In this post I show how to get started with Tensorflow and Keras in R.

```
# Install Tensorflow in RStudio
#install_tensorflow()
# Install Keras
#install_packages("keras")
library(tensorflow)
```

`## Warning: package 'tensorflow' was built under R version 3.6.1`

`library(keras)`

`## Warning: package 'keras' was built under R version 3.6.1`

`library(dplyr)`

```
##
## Attaching package: 'dplyr'
```

```
## The following objects are masked from 'package:stats':
##
## filter, lag
```

```
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
```

`library(dummies)`

`## dummies-1.5.6 provided by Decision Patterns`

```
library(tensorflow)
library(keras)
```

This code performs multivariate regression using Tensorflow and keras on the advent of Parkinson disease through sound recordings see Parkinson Speech Dataset with Multiple Types of Sound Recordings Data Set. The clinicianâ€™s motorUPDRS score has to be predicted from the set of features.

```
# Download the Parkinson's data from UCI Machine Learning repository
dataset <- read.csv("https://archive.ics.uci.edu/ml/machine-learning-databases/parkinsons/telemonitoring/parkinsons_updrs.data")
# Set the column names
names(dataset) <- c("subject","age", "sex", "test_time","motor_UPDRS","total_UPDRS","Jitter","Jitter.Abs",
"Jitter.RAP","Jitter.PPQ5","Jitter.DDP","Shimmer", "Shimmer.dB", "Shimmer.APQ3",
"Shimmer.APQ5","Shimmer.APQ11","Shimmer.DDA", "NHR","HNR", "RPDE", "DFA","PPE")
# Remove the column 'subject' as it is not relevant to analysis
dataset1 <- subset(dataset, select = -c(subject))
# Make the column 'sex' as a factor for using dummies
dataset1$sex=as.factor(dataset1$sex)
# Add dummy variables for categorical cariable 'sex'
dataset2 <- dummy.data.frame(dataset1, sep = ".")
```

```
## Warning in model.matrix.default(~x - 1, model.frame(~x - 1), contrasts =
## FALSE): non-list contrasts argument ignored
```

`dataset3 <- na.omit(dataset2)`

```
## Split data 80% training and 20% test
sample_size <- floor(0.8 * nrow(dataset3))
## set the seed to make your partition reproducible
set.seed(12)
train_index <- sample(seq_len(nrow(dataset3)), size = sample_size)
train_dataset <- dataset3[train_index, ]
test_dataset <- dataset3[-train_index, ]
train_data <- train_dataset %>% select(sex.0,sex.1,age, test_time,Jitter,Jitter.Abs,Jitter.PPQ5,Jitter.DDP,
Shimmer, Shimmer.dB,Shimmer.APQ3,Shimmer.APQ11,
Shimmer.DDA,NHR,HNR,RPDE,DFA,PPE)
train_labels <- select(train_dataset,motor_UPDRS)
test_data <- test_dataset %>% select(sex.0,sex.1,age, test_time,Jitter,Jitter.Abs,Jitter.PPQ5,Jitter.DDP,
Shimmer, Shimmer.dB,Shimmer.APQ3,Shimmer.APQ11,
Shimmer.DDA,NHR,HNR,RPDE,DFA,PPE)
test_labels <- select(test_dataset,motor_UPDRS)
```

```
# Normalize the data by subtracting the mean and dividing by the standard deviation
normalize<-function(x) {
y<-(x - mean(x)) / sd(x)
return(y)
}
normalized_train_data <-apply(train_data,2,normalize)
# Convert to matrix
train_labels <- as.matrix(train_labels)
normalized_test_data <- apply(test_data,2,normalize)
test_labels <- as.matrix(test_labels)
```

```
model <- keras_model_sequential()
model %>%
layer_dense(units = 6, activation = 'relu', input_shape = dim(normalized_train_data)[2]) %>%
layer_dense(units = 9, activation = 'relu') %>%
layer_dense(units = 6, activation = 'relu') %>%
layer_dense(units = 1)
# Set the metrics required to be Mean Absolute Error and Mean Squared Error.For regression, the loss is
# mean_squared_error
model %>% compile(
loss = 'mean_squared_error',
optimizer = optimizer_rmsprop(),
metrics = c('mean_absolute_error','mean_squared_error')
)
# Fit the model
# Use the test data for validation
history <- model %>% fit(
normalized_train_data, train_labels,
epochs = 30, batch_size = 128,
validation_data = list(normalized_test_data,test_labels)
)
```

