pytorch-forecasting

Time series forecasting with PyTorch

Stars: 4049

Visit

PyTorch Forecasting is a PyTorch-based package designed for state-of-the-art timeseries forecasting using deep learning architectures. It offers a high-level API and leverages PyTorch Lightning for efficient training on GPU or CPU with automatic logging. The package aims to simplify timeseries forecasting tasks by providing a flexible API for professionals and user-friendly defaults for beginners. It includes features such as a timeseries dataset class for handling data transformations, missing values, and subsampling, various neural network architectures optimized for real-world deployment, multi-horizon timeseries metrics, and hyperparameter tuning with optuna. Built on pytorch-lightning, it supports training on CPUs, single GPUs, and multiple GPUs out-of-the-box.

README:

PyTorch Forecasting is a PyTorch-based package for forecasting with state-of-the-art deep learning architectures. It provides a high-level API and uses PyTorch Lightning to scale training on GPU or CPU, with automatic logging.

	Documentation · Tutorials · Release Notes
Open Source
Community
CI/CD
Code

Our article on Towards Data Science introduces the package and provides background information.

PyTorch Forecasting aims to ease state-of-the-art timeseries forecasting with neural networks for real-world cases and research alike. The goal is to provide a high-level API with maximum flexibility for professionals and reasonable defaults for beginners. Specifically, the package provides

A timeseries dataset class which abstracts handling variable transformations, missing values, randomized subsampling, multiple history lengths, etc.
A base model class which provides basic training of timeseries models along with logging in tensorboard and generic visualizations such actual vs predictions and dependency plots
Multiple neural network architectures for timeseries forecasting that have been enhanced for real-world deployment and come with in-built interpretation capabilities
Multi-horizon timeseries metrics
Hyperparameter tuning with optuna

The package is built on pytorch-lightning to allow training on CPUs, single and multiple GPUs out-of-the-box.

Installation

If you are working on windows, you need to first install PyTorch with

pip install torch -f https://download.pytorch.org/whl/torch_stable.html.

Otherwise, you can proceed with

pip install pytorch-forecasting

Alternatively, you can install the package via conda

conda install pytorch-forecasting pytorch -c pytorch>=1.7 -c conda-forge

PyTorch Forecasting is now installed from the conda-forge channel while PyTorch is install from the pytorch channel.

To use the MQF2 loss (multivariate quantile loss), also install pip install pytorch-forecasting[mqf2]

Documentation

Visit https://pytorch-forecasting.readthedocs.io to read the documentation with detailed tutorials.

Available models

The documentation provides a comparison of available models.

Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting which outperforms DeepAR by Amazon by 36-69% in benchmarks
N-BEATS: Neural basis expansion analysis for interpretable time series forecasting which has (if used as ensemble) outperformed all other methods including ensembles of traditional statical methods in the M4 competition. The M4 competition is arguably the most important benchmark for univariate time series forecasting.
N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting which supports covariates and has consistently beaten N-BEATS. It is also particularly well-suited for long-horizon forecasting.
DeepAR: Probabilistic forecasting with autoregressive recurrent networks which is the one of the most popular forecasting algorithms and is often used as a baseline
Simple standard networks for baselining: LSTM and GRU networks as well as a MLP on the decoder
A baseline model that always predicts the latest known value

To implement new models or other custom components, see the How to implement new models tutorial. It covers basic as well as advanced architectures.

Usage example

Networks can be trained with the PyTorch Lighning Trainer on pandas Dataframes which are first converted to a TimeSeriesDataSet.

# imports for training
import lightning.pytorch as pl
from lightning.pytorch.loggers import TensorBoardLogger
from lightning.pytorch.callbacks import EarlyStopping, LearningRateMonitor
# import dataset, network to train and metric to optimize
from pytorch_forecasting import TimeSeriesDataSet, TemporalFusionTransformer, QuantileLoss
from lightning.pytorch.tuner import Tuner

# load data: this is pandas dataframe with at least a column for
# * the target (what you want to predict)
# * the timeseries ID (which should be a unique string to identify each timeseries)
# * the time of the observation (which should be a monotonically increasing integer)
data = ...

