# R - Exporting Neural Network logic as a function from R to JavaScript or PHP

By using `R` and the following code:

``````printf <- function(...)print(sprintf(...))

data <- read.csv("https://www.dropbox.com/s/ig4szbkp43kpin1/binary.csv?dl=1", header = TRUE)

data\$gre <- (data\$gre - min(data\$gre)) / (max(data\$gre) - min(data\$gre))
data\$gpa <- (data\$gpa - min(data\$gpa)) / (max(data\$gpa) - min(data\$gpa))
data\$rank <- (data\$rank - min(data\$rank)) / (max(data\$rank) - min(data\$rank))

# Data Partition
set.seed(222)
ind <- sample(2, nrow(data), replace = TRUE, prob = c(0.7, 0.3))
training <- data[ind==1,]
testing <- data[ind==2,]

# Neural Network training
library(neuralnet)
set.seed(333)
n <- neuralnet(admit~gre+gpa+rank,
data = training,
hidden = 1,
err.fct = "ce",
linear.output = FALSE)
plot(n)

params = training[1, -1]

# Prediction 1:
output_A <- compute(n, params)\$net.result[1]

# Prediction 2:
in4 <- 0.0455 + (0.82344*params[1]) + (1.35186*params[2]) + (-0.87435*params[3])
out4 <- 1/(1+exp(-in4))
in5 <- -7.06125 +(8.5741*out4)
out5 <- 1/(1+exp(-in5))
output_B = out5[1,1]

printf('Value A: %.5f', output_A)
printf('Value B: %.5f', output_B)
``````

I created this `Neural Network`:

which is equivalent to the fragment of code (again pasted below):

``````# Prediction 2:
in4 <- 0.0455 + (0.82344*params[1]) + (1.35186*params[2]) + (-0.87435*params[3])
out4 <- 1/(1+exp(-in4))
in5 <- -7.06125 +(8.5741*out4)
out5 <- 1/(1+exp(-in5))
output_B = out5[1,1]
``````

My question: is there some way to export the code just above automatically as a sort of function without having to write it manually? My goal is to use it on `PHP`, `JavaScript`, etc.

Thanks!

This question was answered on the following topic:

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.