Created
July 13, 2017 23:45
-
-
Save psychemedia/ffc5912c037034790b132d3e28ed47d3 to your computer and use it in GitHub Desktop.
Demo notebook - using refine-client-py to access OpenRefine from Python
This file contains 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
{ | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"This example makes use of the Google/OpenRefine client that can be found at https://github.com/PaulMakepeace/refine-client-py\n", | |
"\n", | |
"The example is inspired by, and draws heavily from, Trevor Muñoz's tutorial posted at http://nbviewer.ipython.org/gist/trevormunoz/6265360\n", | |
"\n", | |
"---\n", | |
"First we need to import some necessary libraries..." | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"Collecting git+https://github.com/PaulMakepeace/refine-client-py.git\n", | |
"Collecting urllib2-file (from refine-client==0.2.1)\n", | |
" Using cached urllib2_file-0.2.1.tar.gz\n", | |
"Building wheels for collected packages: urllib2-file\n", | |
" Running setup.py bdist_wheel for urllib2-file ... \u001b[?25l-\b \b\\\b \bdone\n", | |
"Successfully built urllib2-file\n", | |
"Installing collected packages: urllib2-file, refine-client\n", | |
" Running setup.py install for refine-client ... \u001b[?25l-\b \bdone\n", | |
"\u001b[?25hSuccessfully installed refine-client-0.2.1 urllib2-file-0.2.1\n", | |
"\u001b[33mYou are using pip version 7.1.2, however version 9.0.1 is available.\n", | |
"You should consider upgrading via the 'pip install --upgrade pip' command.\u001b[0m\n" | |
] | |
} | |
], | |
"source": [ | |
"!~/anaconda/bin/pip install git+https://github.com/PaulMakepeace/refine-client-py.git" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 10, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"\u001b[33mYou are using pip version 7.1.2, however version 9.0.1 is available.\n", | |
"You should consider upgrading via the 'pip install --upgrade pip' command.\u001b[0m\n" | |
] | |
} | |
], | |
"source": [ | |
"!~/anaconda/bin/pip install refine-client" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 5, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"from google.refine import refine, facet" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Make sure you have OpenRefine running locally before going any further! (You can download and install it from [OpenRefine.org](http://openrefine.org).)\n", | |
"\n", | |
"Once you've started OpenRefine in the normal way, get a link to the server..." | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 8, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"server = refine.RefineServer()\n", | |
"orefine = refine.Refine(server)" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Let's check everything's working by previewing three examples from the list of any projects that have previously been created..." | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 9, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"[(u'1526469065323',\n", | |
" {u'created': u'2015-02-01T13:29:38Z',\n", | |
" u'customMetadata': {},\n", | |
" u'modified': u'2015-02-01T13:29:38Z',\n", | |
" u'name': u'UK MPs'}),\n", | |
" (u'2104805151035',\n", | |
" {u'created': u'2015-09-10T23:45:39Z',\n", | |
" u'customMetadata': {},\n", | |
" u'modified': u'2015-09-10T23:45:39Z',\n", | |
" u'name': u'localweblist csv'}),\n", | |
" (u'2132091692801',\n", | |
" {u'created': u'2015-09-04T10:40:12Z',\n", | |
" u'customMetadata': {},\n", | |
" u'modified': u'2015-09-04T10:40:12Z',\n", | |
" u'name': u'Data on Written Complaints in the NHS 2014 15 KO41b csv csv'})]" | |
] | |
}, | |
"execution_count": 9, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"orefine.list_projects().items()[:3]" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"If we want to work with one of these projects, we can open it directly:" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 5, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"project_file = 'smalltest.csv'" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 17, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"p=orefine.new_project(project_file=project_file)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 25, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"pr=p.get_rows(limit=10)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 14, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"['__class__',\n", | |
" '__delattr__',\n", | |
" '__dict__',\n", | |
" '__doc__',\n", | |
" '__format__',\n", | |
" '__getattribute__',\n", | |
" '__getitem__',\n", | |
" '__hash__',\n", | |
" '__init__',\n", | |
" '__module__',\n", | |
" '__new__',\n", | |
" '__reduce__',\n", | |
" '__reduce_ex__',\n", | |
" '__repr__',\n", | |
" '__setattr__',\n", | |
" '__sizeof__',\n", | |
" '__str__',\n", | |
" '__subclasshook__',\n", | |
" '__weakref__',\n", | |
" 'flagged',\n", | |
" 'index',\n", | |
" 'row',\n", | |
" 'starred']" | |
] | |
}, | |
"execution_count": 14, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"dir(pr.rows[0])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 29, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"[u'! LTD',\n", | |
" 8209948,\n", | |
" None,\n", | |
" None,\n", | |
" u'METROHOUSE 57 PEPPER ROAD',\n", | |
" u'HUNSLET',\n", | |
" u'LEEDS',\n", | |
" u'YORKSHIRE',\n", | |
" u'UNITED KINGDOM',\n", | |
" u'LS10 2RU',\n", | |
" u'Private Limited Company',\n", | |
" u'Active',\n", | |
" u'United Kingdom',\n", | |
" None,\n", | |
" u'11/09/2012',\n", | |
" 30,\n", | |
" 9,\n", | |
" u'11/06/2014',\n", | |
" None,\n", | |
" u'NO ACCOUNTS FILED',\n", | |
" u'09/10/2014',\n", | |
" u'11/09/2013',\n", | |
" 0,\n", | |
" 0,\n", | |
" 0,\n", | |
" 0,\n", | |
" u'99999 - Dormant Company',\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" 0,\n", | |
" 0,\n", | |
" u'http://business.data.gov.uk/id/company/08209948',\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None]" | |
] | |
}, | |
"execution_count": 29, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"pr.rows[0].row" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 32, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"f=facet.TextFacet('CompanyName')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 33, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"['__class__',\n", | |
" '__delattr__',\n", | |
" '__dict__',\n", | |
" '__doc__',\n", | |
" '__format__',\n", | |
" '__getattribute__',\n", | |
" '__hash__',\n", | |
" '__init__',\n", | |
" '__module__',\n", | |
" '__new__',\n", | |
" '__reduce__',\n", | |
" '__reduce_ex__',\n", | |
" '__repr__',\n", | |
" '__setattr__',\n", | |
" '__sizeof__',\n", | |
" '__str__',\n", | |
" '__subclasshook__',\n", | |
" '__weakref__',\n", | |
" 'as_dict',\n", | |
" 'column_name',\n", | |
" 'exclude',\n", | |
" 'expression',\n", | |
" 'include',\n", | |
" 'invert',\n", | |
" 'name',\n", | |
" 'omit_blank',\n", | |
" 'omit_error',\n", | |
" 'reset',\n", | |
" 'select_blank',\n", | |
" 'select_error',\n", | |
" 'selection',\n", | |
" 'type']" | |
] | |
}, | |
"execution_count": 33, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"dir(f)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 42, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"fr=p.compute_facets(facet.TextFacet('CompanyName'))" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 43, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"1 !YOZO FASS LIMITED\n", | |
"1 !OBAC UK LIMITED\n", | |
"1 !NFERNO LTD.\n", | |
"1 !ST MEDIA SOUTHAMPTON LTD\n", | |
"1 !OBAC INSTALLATIONS LIMITED\n", | |
