neural network configuration and tensorflow model hyperparameters
extra instance properties
Predicts new dependent variables
returns tensorflow prediction
Adds dense layers to tensorflow classification model
independent variables
dependent variables
model dense layer parameters
Loads a saved tensoflow / keras model, this is an alias for
tensorflow load model options
tensorflow model
Returns prediction values from tensorflow model
predicted model values
saves a tensorflow model, this is an alias for
tensorflow save model options
tensorflow model
Creates dataset data
array of values
number of values in each feature
returns x matrix and y matrix for model trainning
Drops columns by array index
data set to drop columns
array of column indexes
matrix with dropped columns
Calculates which columns to drop by index
number of independent variables
look backs
future iterations (currently only 1 supported)
array indexes to drop
Returns the shape of an input matrix
input matrix
returns the shape of a matrix (e.g. [2,2])
Returns data for predicting values
Reshape input to be [samples, time steps, features]
dataset array of values
returns proper timeseries forecasting shape
Reshapes an array
input array
shape array
returns a matrix with the defined shape
Converts data set to supervised labels for forecasting, the first column must be the dependent variable
data set
look backs
future iterations (only 1 supported)
multivariate dataset for time series
Long Short Term Memory Multivariate Time Series with Tensorflow