# define the dataset, i.e. add metadata to pandas dataframe for the model to understand it
max_encoder_length = 36
max_prediction_length = 6
training_cutoff = "YYYY-MM-DD"  # day for cutoff

training = TimeSeriesDataSet(
    data[lambda x: x.date <= training_cutoff],
    time_idx= ...,  # column name of time of observation
    target= ...,  # column name of target to predict
    group_ids=[ ... ],  # column name(s) for timeseries IDs
    max_encoder_length=max_encoder_length,  # how much history to use
    max_prediction_length=max_prediction_length,  # how far to predict into future
    # covariates static for a timeseries ID
    static_categoricals=[ ... ],
    static_reals=[ ... ],
    # covariates known and unknown in the future to inform prediction
    time_varying_known_categoricals=[ ... ],
    time_varying_known_reals=[ ... ],
    time_varying_unknown_categoricals=[ ... ],
    time_varying_unknown_reals=[ ... ],
)

# create validation dataset using the same normalization techniques as for the training dataset
validation = TimeSeriesDataSet.from_dataset(training, data, min_prediction_idx=training.index.time.max() + 1, stop_randomization=True)

# convert datasets to dataloaders for training
batch_size = 128
train_dataloader = training.to_dataloader(train=True, batch_size=batch_size, num_workers=2)
val_dataloader = validation.to_dataloader(train=False, batch_size=batch_size, num_workers=2)

# create PyTorch Lighning Trainer with early stopping
early_stop_callback = EarlyStopping(monitor="val_loss", min_delta=1e-4, patience=1, verbose=False, mode="min")
lr_logger = LearningRateMonitor()
trainer = pl.Trainer(
    max_epochs=100,
    accelerator="auto",  # run on CPU, if on multiple GPUs, use strategy="ddp"
    gradient_clip_val=0.1,
    limit_train_batches=30,  # 30 batches per epoch
    callbacks=[lr_logger, early_stop_callback],
    logger=TensorBoardLogger("lightning_logs")
)

# define network to train - the architecture is mostly inferred from the dataset, so that only a few hyperparameters have to be set by the user
tft = TemporalFusionTransformer.from_dataset(
    # dataset
    training,
    # architecture hyperparameters
    hidden_size=32,
    attention_head_size=1,
    dropout=0.1,
    hidden_continuous_size=16,
    # loss metric to optimize
    loss=QuantileLoss(),
    # logging frequency
    log_interval=2,
    # optimizer parameters
    learning_rate=0.03,
    reduce_on_plateau_patience=4
)
print(f"Number of parameters in network: {tft.size()/1e3:.1f}k")

# find the optimal learning rate
res = Tuner(trainer).lr_find(
    tft, train_dataloaders=train_dataloader, val_dataloaders=val_dataloader, early_stop_threshold=1000.0, max_lr=0.3,
)
# and plot the result - always visually confirm that the suggested learning rate makes sense
print(f"suggested learning rate: {res.suggestion()}")
fig = res.plot(show=True, suggest=True)
fig.show()

# fit the model on the data - redefine the model with the correct learning rate if necessary
trainer.fit(
    tft, train_dataloaders=train_dataloader, val_dataloaders=val_dataloader,
)

For Tasks:

Click tags to check more tools for each tasks

predict sales forecast stock prices analyze trends predict demand optimize resource allocation

For Jobs:

data scientist machine learning engineer forecasting analyst research scientist ai engineer

Alternative AI tools for pytorch-forecasting

Similar Open Source Tools

pytorch-forecasting

github

: 4.0k

pytorch-forecasting

PyTorch Forecasting is a PyTorch-based package for time series forecasting with state-of-the-art network architectures. It offers a high-level API for training networks on pandas data frames and utilizes PyTorch Lightning for scalable training on GPUs and CPUs. The package aims to simplify time series forecasting with neural networks by providing a flexible API for professionals and default settings for beginners. It includes a timeseries dataset class, base model class, multiple neural network architectures, multi-horizon timeseries metrics, and hyperparameter tuning with optuna. PyTorch Forecasting is built on pytorch-lightning for easy training on various hardware configurations.

github

: 3.8k

mlflow

MLflow is a platform to streamline machine learning development, including tracking experiments, packaging code into reproducible runs, and sharing and deploying models. MLflow offers a set of lightweight APIs that can be used with any existing machine learning application or library (TensorFlow, PyTorch, XGBoost, etc), wherever you currently run ML code (e.g. in notebooks, standalone applications or the cloud). MLflow's current components are: * `MLflow Tracking `_: An API to log parameters, code, and results in machine learning experiments and compare them using an interactive UI. * `MLflow Projects `_: A code packaging format for reproducible runs using Conda and Docker, so you can share your ML code with others. * `MLflow Models `_: A model packaging format and tools that let you easily deploy the same model (from any ML library) to batch and real-time scoring on platforms such as Docker, Apache Spark, Azure ML and AWS SageMaker. * `MLflow Model Registry `_: A centralized model store, set of APIs, and UI, to collaboratively manage the full lifecycle of MLflow Models.

github

: 19.1k

flashinfer

FlashInfer is a library for Language Languages Models that provides high-performance implementation of LLM GPU kernels such as FlashAttention, PageAttention and LoRA. FlashInfer focus on LLM serving and inference, and delivers state-the-art performance across diverse scenarios.

github

: 1.7k

only_train_once

Only Train Once (OTO) is an automatic, architecture-agnostic DNN training and compression framework that allows users to train a general DNN from scratch or a pretrained checkpoint to achieve high performance and slimmer architecture simultaneously in a one-shot manner without fine-tuning. The framework includes features for automatic structured pruning and erasing operators, as well as hybrid structured sparse optimizers for efficient model compression. OTO provides tools for pruning zero-invariant group partitioning, constructing pruned models, and visualizing pruning and erasing dependency graphs. It supports the HESSO optimizer and offers a sanity check for compliance testing on various DNNs. The repository also includes publications, installation instructions, quick start guides, and a roadmap for future enhancements and collaborations.

github

: 261

HAMi

HAMi is a Heterogeneous AI Computing Virtualization Middleware designed to manage Heterogeneous AI Computing Devices in a Kubernetes cluster. It allows for device sharing, device memory control, device type specification, and device UUID specification. The tool is easy to use and does not require modifying task YAML files. It includes features like hard limits on device memory, partial device allocation, streaming multiprocessor limits, and core usage specification. HAMi consists of components like a mutating webhook, scheduler extender, device plugins, and in-container virtualization techniques. It is suitable for scenarios requiring device sharing, specific device memory allocation, GPU balancing, low utilization optimization, and scenarios needing multiple small GPUs. The tool requires prerequisites like NVIDIA drivers, CUDA version, nvidia-docker, Kubernetes version, glibc version, and helm. Users can install, upgrade, and uninstall HAMi, submit tasks, and monitor cluster information. The tool's roadmap includes supporting additional AI computing devices, video codec processing, and Multi-Instance GPUs (MIG).

github

: 1.1k

DotRecast

DotRecast is a C# port of Recast & Detour, a navigation library used in many AAA and indie games and engines. It provides automatic navmesh generation, fast turnaround times, detailed customization options, and is dependency-free. Recast Navigation is divided into multiple modules, each contained in its own folder: - DotRecast.Core: Core utils - DotRecast.Recast: Navmesh generation - DotRecast.Detour: Runtime loading of navmesh data, pathfinding, navmesh queries - DotRecast.Detour.TileCache: Navmesh streaming. Useful for large levels and open-world games - DotRecast.Detour.Crowd: Agent movement, collision avoidance, and crowd simulation - DotRecast.Detour.Dynamic: Robust support for dynamic nav meshes combining pre-built voxels with dynamic objects which can be freely added and removed - DotRecast.Detour.Extras: Simple tool to import navmeshes created with A* Pathfinding Project - DotRecast.Recast.Toolset: All modules - DotRecast.Recast.Demo: Standalone, comprehensive demo app showcasing all aspects of Recast & Detour's functionality - Tests: Unit tests Recast constructs a navmesh through a multi-step mesh rasterization process: 1. First Recast rasterizes the input triangle meshes into voxels. 2. Voxels in areas where agents would not be able to move are filtered and removed. 3. The walkable areas described by the voxel grid are then divided into sets of polygonal regions. 4. The navigation polygons are generated by re-triangulating the generated polygonal regions into a navmesh. You can use Recast to build a single navmesh, or a tiled navmesh. Single meshes are suitable for many simple, static cases and are easy to work with. Tiled navmeshes are more complex to work with but better support larger, more dynamic environments. Tiled meshes enable advanced Detour features like re-baking, hierarchical path-planning, and navmesh data-streaming.

github

: 517

nixtla

Nixtla is a production-ready generative pretrained transformer for time series forecasting and anomaly detection. It can accurately predict various domains such as retail, electricity, finance, and IoT with just a few lines of code. TimeGPT introduces a paradigm shift with its standout performance, efficiency, and simplicity, making it accessible even to users with minimal coding experience. The model is based on self-attention and is independently trained on a vast time series dataset to minimize forecasting error. It offers features like zero-shot inference, fine-tuning, API access, adding exogenous variables, multiple series forecasting, custom loss function, cross-validation, prediction intervals, and handling irregular timestamps.

github

: 2.3k

lima

LIMA is a multilingual linguistic analyzer developed by the CEA LIST, LASTI laboratory. It is Free Software available under the MIT license. LIMA has state-of-the-art performance for more than 60 languages using deep learning modules. It also includes a powerful rules-based mechanism called ModEx for extracting information in new domains without annotated data.

github

: 102

TornadoVM

TornadoVM is a plug-in to OpenJDK and GraalVM that allows programmers to automatically run Java programs on heterogeneous hardware. TornadoVM targets OpenCL, PTX and SPIR-V compatible devices which include multi-core CPUs, dedicated GPUs (Intel, NVIDIA, AMD), integrated GPUs (Intel HD Graphics and ARM Mali), and FPGAs (Intel and Xilinx).

github

: 1.2k

MineStudio

MineStudio is a simple and efficient Minecraft development kit for AI research. It contains tools and APIs for developing Minecraft AI agents, including a customizable simulator, trajectory data structure, policy models, offline and online training pipelines, inference framework, and benchmarking automation. The repository is under development and welcomes contributions and suggestions.

github

: 154

swiftide

Swiftide is a fast, streaming indexing and query library tailored for Retrieval Augmented Generation (RAG) in AI applications. It is built in Rust, utilizing parallel, asynchronous streams for blazingly fast performance. With Swiftide, users can easily build AI applications from idea to production in just a few lines of code. The tool addresses frustrations around performance, stability, and ease of use encountered while working with Python-based tooling. It offers features like fast streaming indexing pipeline, experimental query pipeline, integrations with various platforms, loaders, transformers, chunkers, embedders, and more. Swiftide aims to provide a platform for data indexing and querying to advance the development of automated Large Language Model (LLM) applications.

github

: 300

Quantus

Quantus is a toolkit designed for the evaluation of neural network explanations. It offers more than 30 metrics in 6 categories for eXplainable Artificial Intelligence (XAI) evaluation. The toolkit supports different data types (image, time-series, tabular, NLP) and models (PyTorch, TensorFlow). It provides built-in support for explanation methods like captum, tf-explain, and zennit. Quantus is under active development and aims to provide a comprehensive set of quantitative evaluation metrics for XAI methods.

github

: 502

NeMo-Curator

NeMo Curator is a GPU-accelerated open-source framework designed for efficient large language model data curation. It provides scalable dataset preparation for tasks like foundation model pretraining, domain-adaptive pretraining, supervised fine-tuning, and parameter-efficient fine-tuning. The library leverages GPUs with Dask and RAPIDS to accelerate data curation, offering customizable and modular interfaces for pipeline expansion and model convergence. Key features include data download, text extraction, quality filtering, deduplication, downstream-task decontamination, distributed data classification, and PII redaction. NeMo Curator is suitable for curating high-quality datasets for large language model training.

github

: 689

crab

CRAB is a framework for building LLM agent benchmark environments in a Python-centric way. It is cross-platform and multi-environment, allowing the creation of agent environments supporting various deployment options. The framework offers easy-to-use configuration with the ability to add new actions and define environments seamlessly. CRAB also provides a novel benchmarking suite with tasks and evaluators defined in Python, along with a unique graph evaluator method for detailed metrics.

github

: 155

Atom

Atom is an accurate low-bit weight-activation quantization algorithm that combines mixed-precision, fine-grained group quantization, dynamic activation quantization, KV-cache quantization, and efficient CUDA kernels co-design. It introduces a low-bit quantization method, Atom, to maximize Large Language Models (LLMs) serving throughput with negligible accuracy loss. The codebase includes evaluation of perplexity and zero-shot accuracy, kernel benchmarking, and end-to-end evaluation. Atom significantly boosts serving throughput by using low-bit operators and reduces memory consumption via low-bit quantization.

github

: 208

For similar tasks

Awesome-Segment-Anything

Awesome-Segment-Anything is a powerful tool for segmenting and extracting information from various types of data. It provides a user-friendly interface to easily define segmentation rules and apply them to text, images, and other data formats. The tool supports both supervised and unsupervised segmentation methods, allowing users to customize the segmentation process based on their specific needs. With its versatile functionality and intuitive design, Awesome-Segment-Anything is ideal for data analysts, researchers, content creators, and anyone looking to efficiently extract valuable insights from complex datasets.

github

: 789

Time-LLM

Time-LLM is a reprogramming framework that repurposes large language models (LLMs) for time series forecasting. It allows users to treat time series analysis as a 'language task' and effectively leverage pre-trained LLMs for forecasting. The framework involves reprogramming time series data into text representations and providing declarative prompts to guide the LLM reasoning process. Time-LLM supports various backbone models such as Llama-7B, GPT-2, and BERT, offering flexibility in model selection. The tool provides a general framework for repurposing language models for time series forecasting tasks.

github

: 764

crewAI

CrewAI is a cutting-edge framework designed to orchestrate role-playing autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. It enables AI agents to assume roles, share goals, and operate in a cohesive unit, much like a well-oiled crew. Whether you're building a smart assistant platform, an automated customer service ensemble, or a multi-agent research team, CrewAI provides the backbone for sophisticated multi-agent interactions. With features like role-based agent design, autonomous inter-agent delegation, flexible task management, and support for various LLMs, CrewAI offers a dynamic and adaptable solution for both development and production workflows.

github

: 23.8k

Transformers_And_LLM_Are_What_You_Dont_Need

Transformers_And_LLM_Are_What_You_Dont_Need is a repository that explores the limitations of transformers in time series forecasting. It contains a collection of papers, articles, and theses discussing the effectiveness of transformers and LLMs in this domain. The repository aims to provide insights into why transformers may not be the best choice for time series forecasting tasks.

github

: 587

pytorch-forecasting

github

: 3.8k

spider

Spider is a high-performance web crawler and indexer designed to handle data curation workloads efficiently. It offers features such as concurrency, streaming, decentralization, headless Chrome rendering, HTTP proxies, cron jobs, subscriptions, smart mode, blacklisting, whitelisting, budgeting depth, dynamic AI prompt scripting, CSS scraping, and more. Users can easily get started with the Spider Cloud hosted service or set up local installations with spider-cli. The tool supports integration with Node.js and Python for additional flexibility. With a focus on speed and scalability, Spider is ideal for extracting and organizing data from the web.

github

: 946

AI_for_Science_paper_collection

AI for Science paper collection is an initiative by AI for Science Community to collect and categorize papers in AI for Science areas by subjects, years, venues, and keywords. The repository contains `.csv` files with paper lists labeled by keys such as `Title`, `Conference`, `Type`, `Application`, `MLTech`, `OpenReviewLink`. It covers top conferences like ICML, NeurIPS, and ICLR. Volunteers can contribute by updating existing `.csv` files or adding new ones for uncovered conferences/years. The initiative aims to track the increasing trend of AI for Science papers and analyze trends in different applications.

github

: 55

pytorch-forecasting

github

: 4.0k

For similar jobs

sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github

: 7.1k

teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github

: 390

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github

: 572

chatbot-ui

Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

github

: 27.7k

BricksLLM

BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

github

: 953

uAgents

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

github

: 1.2k

griptape

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

github

: 2.1k