Type: Package
Title: Spatial Association of Different Types of Polygon
Version: 0.8.0
Date: 2024-10-02
Description: In ecology, spatial data is often represented using polygons. These polygons can represent a variety of spatial entities, such as ecological patches, animal home ranges, or gaps in the forest canopy. Researchers often need to determine if two spatial processes, represented by these polygons, are independent of each other. For instance, they might want to test if the home range of a particular animal species is influenced by the presence of a certain type of vegetation. To address this, Godoy et al. (2022) (<doi:10.1016/j.spasta.2022.100695>) developed conditional Monte Carlo tests. These tests are designed to assess spatial independence while taking into account the shape and size of the polygons.
License: GPL (≥ 3)
Encoding: UTF-8
SystemRequirements: GDAL (>= 2.0.1), GEOS (>= 3.4.0), PROJ (>= 4.8.0)
Imports: sf, methods, stats
Depends: R (≥ 4.0)
URL: https://github.com/lcgodoy/sapo/
BugReports: https://github.com/lcgodoy/sapo/issues/
RoxygenNote: 7.3.2
Language: en-US
Suggests: knitr, rmarkdown
VignetteBuilder: knitr
NeedsCompilation: no
Packaged: 2024-10-08 22:13:31 UTC; lcgodoy
Author: Lucas da Cunha Godoy ORCID iD [aut, cre]
Maintainer: Lucas da Cunha Godoy <lcgodoy@duck.com>
Repository: CRAN
Date/Publication: 2024-10-11 08:20:02 UTC

h_{12}(t) from matrix

Description

Computes the h_{12} (K or L) based on a distance matrix based on a method

Usage

calc_h(x, var_st = FALSE, dists = NULL)

Arguments

x

distance matrix

var_st

logical scalar indicating if the L function should be used instead

dists

vector of distances to compute h_{12}(t).

Value

a numeric vector

Polygons Spatial Association Test - Global Envelope

Description

A Monte Carlo test to verify if two sets of polygons are associated based in a global envelope of the functions K_{12}(d) and L_{12}(d) using different test statistics.

Usage

cmc_psat(
  p1,
  p2,
  id_col = NULL,
  n_sim = 499L,
  alpha = 0.01,
  var_st = TRUE,
  ts = "SMAD",
  distances = NULL,
  hausdorff = TRUE,
  method = "rnd_poly"
)

Arguments

p1

a sf object containing one column specifying the objects id.

p2

a sf object containing one column specifying the objects id.

id_col

a character or integer indicating the column of p1 storing the unique identifier for the polygons/sample units.

n_sim

an integer corresponding to the number of Monte Carlo simulations for the test

alpha

a numeric indicating the confidence level.

var_st

use the variance stabilizing funciton?

ts

a character associated to a test statistic. Inputs acepted: c('IM', 'MAD', 'SIM', 'SMAD', 'IMDQ', 'MADDQ').

distances

a numeric vector indicating the distances to evaluate H(d). If NULL then the range considered goes from 5% to 20% of the max distance that can be observed inside the study region.

hausdorff

a logical scalar indicating whether the Hausdorff distance should be used (default is TRUE).

method

(default = "rng_poly") a character indicating the method used to deal with broken polygons in the Toroidal Shift. Valid options are c("min", "max", "mean", "rnd_poly", "rnd_dist", "min_norm", "max_norm", "hybrid", "hyb_center", "hybrid_nc", "old_min").

Value

a list with values:

p_value

a numeric scalar giving the p-value of the test

mc_sample

a numeric vector giving the test statistic for each of the Monte Carlo simulations

mc_funct

a matrix where each line correspond to the function (K or L) estimated for the Monte Carlo simulations

distances

numeric vector containing the distances where mc_func were evaluated.

alpha

a numeric scalar giving the significance level

rejects

a logical scalar, TRUE if the null hypothesis is reject

Examples

library(sapo)
library(sf)
set.seed(2024)

 ## loading toy data
poly1 <- system.file("extdata", "poly1.rds", package = "sapo") |>
  readRDS()
poly2 <- system.file("extdata", "poly2.rds", package = "sapo") |>
  readRDS()

my_ht <- cmc_psat(poly1, poly2, n_sim = 199)
my_ht$p_value

Create jumps for random movements

Description

Create jumps for random movements

Usage

create_jump(unique_bb)

Arguments

unique_bb

a bbox shared between both "Polygon Patterns"

Details

This is an internal function.

Value

a sfc object representing a random jump or shift.

Author(s)

Lucas Godoy

Fix distance matrix containing broken polygons

Description

fix a polygons' distance matrix based on a given method. This function assumes the polygon that has been broken is represented by the rows of the distance matrix.

Usage

fix_dist(x, method = "rnd_poly")

Arguments

x

distance matrix

method

method used to fix. The options are "min", "max", "mean", "rnd_poly", "rnd_dist", "min_norm", "max_norm", "hybrid", "hyb_center", "hybrid_nc", "old_min"

Value

a distance matrix

h_{12}(t) from polygons

Description

Computes the h_{12} (K or L) based on a distance matrix based on a method

Usage

h_func(
  p1,
  p2,
  hausdorff = TRUE,
  method = "rnd_poly",
  var_st = FALSE,
  dists = NULL
)

h_func.list(x, ...)

Arguments

p1

sf object

p2

sf object

hausdorff

logical parameter indicating whether the Hausdorff distance should be used

method

method to deal with broken polygons

var_st

logical scalar indicating if the L function should be used instead

dists

vector of distances to compute h_{12}(t).

x

a list with two sf objects.

...

Parameters to be used with h_func when inputting a list.

Value

a numeric vector

ID aware distance matrix

Description

Distance between polygons accounting for toroidal shift.

Usage

iadist(p1, p2, hausdorff = TRUE, method = "rnd_poly")

Arguments

p1

a sf object containing one column specifying the objects id.

p2

a sf object containing one column specifying the objects id.

hausdorff

logical scalar indicating whether the Hausdorff distance should be used.

method

method for "fixing" the distance matrix.

Value

a distance matrix.

Author(s)

Lucas Godoy

Integram Measure

Description

Integram Measure

Usage

im(x, h = 1)

Arguments

x

numeric matrix

h

numeric

Value

numeric vector

Integram Measure with Assimetry Correction

Description

Integram Measure with Assimetry Correction

Usage

im_ac(x, h = 1)

Arguments

x

numeric matrix

h

numeric

Value

numeric vector

Maximum Absolute Deviation

Description

Maximum Absolute Deviation

Usage

mad(x)

Arguments

x

numeric matrix

Value

numeric vector

Maximum Absolute Deviation with Assimetry Correction

Description

Maximum Absolute Deviation with Assimetry Correction

Usage

mad_ac(x)

Arguments

x

numeric matrix

Value

numeric vector

auxiliary mean

Description

aux function to calculate the mean of a vector when removing each of its elements one by one.

Usage

mean_aux(x)

Arguments

x

a numeric vector

Value

a numeric vector

Author(s)

Lucas Godoy

Pre-TS

Description

Create rigid copies of a polygon. This function an auxilliary function for the Toroidal Shift method

Usage

pre_ts(poly, bb = NULL, id_col = NULL)

Arguments

poly

an object of class sf or sfc.

bb

(optional) a unique bounding box.

id_col

a character indicating the id column in poly.

Value

an sf with 8 additional rigid copies of poly.

Author(s)

Lucas Godoy

Studentized Integram Measure

Description

Studentized Integram Measure

Usage

s_im(x, h = 1)

Arguments

x

numeric matrix

h

numeric

Value

numeric vector

Studentized Maximum Absolute Deviation

Description

Studentized Maximum Absolute Deviation

Usage

s_mad(x)

Arguments

x

numeric matrix

Value

numeric vector

sapo: Spatial Association of Polygon Types

Description

sapo: Spatial Association of Polygon Types

Toroidal Shift

Description

Toroidal Shift

Usage

toroidal_shift(x, y, shifted = FALSE, unique_bb = NULL)

Arguments

x

a sf or sfc object. Its geometry may contain POLYGONS and/or POINTS.

y

a sf or sfc object. Its geometry may contain POLYGONS and/or POINTS.

shifted

logical indicating whether x has been "shifted". This parameter is mainly for internal use and testing.

unique_bb

a bbox shared between both "Polygon Patterns"

Value

a list

Author(s)

Lucas Godoy

Translate an sf object by a "point"

Description

Translate an sf object by a "point"

Usage

translate_by_pt(pt, poly)

Arguments

pt

sfc representing a shift.

poly

sfc of sf to be shifted

Value

a sf or sfc representing poly shifted by pt

Author(s)

Lucas Godoy