nn_twolayer: Neural Network with Two Layers
In pchest/simpleNN: Provides Accessable Deep Learning Tools

Description Usage Arguments

This function is a wrapper for a two layered neural network written using the Keras Package. It takes a

nn_twolayer(Text, Codes, Words = 10000, Seed = 17,
  Weighting = "count", Train_prop = 0.5, Epochs = 3, Units = 512,
  Batch = 32, Dropout = 0.2, Valsplit = 0.1,
  Metric = "binary_accuracy", Loss = "binary_crossentropy",
  Optimizer = "adam", CM = TRUE, Model = FALSE)

`Text`	The text that will be used as training and test data.
`Codes`	The codes that will be used as outcomes to be predicted by the NN model.
`Words`	The number of top words included in document feature matrixes used as training and testing data.
`Seed`	The seed used in the model. Defaults to 17
`Weighting`	The type of feature weighting used in the document feature matrix. I.e., count and tfidf.
`Train_prop`	The proportion of the data used to train the model. The remainder is used as test data.
`Epochs`	The number of epochs used in the NN model.
`Units`	The number of network nodes used in the first layer of the sequential model
`Batch`	The number of batches estimated
`Dropout`	A floating variable bound between 0 and 1. It determines the rate at which units are dropped for the linear tranformation of the inputs.
`Metric`	Metric used to train algorithm
`Loss`	Metric used to train algorithm
`Optimizer`	Optimizer used to fit model to training data
`CM`	A logical variable that indicates whether a confusion matrix will be output from the function
`Model`	A logical variable that indicates whether the trained model should be included in the output of this function
`ValSplit`	The validation split of the data used in the training of the LSTM model