Last active
August 29, 2015 13:57
-
-
Save rolph-recto/9593225 to your computer and use it in GitHub Desktop.
document-system.ipynb
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"metadata": { | |
"name": "Document System" | |
}, | |
"nbformat": 3, | |
"nbformat_minor": 0, | |
"worksheets": [ | |
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"collapsed": false, | |
"input": "from document_system import DocumentSystem\nfrom document_fetcher import SqliteDocumentFetcher\nfrom document_corpus import DocumentCorpus\nfrom featureset import TfIdfFeatureset, SimilarityFeatureset, VACodeReferenceFeatureset\nfrom marginalia_emitter import SimilarityEmitter, KeywordEmitter, ReferenceEmitter", | |
"language": "python", | |
"metadata": {}, | |
"outputs": [], | |
"prompt_number": 1 | |
}, | |
{ | |
"cell_type": "code", | |
"collapsed": false, | |
"input": "#corpus\nfetcher = SqliteDocumentFetcher(\"vacode2.db\", count=1000, title=\"section\")\ncorpus = DocumentCorpus(fetcher)\ncorpus.build()\n\n#featureset\ntfidf_fs = TfIdfFeatureset()\nsimilarity_fs = SimilarityFeatureset(tfidf_fs)\nreference_fs = VACodeReferenceFeatureset()\n\n#emitter\nsimilarity_emitter = SimilarityEmitter(threshold=0.25)\nkeywords_emitter = KeywordEmitter(threshold=0.30)\nreference_emitter = ReferenceEmitter()\n\n#system\nsys = DocumentSystem(corpus, [tfidf_fs, similarity_fs, reference_fs], [similarity_emitter, keywords_emitter, reference_emitter])", | |
"language": "python", | |
"metadata": {}, | |
"outputs": [], | |
"prompt_number": 2 | |
}, | |
{ | |
"cell_type": "code", | |
"collapsed": true, | |
"input": "sys.build_featuresets()", | |
"language": "python", | |
"metadata": {}, | |
"outputs": [], | |
"prompt_number": 3 | |
}, | |
{ | |
"cell_type": "code", | |
"collapsed": false, | |
"input": "from serialize_marginalia import SQLMarginaliaSerializer\nfrom sqlalchemy import create_engine", | |
"language": "python", | |
"metadata": {}, | |
"outputs": [], | |
"prompt_number": 5 | |
}, | |
{ | |
"cell_type": "code", | |
"collapsed": false, | |
"input": "engine = create_engine(\"sqlite:///vacode2.db\", echo=True)", | |
"language": "python", | |
"metadata": {}, | |
"outputs": [], | |
"prompt_number": 7 | |
}, | |
{ | |
"cell_type": "code", | |
"collapsed": false, | |
"input": "serializer = SQLMarginaliaSerializer(sys, engine)", | |
"language": "python", | |
"metadata": {}, | |
"outputs": [], | |
"prompt_number": 8 | |
}, | |
{ | |
"cell_type": "code", | |
"collapsed": false, | |
"input": "serializer.serialize_corpus_marginalia()", | |
"language": "python", | |
"metadata": {}, | |
"outputs": [] | |
} | |
], | |
"metadata": {} | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment