where time series is observed & valued

Wenjie Du

Elite
@WenjieDu

AI Researcher <​Time Series, Regulatory Science​> More awesome private repos will open source! Follow me to get notified ;-)

PyPOTS. A Python toolkit/library for reality-centric machine/deep learning & data mining on partially-observed time series, with 50+ SOTA neural network models for scientific analysis tasks (imputation, classification, clustering, forecasting, anomaly detection, cleaning) on incomplete industrial irregularly-sampled multivariate TS with NaN missing values

2k

SAITS. The official PyTorch implementation of the paper "SAITS: Self-Attention-based Imputation for Time Series". A fast and state-of-the-art (SOTA) deep-learning neural network model for efficient time-series imputation (impute multivariate incomplete time series containing NaN missing data/values with machine learning). https://arxiv.org/abs/2202.08516

513

Awesome_Imputation. Awesome Deep Learning for Time-Series Imputation, including an unmissable paper and tool list about applying neural networks to impute incomplete time series containing NaN missing values/data

423

TSDB. a Python toolbox loads 173 public time series datasets for machine/deep learning with a single line of code. Datasets from multiple domains including healthcare, financial, power, traffic, weather, and etc.

239

BrewPOTS. The tutorials for PyPOTS, guide you to model partially-observed time series datasets.

126

PyGrinder. PyGrinder: a Python toolkit for grinding data beans into the incomplete for real-world data simulation by introducing missing values with different missingness patterns, including MCAR (complete at random), MAR (at random), MNAR (not at random), sub sequence missing, and block missing

68

BenchPOTS. a Python toolbox for benchmarking machine learning on POTS (Partially-Observed Time Series), supporting processing pipelines of 182 public time-series datasets

44

AI4TS. AI for time series analysis in only 1 line of code

13

Google_Scholar_Badge_Generator. This repository helps you automatically generate citation badges of articles/profiles on Google Scholar. With GitHub actions, you can make yourself a GoogleScholar version of shields.io

12

TimeSeries_Analysis_Skills. Awesome Time-Series Analysis (TSA) Skills for AI Agents, supporting tasks of imputation, forecasting, classification, clustering, anomaly detection

8

eye_game. A python module for parsing human gaze direction

6

WenjieDu.

6

DevNet. An implementation of Deviation Network with a case on the credit card fraud dataset.

3

awesome-time-series. list of papers, code, and other resources

1
14
Apply