hansikaph / time-series-forecasting Goto Github PK
View Code? Open in Web Editor NEWRecurrent Neural Network Implementations for Time Series Forecasting
License: MIT License
Recurrent Neural Network Implementations for Time Series Forecasting
License: MIT License
I read through your paper and mention of Bandara et al paper were clustering approach was used as a part of pre-processing steps (snob algorithm using MML) and in your code there is cluster_results_merger.py at time-series-forecasting/utility_scripts/error_summary_scripts/clusters_results_merger.py but no code for clustering. Can you please add clustering code to get an overall understanding of how cluster were generated and used in cluster_results_merger.py
$ ./utility_scripts/execution_scripts/m3_demo_experiments.sh
Iteration 1 of m3_demo
Traceback (most recent call last):
File "./generic_model_trainer_3.py", line 5, in <module>
from generic_model_tester import testing
File "/home/mulderg/Work/time-series-forecasting/generic_model_tester.py", line 13, in <module>
from rnn_architectures.seq2seq_model.with_decoder.non_moving_window.accumulated_error.seq2seq_model_tester import \
ModuleNotFoundError: No module named 'rnn_architectures.seq2seq_model.with_decoder.non_moving_window.accumulated_error'
Seem to be missing some code:
$ ls -l "`echo "rnn_architectures.seq2seq_model.with_decoder.non_moving_window.accumulated_error" | sed 's/\./*/g'`*"
ls: cannot access 'rnn_architectures*seq2seq_model*with_decoder*non_moving_window*accumulated_error*': No such file or directory
Hi Hansika,
You might want to add the BibTex citation for your paper to the README.md so that it is easy to both find and cite the paper:
@article{hewamalage2019recurrent,
title={Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions},
author={Hewamalage, Hansika and Bergmeir, Christoph and Bandara, Kasun},
journal={arXiv preprint arXiv:1909.00590},
year={2019}
}
$ python ../../train_test_data_splitter.py
Traceback (most recent call last):
File "../../train_test_data_splitter.py", line 8, in <module>
with open(data_file, "r") as original_file, open(train_data_file, "w") as train_out, open(results_file, "w") as results_out:
FileNotFoundError: [Errno 2] No such file or directory: '../../datasets/text_data/M3/M3C.csv'
$ ls -l '../../datasets/text_data/M3/M3C.csv'
ls: cannot access '../../datasets/text_data/M3/M3C.csv': No such file or directory
Problem:
$ ./utility_scripts/execution_scripts/m3_demo_experiments.sh
Iteration 1 of m3_demo
python: can't open file './generic_model_trainer_3.py': [Errno 2] No such file or directory
[...]
Quick fix:
$ ln -s generic_model_trainer.py ./generic_model_trainer_3.py
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.