问题
If you have spatial point and polygon time series data, how do you do a spatial join/merge and "normal" merge of a non-spatial variable together?
Point data over years that I want to merge into yearly polygons and then summarise (xvar) by year:
#spatial point data by year
library(sf)
set.seed(10)
df_point <- data.frame(id = c(1, 1, 1, 1, 2, 2, 2, 2, 3, 3,
4, 4, 5, 5,
6, 6, 7, 7),
year = c(2016, 2017, 2018, 2019, 2016, 2017, 2018, 2019, 2016, 2017,
2016, 2017, 2016, 2017,
2016, 2017, 2016, 2017),
xvar = sample(1:10, 18, replace = T))
df_point$geometry <- st_cast(st_sfc(st_multipoint(rbind(c(.1, .2), c(.1, .2), c(.1, .2), c(.1, .2),
c(.3, 1), c(.3, 1), c(.3, 1), c(.3, 1),
c(1, 1), c(1, 1),
c(2, 2.1), c(2, 2.1), c(2.2, 2.4), c(2.2, 2.4),
c(4, 2.1), c(4, 2.1), c(4, 2.2), c(4, 2.2)))), "POINT")
df_point <- st_as_sf(df_point)
df_point
# Simple feature collection with 18 features and 3 fields
# geometry type: POINT
# dimension: XY
# bbox: xmin: 0.1 ymin: 0.2 xmax: 4 ymax: 2.4
# CRS: NA
# First 10 features:
# id year xvar geometry
# 1 1 2016 9 POINT (0.1 0.2)
# 2 1 2017 10 POINT (0.1 0.2)
# 3 1 2018 7 POINT (0.1 0.2)
# 4 1 2019 8 POINT (0.1 0.2)
# 5 2 2016 6 POINT (0.3 1)
# 6 2 2017 7 POINT (0.3 1)
# 7 2 2018 3 POINT (0.3 1)
# 8 2 2019 8 POINT (0.3 1)
# 9 3 2016 10 POINT (1 1)
# 10 3 2017 7 POINT (1 1)
and polygon data:
df_poly <- data.frame(poly_id = c(1, 2, 3, 1, 2, 3, 1, 2, 3, 1, 2, 3),
year = rep(2016:2019, each = 3))
pol = st_polygon(list(rbind(c(0, 0), c(2, 0), c(2, 2), c(0, 2), c(0, 0))))
b = st_sfc(pol, pol + c(2, 2), pol + c(4, .8))
df_poly$geomtry <- c(b, b, b, b)
df_poly <- st_as_sf(df_poly)
df_poly
# Simple feature collection with 12 features and 2 fields
# geometry type: POLYGON
# dimension: XY
# bbox: xmin: 0 ymin: 0 xmax: 6 ymax: 4
# CRS: NA
# First 10 features:
# poly_id year geomtry
# 1 1 2016 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 2 2 2016 POLYGON ((2 2, 4 2, 4 4, 2 ...
# 3 3 2016 POLYGON ((4 0.8, 6 0.8, 6 2...
# 4 1 2017 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 5 2 2017 POLYGON ((2 2, 4 2, 4 4, 2 ...
# 6 3 2017 POLYGON ((4 0.8, 6 0.8, 6 2...
# 7 1 2018 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 8 2 2018 POLYGON ((2 2, 4 2, 4 4, 2 ...
# 9 3 2018 POLYGON ((4 0.8, 6 0.8, 6 2...
# 10 1 2019 POLYGON ((0 0, 2 0, 2 2, 0 ...
Desired output:
