seq2seq-time/README.md

seq2seq-time

Using sequence to sequence interfaces for timeseries regression

	BaselineLast	RANP	LSTM	LSTMSeq2Seq	TransformerSeq2Seq	TransformerProcess
IMOSCurrentsVel	1.63	23.31	19.44	14.52	46.98	7.35
BejingPM25	1.71	1.48	1.41	1.39	2.86	1.44
GasSensor	1.88	-2.24	16.40	-1.53	NaN	0.63
AppliancesEnergyPrediction	1.56	1.31	1.94	1.57	2.33	1.08
MetroInterstateTraffic	1.76	-0.27	-0.17	-0.25	4.15	-0.27

Project Organization

├── LICENSE
├── Makefile           <- Makefile with commands like `make data` or `make train`
├── README.md          <- The top-level README for developers using this project.
├── data
│   ├── interim        <- Intermediate data that has been transformed.
│   ├── processed      <- The final, canonical data sets for modeling.
│   └── raw            <- The original, immutable data dump.
│
├── notebooks          <- Jupyter notebooks. Naming convention is a number (for ordering),
│                         the creator's initials, and a short `-` delimited description, e.g.
│                         `1.0-jqp-initial-data-exploratio    │
│
├── reports            <- Generated analysis as HTML, PDF, LaTeX, etc.
│   └── figures        <- Generated graphics and figures to be used in reporting
│
├── requirements.txt   <- The requirements file for reproducing the analysis environment, e.g.
│                         generated with `pip freeze > requirements.txt`
│
├── setup.py           <- makes project pip installable (pip install -e .) so src can be imported
├── seq2seq_time       <- Source code for use in this project.
│
└── tox.ini            <- tox file with settings for running tox; see tox.readthedocs.io

---

Project based on the cookiecutter data science project template. #cookiecutterdatascience