unit8co/darts

View on GitHub

A python library for user-friendly forecasting and anomaly detection on time series.

Stars: 9.5k
Forks: 1k
Open beginner issues: 0
Indexed issues: 191
Avg merge: 5d 22h
Merged PRs (30d): 14

Dominant language: Python
License: Apache-2.0
Last GitHub push: Sep 18, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: good first issue

Beginner friendly Everything

Open All

191 open issues indexed

[New Model] TiRex-2 zero-shot multivariate forecasting Open

new model

Difficulty 4/5 3-5 days Newbie friendliness 52/100

unit8co/darts#3200 · 4 comments · 2 reactions · Opened Sep 9, 2026
Support cold-start forecasting for Torch models without target history Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

unit8co/darts#3179 · 1 comment · Opened Aug 16, 2026
Safe-by-default model loading Open

core improvement

Difficulty 5/5 Over a week Newbie friendliness 35/100

unit8co/darts#3177 · 6 comments · Opened Aug 13, 2026
Allow TFTExplainer to explain more series than the model batch size Open

Difficulty 4/5 3-5 days Newbie friendliness 58/100

unit8co/darts#3171 · 2 comments · Opened Jul 30, 2026
[Feature] Efficient DTW and clustering Open

triage

Difficulty 4/5 3-5 days Newbie friendliness 30/100

unit8co/darts#3140 · Opened Jun 20, 2026
[QUESTION] Have you considered more advanced outlier detection and value imputation? Open

core improvement feature request

Difficulty 5/5 Over a week Newbie friendliness 25/100

unit8co/darts#3128 · 3 comments · Opened Jun 2, 2026
Add `save()` and `load()` methods to`KMeansScorer` Open

feature request good first issue

Difficulty 3/5 1-2 days Newbie friendliness 55/100

unit8co/darts#3051 · 8 comments · Opened Mar 30, 2026
[FEATURE] Add `TimeSeriesSequence` collection type for more accessible multiple time series representation Open

core improvement feature request

unit8co/darts#3037 · 2 comments · 5 reactions · 1 assignee · Opened Mar 16, 2026
[New Model] Reverso Foundation Model Open

triage

Difficulty 5/5 Over a week Newbie friendliness 35/100

unit8co/darts#3034 · 7 comments · 1 reaction · Opened Mar 3, 2026
Statsmodels Summary addition into Darts Open

triage

Difficulty 5/5 Over a week Newbie friendliness 25/100

unit8co/darts#3030 · Opened Feb 24, 2026
[Feature] add encoder support for torch datasets Open

core improvement feature request

Difficulty 5/5 Over a week Newbie friendliness 25/100

unit8co/darts#3007 · 3 comments · Opened Feb 5, 2026
[Feature] Improve handling & documentation of encoders and categorical static covariates in .fit_from_dataset() Open

documentation good first issue

Difficulty 5/5 Over a week Newbie friendliness 20/100

unit8co/darts#3006 · 3 comments · 1 reaction · Opened Feb 4, 2026
multi_models = True and output_chunk_length > 1 : index future covariates relatively to the forecasted step Open

core improvement feature request

Difficulty 5/5 Over a week Newbie friendliness 38/100

unit8co/darts#2968 · 8 comments · 3 reactions · Opened Dec 11, 2025
Discussion: Foundational / Pre-trained Models in Darts Open

core improvement feature request new model

Difficulty 5/5 Over a week Newbie friendliness 25/100

unit8co/darts#2933 · 14 comments · 2 reactions · Opened Oct 20, 2025
Feature request: allow `predict_likelihood_parameters` for auto-regressive `QuantileRegression` Open

feature request

Difficulty 4/5 3-5 days Newbie friendliness 35/100

unit8co/darts#2912 · 8 comments · Opened Sep 29, 2025
[FEATURE] Allow to fit / calibrate conformal models Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 30/100

unit8co/darts#2886 · 6 comments · 2 reactions · Opened Aug 28, 2025
[FEATURE] Add conformal models for classification-based forecasting models Open

feature request

Difficulty 4/5 3-5 days Newbie friendliness 30/100

unit8co/darts#2884 · 1 comment · Opened Aug 27, 2025
[FEATURE] Add zero-inflated distribution likelihood models Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 35/100

unit8co/darts#2866 · 2 comments · Opened Aug 6, 2025
Add One-Hot Encoder to Time Axis Encoders Open

feature request pr_welcome

Difficulty 4/5 3-5 days Newbie friendliness 48/100

unit8co/darts#2842 · 7 comments · Opened Jul 7, 2025
How are samples drawn from conformal prediction model / quantiles? Open

q&a question

Difficulty 4/5 3-5 days Newbie friendliness 30/100

unit8co/darts#2830 · 4 comments · Opened Jun 23, 2025
Add Reproducible Paper Benchmarks Open

triage

Difficulty 5/5 Over a week Newbie friendliness 25/100

unit8co/darts#2819 · Opened Jun 6, 2025
Needs clarification on self.input_size_total of _VariableSelectionNetwork Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

unit8co/darts#2817 · 2 comments · Opened Jun 5, 2025
[QUESTION] Handling correlations for multi-step probabilistic forecasts Open

question triage

Difficulty 5/5 Over a week Newbie friendliness 30/100

unit8co/darts#2778 · 3 reactions · Opened Apr 17, 2025
Native multilabel support on forecasting classification with CatBoost and XGB Open

improvement

Difficulty 4/5 3-5 days Newbie friendliness 35/100

unit8co/darts#2775 · 1 reaction · Opened Apr 16, 2025
[FEAT] RIN for covariates Open

feature request pr_welcome

unit8co/darts#2758 · 7 comments · 1 assignee · Opened Apr 3, 2025
xLSTM-Mixer for Darts Open

new model

Difficulty 5/5 Over a week Newbie friendliness 30/100

unit8co/darts#2756 · 6 comments · Opened Apr 3, 2025
[BUG] examples/14-transfer-learning.ipynb error on air_train because of missing values Open

bug triage

Difficulty 2/5 1-3 hours Newbie friendliness 62/100

unit8co/darts#2752 · 1 comment · Opened Mar 30, 2025
[QUESTION] Is it possible to compute single point forecasting loss? Open

question triage

Difficulty 4/5 3-5 days Newbie friendliness 30/100

unit8co/darts#2749 · 8 comments · Opened Mar 27, 2025
[QUESTION] How to use TKAN with darts wrapper? Open

question

Difficulty 5/5 Over a week Newbie friendliness 25/100

unit8co/darts#2744 · 1 comment · Opened Mar 24, 2025
[BUG] RIN and Likelihood models Open

bug triage

Difficulty 4/5 3-5 days Newbie friendliness 38/100

unit8co/darts#2743 · 2 comments · Opened Mar 24, 2025
[BUG] RIN does not seem to be scale invariant Open

bug triage

Difficulty 3/5 1-2 days Newbie friendliness 35/100

unit8co/darts#2739 · 4 comments · Opened Mar 19, 2025
TimeSeries.max(axis=0), .min(axis=0) return a meaningless index Open

question

Difficulty 5/5 Over a week Newbie friendliness 35/100

unit8co/darts#2696 · 5 comments · Opened Feb 25, 2025
Add support for TFT feature importance over time Open

feature request pr_welcome

Difficulty 4/5 3-5 days Newbie friendliness 45/100

unit8co/darts#2685 · 8 comments · Opened Feb 19, 2025
[QUESTION] Speed up scoring in ForecastAnomalyModel Open

question

Difficulty 3/5 1-2 days Newbie friendliness 35/100

unit8co/darts#2673 · 8 comments · Opened Feb 14, 2025
[BUG] - TPU training not working in Google Colab Open

bug gpu

Difficulty 4/5 3-5 days Newbie friendliness 25/100

unit8co/darts#2670 · 1 comment · Opened Feb 14, 2025
Nice summary table, why no benchmarking leaderboards? Open

documentation improvement

Difficulty 5/5 Over a week Newbie friendliness 25/100

unit8co/darts#2668 · 2 comments · Opened Feb 13, 2025
Speed up parallel from_group_dataframe Open

improvement

Difficulty 4/5 3-5 days Newbie friendliness 32/100

unit8co/darts#2645 · 1 comment · Opened Jan 19, 2025
Help Reproducing the TIDE Paper Open

question

Difficulty 4/5 3-5 days Newbie friendliness 30/100

unit8co/darts#2644 · 6 comments · Opened Jan 18, 2025
[QUESTION] Error during inference with NBEATS model. Open

question triage

Difficulty 3/5 1-2 days Newbie friendliness 25/100

unit8co/darts#2642 · 8 comments · Opened Jan 17, 2025
[BUG] Uncomplete metrics on callback since darts 0.30 (everything still works with darts 0.29) Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 35/100

unit8co/darts#2637 · 4 comments · Opened Jan 6, 2025
[BUG] - TransformerModel does not work on multiple GPUs - darts [0.31 - 0.32] Open

bug triage

Difficulty 4/5 3-5 days Newbie friendliness 28/100

unit8co/darts#2631 · 2 comments · Opened Dec 22, 2024
[QUESTION] Trouble creating the right dataset for historical backtest with updating covariates Open

question

Difficulty 4/5 3-5 days Newbie friendliness 25/100

unit8co/darts#2575 · 1 comment · Opened Oct 28, 2024
[BUG] optimization is too slow AWS EC2 instances Open

bug triage

Difficulty 4/5 3-5 days Newbie friendliness 30/100

unit8co/darts#2569 · 4 comments · Opened Oct 23, 2024
[QUESTION]Exog vs. Future Covariates: Comparing Statsmodels ARIMA and Darts Open

question

Difficulty 2/5 1-3 hours Newbie friendliness 25/100

unit8co/darts#2539 · 4 comments · Opened Sep 23, 2024
Make torch forecasting model loadable from BufferedReader Open

feature request

Difficulty 3/5 1-2 days Newbie friendliness 50/100

unit8co/darts#2536 · Opened Sep 20, 2024
[FEAT] Add tsmixer-basic Open

improvement

unit8co/darts#2510 · 2 comments · 1 assignee · Opened Aug 25, 2024
[BUG] Training on multiple gpus Open

bug gpu

Difficulty 4/5 3-5 days Newbie friendliness 30/100

unit8co/darts#2499 · 1 comment · Opened Aug 14, 2024
Backtest with custom forecast dates Open

feature request

Difficulty 4/5 3-5 days Newbie friendliness 35/100

unit8co/darts#2497 · 2 comments · Opened Aug 13, 2024
[BUG] LinearRegression get_estimator method's required arguments appear to do nothing Open

improvement

Difficulty 3/5 1-2 days Newbie friendliness 55/100

unit8co/darts#2494 · 4 comments · Opened Aug 9, 2024
TFTExplainer: getting explanations when trained on multiple time series Open

bug good first issue

Difficulty 4/5 3-5 days Newbie friendliness 48/100

unit8co/darts#2489 · 7 comments · Opened Aug 1, 2024

unit8co/darts

Get new issues in your inbox