Libraries

library(regionaldrivers)
library(magrittr)
library(raster)

Data loading

SSCT_data is loaded with the package. Here is what 10 random rows of it looks like:

SSCT_data
SiteID	POINT_Y	POINT_X	ward
NCC_PH_5_13789	38.612	-122.777	3
SAC_LSR_42	41.061	-122.361	7
SCC_CH_2_37655	36.073	-121.600	10
SAC_RGW_43	39.421	-121.424	1
SFE_2018_1324	39.778	-123.754	1
NC_UH_5_2734	40.903	-124.028	10
SAC_LSR_517WE0515	39.414	-120.980	1
SAC_LSR_526CE0483	41.361	-120.299	3
SAC_RGW_9	38.938	-122.341	1
SFE_2018_277	39.731	-123.648	5

Data transformation

We extract some geology data from CA_geology and SSCT_data.

SSCT_labelled_points <- sp::SpatialPoints(
    cbind(SSCT_data$POINT_X, SSCT_data$POINT_Y), 
    proj4string = sp::CRS('+proj=longlat +datum=WGS84')
)
SSCT_labelled_points <- sp::spTransform(SSCT_labelled_points, crs(CA_geology))
SSCT_data <- SSCT_data %>% dplyr::mutate(
    geology = (SSCT_labelled_points %over% CA_geology) %>% dplyr::pull(GENERAL)
    )
head(SSCT_data)
#>         SiteID  POINT_Y   POINT_X ward      geology
#> 1 K_CH_1_00458 41.93455 -123.7270    8    limestone
#> 2 K_CH_1_00493 41.92985 -123.7359    5    limestone
#> 3 K_CH_1_11296 41.71748 -123.8991    8    limestone
#> 4  K_CH_1_1546 41.69550 -124.0925    5  sedimentary
#> 5  K_CH_1_2329 41.84913 -123.0666    9 metasediment
#> 6 K_CH_1_25119 41.20531 -123.2234   10    sandstone

Bootstrapping

We perform the bootstrapping using bootstrap_freq(). We use set.seed() to ensure reproducibility of the random process.

set.seed(1789)
l_boot <- bootstrap_freq(SSCT_data %>% dplyr::select(c("ward", "geology")) %>% na.omit())

plotly::ggplotly(
    plot_bootstrap_pvalue(l_boot),
    tooltip = c("channel_type", "geology", "p.value")
)

plotly::ggplotly(
    plot_bootstrap_probability(l_boot),
    tooltip = c("channel_type", "number_groupings", "probability")
)