{"adoption": {"forks": 236, "observed_at": "2026-08-28T04:04:34.403157+00:00", "stars": 1382}, "canonical_url": "https://ross.abutalabs.com/products/eda_nlp_for_chinese", "card": {"archived": false, "artifact_type": "library", "description": "An implement of the paper of EDA for Chinese corpus.中文语料的EDA数据增强工具。NLP数据增强。论文阅读笔记。", "domain": ["machine-learning", "localization"], "enriched": true, "function": ["nlp", "data-generation", "machine-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["zhanlaoban/EDA_NLP_for_Chinese"], "name": "zhanlaoban/EDA_NLP_for_Chinese", "platform": ["python", "cli"], "pushed_at": "2022-05-31T05:46:50+00:00", "repo": "zhanlaoban/EDA_NLP_for_Chinese", "stars": 1382, "tags": ["data-augmentation", "easy-data-augmentation", "chinese-nlp", "text-classification", "synonym-replacement", "natural-language-processing"], "topics": ["eda", "data-augmentation", "chinese-data-augmentation", "chinese", "easy-data-augmentation", "text-classification"], "urls": [], "use_cases": ["augment a small Chinese text classification training set", "generate synthetic Chinese sentences with synonym replacement", "expand labeled corpus for training a text classifier", "apply random swap and deletion to Chinese sentences", "boost text classification accuracy with limited data"], "what_it_is": "A Python implementation of the EDA (Easy Data Augmentation) paper adapted for Chinese text corpora. It augments labeled text classification datasets via synonym replacement, random insertion, random swap, and random deletion using jieba segmentation and Chinese synonym/stopword resources.", "when_to_avoid": ["your text is not Chinese (use the original eda_nlp)", "you need context-aware or neural augmentation", "you need an actively maintained library with a license"], "when_to_choose": ["you need data augmentation for Chinese-language text classification", "you want a simple CLI tool following the EDA paper", "your corpus is small and classifier overfits"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/eda_nlp_for_chinese", "repo": "zhanlaoban/EDA_NLP_for_Chinese", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.403157+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:40:08.915710+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7359b2cf43b8d70371010b5b6e7b236e9ffd028831cc8c01a036ed4fe797201", "fetched_at": "2026-08-28T04:04:34.403157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zhanlaoban/EDA_NLP_for_Chinese"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.403157+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:40:08.915710+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7359b2cf43b8d70371010b5b6e7b236e9ffd028831cc8c01a036ed4fe797201", "fetched_at": "2026-08-28T04:04:34.403157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zhanlaoban/EDA_NLP_for_Chinese"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:40:08.915710+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7359b2cf43b8d70371010b5b6e7b236e9ffd028831cc8c01a036ed4fe797201", "fetched_at": "2026-08-28T04:04:34.403157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zhanlaoban/EDA_NLP_for_Chinese"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.403157+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.403157+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.403157+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:40:08.915710+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7359b2cf43b8d70371010b5b6e7b236e9ffd028831cc8c01a036ed4fe797201", "fetched_at": "2026-08-28T04:04:34.403157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zhanlaoban/EDA_NLP_for_Chinese"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.403157+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.403157+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:40:08.915710+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7359b2cf43b8d70371010b5b6e7b236e9ffd028831cc8c01a036ed4fe797201", "fetched_at": "2026-08-28T04:04:34.403157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zhanlaoban/EDA_NLP_for_Chinese"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.403157+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.403157+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.403157+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:40:08.915710+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7359b2cf43b8d70371010b5b6e7b236e9ffd028831cc8c01a036ed4fe797201", "fetched_at": "2026-08-28T04:04:34.403157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zhanlaoban/EDA_NLP_for_Chinese"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.403157+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:34.403157+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:40:08.915710+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7359b2cf43b8d70371010b5b6e7b236e9ffd028831cc8c01a036ed4fe797201", "fetched_at": "2026-08-28T04:04:34.403157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zhanlaoban/EDA_NLP_for_Chinese"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:40:08.915710+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7359b2cf43b8d70371010b5b6e7b236e9ffd028831cc8c01a036ed4fe797201", "fetched_at": "2026-08-28T04:04:34.403157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zhanlaoban/EDA_NLP_for_Chinese"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:40:08.915710+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7359b2cf43b8d70371010b5b6e7b236e9ffd028831cc8c01a036ed4fe797201", "fetched_at": "2026-08-28T04:04:34.403157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zhanlaoban/EDA_NLP_for_Chinese"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:40:08.915710+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7359b2cf43b8d70371010b5b6e7b236e9ffd028831cc8c01a036ed4fe797201", "fetched_at": "2026-08-28T04:04:34.403157+00:00", "kind": "readme", "missing": false, "url": "https://github.com/zhanlaoban/EDA_NLP_for_Chinese"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2718, "days_push": 1555, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}