MXNet_Regression_FeedForwardNeuralNet.R

# -------------------------------------------------------------------------------------------
# -------------------------------------------------------------------------------------------
# Develop a Neural Network with MXNet in Five Minutes (Regression)
# R Notebook Author: @Korkrid Akepanidtaworn
# Tutorial from MXNet Community
# Source: https://mxnet.incubator.apache.org/tutorials/r/fiveMinutesNeuralNetwork.html
# -------------------------------------------------------------------------------------------
# -------------------------------------------------------------------------------------------
library(mlbench)
library(tidyverse)
library(caret)

# To install MXNet, you need to run these 4 lines of codes
cran <- getOption("repos")
cran["dmlc"] <- "https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/R/CRAN/"
options(repos = cran)
# install.packages("mxnet")
library(mxnet)

# -------------------------------------------------------------------------------------------
# -------------------------------------------------------------------------------------------
# Load Data
# -------------------------------------------------------------------------------------------
# -------------------------------------------------------------------------------------------
data(BostonHousing, package="mlbench")

# -------------------------------------------------------------------------------------------
# Split Training/Testing 80:20
# -------------------------------------------------------------------------------------------
# -------------------------------------------------------------------------------------------

# 80% of the sample size
smp_size <- floor(0.80 * nrow(BostonHousing))

# Set the seed to make your partition reproducible
set.seed(1234)
train_ind <- sample(seq_len(nrow(BostonHousing)), size = smp_size)

train <- BostonHousing[train_ind, ]
test <- BostonHousing[-train_ind, ]

train_x = as.matrix(train[, 1:13])
class(train_x) <- "numeric"
train_y = as.numeric(as.matrix(train[, 14]))
test_x = as.matrix(test[, 1:13])
class(test_x) <- "numeric"
test_y = as.numeric(as.matrix(test[, 14]))


# Define the input data
data <- mx.symbol.Variable("data")
# A fully connected hidden layer
# data: input source
# num_hidden: number of neurons in this hidden layer
fc1 <- mx.symbol.FullyConnected(data, num_hidden=1)

# Use linear regression for the output layer
lro <- mx.symbol.LinearRegressionOutput(fc1)

mx.set.seed(1234)
model <- mx.model.FeedForward.create(symbol = lro, 
                                     X=train_x, 
                                     y=train_y,
                                     ctx=mx.cpu(),
                                     num.round=50,
                                     array.batch.size=20,
                                     learning.rate=2e-6,
                                     momentum=0.9,
                                     eval.metric= mx.metric.rmse)

## Auto detect layout of input matrix, use rowmajor.
## Start training with 1 devices
## [1] Train-rmse=16.063282524034
## [2] Train-rmse=12.2792375712573
## [3] Train-rmse=11.1984634005885
## [4] Train-rmse=10.2645236892904
## [5] Train-rmse=9.49711005504284
## [6] Train-rmse=9.07733734175182
## [7] Train-rmse=9.07884450847991
## [8] Train-rmse=9.10463850277417
## [9] Train-rmse=9.03977049028532
## [10] Train-rmse=8.96870685004475
## [11] Train-rmse=8.93113287361574
## [12] Train-rmse=8.89937257821847
## [13] Train-rmse=8.87182096922953
## [14] Train-rmse=8.84476075083586
## [15] Train-rmse=8.81464673014974
## [16] Train-rmse=8.78672567900196
## [17] Train-rmse=8.76265872846474
## [18] Train-rmse=8.73946101419974
## [19] Train-rmse=8.71651926303267
## [20] Train-rmse=8.69457600919277
## [21] Train-rmse=8.67354928674563
## [22] Train-rmse=8.65328755392436
## [23] Train-rmse=8.63378039680078
## [24] Train-rmse=8.61488162586984
## [25] Train-rmse=8.5965105183022
## [26] Train-rmse=8.57868133563275
## [27] Train-rmse=8.56135851937663
## [28] Train-rmse=8.5444819772098
## [29] Train-rmse=8.52802114610432
## [30] Train-rmse=8.5119504512622
## [31] Train-rmse=8.49624261719241
## [32] Train-rmse=8.48087453238701
## [33] Train-rmse=8.46582689119887
## [34] Train-rmse=8.45107881002491
## [35] Train-rmse=8.43661331401712
## [36] Train-rmse=8.42241575909639
## [37] Train-rmse=8.40847217331365
## [38] Train-rmse=8.39476931796395
## [39] Train-rmse=8.38129658373974
## [40] Train-rmse=8.36804269059018
## [41] Train-rmse=8.35499817678397
## [42] Train-rmse=8.34215505742154
## [43] Train-rmse=8.32950441908131
## [44] Train-rmse=8.31703985777311
## [45] Train-rmse=8.30475363906755
## [46] Train-rmse=8.29264031506106
## [47] Train-rmse=8.28069372820073
## [48] Train-rmse=8.26890902770415
## [49] Train-rmse=8.25728089053853
## [50] Train-rmse=8.24580511500735

pred_test = predict(model, test_x) # Array of Regression Predictions
pred_test = as.numeric(t(pred_test)) # Vector of Predictions
sqrt(mean((pred_test - test_y)^2)) # RMSE = 9.452149