{"adoption": {"forks": 785, "observed_at": "2026-08-28T04:03:54.897159+00:00", "stars": 1185}, "canonical_url": "https://ross.abutalabs.com/products/nlp-in-practice", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Starter code to solve real world text data problems. Includes: Gensim Word2Vec, phrase embeddings, Text Classification with Logistic Regression, word count with pyspark, simple text preprocessing, pre-trained embeddings and more.", "domain": ["machine-learning", "data-science", "tutorials"], "enriched": true, "function": ["nlp", "machine-learning", "data-science", "data-visualization"], "health_score": 20, "homepage": "http://kavita-ganesan.com/kavitas-tutorials/#.WvIizNMvyog", "language": "Jupyter Notebook", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["kavgan/nlp-in-practice"], "name": "kavgan/nlp-in-practice", "platform": ["python"], "pushed_at": "2020-12-02T18:46:45+00:00", "repo": "kavgan/nlp-in-practice", "stars": 1185, "tags": ["jupyter-notebooks", "word2vec", "tf-idf", "text-classification", "gensim", "pyspark", "text-preprocessing", "word-embeddings", "starter-code", "natural-language-processing"], "topics": ["nlp", "natural-language-processing", "word2vec", "text-classification", "gensim", "tf-idf", "machine-learning", "text-mining"], "urls": [], "use_cases": ["learn how to train and use gensim word2vec embeddings", "extract keywords from text with tf-idf", "build a text classifier with logistic regression", "preprocess text with stemming, lemmatization, and stop word removal", "do word count on large files with pyspark", "load pre-trained GloVe and word2vec embeddings", "understand tfidftransformer vs tfidfvectorizer"], "what_it_is": "A collection of Jupyter notebooks and Python scripts demonstrating practical NLP and text mining techniques, including Word2Vec, TF-IDF keyword extraction, text classification, and text preprocessing. It serves as starter code with accompanying tutorials for solving real-world text data problems.", "when_to_avoid": ["you need a production-ready NLP library or maintained package", "you require a licensed dependency for commercial use (no license is provided)", "you need up-to-date code, as the repository has not been updated since 2020"], "when_to_choose": ["you want hands-on starter code for common NLP tasks in Python", "you are learning text mining concepts through runnable notebooks", "you need simple examples of word embeddings, TF-IDF, or text classification"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/nlp-in-practice", "repo": "kavgan/nlp-in-practice", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.897159+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:24:07.505858+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ccc1f91a4cfb0277672066a8a9158bba1340c2c84a4294b6e6fe3f33dcb4a78", "fetched_at": "2026-08-28T04:03:54.897159+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kavgan/nlp-in-practice"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:31:17.574084+00:00", "kind": "homepage", "missing": false, "url": "http://kavita-ganesan.com/kavitas-tutorials/#.WvIizNMvyog"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.897159+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:24:07.505858+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ccc1f91a4cfb0277672066a8a9158bba1340c2c84a4294b6e6fe3f33dcb4a78", "fetched_at": "2026-08-28T04:03:54.897159+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kavgan/nlp-in-practice"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:31:17.574084+00:00", "kind": "homepage", "missing": false, "url": "http://kavita-ganesan.com/kavitas-tutorials/#.WvIizNMvyog"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:24:07.505858+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ccc1f91a4cfb0277672066a8a9158bba1340c2c84a4294b6e6fe3f33dcb4a78", "fetched_at": "2026-08-28T04:03:54.897159+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kavgan/nlp-in-practice"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:31:17.574084+00:00", "kind": "homepage", "missing": false, "url": "http://kavita-ganesan.com/kavitas-tutorials/#.WvIizNMvyog"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.897159+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.897159+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.897159+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:24:07.505858+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ccc1f91a4cfb0277672066a8a9158bba1340c2c84a4294b6e6fe3f33dcb4a78", "fetched_at": "2026-08-28T04:03:54.897159+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kavgan/nlp-in-practice"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:31:17.574084+00:00", "kind": "homepage", "missing": false, "url": "http://kavita-ganesan.com/kavitas-tutorials/#.WvIizNMvyog"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.897159+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.897159+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:24:07.505858+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ccc1f91a4cfb0277672066a8a9158bba1340c2c84a4294b6e6fe3f33dcb4a78", "fetched_at": "2026-08-28T04:03:54.897159+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kavgan/nlp-in-practice"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:31:17.574084+00:00", "kind": "homepage", "missing": false, "url": "http://kavita-ganesan.com/kavitas-tutorials/#.WvIizNMvyog"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.897159+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.897159+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.897159+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:24:07.505858+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ccc1f91a4cfb0277672066a8a9158bba1340c2c84a4294b6e6fe3f33dcb4a78", "fetched_at": "2026-08-28T04:03:54.897159+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kavgan/nlp-in-practice"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:31:17.574084+00:00", "kind": "homepage", "missing": false, "url": "http://kavita-ganesan.com/kavitas-tutorials/#.WvIizNMvyog"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.897159+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.897159+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:24:07.505858+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ccc1f91a4cfb0277672066a8a9158bba1340c2c84a4294b6e6fe3f33dcb4a78", "fetched_at": "2026-08-28T04:03:54.897159+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kavgan/nlp-in-practice"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:31:17.574084+00:00", "kind": "homepage", "missing": false, "url": "http://kavita-ganesan.com/kavitas-tutorials/#.WvIizNMvyog"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:24:07.505858+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ccc1f91a4cfb0277672066a8a9158bba1340c2c84a4294b6e6fe3f33dcb4a78", "fetched_at": "2026-08-28T04:03:54.897159+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kavgan/nlp-in-practice"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:31:17.574084+00:00", "kind": "homepage", "missing": false, "url": "http://kavita-ganesan.com/kavitas-tutorials/#.WvIizNMvyog"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:24:07.505858+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ccc1f91a4cfb0277672066a8a9158bba1340c2c84a4294b6e6fe3f33dcb4a78", "fetched_at": "2026-08-28T04:03:54.897159+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kavgan/nlp-in-practice"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:31:17.574084+00:00", "kind": "homepage", "missing": false, "url": "http://kavita-ganesan.com/kavitas-tutorials/#.WvIizNMvyog"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:24:07.505858+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2ccc1f91a4cfb0277672066a8a9158bba1340c2c84a4294b6e6fe3f33dcb4a78", "fetched_at": "2026-08-28T04:03:54.897159+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kavgan/nlp-in-practice"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:31:17.574084+00:00", "kind": "homepage", "missing": false, "url": "http://kavita-ganesan.com/kavitas-tutorials/#.WvIizNMvyog"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+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": 3139, "days_push": 2100, "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}}