arsilva87

library(shiny)
library(terra)
library(mgcv)

# load the trained model
# GAM, predictor: ni ( r425/(r655+r965) )
# R2 = 0.79
model_gam <- readRDS(url("https://raw.githubusercontent.com/arsilva87/misc/main/gam_model_ntotal.rds"))

# set the max file size to 200 MB

arsilva87

install.packages(c("PMCMRplus", "dunn.test", "agricolae", "readxl", "ExpDes"))

arsilva87

install.packages(c('rgdal', 'sp', 'raster', 'mapview', 'spdep', 'gstat'))

arsilva87

library(shiny)
library(EBImage)

# ----------------------------------------
load(url("https://raw.githubusercontent.com/arsilva87/misc/main/model_nnet.rda"))

ANALYZEPAPER <- function(x, 
	paper_dim = c(76, 26), distance = 0.7, 
	display.it = FALSE, align.x = FALSE) 
{

arsilva87

library(rhandsontable)
library(shiny)
library(shinydashboard)
# -------------------------------------------------------------------
# automatically find the best fit WRC using maximum likelihood

findWRC = function(w, h,
                   mod2fit = c(TRUE, TRUE, TRUE, TRUE, TRUE))
{
  y = w; x = h

arsilva87

arsilva87

library(shiny)
library(shinydashboard)
library(MASS)

model <- readRDS(url("https://github.com/arsilva87/misc/raw/main/model_PQ.rds"), "rb")

# UI
about <- mainPanel(
  helpText("Este é apenas um SIMULADOR do resultado de julgamento de propostas

arsilva87

install.packages(c("learnr", "rmarkdown"))

arsilva87

# Script R para simular distâncias sistemáticas entre pontos amostrais em grid espacial misto

dists <- c(5, 10, 20, 40)       # metros
props <- c(0.2, 0.2, 0.3, 0.3)
npts <- 90
pts <- npts * props

x <- rep(dists, times = pts)
table(x)/npts

arsilva87