而我希望在最后一行有 3.2。我该如何解决这个问题？

Answer 1

SQL 数据库表中的行没有固有的顺序。因此，您不能像在 R 中那样分配值的“向量”。但是，您可以稍微修改查询:

library(dplyr)
library(DBI)
con <- DBI::dbConnect(RSQLite::SQLite(), path = ":memory:")
copy_to(con, iris[c(1,2,51),],"iris")

用聚合数据创建一个单独的表

DBI::dbSendQuery(con, "CREATE TABLE new_table AS 
                       SELECT Species, sum(`Sepal.Width`) as new_col FROM iris GROUP BY Species")

tbl(con,"new_table")
#> # Source:   table<new_table> [?? x 2]
#> # Database: sqlite 3.22.0 []
#>   Species    new_col
#>   <chr>        <dbl>
#> 1 setosa         6.5
#> 2 versicolor     3.2

在旧表中创建新列

DBI::dbSendQuery(con, "ALTER TABLE iris ADD COLUMN new_col DOUBLE")

通过相关子查询将数据移动到原始表

DBI::dbSendQuery(con, "UPDATE iris SET new_col = (SELECT new_col FROM new_table t2
                               WHERE iris.Species = t2.Species)")

tbl(con,"iris")
#> # Source:   table<iris> [?? x 6]
#> # Database: sqlite 3.22.0 []
#>   Sepal.Length Sepal.Width Petal.Length Petal.Width Species    new_col
#>          <dbl>       <dbl>        <dbl>       <dbl> <chr>        <dbl>
#> 1          5.1         3.5          1.4         0.2 setosa         6.5
#> 2          4.9         3            1.4         0.2 setosa         6.5
#> 3          7           3.2          4.7         1.4 versicolor     3.2

如果您有多个计算列，您可以像这样使用 UPDATE ... SET (c1, c2, ...) = (...):

library(dplyr)
library(dbplyr)
library(DBI)
con <- DBI::dbConnect(RSQLite::SQLite(), path = ":memory:")
copy_to(con, iris[c(1,2,51),],"iris")

DBI::dbSendQuery(con, "CREATE TABLE aggs AS 
                       SELECT Species, 
                              SUM(`Sepal.Width`) AS sw_sum,
                              AVG(`Sepal.Width`) AS sw_avg 
                       FROM iris GROUP BY Species")
tbl(con,"aggs")
#> # Source:   table<aggs> [?? x 3]
#> # Database: sqlite 3.22.0 []
#>   Species    sw_sum sw_avg
#>   <chr>       <dbl>  <dbl>
#> 1 setosa        6.5   3.25
#> 2 versicolor    3.2   3.2

DBI::dbSendQuery(con, "ALTER TABLE iris ADD COLUMN sw_sum DOUBLE")
DBI::dbSendQuery(con, "ALTER TABLE iris ADD COLUMN sw_avg DOUBLE")

DBI::dbSendQuery(con, "UPDATE iris 
                       SET (sw_sum, sw_avg) = (SELECT sw_sum, sw_avg 
                           FROM aggs WHERE iris.Species = aggs.Species)")

tbl(con,"iris")
#> # Source:   table<iris> [?? x 7]
#> # Database: sqlite 3.22.0 []
#>   Sepal.Length Sepal.Width Petal.Length Petal.Width Species  sw_sum sw_avg
#>          <dbl>       <dbl>        <dbl>       <dbl> <chr>     <dbl>  <dbl>
#> 1          5.1         3.5          1.4         0.2 setosa      6.5   3.25
#> 2          4.9         3            1.4         0.2 setosa      6.5   3.25
#> 3          7           3.2          4.7         1.4 versico…    3.2   3.2

这也适用于 Postgres，但可能不适用于 SQL Server。

实际上，在这种情况下不需要中间表:

library(dplyr)
library(dbplyr)
library(DBI)
con <- DBI::dbConnect(RSQLite::SQLite(), path = ":memory:")
copy_to(con, iris[c(1,2,51),],"iris")

DBI::dbSendQuery(con, "ALTER TABLE iris ADD COLUMN sw_sum DOUBLE")
DBI::dbSendQuery(con, "ALTER TABLE iris ADD COLUMN sw_avg DOUBLE")

DBI::dbSendQuery(con, "UPDATE iris 
                       SET (sw_sum, sw_avg) = 
                              (SELECT sw_sum, sw_avg FROM 
                                    (SELECT Species, 
                                            SUM(`Sepal.Width`) AS sw_sum, 
                                            AVG(`Sepal.Width`) AS sw_avg 
                                     FROM iris GROUP BY Species) aggs 
                               WHERE iris.Species = aggs.Species)")

tbl(con,"iris")
#> # Source:   table<iris> [?? x 7]
#> # Database: sqlite 3.22.0 []
#>   Sepal.Length Sepal.Width Petal.Length Petal.Width Species  sw_sum sw_avg
#>          <dbl>       <dbl>        <dbl>       <dbl> <chr>     <dbl>  <dbl>
#> 1          5.1         3.5          1.4         0.2 setosa      6.5   3.25
#> 2          4.9         3            1.4         0.2 setosa      6.5   3.25
#> 3          7           3.2          4.7         1.4 versico…    3.2   3.2

不过，中间表在其他情况下可能会有帮助。例如，当它是在链接问题中使用 R 创建时。