{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"dedupe","owner":"dedupeio","isFork":false,"description":"🆔 A python library for accurate and scalable fuzzy matching, record deduplication and entity-resolution.","topicNames":["python","dedupe","datamade","clustering","record-linkage","python-library","entity-resolution","dedupe-library","de-duplicating"],"topicsNotShown":0,"allTopics":["python","dedupe","datamade","clustering","record-linkage","python-library","entity-resolution","dedupe-library","de-duplicating"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":10,"issueCount":69,"starsCount":3990,"forksCount":540,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-18T02:23:40.330Z"}},{"type":"Public","name":"pyhacrf","owner":"dedupeio","isFork":true,"description":"📐 Hidden alignment conditional random field for classifying string pairs.","topicNames":["nlp","edit-distance","string-distance","conditional-random-fields","python"],"topicsNotShown":0,"allTopics":["nlp","edit-distance","string-distance","conditional-random-fields","python"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":4,"issueCount":5,"starsCount":24,"forksCount":21,"license":"BSD 3-Clause \"New\" or \"Revised\" License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-13T19:30:03.373Z"}},{"type":"Public","name":"dedupe-examples","owner":"dedupeio","isFork":false,"description":"🆔 Examples for using the dedupe library","topicNames":["entity-resolution","python","dedupe","record-linkage"],"topicsNotShown":0,"allTopics":["entity-resolution","python","dedupe","record-linkage"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":6,"issueCount":9,"starsCount":394,"forksCount":216,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-05-26T19:47:43.985Z"}},{"type":"Public","name":"dedupe-variable-datetime","owner":"dedupeio","isFork":false,"description":"DateTime variable for dedupe","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":4,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-12-11T11:59:43.257Z"}},{"type":"Public","name":"dedupe-variable-name","owner":"dedupeio","isFork":false,"description":"name variable type for dedupe","topicNames":["dedupe","dedupe-variable"],"topicsNotShown":0,"allTopics":["dedupe","dedupe-variable"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":1,"starsCount":7,"forksCount":8,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-17T06:49:57.790Z"}},{"type":"Public","name":"dedupe-geocoder","owner":"dedupeio","isFork":false,"description":" 📍 Demonstration of how dedupe might be used as geocoder","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":4,"issueCount":2,"starsCount":17,"forksCount":6,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-06-21T21:08:21.649Z"}},{"type":"Public archive","name":"hcluster","owner":"dedupeio","isFork":false,"description":"Hierarchical Clustering Algorithms","topicNames":["hierarchical-clustering","python","clustering"],"topicsNotShown":0,"allTopics":["hierarchical-clustering","python","clustering"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":2,"starsCount":35,"forksCount":20,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-05-30T10:24:35.945Z"}},{"type":"Public archive","name":"rlr","owner":"dedupeio","isFork":false,"description":"Regularized Logistic Regression","topicNames":["logistic-regression","python","l2-regularization"],"topicsNotShown":0,"allTopics":["logistic-regression","python","l2-regularization"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":3,"starsCount":11,"forksCount":9,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-12-20T12:42:54.172Z"}},{"type":"Public","name":"dedupe-variable-ilcs","owner":"dedupeio","isFork":false,"description":"Dedupe variable for Illinois Compiled Statute (ILCS) codes","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":2,"forksCount":1,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-06-16T20:42:56.776Z"}},{"type":"Public","name":"dedupeio-web-api-docs","owner":"dedupeio","isFork":false,"description":"Dedupe.io web API allows for matching and training against projects using a standard RESTful framework.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":6,"forksCount":3,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-05-26T19:52:55.761Z"}},{"type":"Public","name":"dedupe-variable-number","owner":"dedupeio","isFork":false,"description":"Try to cast strings to numbers, then compare","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":3,"forksCount":1,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:59:39.511Z"}},{"type":"Public","name":"parseratorvariable","owner":"dedupeio","isFork":false,"description":"Base class for dedupe variables for parsed fields","topicNames":["dedupe","dedupe-variable"],"topicsNotShown":0,"allTopics":["dedupe","dedupe-variable"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":3,"forksCount":3,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:59:07.274Z"}},{"type":"Public","name":"highered","owner":"dedupeio","isFork":false,"description":"CRF Edit Distance","topicNames":["edit-distance","string-distance","conditional-random-fields","python"],"topicsNotShown":0,"allTopics":["edit-distance","string-distance","conditional-random-fields","python"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":6,"forksCount":4,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:57:05.695Z"}},{"type":"Public","name":"simplecosine","owner":"dedupeio","isFork":false,"description":"📐 simple cosine distance","topicNames":["string-similarity","python"],"topicsNotShown":0,"allTopics":["string-similarity","python"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":3,"forksCount":4,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:56:37.458Z"}},{"type":"Public","name":"categorical-distance","owner":"dedupeio","isFork":false,"description":"📐 Compare categorical variables","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":4,"forksCount":4,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:55:56.288Z"}},{"type":"Public","name":"datetime-distance","owner":"dedupeio","isFork":false,"description":" 📐 Compare dates and times","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":3,"forksCount":5,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:54:59.822Z"}},{"type":"Public","name":"fuzzycategory","owner":"dedupeio","isFork":false,"description":"📐 Fuzzy Categorical Distances","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":14,"forksCount":5,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:54:31.102Z"}},{"type":"Public","name":"dedupe-variable-employer","owner":"dedupeio","isFork":false,"description":"","topicNames":["dedupe","dedupe-variable"],"topicsNotShown":0,"allTopics":["dedupe","dedupe-variable"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":5,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:53:55.303Z"}},{"type":"Public","name":"dedupe-variable-fuzzycategory","owner":"dedupeio","isFork":false,"description":"Dedupe Variable for Fuzzy Categories","topicNames":["dedupe","dedupe-variable"],"topicsNotShown":0,"allTopics":["dedupe","dedupe-variable"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":4,"forksCount":4,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:53:19.237Z"}},{"type":"Public","name":"dedupe-variable-address","owner":"dedupeio","isFork":false,"description":"Address Variable Type for dedupe","topicNames":["dedupe-variable","dedupe"],"topicsNotShown":0,"allTopics":["dedupe-variable","dedupe"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":6,"starsCount":8,"forksCount":3,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:52:25.846Z"}},{"type":"Public","name":"learned-string-alignments","owner":"dedupeio","isFork":true,"description":"Learning String Alignments for Entity Aliases","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":4,"forksCount":6,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:51:16.288Z"}},{"type":"Public","name":"dedupe-vowpal","owner":"dedupeio","isFork":false,"description":"Vowpal Wabbit Active Labeler for Dedupe","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":4,"forksCount":3,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:48:34.256Z"}},{"type":"Public","name":"dedupe-variable-person","owner":"dedupeio","isFork":false,"description":"Dedupe variable for person names. just people. no companies.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":9,"forksCount":3,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:47:52.088Z"}},{"type":"Public","name":"address-matching","owner":"dedupeio","isFork":false,"description":"Python script for matching a list of messy addresses against a gazetteer using dedupe.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":5,"starsCount":59,"forksCount":19,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:47:01.965Z"}},{"type":"Public","name":"csvdedupe","owner":"dedupeio","isFork":false,"description":"🆔 Command line tool for deduplicating CSV files","topicNames":["cli","record-linkage","entity-resolution","dedupe","csv-files"],"topicsNotShown":0,"allTopics":["cli","record-linkage","entity-resolution","dedupe","csv-files"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":3,"issueCount":22,"starsCount":404,"forksCount":83,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-03-31T20:36:59.488Z"}}],"repositoryCount":25,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"Repositories"}