{"uid":"cap_Oud7xbjMcFWJ_Z_S3MbWx","slug":"training-question-classifier-macro-micro-weighted-f1-scores-9d0f86d3","name":"Training Question Classifier — Macro, Micro & Weighted F1 Scores","description":"Training question - Macro micro and weighted scores: Macro micro and weighted scores for Training question. 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 macro micro and weighted scores deliverable.","url":"https://market.datapackvibe.com/x402/assistant-sector-ml-training-question-aggregate-scores?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"records":{"type":"array","items":{"type":"object","required":["id","text","actual","predicted"],"properties":{"id":{"type":"string","default":"","maxLength":80,"minLength":1},"text":{"type":"string","default":"","maxLength":1000},"actual":{"enum":["concept","procedure","example","assessment"],"type":"string"},"predicted":{"enum":["concept","procedure","example","assessment"],"type":"string"}},"additionalProperties":false},"default":[{"id":"example-0-0","text":"concept sample document number 0 for this supplied dataset.","actual":"concept","predicted":"concept"},{"id":"example-0-1","text":"concept sample document number 1 for this supplied dataset.","actual":"concept","predicted":"concept"},{"id":"example-0-2","text":"concept sample document number 2 for this supplied dataset.","actual":"concept","predicted":"concept"},{"id":"example-1-0","text":"procedure sample document number 0 for this supplied dataset.","actual":"procedure","predicted":"procedure"},{"id":"example-1-1","text":"procedure sample document number 1 for this supplied dataset.","actual":"procedure","predicted":"procedure"},{"id":"example-1-2","text":"procedure sample document number 2 for this supplied dataset.","actual":"procedure","predicted":"procedure"},{"id":"example-2-0","text":"example sample document number 0 for this supplied dataset.","actual":"example","predicted":"example"},{"id":"example-2-1","text":"example sample document number 1 for this supplied dataset.","actual":"example","predicted":"example"},{"id":"example-2-2","text":"example sample document number 2 for this supplied dataset.","actual":"example","predicted":"example"},{"id":"example-3-0","text":"assessment sample document number 0 for this supplied dataset.","actual":"assessment","predicted":"assessment"},{"id":"example-3-1","text":"assessment sample document number 1 for this supplied dataset.","actual":"assessment","predicted":"assessment"},{"id":"example-3-2","text":"assessment sample document number 2 for this supplied dataset.","actual":"assessment","predicted":"assessment"}],"maxItems":200,"minItems":2}}},"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_XpN9HTuP5_riGoX4z-8k3","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":"Computes macro, micro, and weighted aggregate classification scores (precision, recall, F1) for a set of labelled training question records with actual vs. predicted categories.","exampleAgentPrompt":"I have up to 200 labelled training question records — each with an actual label and a predicted label from my classifier (concept, procedure, example, or assessment) — can you compute the macro, micro, and weighted precision/recall/F1 scores so I can see how well my model is doing overall?","exampleUseCases":[{"title":"Evaluating a question-type classifier model","prompt":"I've got 150 training question records where each one has the actual label (concept, procedure, example, or assessment) and what my classifier predicted — can you calculate the macro, micro, and weighted F1 scores so I can evaluate how well it's doing?"},{"title":"Comparing two labelling approaches","prompt":"I ran two different labelling passes on my training question dataset and want to check the macro, micro, and weighted scores for one of them — here are 120 records with actual and predicted labels across concept, procedure, example, and assessment categories."},{"title":"Quality check before model submission","prompt":"Before I submit my question classifier, I need to verify its aggregate performance — can you take these 80 labelled records with actual and predicted labels and give me the macro, micro, and weighted precision, recall, and F1 breakdown?"}],"resultDescription":"Returns macro-averaged, micro-averaged, and weighted-averaged precision, recall, and F1 scores computed over the supplied labelled records, with class labels spanning concept, procedure, example, and assessment. The output is a bounded, single-deliverable evaluation summary for the provided dataset.","failureModes":["Too many records supplied (over 200 limit) — request rejected","Missing required fields (id, text, actual, predicted) on any record — validation error","Invalid label values outside the enum (concept, procedure, example, assessment) — schema error","Empty records array — no scores can be computed","Malformed JSON input — parse error"],"whenToPreferThis":"Choose this endpoint when you need lightweight, on-demand aggregate classification metrics (macro, micro, weighted F1) for a small labelled dataset of training question records categorised as concept, procedure, example, or assessment — without needing to host a model or use a foundation model training service. Ideal for rapid evaluation loops on datasets up to 200 records at minimal cost ($0.01 USDC).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T06:56:53.949Z","isFirstParty":false,"canonicalSlug":"training-question-classifier-macro-micro-weighted-f1-scores-9d0f86d3"}