nni
tsflex
| nni | tsflex | |
|---|---|---|
| 5 | 3 | |
| 13,765 | 363 | |
| 0.6% | 1.9% | |
| 6.7 | 6.3 | |
| 2 months ago | 16 days ago | |
| Python | Python | |
| 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.
nni
- Filter Pruning for PyTorch
-
Automated Machine Learning (AutoML) - 9 Different Ways with Microsoft AI
For a complete tutorial, navigate to this Jupyter Notebook: https://github.com/microsoft/nni/blob/master/examples/notebooks/tabular_data_classification_in_AML.ipynb
-
[D] Efficient ways of choosing number of layers/neurons in a neural network
optuna, hyperopt, nni, plenty of less-known tools too.
-
Top 10 Developer Trends, Sun Oct 18 2020
microsoft / nni
tsflex
-
[P] tsflex: flexible and efficient feature extraction for time series
tsflex its core functionality is strided-window feature extraction. This toolkit focusses on being flexible (e.g., few assumptions about sequence data, integration with other packages) and efficient (in both time & memory consumption -> see benchmark).
-
Request - a good book for anomaly detection on time series
If you plan to transform your time series data in feature vectors, I would suggest to use tsflex (a rather new package) instead of TSfresh. tsflex is imo more convenient to use & multitudes more efficient for window-stride feature extraction.
What are some alternatives?
optuna - A hyperparameter optimization framework
tsfresh - Automatic extraction of relevant features from time series:
FLAML - A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.
sspipe - Simple Smart Pipe: python productivity-tool for rapid data manipulation
autogluon - Fast and Accurate ML in 3 Lines of Code
temporian - Temporian is an open-source Python library for preprocessing ⚡ and feature engineering 🛠 temporal data 📈 for machine learning applications 🤖
AutoML - This is a collection of our NAS and Vision Transformer work. [Moved to: https://github.com/microsoft/Cream]
MultiModalStory-demo - FairyTailor: Multimodal Generative Framework for Storytelling
hyperopt - Distributed Asynchronous Hyperparameter Optimization in Python
prosto - Prosto is a data processing toolkit radically changing how data is processed by heavily relying on functions and operations with functions - an alternative to map-reduce and join-groupby
archai - Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.
orange - 🍊 :bar_chart: :bulb: Orange: Interactive data analysis