def trackWord(terms):
'''VocabularyMonitor.trackClouds service. Expects a list of terms to be
sent to the Vocabulary monitor, and returns a JSON representation of the
response.'''
params = app.config['trackParser'].parse_args()
termList = terms.split(',')
termList = [ term.strip() for term in termList ]
termList = [ term.lower() for term in termList ]
results, links = \
app.config['vm'].trackClouds(termList, maxTerms=params['maxTerms'],
maxRelatedTerms=params['maxRelatedTerms'],
startKey=params['startKey'],
endKey=params['endKey'],
minSim=params['minSim'],
wordBoost=params['wordBoost'],
forwards=params['forwards'],
sumSimilarity=params['boostMethod'],
algorithm=params['algorithm'],
cleaningFunction=app.config['cleaningFunction'] if params[
'doCleaning'] else None
)
agg = VocabularyAggregator(weighF=params['aggWeighFunction'],
wfParam=params['aggWFParam'],
yearsInInterval=params['aggYearsInInterval'],
nWordsPerYear=params['aggWordsPerYear']
)
aggResults, aggMetadata = agg.aggregate(results)
embedded = doSpaceEmbedding(app.config['vm'], results, aggMetadata)
networks = yearlyNetwork(aggMetadata, aggResults, results, links)
return jsonify(stream=yearTuplesAsDict(aggResults),
networks=networks,
embedded=embedded,
vocabs=links)
def trackWord(terms):
'''VocabularyMonitor.trackClouds service. Expects a list of terms to be
sent to the Vocabulary monitor, and returns a JSON representation of the
response.'''
params = app.config['trackParser'].parse_args()
termList = terms.split(',')
termList = [term.strip() for term in termList]
termList = [term.lower() for term in termList]
results, links = \
app.config['vm'].trackClouds(termList, maxTerms=params['maxTerms'],
maxRelatedTerms=params['maxRelatedTerms'],
startKey=params['startKey'],
endKey=params['endKey'],
minSim=params['minSim'],
wordBoost=params['wordBoost'],
forwards=params['forwards'],
sumSimilarity=params['boostMethod'],
algorithm=params['algorithm'],
cleaningFunction=app.config['cleaningFunction'] if params[
'doCleaning'] else None
)
agg = VocabularyAggregator(weighF=params['aggWeighFunction'],
wfParam=params['aggWFParam'],
yearsInInterval=params['aggYearsInInterval'],
nWordsPerYear=params['aggWordsPerYear'])
aggResults, aggMetadata = agg.aggregate(results)
embedded = doSpaceEmbedding(app.config['vm'], results, aggMetadata)
networks = yearlyNetwork(aggMetadata, aggResults, results, links)
return jsonify(stream=yearTuplesAsDict(aggResults),
networks=networks,
embedded=embedded,
vocabs=links)
def testYearlyNetwork(self):
'''Test building of yearly networks'''
networks = fmt.yearlyNetwork(self._aggPeriods, self._aggVocab,
self._vocab, self._links)
self.assertEqual(sorted(networks.keys()), list(self._aggVocab.keys()),
'A network should be created for each aggregated '
'vocabulary')
self.assertEqual(
sorted(networks.keys()), list(self._aggPeriods.keys()),
'A network should be created for each aggregation period')
for year, net in networks.iteritems():
self.assertEqual(sorted(net.keys()), sorted(['nodes', 'links']),
'Each network should contain "nodes" and "links"'
'but %s does not' % year)
for node in net['nodes']:
self.assertEqual(sorted(node.keys()),
sorted(['name', 'type', 'count']),
'Each node should contain "name", "type" and '
'"count", but a node on %s does not' % year)
for link in net['links']:
self.assertEqual(sorted(link.keys()),
sorted(['source', 'target', 'value']),
'Each link should contain "source", "target" '
'and "value", but a link on %s does not'
% year)
