{"uid":"cap_1KenJAurEGMzBFACA6s-J","slug":"release-change-local-text-classifier-naive-bayes-7a1f610a","name":"Release Change Local Text Classifier (Naive Bayes)","description":"Release change - Train local text baseline and classify: Train local text baseline and classify for Release change. Up to 200 supplied labelled text records. Local dataset tools, evaluation and small naive-Bayes baselines; no hosted model or foundation-model training. One of 25 profiles or calculations across 20 shared operations in this sector. 0.01 USDC includes one bounded train local text baseline and classify deliverable.","url":"https://market.datapackvibe.com/x402/assistant-sector-ml-release-change-local-classifier?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"records":{"type":"array","items":{"type":"object","required":["id","text","actual"],"properties":{"id":{"type":"string","default":"","maxLength":80,"minLength":1},"text":{"type":"string","default":"","maxLength":1000},"actual":{"enum":["feature","fix","documentation","maintenance"],"type":"string"}},"additionalProperties":false},"default":[{"id":"example-0-0","text":"feature sample document number 0 for this supplied dataset.","actual":"feature"},{"id":"example-0-1","text":"feature sample document number 1 for this supplied dataset.","actual":"feature"},{"id":"example-0-2","text":"feature sample document number 2 for this supplied dataset.","actual":"feature"},{"id":"example-1-0","text":"fix sample document number 0 for this supplied dataset.","actual":"fix"},{"id":"example-1-1","text":"fix sample document number 1 for this supplied dataset.","actual":"fix"},{"id":"example-1-2","text":"fix sample document number 2 for this supplied dataset.","actual":"fix"},{"id":"example-2-0","text":"documentation sample document number 0 for this supplied dataset.","actual":"documentation"},{"id":"example-2-1","text":"documentation sample document number 1 for this supplied dataset.","actual":"documentation"},{"id":"example-2-2","text":"documentation sample document number 2 for this supplied dataset.","actual":"documentation"},{"id":"example-3-0","text":"maintenance sample document number 0 for this supplied dataset.","actual":"maintenance"},{"id":"example-3-1","text":"maintenance sample document number 1 for this supplied dataset.","actual":"maintenance"},{"id":"example-3-2","text":"maintenance sample document number 2 for this supplied dataset.","actual":"maintenance"}],"maxItems":200,"minItems":2},"query_texts":{"type":"array","items":{"type":"string","default":"","maxLength":1000},"default":["feature sample"],"maxItems":20,"minItems":1}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_LY7CnnGRJuEEhk6Mt4uzb","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Trains a local naive Bayes text classifier on up to 200 labelled release-change records and classifies query texts into feature, fix, documentation, or maintenance categories.","exampleAgentPrompt":"Train a local text classifier on my 12 labelled commit messages — 3 each for feature, fix, documentation, and maintenance — and then classify these two new texts: 'added dark mode toggle' and 'patched null pointer crash'.","exampleUseCases":[{"title":"Automated commit message tagger","prompt":"I have 50 labelled commit messages from our repo — mix of features, fixes, docs, and maintenance — train a local classifier on them and then tell me which category these 5 new commits fall into: 'refactor auth module', 'fix login timeout bug', 'update README', 'add user export feature', 'bump dependency versions'."},{"title":"Changelog category accuracy check","prompt":"We've got 80 manually labelled release notes split across feature, fix, documentation, and maintenance. Can you train a quick local naive Bayes model on them and evaluate how well it classifies a few held-out samples I'll give you as query texts?"},{"title":"PR description type predictor","prompt":"Here are 30 labelled pull request titles — some are features, some are fixes, some are docs, some are maintenance — train a local text model on those and classify these 10 new PR descriptions to tell me what type each one is."}],"resultDescription":"Returns classification predictions for each query text, mapping them to one of the four categories (feature, fix, documentation, maintenance), along with evaluation metrics from the locally trained naive Bayes model. No hosted model is retained; the result is bounded to the supplied dataset.","failureModes":["Fewer than 2 records supplied — minimum input violation","More than 200 records supplied — exceeds maxItems limit","Record text exceeds 1000 characters — field length violation","Invalid 'actual' label value not in enum (feature, fix, documentation, maintenance)","Query texts array empty or exceeds 20 items","Insufficient class diversity in training data leading to poor classification","Payment of 0.01 USDC not completed — x402 payment required before response"],"whenToPreferThis":"Choose this endpoint when you need a lightweight, local, no-frills text classifier for software release change categorisation without relying on a hosted model or large language model. It is ideal when your dataset is small (under 200 records), you want per-call pricing with no subscription, and the four-class taxonomy (feature, fix, documentation, maintenance) matches your use case exactly.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T18:48:12.098Z","isFirstParty":false,"canonicalSlug":"release-change-local-text-classifier-naive-bayes-7a1f610a"}