monogenea

# Takes approx. 15min
trainData <- extract_feature("train/", width, height)
# Takes slightly less
testData <- extract_feature("test1/", width, height, labelsExist = F)

monogenea

# Check processing on second cat
par(mar = rep(0, 4))
testCat <- t(matrix(as.numeric(trainData$X[2,]),
                    nrow = width, ncol = height, T))
image(t(apply(testCat, 2, rev)), col = gray.colors(12),
      axes = F)

# Save / load
save(trainData, testData, file = "catdogData.RData")
# load("catdogData.RData")

monogenea

# Fix structure for 2d CNN
train_array <- t(trainData$X)
dim(train_array) <- c(50, 50, nrow(trainData$X), 1)
# Reorder dimensions
train_array <- aperm(train_array, c(3,1,2,4))

test_array <- t(testData)
dim(test_array) <- c(50, 50, nrow(testData), 1)
# Reorder dimensions
test_array <- aperm(test_array, c(3,1,2,4))

monogenea

# Compute probabilities and predictions on test set
predictions <-  predict_classes(model, test_array)
probabilities <- predict_proba(model, test_array)

# Visual inspection of 32 cases
set.seed(100)
random <- sample(1:nrow(testData), 32)
preds <- predictions[random,]
probs <- as.vector(round(probabilities[random,], 2))

monogenea

# Install (if necessary) and load nlme and lme4
library(nlme)
library(lme4)
# Load dataset, inspect size and additional info
data(Arabidopsis)
dim(Arabidopsis) # 625 observations, 8 variables
?Arabidopsis
attach(Arabidopsis)

monogenea

# Overview of the variables
par(mfrow = c(2,4))
barplot(table(reg), ylab = "Frequency", main = "Region")
barplot(table(popu), ylab = "Frequency", main = "Population")
barplot(table(gen), ylab = "Frequency", las = 2, main = "Genotype")
barplot(table(rack), ylab = "Frequency", main = "Rack")
barplot(table(nutrient), ylab = "Frequency", main = "Nutrient")
barplot(table(amd), ylab = "Frequency", main = "AMD")
barplot(table(status), ylab = "Frequency", main = "Status")
hist(total.fruits, col = "grey", main = "Total fruits", xlab = NULL)

monogenea

# Transform the three factor variables gen, rack and nutrient
Arabidopsis[,c("gen","rack","nutrient")] <- lapply(Arabidopsis[,c("gen","rack","nutrient")], factor)
str(Arabidopsis)
# Re-attach after correction, ignore warnings
attach(Arabidopsis)
# Add 1 to total fruits, otherwise log of 0 will prompt error
total.fruits <- log(1 + total.fruits)

monogenea

# gen x popu table
table(gen, popu)
# Any NAs?
any(is.na(Arabidopsis)) # FALSE

monogenea

LM <- lm(total.fruits ~ rack + nutrient + amd + status)
summary(LM)
par(mfrow = c(2,2))
plot(LM)

monogenea

GLM <- gls(total.fruits ~ rack + nutrient + amd + status,
           method = "ML")
summary(GLM)