15 Repos
Utilities for automatically selecting the appropriate tokenization configuration based on model identifiers.
Distinct from Model Selection Tools: Distinct from general model selection tools: focuses on tokenization-specific configuration retrieval rather than model performance optimization.
Explore 15 awesome GitHub repositories matching artificial intelligence & ml · Automated Selection. Refine with filters or upvote what's useful.
DevToys is a cross-platform desktop application that functions as a comprehensive suite of offline utilities for common software development tasks. It provides a unified interface for performing data formatting, encoding, validation, and asset generation locally without requiring an internet connection. The application is built on a plugin-based extensibility framework that allows users to integrate custom utility modules to meet specific technical requirements. A core differentiator is its clipboard-aware management system, which monitors clipboard content to automatically suggest or open th
Provides a clipboard-aware management system that automatically suggests relevant tools for detected data formats.
Tiktoken is a library for converting raw text into numerical sequences using byte pair encoding schemes. It functions as a toolkit for managing tokenization processes, enabling the transformation of text into the specific numerical formats required by language models. The library provides mechanisms for automated encoder selection, allowing users to retrieve the correct tokenization configuration based on specific model names. It also supports the definition and registration of custom tokenization schemes, which facilitates the use of specialized vocabularies or unique model architectures wit
Retrieves the correct tokenization configuration automatically based on the specific model name provided.
This project is an educational resource providing practical code examples and implementations of machine learning algorithms using the Python language. It serves as a guide for constructing predictive pipelines, clustering models, and dimensionality reduction within the Scikit-Learn ecosystem. The repository includes comprehensive demonstrations for supervised and unsupervised learning, as well as detailed examples for implementing neural networks and deep architectures. It also provides practical guidance on exporting model parameters to JSON and wrapping trained models in web APIs for produ
Explains the logic for selecting the most effective machine learning algorithm and parameters based on performance and efficiency.
This project is a local AI inpainting tool designed to erase hard-coded subtitles and watermarks from videos and images. It functions as a content-aware media restorer that uses deep learning to reconstruct missing pixels and preserve the original resolution of the source files. The software is distinguished by its local execution model, running inference on host hardware to process media without relying on external cloud APIs. It employs content-aware model selection, allowing the use of different generative algorithms based on media types, such as animation or live action, to optimize visua
Allows users to choose specific AI models to optimize visual results based on motion levels and content types.
This project is an automated machine learning framework and toolkit designed for training and tuning custom models for classification, regression, and recommendations. It functions as a multimodal machine learning toolkit capable of processing and training models using a combination of text, image, audio, and sensor data. The framework distinguishes itself as a multimodal data processor that can handle and visualize large datasets on a single machine using column-oriented disk storage. It includes a core machine learning model generator that converts trained models into formats compatible wit
Provides automated selection of the most effective machine learning algorithms by analyzing dataset statistics.
This repository is a collection of Jupyter notebooks providing reference implementations and templates for building, training, and deploying machine learning models using Amazon SageMaker. It serves as an example library for implementing model architectures and automating the machine learning lifecycle. The library provides practical patterns for machine learning training, data engineering, and model deployment. It includes implementation guides for MLOps, including workflows for model monitoring, lineage tracking, and hyperparameter tuning. The examples cover a broad range of capabilities i
Uses automated machine learning to handle feature selection and model generation based on dataset characteristics.
AutoGluon is an automated machine learning framework and multimodal library designed to automate the end-to-end pipeline from data preprocessing to high-accuracy model training and validation. It functions as an automated model trainer for tabular, image, text, and time series data, as well as a tool for time series forecasting and foundation model finetuning. The project is distinguished by its ability to jointly process and fuse different data types, allowing for the construction of multimodal neural networks that integrate images, text, and structured tables. It supports zero-shot inferenc
Automatically selects the best local, global, and ensemble models based on quality presets or time limits.
