Skip to content

gargantext
gargantext
Commit 0b35b6a7 authored by Administrator's avatar Administrator
Browse files
Options

Merge branch 'mat' 

Intégration des modifs de Mat (dev parsing, bug fix for ngrams)
parents 0aa95012 610ee647
Hide whitespace changes
Inline Side-by-side
Showing with 421 additions and 0 deletions
.ipynb_checkpoints/Test extractor cache-checkpoint.ipynb 0 → 100644
View file @ 0b35b6a7
{
"metadata": {
"name": "",
"signature": "sha256:d03d3f5dbf9a1dbfc43deb947718f31529d3d67b0901f8e743b23ce28a9f3205"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "code",
"collapsed": false,
"input": [
"from parsing.NgramsExtractors import NgramsExtractorsCache"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c = NgramsExtractorsCache()"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"en\"]"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 3,
"text": [
"<parsing.NgramsExtractors.EnglishNgramsExtractor.EnglishNgramsExtractor at 0x7fc3aa431f98>"
]
}
],
"prompt_number": 3
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"fre\"]"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 5,
"text": [
"<parsing.NgramsExtractors.FrenchNgramsExtractor.FrenchNgramsExtractor at 0x7f0e1fb0c978>"
]
}
],
"prompt_number": 5
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"p = c[\"fr\"]"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 6
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"p.extract_ngrams(\"En voil\u00e0 un beau parseur !\")"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 8,
"text": [
"[[('beau', 'NN'), ('parseur', 'NN')]]"
]
}
],
"prompt_number": 8
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"fr\"]"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 9,
"text": [
"<parsing.NgramsExtractors.FrenchNgramsExtractor.FrenchNgramsExtractor at 0x7f0e1fb0c978>"
]
}
],
"prompt_number": 9
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"french\"]"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 10,
"text": [
"<parsing.NgramsExtractors.FrenchNgramsExtractor.FrenchNgramsExtractor at 0x7f0e1fb0c978>"
]
}
],
"prompt_number": 10
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"german\"]"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 11,
"text": [
"<parsing.NgramsExtractors.FrenchNgramsExtractor.FrenchNgramsExtractor at 0x7f0e1fb0c978>"
]
}
],
"prompt_number": 11
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"dutch\"]"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 12,
"text": [
"<parsing.NgramsExtractors.FrenchNgramsExtractor.FrenchNgramsExtractor at 0x7f0e1fb0c978>"
]
}
],
"prompt_number": 12
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"]"
],
"language": "python",
"metadata": {},
"outputs": []
}
],
"metadata": {}
}
]
}
\ No newline at end of file
Test extractor cache.ipynb 0 → 100644
View file @ 0b35b6a7
{
"metadata": {
"name": "",
"signature": "sha256:cb74945a57bed4d2ec124c7c05411b9346c7601e8339e613ddbc37fb950c4d86"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "code",
"collapsed": false,
"input": [
"from parsing.NgramsExtractors import NgramsExtractorsCache"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c = NgramsExtractorsCache()"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"en\"]"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 3,
"text": [
"<parsing.NgramsExtractors.EnglishNgramsExtractor.EnglishNgramsExtractor at 0x7f8d14947c88>"
]
}
],
"prompt_number": 3
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"fre\"]"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 4,
"text": [
"<parsing.NgramsExtractors.FrenchNgramsExtractor.FrenchNgramsExtractor at 0x7f8d24a97d30>"
]
}
],
"prompt_number": 4
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"p = c[\"fr\"]"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 5
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"p.extract_ngrams(\"En voil\u00e0 un beau parseur !\")"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 6,
"text": [
"[[('beau', 'NN'), ('parseur', 'NN')]]"
]
}
],
"prompt_number": 6
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"fr\"]"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 7,
"text": [
"<parsing.NgramsExtractors.FrenchNgramsExtractor.FrenchNgramsExtractor at 0x7f8d24a97d30>"
]
}
],
"prompt_number": 7
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"french\"]"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 8,
"text": [
"<parsing.NgramsExtractors.FrenchNgramsExtractor.FrenchNgramsExtractor at 0x7f8d24a97d30>"
]
}
],
"prompt_number": 8
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"german\"]"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 9,
"text": [
"<parsing.NgramsExtractors.NgramsExtractor.NgramsExtractor at 0x7f8d24a979e8>"
]
}
],
"prompt_number": 9
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"dutch\"]"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 10,
"text": [
"<parsing.NgramsExtractors.NgramsExtractor.NgramsExtractor at 0x7f8d24a979e8>"
]
}
],
"prompt_number": 10
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"c[\"italian\"].extract_ngrams(\"Est-ce un texte ?\")"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"Warning: parsing empty text\n"
]
},
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 14,
"text": [
"[]"
]
}
],
"prompt_number": 14
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
}
],
"metadata": {}
}
]
}
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment