Skip to main content
Ctrl+K
darts  documentation - Home darts  documentation - Home
  • Quickstart
  • User Guide
  • API Reference
  • Examples
  • Release Notes
  • GitHub
  • Twitter
  • Quickstart
  • User Guide
  • API Reference
  • Examples
  • Release Notes
  • GitHub
  • Twitter

Section Navigation

  • Anomaly Detection
    • Anomaly Aggregators
      • AND Aggregator
      • Ensemble scikit-learn aggregator
      • OR Aggregator
    • Anomaly Models
      • Filtering Anomaly Model
      • Forecasting Anomaly Model
    • Anomaly Detectors
      • Interquartile Range (IQR) Detector
      • Quantile Detector
      • Threshold Detector
    • Anomaly Scorers
      • Difference Scorer
      • k-means Scorer
      • NLL Cauchy Scorer
      • NLL Exponential Scorer
      • NLL Gamma Scorer
      • NLL Gaussian Scorer
      • NLL Laplace Scorer
      • NLL Poisson Scorer
      • Norm Scorer
      • PyOD Scorer
      • Wasserstein Scorer
    • Utils for Anomaly Detection
  • Data Processing
    • Dynamic Time Warping (DTW)
      • DTW Cost Matrix
      • Dynamic Time Warping (DTW)
      • DTW Windows
    • Time Axis Encoders
      • Encoder Base Classes
      • Time Axes Encoders
    • Data Transformers
      • Data Transformer Base Class
      • Box-Cox Transformer
      • Differencing Transformer
      • Fittable Data Transformer Base Class
      • Invertible Data Transformer Base Class
      • Mapper and InvertibleMapper
      • Mixed-data sampling (MIDAS) Transformer
      • Missing Values Filler
      • Hierarchical Reconciliation
      • Scaler
      • Static Covariates Transformer
      • Window Transformer
    • Pipeline
  • Datasets
    • Datasets
  • Explainability
    • Explainability Result
    • Shap Explainer for SKLearnModels
    • TFTModel Explainer
  • Metrics
    • Metrics
    • Metric Utils
  • Models
    • Filtering Models
      • Gaussian Process Filter
      • Kalman Filter
      • Moving Average Filter
    • Forecasting Models
      • ARIMA
      • Baseline Models
      • Block Recurrent Neural Networks
      • CatBoost Models
      • Chronos-2
      • Conformal Models
      • D-Linear
      • Exponential Smoothing
      • Fast Fourier Transform
      • Global Baseline Models (Naive)
      • Kalman Filter Forecaster
      • LightGBM Models
      • Linear Regression Model
      • N-BEATS
      • N-HiTS
      • N-Linear
      • Facebook Prophet
      • Random Forest
      • Regression Ensemble Model
      • Recurrent Neural Networks
      • AutoARIMA
      • AutoCES
      • AutoETS
      • AutoMFLES
      • AutoTBATS
      • AutoTheta
      • Croston Method
      • StatsForecastModel
      • TBATS
      • SKLearn-Like Models
      • Temporal Convolutional Network
      • Temporal Fusion Transformer (TFT)
      • TFTModel Sub-Modules
      • Theta Method
      • Time-series Dense Encoder (TiDE)
      • Transformer Model
      • Time-Series Mixer (TSMixer)
      • VARIMA
      • XGBoost Models
  • Utils
    • TimeSeries Datasets
      • Datasets for TorchForecastingModel
        • Inference Datasets
        • Training Datasets
    • Likelihood Models
      • Likelihoods for SKLearnModel
      • Likelihoods for StatsForecastModel
      • Likelihoods for TorchForecastingModel
    • Callbacks for TorchForecastingModel
    • PyTorch Loss Functions
    • Utils for filling missing values
    • Model selection utilities
    • TimeSeries Statistics
    • Utils for TimeSeries generation
    • Utils for Pytorch and its usage
    • Additional util functions
  • Timeseries
  • Darts

Darts#

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

  • Anomaly Detection

  • Data Processing

  • Datasets

  • Explainability

  • Metrics

  • Models

  • Utils

  • Timeseries

previous

Frequently Asked Questions

next

Anomaly Detection

This Page

  • Show Source

© Copyright 2020 - 2025, Unit8 SA (Apache 2.0 License).

Created using Sphinx 8.1.3.

Built with the PyData Sphinx Theme 0.16.1.