df_sf_merge
# Simple feature collection with 12 features and 3 fields
# geometry type: POLYGON
# dimension: XY
# bbox: xmin: 0 ymin: 0 xmax: 6 ymax: 4
# CRS: NA
# poly_id year total_sum geomtry
# 1 1 2016 25 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 2 2 2016 32 POLYGON ((2 2, 4 2, 4 4, 2 ...
# 3 3 2016 14 POLYGON ((4 0.8, 6 0.8, 6 2...
# 4 1 2017 24 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 5 2 2017 22 POLYGON ((2 2, 4 2, 4 4, 2 ...
# 6 3 2017 12 POLYGON ((4 0.8, 6 0.8, 6 2...
# 7 1 2018 10 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 8 2 2018 NA POLYGON ((2 2, 4 2, 4 4, 2 ...
# 9 3 2018 NA POLYGON ((4 0.8, 6 0.8, 6 2...
# 10 1 2019 16 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 11 2 2019 NA POLYGON ((2 2, 4 2, 4 4, 2 ...
# 12 3 2019 NA POLYGON ((4 0.8, 6 0.8, 6 2...
The general approach for one time point would be something like:
df_sf_merge <- df_poly %>%
st_join(df_point) %>% #AND MERGE OF YEAR?
group_by(poly_id, year) %>% #year.x or year.y
summarise(total_sum = sum(xvar, na.rm = T))
but this won't work because the merge creates duplicate copies:
df_sf_merge <- df_poly %>%
st_join(df_point) %>%
dplyr::arrange(id, year.x)
df_sf_merge
# Simple feature collection with 88 features and 5 fields
# geometry type: POLYGON
# dimension: XY
# bbox: xmin: 0 ymin: 0 xmax: 6 ymax: 4
# CRS: NA
# First 10 features:
# poly_id year.x id year.y xvar geomtry
# 1 1 2016 1 2016 9 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 2 1 2016 1 2017 10 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 3 1 2016 1 2018 7 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 4 1 2016 1 2019 8 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 5 1 2017 1 2016 9 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 6 1 2017 1 2017 10 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 7 1 2017 1 2018 7 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 8 1 2017 1 2019 8 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 9 1 2018 1 2016 9 POLYGON ((0 0, 2 0, 2 2, 0 ...
# 10 1 2018 1 2017 10 POLYGON ((0 0, 2 0, 2 2, 0 ...
I could, in a round about way remove the duplicates but I don't want the duplicate copies to made in the first place as it slows the process down considerably as I am working with large files.
I'm not sure if you can do a spatial and normal join at the same time but I'm sure theres an easier work around?
Any suggestions? thanks
回答1:
One solution is to split the two dataframes into two lists composed of separate dataframes for each year and then iterate over them using map2(). So, 2016 points get st_joined()ed to only the 2016 polygons, and 2017 points to 2017 polygons, etc.
map2_dfr() is the same as map2(), except it flattens the resulting list into a dataframe.
library(dplyr)
library(purrr)
df_point_list <- split(select(df_point, -year), # drop the year column for one of these objects so we don't get year.x and year.y
df_point$year)
df_poly_list <- split(df_poly, df_poly$year)
df_sf_merge<- map2_dfr(df_poly_list, df_point_list,
~ .x %>%
st_join(.y) %>%
group_by(poly_id, year) %>%
summarise(total_sum = sum(xvar, na.rm = T)))
df_sf_merge
Simple feature collection with 12 features and 3 fields
geometry type: POLYGON
dimension: XY
bbox: xmin: 0 ymin: 0 xmax: 6 ymax: 4
CRS: NA
First 10 features:
poly_id year total_sum geomtry
1 1 2016 25 POLYGON ((0 0, 2 0, 2 2, 0 ...
2 2 2016 32 POLYGON ((2 2, 4 2, 4 4, 2 ...
3 3 2016 14 POLYGON ((4 0.8, 6 0.8, 6 2...
4 1 2017 24 POLYGON ((0 0, 2 0, 2 2, 0 ...
5 2 2017 22 POLYGON ((2 2, 4 2, 4 4, 2 ...
6 3 2017 12 POLYGON ((4 0.8, 6 0.8, 6 2...
7 1 2018 10 POLYGON ((0 0, 2 0, 2 2, 0 ...
8 2 2018 0 POLYGON ((2 2, 4 2, 4 4, 2 ...
9 3 2018 0 POLYGON ((4 0.8, 6 0.8, 6 2...
10 1 2019 16 POLYGON ((0 0, 2 0, 2 2, 0 ...
来源：https://stackoverflow.com/questions/62862535/st-join-on-geometry-and-grouping-column-together