`plot(history)`

```
## Registered S3 methods overwritten by 'ggplot2':
## method from
## [.quosures rlang
## c.quosures rlang
## print.quosures rlang
```

```

It can be seen that the mean absolute error is on an average about +/- 4.0. The validation error also is about the same. This can be reduced by playing around with the hyperparamaters and increasing the number of iterations

This is a simple binary classification problem from UCI Machine Learning repository and deals with data on Breast cancer from the Univ. of Wisconsin Breast Cancer Wisconsin (Diagnostic) Data Set

```
# Read the data for Breast cancer (Wisconsin)
dataset <- read.csv("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data")
# Rename the columns
names(dataset) <- c("id","thickness", "cellsize", "cellshape","adhesion","epicellsize",
"barenuclei","chromatin","normalnucleoli","mitoses","class")
# Remove the columns id and class
dataset1 <- subset(dataset, select = -c(id, class))
dataset2 <- na.omit(dataset1)
# Convert the column to numeric
dataset2$barenuclei <- as.numeric(dataset2$barenuclei)
```

```
train_data <-apply(dataset2,2,normalize)
train_labels <- as.matrix(select(dataset,class))
# Set the target variables as 0 or 1 as it binary classification
train_labels[train_labels==2,]=0
train_labels[train_labels==4,]=1
```

```
model <- keras_model_sequential()
model %>%
layer_dense(units = 6, activation = 'relu', input_shape = dim(train_data)[2]) %>%
layer_dense(units = 9, activation = 'relu') %>%
layer_dense(units = 6, activation = 'relu') %>%
layer_dense(units = 1)
# Since this is a binary classification we use binary cross entropy
model %>% compile(
loss = 'binary_crossentropy',
optimizer = optimizer_rmsprop(),
metrics = c('accuracy') # Metrics is accuracy
)
```

```
history <- model %>% fit(
train_data, train_labels,
epochs = 30, batch_size = 128,
validation_split = 0.2
)
```

`plot(history)`

The following code uses Tensorflow to learn MNISTâ€™s handwritten digits ### Load MNIST data

```
mnist <- dataset_mnist()
x_train <- mnist$train$x
y_train <- mnist$train$y
x_test <- mnist$test$x
y_test <- mnist$test$y
```

```
# Reshape the array
x_train <- array_reshape(x_train, c(nrow(x_train), 784))
x_test <- array_reshape(x_test, c(nrow(x_test), 784))
# Rescale
x_train <- x_train / 255
x_test <- x_test / 255
```

```
y_train <- to_categorical(y_train, 10)
y_test <- to_categorical(y_test, 10)
```

Use the softmax activation for recognizing 10 digits and categorical cross entropy for loss

```
model <- keras_model_sequential()
model %>%
layer_dense(units = 256, activation = 'relu', input_shape = c(784)) %>%
layer_dense(units = 128, activation = 'relu') %>%
layer_dense(units = 10, activation = 'softmax') # Use softmax
model %>% compile(
loss = 'categorical_crossentropy',
optimizer = optimizer_rmsprop(),
metrics = c('accuracy')
)
```

*Note*: A smaller number of epochs has been used. For better performance increase number of epochs

```
history <- model %>% fit(
x_train, y_train,
epochs = 20, batch_size = 128,
validation_data = list(x_test,y_test)
)
```

`plot(history)`