基于@m-viking 的答案,如果使用 WRDS PostgreSQL 服务器,您只需使用window_order
(from dplyr
) 代替arrange
. (我使用 Compustat 公司标识符gvkey
代替,permno
以便此代码有效,但想法是相同的。)
library(dplyr, warn.conflicts = FALSE)
library(DBI)
pg <- dbConnect(RPostgres::Postgres(),
bigint = "integer", sslmode='allow')
fundq <- tbl(pg, sql("SELECT * FROM comp.fundq"))
comp2 <-
fundq %>%
filter(indfmt == "INDL", datafmt == "STD",
consol == "C", popsrc == "D")
comp2 <-
comp2 %>%
group_by(gvkey) %>%
dbplyr::window_order(datadate) %>%
mutate(cxsgaq = cumsum(xsgaq))
comp2 %>%
filter(!is.na(xsgaq)) %>%
select(gvkey, datadate, xsgaq, cxsgaq)
#> # Source: lazy query [?? x 4]
#> # Database: postgres [iangow@wrds-pgdata.wharton.upenn.edu:9737/wrds]
#> # Groups: gvkey
#> # Ordered by: datadate
#> gvkey datadate xsgaq cxsgaq
#> <chr> <date> <dbl> <dbl>
#> 1 001000 1966-12-31 0.679 0.679
#> 2 001000 1967-12-31 1.02 1.70
#> 3 001000 1968-12-31 5.86 7.55
#> 4 001000 1969-12-31 7.18 14.7
#> 5 001000 1970-12-31 8.25 23.0
#> 6 001000 1971-12-31 7.96 30.9
#> 7 001000 1972-12-31 7.55 38.5
#> 8 001000 1973-12-31 8.53 47.0
#> 9 001000 1974-12-31 8.86 55.9
#> 10 001000 1975-12-31 9.59 65.5
#> # … with more rows
由reprex 包于 2021-04-05 创建(v1.0.0)