In WinVector/replyr: Patches to Use 'dplyr' on Remote Data Sources

Union order issue

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = " # "
)
options(width =100)

OSX 10.11.6. Spark installed as described at http://spark.rstudio.com

library('sparklyr')
spark_install(version = "2.0.0")

library('dplyr')
library('sparklyr')
R.Version()$version.string
packageVersion('dplyr')
packageVersion('sparklyr')
my_db <- sparklyr::spark_connect(version='2.0.0', master = "local")
class(my_db)
my_db$spark_home
print(my_db)

Expected outcome: dplyr::union and dplyr::union_all should match columns.
Observed outcome: matches columns on local data frames, matches positions on spark2.0.0.

d1 <- data.frame(year=2005:2010,
                 name='a',
                 stringsAsFactors = FALSE)
d2 <- data.frame(name='b',
                 year=2005:2010,
                 stringsAsFactors = FALSE)

# local frames: uses names on union
dplyr::union(d1, d2)
dplyr::union_all(d1, d2)


s1 <- copy_to(my_db, d1, 's1')
s2 <- copy_to(my_db, d2, 's2')

# remore frames: uses position, co-mingline different types
dplyr::union(s1,s2)
dplyr::union_all(s1,s2)