monogenea

# Design recipe
myRec <- recipe(Y ~ ., data = trainSet) %>% 
      step_YeoJohnson(all_predictors(), -binVars) %>% 
      step_center(all_predictors(), -binVars) %>% 
      step_scale(all_predictors(), -binVars) %>% 
      step_meanimpute(missingVars)

monogenea

# binary vars
binVars <- which(sapply(X, function(x){all(x %in% 0:1)}))
missingVars <- which(apply(X, 2, function(k){any(is.na(k))}))

monogenea

# binary vars
binVars <- which(sapply(X, function(x){all(x %in% 0:1)}))
missingVars <- which(apply(X, 2, function(k){any(is.na(k))}))

monogenea

# Split train/test with rsample
set.seed(100)
initSplit <- initial_split(X, prop = .9,
                           strata = "Y")
trainSet <- training(initSplit)
testSet <- testing(initSplit)

# Create 5-fold cross-validation, convert to caret class
set.seed(100)
myFolds <- vfold_cv(trainSet, v = 5, repeats = 5,

monogenea

# Filter nzv
X <- X[,-nearZeroVar(X, freqCut = 4)] # == 80/20

monogenea

# Determine intersection of compounds in features and responses
commonMols <- intersect(responses$CID,
                        molFeats$CID)
# Subset features and responses accordingly
responses %<>% filter(CID %in% commonMols)
molFeats %<>% filter(CID %in% commonMols)

# Compute median pleasantness across the population
medianPlsnt <- responses %>% 
      group_by(CID) %>% 

monogenea

# Mon Oct 29 13:17:55 2018 ------------------------------
## DREAM olfaction prediction challenge
library(caret)
library(rsample)
library(tidyverse)
library(recipes)
library(magrittr)
library(doMC)

# Create directory and download files

monogenea

# Simulation with average eggs laid, egg size and group size, w/ and w/o parasitism
seqX <- seq(-3, 3, length.out = 100)
probsNoPar <- sapply(seqX, function(x){
      scenario <- ilogit(a + x*bA)
      probs <- calculate(scenario, draws)
      return(unlist(probs))
})
probsPar <- sapply(seqX, function(x){
      scenario <- ilogit(a + x*bA + bP + x*bPA)
      probs <- calculate(scenario, draws)

monogenea

# Define model effects
sigmaML <- cauchy(0, 1, truncation = c(0, Inf), dim = 3)
a_fem <- normal(0, sigmaML[1], dim = max(female_id))
a_year <- normal(0, sigmaML[2], dim = max(year))
a_group <- normal(0, sigmaML[3], dim = max(group_id))

a <- normal(0, 5)
bA <- normal(0, 3)
bEL <- normal(0, 3)
bES <- normal(0, 3)

monogenea

library(tensorflow)
use_condaenv("greta")
library(greta)
library(tidyverse)
library(bayesplot)
library(readxl)

# Read female reproductive output and discard records w/ NAs
fro <- read_xlsx("data.xlsx", sheet = allTabs[2])
fro <- fro[complete.cases(fro),]