They would have a better answer than me. ]]>

These functions are more mature than those on these older blog posts.

]]>Thanks for your useful explanation.

I try to analyze tidal components and their amplitude of my ADCP data, but i unfortunately did not record pressure (sealevel). The only data i have are the horizontal flow components (N+E in m/s). Do you know if the tidem() package is also able to analyze this kind of data? ]]>

thanks for providing your functions.

I tried to apply the functions plot.net and gar.fun to my unwrapped nnet model from mlr package as well as to your example models, but i get the following error messages:

1. gar.fun with your example nnet model

Error in gar.fun(“y”, mod1, col = cols, ylab = “Rel. importance”, ylim = c(-1, :

unused arguments (col = cols, ylab = “Rel. importance”, ylim = c(-1, 1))

2. plot.nnet with my nnet model

Error in eval(mod.in$call$formula) : object ‘f’ not found

As I am not a pro in in r, do you have an idea why?

Could it be related to differing package versions?

Best wishes,

Max

I am just wondering whether correlations between dependent and independent variables can be considered, such that among variables showing multicollinearity, the code keeps the independent variable which has the highest correlation with the dependent score. ]]>

Download the development version of the NeuralNetTools package and use the bias_y argument to change the relative location of the bias nodes on the y-axis.

# devtools::install_github('fawda123/NeuralNetTools', ref = 'development') library(NeuralNetTools) library(nnet) data(neuraldat) set.seed(123) mod <- nnet(Y1 ~ X1 + X2 + X3, data = neuraldat, size = 5) plotnet(mod, circle_cex = 7, bias_y = 0.9)]]>