tsfresh
TimeSynth
tsfresh | TimeSynth | |
---|---|---|
4 | 1 | |
8,096 | 327 | |
0.5% | 0.9% | |
5.4 | 0.0 | |
15 days ago | 6 months ago | |
Jupyter Notebook | Jupyter Notebook | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tsfresh
-
For deep learning practitioners in industry, is the workflow always this annoying? [D]
This is definitely a good thing to try for time-series; you can automate your feature extraction too (eg using https://github.com/blue-yonder/tsfresh ).
-
[D] Incorporating external data in LSTM models for sales forecasting in e-commerce
don't forget your feature engineering -> https://github.com/blue-yonder/tsfresh
-
[R] Approach to identify clusters on a time series
Rather than the exact clustering algorithm, I think the main issue here is the feature extraction for the clustering. https://github.com/blue-yonder/tsfresh might be useful for that.
- Automatic time series feature extraction based on scalable hypothesis tests
TimeSynth
-
What is the best way to generate synthetic OHLC data?
I have the same question so I cant give a direct answer. However, I've been thinking of using SDV and TimeSynth python packages to produce synthetic data for backtesting.
What are some alternatives?
tsflex - Flexible time series feature extraction & processing
SDV - Synthetic data generation for tabular data
Deep_Learning_Machine_Learning_Stock - Deep Learning and Machine Learning stocks represent promising opportunities for both long-term and short-term investors and traders.
ta - Technical Analysis Library using Pandas and Numpy
tempo - API for manipulating time series on top of Apache Spark: lagged time values, rolling statistics (mean, avg, sum, count, etc), AS OF joins, downsampling, and interpolation
Time-Series-Transformer - A data preprocessing package for time series data. Design for machine learning and deep learning.
stingray - Anything can happen in the next half hour (including spectral timing made easy)!
darts - A python library for user-friendly forecasting and anomaly detection on time series.
pycaret - An open-source, low-code machine learning library in Python
tsfel - An intuitive library to extract features from time series.
tsai - Time series Timeseries Deep Learning Machine Learning Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai