add st_join and st_example

Author: Harry Zhu

DESCRIPTION

@@ -13,3 +13,4 @@ Depends:
   R (>= 3.1.2)
 Imports:
   sparklyr (>= 1.0.0)
+RoxygenNote: 6.0.1.9000

NAMESPACE

@@ -1,2 +1,7 @@
+# Generated by roxygen2: do not edit by hand
+
 export(register_gis)
+export(st_join)
+export(st_pit_example)
+export(st_plg_example)
 import(sparklyr)

R/st_example.R

@@ -0,0 +1,33 @@
+#' Spark polygons example.
+#'
+#' @examples
+#' \dontrun{
+#' library(sparklyr)
+#' sc <- spark_connect(master = "local")
+#' register_gis(sc)
+#' st_plg_example(sc)
+#' }
+#' @export
+st_plg_example <- function(sc) {
+    polygons <- read.table(system.file(package="geospark","examples/polygons.txt"), sep="|", col.names=c("area","geom"))
+    polygons_wkt <- copy_to(dest = sc, df = polygons, name = "geospark_example_polygons", overwrite = T) %>% 
+        mutate(geom = st_geomfromwkt(geom))
+    return(polygons_wkt)
+}
+
+#' Spark points example.
+#'
+#' @examples
+#' \dontrun{
+#' library(sparklyr)
+#' sc <- spark_connect(master = "local")
+#' register_gis(sc)
+#' st_pit_example(sc)
+#' }
+#' @export
+st_pit_example <- function(sc) {
+    points <- read.table(system.file(package="geospark","examples/points.txt"), sep="|", col.names=c("city","state","geom"))
+    points_wkt <- copy_to(dest = sc, df = points, name = "geospark_example_points", overwrite = T) %>% 
+        mutate(geom = st_geomfromwkt(geom))
+    return(points_wkt)
+}

R/st_join.R

@@ -0,0 +1,36 @@
+#' @title spatial join
+#' @name st_join
+#' @import sparklyr
+#' @param x a spark spatial data frame
+#' @param y a spark spatial data frame
+#' @description 
+#' st_join: spatial join 
+#' 
+#' @details alternative values for argument join are: ST_Contains, ST_Intersects, ST_Within, ST_Equals, ST_Crosses, ST_Touches, ST_Overlaps, ST_Distance
+#' 
+#' @return a spark spatial data frame, joined based on geometry
+#' 
+#' @examples
+#' \dontrun{
+#' 
+#' library(dplyr)
+#' polygons <- read.table(system.file(package="geospark","examples/polygons.txt"), sep="|", col.names=c("area","geom"))
+#' points <- read.table(system.file(package="geospark","examples/points.txt"), sep="|", col.names=c("city","state","geom"))
+#' polygons_wkt <- copy_to(sc, polygons)
+#' points_wkt <- copy_to(sc, points)
+
+#' polygons_wkt <- mutate(polygons_wkt, y = st_geomfromwkt(geom))
+#' points_wkt <- mutate(points_wkt, x = st_geomfromwkt(geom))
+
+#' sc_res = st_join(polygons_wkt, points_wkt, join = sql("st_contains(y,x)"))
+#'     group_by(area, state) %>%
+#'     summarise(cnt = n()) 
+#' }
+#' @export
+st_join <- function(x, y, join = NULL) {
+    full_join(x  %>% mutate(dummy_s4pu629cnd=TRUE),
+              y %>% mutate(dummy_s4pu629cnd=TRUE),
+              by = "dummy_s4pu629cnd") %>% 
+        filter(join) %>%
+        select(-dummy_s4pu629cnd)
+}

README.Rmd

@@ -118,12 +118,15 @@ Then, you can join as follows:
 
 ``` r
 library(dplyr)
-polygons_wkt <- mutate(polygons_wkt, y = st_geomfromwkt(geom, "4326"))
-points_wkt <- mutate(points_wkt, x = st_geomfromwkt(geom, "4326"))
+polygons_wkt <- mutate(polygons_wkt, y = st_geomfromwkt(geom))
+points_wkt <- mutate(points_wkt, x = st_geomfromwkt(geom))
 
-sc_res = inner_join(polygons_wkt, points_wkt, by = sql("st_contains(y, x)")) %>%
+sc_res = full_join(polygons_wkt  %>% mutate(dummy=TRUE),
+                   points_wkt %>% mutate(dummy=TRUE),
+                   by = "dummy") %>% 
+   filter(sql("st_contains(y,x)")) %>%
   group_by(area, state) %>%
-  summarise(cnt = n())
+  summarise(cnt = n()) 
 
 sc_res %>%
   head()