问题
I am using src_postgres to connect and dplyr::tbl function to fetch data from redshift database. I have applied some filters and top function to it using the dplyr itself. Now my data looks as below:
riid day hour
<dbl> <chr> <chr>
1 5542. "THURSDAY " 12
2 5862. "FRIDAY " 15
3 5982. "TUESDAY " 15
4 6022. WEDNESDAY 16
My final output should be as below:
riid MON TUES WED THUR FRI SAT SUN
5542 12
5862 15
5988 15
6022 16
I have tried spread. It throws the below error because of the class type:
Error in UseMethod("spread_") : no applicable method for 'spread_' applied to an object of class "c('tbl_dbi', 'tbl_sql', 'tbl_lazy', 'tbl')"
Since this is a really big table, I do not want to use dataframe as it takes a longer time. I was able to use as below:
df_mon <- df2 %>% filter(day == 'MONDAY') %>% mutate(MONDAY = hour) %>% select(riid,MONDAY)
df_tue <- df2 %>% filter(day == 'TUESDAY') %>% mutate(TUESDAY = hour) %>% select(riid,TUESDAY)
df_wed <- df2 %>% filter(day == 'WEDNESDAY') %>% mutate(WEDNESDAY = hour) %>% select(riid,WEDNESDAY)
df_thu <- df2 %>% filter(day == 'THURSDAY') %>% mutate(THURSDAY = hour) %>% select(riid,THURSDAY)
df_fri <- df2 %>% filter(day == 'FRIDAY') %>% mutate(FRIDAY = hour) %>% select(riid,FRIDAY)
Is it possible to write all above in one statement?
Any help to transpose this in a faster manner is really appreciated.
EDIT Adding the dput of the tbl object:
structure(list(src = structure(list(con = <S4 object of class structure("PostgreSQLConnection", package = "RPostgreSQL")>,
disco = <environment>), .Names = c("con", "disco"), class = c("src_dbi",
"src_sql", "src")), ops = structure(list(name = "select", x = structure(list(
name = "filter", x = structure(list(name = "filter", x = structure(list(
name = "group_by", x = structure(list(x = structure("SELECT riid,day,hour,sum(weightage) AS score FROM\n (SELECT riid,day,hour,\n POWER(2,(cast(datediff (seconds,convert_timezone('UTC','PKT',SYSDATE),TO_DATE(TO_CHAR(event_captured_dt,'mm/dd/yyyy hh24:mi:ss'),'mm/dd/yyyy hh24:mi:ss')) as decimal) / cast(7862400 as decimal))) AS weightage\n FROM (\n SELECT riid,convert_timezone('GMT','PKT',event_captured_dt) AS EVENT_CAPTURED_DT,\n TO_CHAR(convert_timezone('GMT','PKT',event_captured_dt),'DAY') AS day,\n TO_CHAR(convert_timezone('GMT','PKT',event_captured_dt),'HH24') AS hour\n FROM Zameen_STO_DATA WHERE EVENT_CAPTURED_DT >= TO_DATE((sysdate -30),'yyyy-mm-dd') and LIST_ID = 4282\n )) group by riid,day,hour", class = c("sql",
"character")), vars = c("riid", "day", "hour", "score"
)), .Names = c("x", "vars"), class = c("op_base_remote",
"op_base", "op")), dots = structure(list(riid = riid,
day = day), .Names = c("riid", "day")), args = structure(list(
add = FALSE), .Names = "add")), .Names = c("name",
"x", "dots", "args"), class = c("op_group_by", "op_single",
"op")), dots = structure(list(~min_rank(desc(~score)) <=
1), .Names = ""), args = list()), .Names = c("name",
"x", "dots", "args"), class = c("op_filter", "op_single",
"op")), dots = structure(list(~row_number() == 1), .Names = ""),
args = list()), .Names = c("name", "x", "dots", "args"), class = c("op_filter",
"op_single", "op")), dots = structure(list(~riid, ~day, ~hour), class = "quosures", .Names = c("",
"", "")), args = list()), .Names = c("name", "x", "dots", "args"
), class = c("op_select", "op_single", "op"))), .Names = c("src",
"ops"), class = c("tbl_dbi", "tbl_sql", "tbl_lazy", "tbl"))
回答1:
I think what you're looking for is the ability to run the tidyr::spread() function against a remote source, or database. I have a PR for dbplyr that attempts to implement that here: https://github.com/tidyverse/dbplyr/pull/72, you can try it out by using: devtools::install_github("tidyverse/dbplyr", ref = devtools::github_pull(72)).
回答2:
Use dcast from reshape2 package
> data
# A tibble: 4 x 3
riid day hour
<dbl> <chr> <dbl>
1 1.00 TH 12.0
2 2.00 FR 15.0
3 3.00 TU 15.0
4 4.00 WE 16.0
> dcast(data, riid~day, value.var = "hour")
riid FR TH TU WE
1 1 NA 12 NA NA
2 2 15 NA NA NA
3 3 NA NA 15 NA
4 4 NA NA NA 16
Further if you want to remove NA, then
> z <- dcast(data, riid~day, value.var = "hour")
> z[is.na(z)] <- ""
> z
riid FR TH TU WE
1 1 12
2 2 15
3 3 15
4 4 16
回答3:
I tried to combine your multiple line attempts into one. Can you try this and let us know the outcome?
library(dplyr)
df %>%
rowwise() %>%
mutate(Mon = ifelse(day=='MONDAY', hour[day=='MONDAY'], NA),
Tue = ifelse(day=='TUESDAY', hour[day=='TUESDAY'], NA),
Wed = ifelse(day=='WEDNESDAY', hour[day=='WEDNESDAY'], NA),
Thu = ifelse(day=='THURSDAY', hour[day=='THURSDAY'], NA),
Fri = ifelse(day=='FRIDAY', hour[day=='FRIDAY'], NA),
Sat = ifelse(day=='SATURDAY', hour[day=='SATURDAY'], NA),
Sun = ifelse(day=='SUNDAY', hour[day=='SUNDAY'], NA)) %>%
select(-day, -hour)
Output is:
riid Mon Tue Wed Thu Fri Sat Sun
1 5542 NA NA NA 12 NA NA NA
2 5862 NA NA NA NA 15 NA NA
3 5982 NA 15 NA NA NA NA NA
4 6022 NA NA 16 NA NA NA NA
Sample data:
# A tibble: 4 x 3
riid day hour
* <dbl> <chr> <int>
1 5542 THURSDAY 12
2 5862 FRIDAY 15
3 5982 TUESDAY 15
4 6022 WEDNESDAY 16
Update:
Can you try below approach using data.table?
library(data.table)
dt <- setDT(df)[, c("Mon","Tue","Wed","Thu","Fri","Sat","Sun") :=
list(ifelse(day=='MONDAY', hour[day=='MONDAY'], NA),
ifelse(day=='TUESDAY', hour[day=='TUESDAY'], NA),
ifelse(day=='WEDNESDAY', hour[day=='WEDNESDAY'], NA),
ifelse(day=='THURSDAY', hour[day=='THURSDAY'], NA),
ifelse(day=='FRIDAY', hour[day=='FRIDAY'], NA),
ifelse(day=='SATURDAY', hour[day=='SATURDAY'], NA),
ifelse(day=='SUNDAY', hour[day=='SUNDAY'], NA))][, !c("day","hour"), with=F]
来源：https://stackoverflow.com/questions/50049804/transpose-dplyrtbl-object