PyCaret is a Python AutoML platform and MLOps lifecycle manager designed to automate machine learning workflows. It functions as a low-code environment that leverages a scikit-learn native engine to execute preprocessing, training, and evaluation for tabular data. The platform distinguishes itself as an LLM-powered ML copilot, using large language model agents to analyze datasets, design experiment configurations, and explain model results. It also serves as a Kubernetes ML orchestrator and model registry, enabling the versioning of trained pipelines and their promotion to production API endp
Automatically identifies the best performing machine learning algorithm for a specific analytical task.
PathFinding.js is a grid-based pathfinding library that implements multiple search algorithms for computing optimal routes on 2D maps. It provides implementations of A*, Dijkstra, Breadth-First Search, and Jump Point Search, each designed to find the shortest path between two points on a grid while avoiding obstacles. The library is built around a pluggable architecture where each pathfinding strategy shares a common interface, allowing algorithms to be selected at runtime without modifying core logic. It includes a configurable diagonal movement rule engine that controls diagonal traversal b
Allows selection from multiple pathfinding strategies including A*, Dijkstra, Breadth-First, and Jump Point Search.
h2o-3 is a distributed machine learning platform and automated machine learning framework designed for training and deploying predictive models using distributed in-memory computing. It functions as a deep learning framework and a distributed model scoring engine, capable of operating as a Kubernetes ML cluster to process large datasets in parallel. The platform distinguishes itself through automated machine learning capabilities that automatically select the best algorithms and hyperparameters to optimize model performance. It provides specialized deep learning toolkits for tasks including i
Automatically selects the optimal algorithm and hyperparameters to maximize predictive model performance.
Dieses Projekt ist ein Lehrplan für Machine Learning und eine Lernplattform, die über interaktive Jupyter Notebooks bereitgestellt wird. Es dient als umfassender Leitfaden zur Beherrschung des Python-Data-Science-Toolkits und bietet strukturierte Tutorials für numerisches Rechnen, Manipulation tabellarischer Daten und statistische Visualisierung. Der Lehrplan enthält spezifische Implementierungsleitfäden für Scikit-Learn und einen praktischen Kurs zu TensorFlow für den Aufbau, das Training und das Deployment neuronaler Netze und Computer-Vision-Modelle. Er deckt den End-to-End-Prozess des Aufbaus prädiktiver Modelle ab, von der anfänglichen Problemformulierung und Aufgabenkategorisierung bis hin zum Deployment der Modelle über interaktive Weboberflächen. Das Projekt deckt ein breites Funktionsspektrum ab, einschließlich numerischem Rechnen mit mehrdimensionalen Arrays, explorativer Datenanalyse und Datenvorverarbeitungsroutinen. Es bietet detaillierte Workflows für überwachtes und unüberwachtes Lernen, automatisierte Machine-Learning-Pipelines, Hyperparameter-Optimierung und Modellbewertung mittels Klassifizierungsmetriken und Kreuzvalidierung. Der Bildungsinhalt ist als eine Reihe von Notebooks strukturiert, die Python-Code mit narrativen Erklärungen verknüpfen, um Data-Science-Workflows zu dokumentieren.
Teaches how to select the most effective machine learning algorithm and hyperparameters based on dataset characteristics.
statsforecast ist eine statistische Hochleistungs-Bibliothek für Zeitreihenprognosen, die darauf ausgelegt ist, Punktprognosen und Vorhersageintervalle zu generieren. Sie fungiert als verteiltes Zeitreihen-Framework, das eine C-basierte Prognose-Engine und einen automatisierten Modellselektor nutzt, um das optimale statistische Modell für jede einzigartige Serie in einem Datensatz zu identifizieren und anzupassen. Das System enthält zudem einen Zeitreihen-Anomaliedetektor, um ungewöhnliche Datenpunkte durch den Vergleich beobachteter Werte mit probabilistischen Prognoseintervallen zu identifizieren. Das Projekt zeichnet sich durch seine Fähigkeit aus, massiv parallele Prognosen für Millionen individueller Serien zu verarbeiten. Dies erreicht es durch ein verteiltes Computing-Framework, Multi-Core-Parallel-Ausführung und kompilierte C-Kernels, die die Kernlogik von ARIMA und exponentieller Glättung beschleunigen. Das System optimiert die großskalige Verarbeitung weiter unter Verwendung eines Long-Format-Datenlayouts und einer Lazy-Evaluation-Datenpipeline, um den Speicher-Overhead zu reduzieren. Die Bibliothek bietet eine umfassende Suite von Modellen, einschließlich AutoARIMA, verschiedenen Methoden der exponentiellen Glättung für intermittierende oder saisonale Nachfrage, Theta-Dekomposition und GARCH-Volatilitätsmodellierung für finanzielles Risiko. Sie deckt breitere Funktionsbereiche ab, wie multivariate Prognosen mit exogenen Variablen, Zeitreihen-Dekomposition und Modellevaluierung mittels historischer Kreuzvalidierung und Sliding-Window-Analyse. Die Bibliothek integriert sich mit Hochleistungs-Datenstrukturen wie Polars und bietet Dienstprogramme, um gespeicherte Modelle als REST-Endpunkte für netzwerkzugängliche Vorhersagen bereitzustellen.
Provides automated selection of the best performing statistical forecasting models for every unique time series in a dataset.
EconML ist eine Python-Bibliothek für kausale Inferenz, die darauf ausgelegt ist, heterogene Behandlungseffekte unter Verwendung einer Kombination aus maschinellem Lernen und Ökonometrie zu schätzen. Sie dient als Toolkit zur Berechnung bedingter durchschnittlicher Behandlungseffekte, um zu bestimmen, wie sich spezifische Interventionen auf Einzelpersonen oder Untergruppen auswirken. Das Projekt bietet ein Framework für Double Machine Learning und orthogonales maschinelles Lernen, um kausale Signale von hochdimensionalen Störfaktoren zu isolieren. Es enthält spezialisierte Implementierungen für kausale Wälder und Instrumentalvariablen-Lerner, die die Wiederherstellung kausaler Beziehungen selbst bei Vorhandensein unbeobachteter Störfaktoren ermöglichen. Die Bibliothek deckt ein breites Spektrum an Funktionen ab, einschließlich der Validierung kausaler Modelle durch Widerlegungstests und Kalibrierungskurven, der Konstruktion personalisierter Behandlungsrichtlinien und der Analyse dynamischer Behandlungsregime. Sie unterstützt zudem statistische Inferenz zur Quantifizierung von Unsicherheit und die Interpretation von Effekt-Heterogenität unter Verwendung baumbasierter Modelle und Shapley-Werte. Das Projekt wird primär durch Jupyter Notebooks implementiert und demonstriert.
Provides tools to optimize the choice of nuisance models to improve the accuracy of treatment effect estimation.
This project is a collection of comprehensive guides and reference materials designed for technical interviews, machine learning system design, and professional development. It serves as a technical knowledge base and a career coaching manual, providing structured resources to help candidates navigate the machine learning hiring landscape. The resource distinguishes itself by offering detailed frameworks for comparing industry roles, analyzing company types, and planning long-term career progression. It provides specific guidance on evaluating employer organizational health, identifying resea
Provides frameworks for comparing algorithm tradeoffs as a core part of ML interview preparation.
hledger is a plain text accounting tool and double-entry ledger manager that stores financial transactions in human-readable text files. It functions as a financial reporting engine for generating balance sheets and income statements, and as a multi-currency investment tracker for managing commodity lots and capital gains. The project distinguishes itself by providing multi-interface data access, allowing users to interact with their financial data via a command line interface, a terminal user interface, and a web server. It features a market-price valuation system to calculate the current va
Provides configurable lot-matching strategies including FIFO, LIFO, and Average Cost for asset disposal.