如何使用 R DBI 和 bigrquery 将虚拟 BQ table 写回 BQ？

Question

我希望能够

访问 BQtable。这是class

[1] "tbl_BigQueryConnection" "tbl_dbi"                "tbl_sql"               
[4] "tbl_lazy"               "tbl"   `

使用 dbplyr 更改 table 以创建新的 table。同样，有 class

[1] "tbl_BigQueryConnection" "tbl_dbi"                "tbl_sql"               
[4] "tbl_lazy"               "tbl"

将这个新的 table 写入 BQ。

我收到以下错误：

Error in (function (classes, fdef, mtable) : unable to find an inherited method for function ‘dbWriteTable’ for signature ‘"BigQueryConnection", "character", "tbl_BigQueryConnection"’

MRE

library(DBI)
library(dplyr, warn.conflicts = FALSE)
library(bigrquery)

############  CREATE BQ TABLE TO ACCESS  #################
dataset = bq_dataset(bq_test_project(), "test_dataset")

if (bq_dataset_exists(dataset))
{
  bq_dataset_delete(dataset, delete_contents = T)
}
#> Suitable tokens found in the cache, associated with these emails:
#>   * ariel.balter@gmail.com
#>   * ariel.balter@providence.org
#> The first will be used.
#> Using an auto-discovered, cached token.
#> To suppress this message, modify your code or options to clearly consent to the use of a cached token.
#> See gargle's "Non-interactive auth" vignette for more details:
#> https://gargle.r-lib.org/articles/non-interactive-auth.html
#> The bigrquery package is using a cached token for ariel.balter@gmail.com.

bq_dataset_create(dataset)
#> <bq_dataset> elite-magpie-257717.test_dataset

conn = DBI::dbConnect(
  bigrquery::bigquery(),
  project = bq_test_project(),
  dataset = "test_dataset",
  KeyFilePath = "google_service_key.json",
  OAuthMechanism = 0
)


if (dbExistsTable(conn, "mtcars"))
{
  dbRemoveTable(conn, "mtcars")
}

dbWriteTable(conn, "mtcars", mtcars)

#######################################################


### Access BQ table
mtcars_tbl = tbl(conn, "mtcars")
class(mtcars_tbl)
#> [1] "tbl_BigQueryConnection" "tbl_dbi"                "tbl_sql"               
#> [4] "tbl_lazy"               "tbl"

### Create new virtual table
hp_gt_100_tbl = mtcars_tbl %>% filter(hp>100)
class(hp_gt_100_tbl)
#> [1] "tbl_BigQueryConnection" "tbl_dbi"                "tbl_sql"               
#> [4] "tbl_lazy"               "tbl"

### Write new table
dbWriteTable(conn, "hp_gt_100", hp_gt_100_tbl)
#> Error in (function (classes, fdef, mtable) : unable to find an inherited method for function 'dbWriteTable' for signature '"BigQueryConnection", "character", "tbl_BigQueryConnection"'

dbExecute(conn, "DROP TABLE mtcars")
#> [1] 0
dbExecute(conn, "DROP TABLE hp_gt_100")
#> Error: Job 'elite-magpie-257717.job_O8e7BtdfAnAb_8Vdtwybibgd7DpA.US' failed
#> x Not found: Table elite-magpie-257717:test_dataset.hp_gt_100 [notFound]

^{由 reprex package (v0.3.0)}

于 2020-11-11 创建

Answer 1

我认为您无法使用 dbWriteTable 使用您当前的方法来做到这一点。 dbWriteTable“将[本地]数据框写入、覆盖或附加到数据库table”(source)。

因此，一种选择是将该数据收集到 R 中，然后他们使用 dbWriteTable 将其写回 SQL。但这很可能是低效的。

我推荐的方法是创建一个 bigquery INSERT INTO 语句并将其传递给 dbExecute。类似于以下内容：

sql_query <- glue::glue("INSERT INTO {db}.{schema}.{tbl_name}\n",
                         dbplyr::sql_render(input_tbl))

result <- dbExecute(db_connection, as.character(sql_query))

sql_render 将采用您当前定义的虚拟 table 和 return 查询的文本。 dbExecute 会将此命令传递给要执行的 bigquery 服务器。

请注意，我对 bigquery 的 INSERT INTO 语法不够熟悉，无法确保上面 sql_query 的语法正确，但我知道一般方法在我使用 dbplyr 和 DBI 时有效广泛存在于 SQL 服务器中。

Answer 2

我接受 Simon S.A. 的回答。但是，我确实设法使用 bigrquery 函数 bq_project_query.

找到了更直接的方法

library(DBI)
library(dplyr, warn.conflicts = FALSE)
library(bigrquery)

bq_deauth()
bq_auth(email="ariel.balter@gmail.com")


############  CREATE BQ TABLE TO ACCESS  #################

dataset = bq_dataset("elite-magpie-257717", "test_dataset")

if (bq_dataset_exists(dataset))
{
  bq_dataset_delete(dataset, delete_contents = T)
}
bq_dataset_create(dataset)
#> <bq_dataset> elite-magpie-257717.test_dataset

conn = dbConnect(
  bigrquery::bigquery(),
  project = "elite-magpie-257717",
  dataset = "test_dataset",
  KeyFilePath = "google_service_key.json",
  OAuthMechanism = 0
)

dbWriteTable(conn, "mtcars", mtcars, overwrite=T)

dbListTables(conn)
#> [1] "mtcars"

#######################################################


### Access BQ table
mtcars_tbl = tbl(conn, "test_dataset.mtcars")
class(mtcars_tbl)
#> [1] "tbl_BigQueryConnection" "tbl_dbi"                "tbl_sql"               
#> [4] "tbl_lazy"               "tbl"

### Create new virtual table
hp_gt00_tbl = mtcars_tbl %>% filter(hp>100)
class(hp_gt00_tbl)
#> [1] "tbl_BigQueryConnection" "tbl_dbi"                "tbl_sql"               
#> [4] "tbl_lazy"               "tbl"

hp_gt00_tbl %>% dbplyr::sql_render()
#> <SQL> SELECT *
#> FROM `test_dataset.mtcars`
#> WHERE (`hp` > 100.0)

bq_project_query(
  x = dataset$project,
  query = hp_gt00_tbl %>% dbplyr::sql_render(),
  destination = bq_table(dataset, "hp_gt_00")
)
#> <bq_table> elite-magpie-257717.test_dataset.hp_gt_00

bq_dataset_tables(dataset)
#> [[1]]
#> <bq_table> elite-magpie-257717.test_dataset.hp_gt_00
#> 
#> [[2]]
#> <bq_table> elite-magpie-257717.test_dataset.mtcars

bq_dataset_delete(dataset, delete_contents = T)

^{由 reprex package (v0.3.0)}

于 2020-11-15 创建

如何使用 R DBI 和 bigrquery 将虚拟 BQ table 写回 BQ？

How to write virtual BQ table back to BQ using R DBI and bigrquery?

r

google-bigquery

dplyr

dbplyr

bigrquery