"1 !NSPIRED LTD\n", | |
"1 !OBAC MAGNETIC FLOOR TECHNOLOGY\n", | |
"1 ! LTD\n", | |
"1 !BIG IMPACT GRAPHICS LIMITED\n" | |
] | |
} | |
], | |
"source": [ | |
"facets = fr.facets[0]\n", | |
"for k in sorted(facets.choices, key=lambda k: facets.choices[k].count, reverse=True):\n", | |
" print facets.choices[k].count, k" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 50, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"[{u'cells': [{u'v': u'! LTD'},\n", | |
" {u'v': 8209948},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': u'METROHOUSE 57 PEPPER ROAD'},\n", | |
" {u'v': u'HUNSLET'},\n", | |
" {u'v': u'LEEDS'},\n", | |
" {u'v': u'YORKSHIRE'},\n", | |
" {u'v': u'UNITED KINGDOM'},\n", | |
" {u'v': u'LS10 2RU'},\n", | |
" {u'v': u'Private Limited Company'},\n", | |
" {u'v': u'Active'},\n", | |
" {u'v': u'United Kingdom'},\n", | |
" None,\n", | |
" {u'v': u'11/09/2012'},\n", | |
" {u'v': 30},\n", | |
" {u'v': 9},\n", | |
" {u'v': u'11/06/2014'},\n", | |
" None,\n", | |
" {u'v': u'NO ACCOUNTS FILED'},\n", | |
" {u'v': u'09/10/2014'},\n", | |
" {u'v': u'11/09/2013'},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'99999 - Dormant Company'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'http://business.data.gov.uk/id/company/08209948'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None],\n", | |
" u'flagged': False,\n", | |
" u'i': 0,\n", | |
" u'starred': False},\n", | |
" {u'cells': [{u'v': u'!BIG IMPACT GRAPHICS LIMITED'},\n", | |
" {u'v': 7382019},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': u'335 ROSDEN HOUSE'},\n", | |
" {u'v': u'372 OLD STREET'},\n", | |
" {u'v': u'LONDON'},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': u'EC1V 9AV'},\n", | |
" {u'v': u'Private Limited Company'},\n", | |
" {u'v': u'Active'},\n", | |
" {u'v': u'United Kingdom'},\n", | |
" None,\n", | |
" {u'v': u'21/09/2010'},\n", | |
" {u'v': 30},\n", | |
" {u'v': 9},\n", | |
" {u'v': u'30/06/2014'},\n", | |
" {u'v': u'30/09/2012'},\n", | |
" {u'v': u'DORMANT'},\n", | |
" {u'v': u'19/10/2014'},\n", | |
" {u'v': u'21/09/2013'},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'59112 - Video production activities'},\n", | |
" {u'v': u'59113 - Television programme production activities'},\n", | |
" {u'v': u'74100 - specialised design activities'},\n", | |
" {u'v': u'74202 - Other specialist photography'},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'http://business.data.gov.uk/id/company/07382019'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None],\n", | |
" u'flagged': False,\n", | |
" u'i': 1,\n", | |
" u'starred': False},\n", | |
" {u'cells': [{u'v': u'!NFERNO LTD.'},\n", | |
" {u'v': 4753368},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': u'FIRST FLOOR THAVIES INN HOUSE 3-4'},\n", | |
" {u'v': u'HOLBORN CIRCUS'},\n", | |
" {u'v': u'LONDON'},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': u'EC1N 2HA'},\n", | |
" {u'v': u'Private Limited Company'},\n", | |
" {u'v': u'Active'},\n", | |
" {u'v': u'United Kingdom'},\n", | |
" None,\n", | |
" {u'v': u'03/05/2003'},\n", | |
" {u'v': 31},\n", | |
" {u'v': 10},\n", | |
" {u'v': u'31/07/2014'},\n", | |
" {u'v': u'31/10/2012'},\n", | |
" {u'v': u'TOTAL EXEMPTION FULL'},\n", | |
" {u'v': u'31/05/2014'},\n", | |
" {u'v': u'03/05/2013'},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'82990 - Other business support service activities n.e.c.'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'http://business.data.gov.uk/id/company/04753368'},\n", | |
" {u'v': u'27/01/2009'},\n", | |
" {u'v': u'DISTINCTIVE IMPRINT WORLDWIDE LIMITED'},\n", | |
" {u'v': u'02/09/2003'},\n", | |
" {u'v': u'DISTINCTIVE IMPRINT CONSULTANTS LIMITED'},\n", | |
" {u'v': u'03/07/2003'},\n", | |
" {u'v': u'AMEROOLA CONSULTANTS LIMITED'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None],\n", | |
" u'flagged': False,\n", | |
" u'i': 2,\n", | |
" u'starred': False},\n", | |
" {u'cells': [{u'v': u'!NSPIRED LTD'},\n", | |
" {u'v': u'SC421617'},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': u'12 BON ACCORD SQUARE'},\n", | |
" None,\n", | |
" {u'v': u'ABERDEEN'},\n", | |
" None,\n", | |
" {u'v': u'SCOTLAND'},\n", | |
" {u'v': u'AB11 6DJ'},\n", | |
" {u'v': u'Private Limited Company'},\n", | |
" {u'v': u'Active'},\n", | |
" {u'v': u'United Kingdom'},\n", | |
" None,\n", | |
" {u'v': u'11/04/2012'},\n", | |
" {u'v': 31},\n", | |
" {u'v': 3},\n", | |
" {u'v': u'31/12/2013'},\n", | |
" None,\n", | |
" {u'v': u'NO ACCOUNTS FILED'},\n", | |
" {u'v': u'09/05/2014'},\n", | |
" {u'v': u'11/04/2013'},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'70229 - Management consultancy activities other than financial management'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'http://business.data.gov.uk/id/company/SC421617'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None],\n", | |
" u'flagged': False,\n", | |
" u'i': 3,\n", | |
" u'starred': False},\n", | |
" {u'cells': [{u'v': u'!OBAC INSTALLATIONS LIMITED'},\n", | |
" {u'v': 7527820},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': u'DEVONSHIRE HOUSE'},\n", | |
" {u'v': u'60 GOSWELL ROAD'},\n", | |
" {u'v': u'LONDON'},\n", | |
" None,\n", | |
" {u'v': u'UNITED KINGDOM'},\n", | |
" {u'v': u'EC1M 7AD'},\n", | |
" {u'v': u'Private Limited Company'},\n", | |
" {u'v': u'Active'},\n", | |
" {u'v': u'United Kingdom'},\n", | |
" None,\n", | |
" {u'v': u'14/02/2011'},\n", | |
" {u'v': 31},\n", | |
" {u'v': 12},\n", | |
" {u'v': u'30/09/2014'},\n", | |
" {u'v': u'31/12/2012'},\n", | |
" {u'v': u'DORMANT'},\n", | |
" {u'v': u'14/03/2014'},\n", | |
" {u'v': u'14/02/2013'},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'43330 - Floor and wall covering'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'http://business.data.gov.uk/id/company/07527820'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None],\n", | |
" u'flagged': False,\n", | |
" u'i': 4,\n", | |
" u'starred': False},\n", | |
" {u'cells': [{u'v': u'!OBAC MAGNETIC FLOOR TECHNOLOGY'},\n", | |
" {u'v': u'FC031362'},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': u'1ST AND 2ND FLOORS ELIZABETH HOUSE'},\n", | |
" {u'v': u'LES RUETIES BRAYES'},\n", | |
" {u'v': u'ST PETER PORT'},\n", | |
" {u'v': u'GY1 1EW'},\n", | |
" {u'v': u'GUERNSEY'},\n", | |
" None,\n", | |
" {u'v': u'Other company type'},\n", | |
" {u'v': u'Active'},\n", | |
" {u'v': u'CHANNEL ISLANDS'},\n", | |
" None,\n", | |
" {u'v': u'30/11/2012'},\n", | |
" {u'v': 31},\n", | |
" {u'v': 12},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': u'NO ACCOUNTS FILED'},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'None Supplied'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'http://business.data.gov.uk/id/company/FC031362'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None],\n", | |
" u'flagged': False,\n", | |
" u'i': 5,\n", | |
" u'starred': False},\n", | |
" {u'cells': [{u'v': u'!OBAC UK LIMITED'},\n", | |
" {u'v': 7687209},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': u'DEVONSHIRE HOUSE'},\n", | |
" {u'v': u'60 GOSWELL ROAD'},\n", | |
" {u'v': u'LONDON'},\n", | |
" None,\n", | |
" {u'v': u'UNITED KINGDOM'},\n", | |
" {u'v': u'EC1M 7AD'},\n", | |
" {u'v': u'Private Limited Company'},\n", | |
" {u'v': u'Active'},\n", | |
" {u'v': u'United Kingdom'},\n", | |
" None,\n", | |
" {u'v': u'29/06/2011'},\n", | |
" {u'v': 29},\n", | |
" {u'v': 12},\n", | |
" {u'v': u'29/09/2014'},\n", | |
" {u'v': u'29/12/2012'},\n", | |
" {u'v': u'TOTAL EXEMPTION FULL'},\n", | |
" {u'v': u'27/07/2014'},\n", | |
" {u'v': u'29/06/2013'},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'70229 - Management consultancy activities other than financial management'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'http://business.data.gov.uk/id/company/07687209'},\n", | |
" {u'v': u'15/07/2011'},\n", | |
" {u'v': u'!OBAC FITTINGS LIMITED'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None],\n", | |
" u'flagged': False,\n", | |
" u'i': 6,\n", | |
" u'starred': False},\n", | |
" {u'cells': [{u'v': u'!ST MEDIA SOUTHAMPTON LTD'},\n", | |
" {u'v': 7904170},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': u'10 NORTHBROOK HOUSE'},\n", | |
" {u'v': u'FREE STREET, BISHOPS WALTHAM'},\n", | |
" {u'v': u'SOUTHAMPTON'},\n", | |
" None,\n", | |
" {u'v': u'ENGLAND'},\n", | |
" {u'v': u'SO32 1NP'},\n", | |
" {u'v': u'Private Limited Company'},\n", | |
" {u'v': u'Active - Proposal to Strike off'},\n", | |
" {u'v': u'United Kingdom'},\n", | |
" None,\n", | |
" {u'v': u'10/01/2012'},\n", | |
" {u'v': 31},\n", | |
" {u'v': 1},\n", | |
" {u'v': u'10/10/2013'},\n", | |
" None,\n", | |
" {u'v': u'NO ACCOUNTS FILED'},\n", | |
" {u'v': u'07/02/2013'},\n", | |
" None,\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'None Supplied'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'http://business.data.gov.uk/id/company/07904170'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None],\n", | |
" u'flagged': False,\n", | |
" u'i': 7,\n", | |
" u'starred': False},\n", | |
" {u'cells': [{u'v': u'!YOZO FASS LIMITED'},\n", | |
" {u'v': 2714021},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': u'1 VERONICA HOUSE'},\n", | |
" {u'v': u'WICKHAM ROAD'},\n", | |
" {u'v': u'BROCKLEY'},\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': u'SE4 1NQ'},\n", | |
" {u'v': u'Private Limited Company'},\n", | |
" {u'v': u'Active'},\n", | |
" {u'v': u'United Kingdom'},\n", | |
" None,\n", | |
" {u'v': u'12/05/1992'},\n", | |
" {u'v': 31},\n", | |
" {u'v': 3},\n", | |
" {u'v': u'31/12/2013'},\n", | |
" {u'v': u'31/03/2012'},\n", | |
" {u'v': u'DORMANT'},\n", | |
" {u'v': u'09/06/2014'},\n", | |
" {u'v': u'12/05/2013'},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'90010 - Performing arts'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" {u'v': 0},\n", | |
" {u'v': 0},\n", | |
" {u'v': u'http://business.data.gov.uk/id/company/02714021'},\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None,\n", | |
" None],\n", | |
" u'flagged': False,\n", | |
" u'i': 8,\n", | |
" u'starred': False}]" | |
] | |
}, | |
"execution_count": 50, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"dir(pr.rows.rows_response)\n", | |
"pr.rows.rows_response" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 53, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"['RefineRows',\n", | |
" '__class__',\n", | |
" '__delattr__',\n", | |
" '__dict__',\n", | |
" '__doc__',\n", | |
" '__format__',\n", | |
" '__getattribute__',\n", | |
" '__hash__',\n", | |
" '__init__',\n", | |
" '__module__',\n", | |
" '__new__',\n", | |
" '__reduce__',\n", | |
" '__reduce_ex__',\n", | |
" '__repr__',\n", | |
" '__setattr__',\n", | |
" '__sizeof__',\n", | |
" '__str__',\n", | |
" '__subclasshook__',\n", | |
" '__weakref__',\n", | |
" 'filtered',\n", | |
" 'limit',\n", | |
" 'mode',\n", | |
" 'rows',\n", | |
" 'start',\n", | |
" 'total']" | |
] | |
}, | |
"execution_count": 53, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"dir(pr)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 54, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"['__doc__',\n", | |
" '__init__',\n", | |
" '__module__',\n", | |
" 'add_column',\n", | |
" 'annotate_one_row',\n", | |
" 'apply_operations',\n", | |
" 'blank_down',\n", | |
" 'clusterer_defaults',\n", | |
" 'column_order',\n", | |
" 'columns',\n", | |
" 'compute_clusters',\n", | |
" 'compute_facets',\n", | |
" 'delete',\n", | |
" 'do_json',\n", | |
" 'do_raw',\n", | |
" 'edit',\n", | |
" 'engine',\n", | |
" 'export',\n", | |
" 'export_rows',\n", | |
" 'fill_down',\n", | |
" 'flag_row',\n", | |
" 'get_models',\n", | |
" 'get_preference',\n", | |
" 'get_reconciliation_service_by_name_or_url',\n", | |
" 'get_reconciliation_services',\n", | |
" 'get_rows',\n", | |
" 'guess_types_of_column',\n", | |
" 'has_records',\n", | |
" 'history_entry',\n", | |
" 'key_column',\n", | |
" 'mass_edit',\n", | |
" 'move_column',\n", | |
" 'project_id',\n", | |
" 'project_name',\n", | |
" 'project_url',\n", | |
" 'recon_services',\n", | |
" 'reconcile',\n", | |
" 'remove_rows',\n", | |
" 'rename_column',\n", | |
" 'reorder_columns',\n", | |
" 'reorder_rows',\n", | |
" 'rows_response_factory',\n", | |
" 'server',\n", | |
" 'sorting',\n", | |
" 'split_column',\n", | |
" 'star_row',\n", | |
" 'text_transform',\n", | |
" 'transpose_columns_into_rows',\n", | |
" 'transpose_rows_into_columns',\n", | |
" 'wait_until_idle']" | |
] | |
}, | |
"execution_count": 54, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"dir(p)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 55, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"[u'CompanyName',\n", | |
" u'CompanyNumber',\n", | |
" u'RegAddress.CareOf',\n", | |
" u'RegAddress.POBox',\n", | |
" u'RegAddress.AddressLine1',\n", | |
" u'RegAddress.AddressLine2',\n", | |
" u'RegAddress.PostTown',\n", | |
" u'RegAddress.County',\n", | |
" u'RegAddress.Country',\n", | |
" u'RegAddress.PostCode',\n", | |
" u'CompanyCategory',\n", | |
" u'CompanyStatus',\n", | |
" u'CountryOfOrigin',\n", | |
" u'DissolutionDate',\n", | |
" u'IncorporationDate',\n", | |
" u'Accounts.AccountRefDay',\n", | |
" u'Accounts.AccountRefMonth',\n", | |
" u'Accounts.NextDueDate',\n", | |
" u'Accounts.LastMadeUpDate',\n", | |
" u'Accounts.AccountCategory',\n", | |
" u'Returns.NextDueDate',\n", | |
" u'Returns.LastMadeUpDate',\n", | |
" u'Mortgages.NumMortCharges',\n", | |
" u'Mortgages.NumMortOutstanding',\n", | |
" u'Mortgages.NumMortPartSatisfied',\n", | |
" u'Mortgages.NumMortSatisfied',\n", | |
" u'SICCode.SicText_1',\n", | |
" u'SICCode.SicText_2',\n", | |
" u'SICCode.SicText_3',\n", | |
" u'SICCode.SicText_4',\n", | |
" u'LimitedPartnerships.NumGenPartners',\n", | |
" u'LimitedPartnerships.NumLimPartners',\n", | |
" u'URI',\n", | |
" u'PreviousName_1.CONDATE',\n", | |
" u'PreviousName_1.CompanyName',\n", | |
" u'PreviousName_2.CONDATE',\n", | |
" u'PreviousName_2.CompanyName',\n", | |
" u'PreviousName_3.CONDATE',\n", | |
" u'PreviousName_3.CompanyName',\n", | |
" u'PreviousName_4.CONDATE',\n", | |
" u'PreviousName_4.CompanyName',\n", | |
" u'PreviousName_5.CONDATE',\n", | |
" u'PreviousName_5.CompanyName',\n", | |
" u'PreviousName_6.CONDATE',\n", | |
" u'PreviousName_6.CompanyName',\n", | |
" u'PreviousName_7.CONDATE',\n", | |
" u'PreviousName_7.CompanyName',\n", | |
" u'PreviousName_8.CONDATE',\n", | |
" u'PreviousName_8.CompanyName',\n", | |
" u'PreviousName_9.CONDATE',\n", | |
" u'PreviousName_9.CompanyName',\n", | |
" u'PreviousName_10.CONDATE',\n", | |
" u'PreviousName_10.CompanyName']" | |
] | |
}, | |
"execution_count": 55, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"p.columns" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 2", | |
"language": "python", | |
"name": "python2" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 2 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython2", | |
"version": "2.7.11" | |
}, | |
"widgets": { | |
"state": {}, | |
"version": "1.1.2" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 0 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment