16 个仓库
Comprehensive libraries and frameworks for building and evaluating models.
Explore 16 awesome GitHub repositories matching part of an awesome list · Analysis Toolkits. Refine with filters or upvote what's useful.
This PyTorch-based deep learning library provides a framework for analyzing and forecasting temporal data. It implements specialized architectures for time series forecasting, anomaly detection, data imputation, and classification. The project distinguishes itself through the inclusion of zero-shot inference capabilities, allowing large-scale temporal models to be evaluated on unseen datasets without requiring task-specific fine-tuning. The framework covers a broad range of analytical capabilities, including the recovery of missing values in incomplete datasets, the identification of irregul
Comprehensive library of deep learning models for sequences.
sktime is a machine learning framework for time series analysis. It provides a unified toolkit for implementing time series classification, forecasting, and anomaly detection using standardized machine learning interfaces. The library serves as a collection of tools for assigning categorical labels to temporal sequences, predicting future values based on historical patterns, and identifying outliers or unusual patterns within temporal data. The framework includes capabilities for panel-data handling and pipeline-based transformations. It utilizes a unified API wrapper and plugin-based model
Unified machine learning framework for diverse tasks.
Darts is a Python time series library designed for forecasting, anomaly detection, and the preprocessing of univariate and multivariate temporal data. It serves as a comprehensive framework for training and evaluating a wide range of statistical, machine learning, and deep learning models to predict future numerical values. The toolkit is distinguished by its support for global time series modeling, allowing a single model to be trained across multiple different series to leverage shared patterns. It also features a hierarchical time series manager to ensure consistency between aggregate and
Unified library for forecasting and anomaly detection tasks.
tsai 是一个用于时间序列分类、回归和预测的深度学习库。它基于 PyTorch 和 fastai 构建,提供了一个框架,用于为序列数据分配标签、预测单变量或多变量序列的未来值,并通过自监督学习在未标记数据上训练表征。 该库的特色在于其专业的时间工程和缩放能力。它包含用于捕捉季节性模式的周期性时间编码工具,以及用于处理超出内存限制数据集的在线窗口切片功能。它还支持多模态输入管道,能够将静态分类特征与动态连续序列相结合。 该工具包涵盖了广泛的预处理和评估需求,包括滑动窗口分割、缺失数据插补以及将表格数据帧转换为结构化张量。模型性能通过向前验证(walk-forward validation)和特征重要性分析进行评估,以确保时间一致性。
Deep learning library optimized for time series analysis.
GluonTS 是一个概率时间序列库和深度学习预测框架。它提供了一套工具包,用于构建、训练和评估神经网络架构,通过将未来值预测为概率分布来量化不确定性。 该项目的独特之处在于支持零样本(zero-shot)预测,并集成了多种建模方法,包括深度概率神经网络以及对 Prophet 和 R forecast 等外部统计库的封装。它实现了因果卷积和可逆残差网络等专门的架构原语,以防止信息泄露并将潜在表示映射为有效的概率分布。 该框架涵盖了全面的数据工程功能,包括时间序列缩放、双射变换和分层建模。它利用 Apache Arrow 和 Parquet 进行高性能数据集流式传输和随机访问管理。在模型评估方面,它包含一套评估套件,使用分位数损失(quantile loss)和连续排名概率分数(CRPS)等指标来衡量预测准确性和概率覆盖率。 该库支持通过集成 Amazon SageMaker 进行模型部署。
Probabilistic modeling and forecasting library.
这是一个深度学习框架,用于使用 PyTorch 架构预测序列数据中的未来值。它提供了一个用于长周期和概率时间序列预测的工具包,包含一个将表格数据转换为序列以进行监督式深度学习训练的数据流水线。 该库利用训练包装器在 CPU 和 GPU 上扩展模型执行。它支持生成未来结果的概率分布,而不是单一的点估计,从而量化预测的不确定性。 该框架包括实现预测模型、优化超参数以及通过多周期指标评估准确性的功能。它还提供了将复杂架构与简单基准模型进行对比的方法。
Deep learning forecasting implementations using PyTorch.
statsforecast 是一个高性能统计时间序列预测库,旨在生成点预测和预测区间。它作为一个分布式时间序列框架,利用基于 C 的预测引擎和自动模型选择器来识别并拟合数据集中每个唯一序列的最佳统计模型。该系统还包括一个时间序列异常检测器,通过将观测值与概率预测区间进行比较来识别异常数据点。 该项目的特色在于其处理数百万个独立序列的大规模并行预测的能力。它通过分布式计算框架、多核并行执行和加速核心 ARIMA 及指数平滑逻辑的编译 C 内核来实现这一点。该系统进一步利用长格式数据布局和惰性求值数据流水线来优化大规模处理,以减少内存开销。 该库提供了一套全面的模型,包括 AutoARIMA、用于间歇性或季节性需求的各种指数平滑方法、Theta 分解以及用于金融风险的 GARCH 波动率建模。它涵盖了更广泛的功能领域,例如带有外生变量的多元预测、时间序列分解以及通过历史交叉验证和滑动窗口分析进行模型评估。 该库与 Polars 等高性能数据结构集成,并提供将保存的模型作为 REST 端点提供服务以进行网络可访问预测的实用程序。
Efficient statistical models for rapid time series forecasting.
Neuralforecast 是一个神经时间序列预测库,旨在利用深度学习架构预测一个或多个序列的未来值。它是一个分布式机器学习预测框架,支持跨多个时间序列训练全局模型,通过交叉学习提高泛化能力。 该项目作为一个概率预测工具包,能够生成不确定性区间和概率分布,而不仅仅是单一的点估计。它还包含一个分层预测协调器,以确保不同组织或地理层级的预测结果与其汇总总数保持一致。 该库涵盖了广泛的功能,包括外生变量集成、自动超参数优化和迁移学习。它提供了通过交叉验证和滑动窗口技术进行模型验证的工具,以及利用 Spark 在计算集群上分发训练任务的能力。 该系统支持通过云存储集成实现模型持久化,并提供了对趋势和季节性等预测组件的解释机制。
High-performance neural network models for forecasting.
Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).
Deep learning framework for complex sequence prediction.
a Python toolbox for machine learning on Partially-Observed Time Series
Python-based toolbox for data imputation and analysis.
A toolkit for time series machine learning and deep learning
Toolkit focused on machine learning for sequential data.
RNAseq analysis notes from Ming Tang
Broad collection of packages and resources for sequencing analysis.
license-image: https://img.shields.io/badge/License-MIT-blue.svg license-url: https://opensource.org/licenses/MIT pypi-image: https://badge.fury.io/py/tfts.svg pypi-url: https://pypi.python.org/pypi/tfts pepy-image: https://pepy.tech/badge/tfts/month pepy-url:…
Curated collection of various predictive modeling methods.
Fost - Framework of Fost - Quick Start - Installation - Train with FOST - Data Format - Examples - Contact Us
Specialized toolkit for forecasting applications.
Comprehensive database of analysis tools and their functional capabilities.
Overview of algorithms for estimating developmental trajectories in cells.