Skip to content

Using a multi-perception neural network perform time series forecasting. Here feed forward technique is used.

Notifications You must be signed in to change notification settings

maheshakya/Time-Series-Forcasting-with-Neural-Networks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 

Repository files navigation

Usage:

Import forcasting module

from Forecast import create_series

create_series() function has following parameters:

  1. in_array : time series data (numpy array or list of values)
  2. window_size : window size for feed forward network
  3. period : number of periods to predict
  4. minV : assumed minimum value for the time series
  5. maxV : assumed maximum value for the time series
  6. layer_nodes : list of values for the number of node for each layer in the neural network(Should be more than or equal to 2 values in the list)
  7. sigmoid : name of the sigmoid function('tanh' or 'logistic')
  8. epochs : number of iterations in the neural network

you can either edit these values in the code itself

time_series = [some series] create_series(time_series, 10, 15, 0, 100, [3,5,7], 'tanh', 700000)

About

Using a multi-perception neural network perform time series forecasting. Here feed forward technique is used.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages