def _getMostRecentPages(self, session):
es_info = self.esInfo(session['domainId'])
hits = []
if session['fromDate'] is None:
hits = get_most_recent_documents(session['pagesCap'], es_info['mapping'], ["url", "x", "y", es_info['mapping']["tag"], es_info['mapping']["timestamp"], es_info['mapping']["text"]],
session['filter'],
es_info['activeCrawlerIndex'],
es_info['docType'],
self._es)
else:
if(session['filter'] is None):
hits = range(es_info['mapping']["timestamp"], session['fromDate'], session['toDate'], ['url',"x", "y", es_info['mapping']['tag'], es_info['mapping']["timestamp"], es_info['mapping']["text"]], True, session['pagesCap'],
es_info['activeCrawlerIndex'],
es_info['docType'],
self._es)
else:
s_fields = {
es_info['mapping']["text"]: "(" + session['filter'].replace('"','\"') + ")",
es_info['mapping']["timestamp"]: "[" + str(session['fromDate']) + " TO " + str(session['toDate']) + "]"
}
hits = multifield_query_search(s_fields, session['pagesCap'], ["url", "x", "y", es_info['mapping']["tag"], es_info['mapping']["timestamp"], es_info['mapping']["text"]],
es_info['activeCrawlerIndex'],
es_info['docType'],
self._es)
return hits
def _getPagesForQueries(self, session):
es_info = self.esInfo(session['domainId'])
s_fields = {}
if not session['filter'] is None:
s_fields[es_info['mapping']["text"]] = session['filter'].replace('"','\"')
if not session['fromDate'] is None:
s_fields[es_info['mapping']["timestamp"]] = "[" + str(session['fromDate']) + " TO " + str(session['toDate']) + "]"
hits=[]
queries = session['selected_queries'].split(',')
for query in queries:
s_fields[es_info['mapping']["query"]] = '"' + query + '"'
results= multifield_query_search(s_fields, session['pagesCap'], ["url", "x", "y", es_info['mapping']["tag"], es_info['mapping']["timestamp"], es_info['mapping']["text"]],
es_info['activeCrawlerIndex'],
es_info['docType'],
self._es)
hits.extend(results)
return hits
def getTermsSummarySeedCrawler(self, opt_maxNumberOfTerms = 40, session = None):
es_info = self.esInfo(session['domainId'])
format = '%m/%d/%Y %H:%M %Z'
if not session['fromDate'] is None:
session['fromDate'] = long(CrawlerModel.convert_to_epoch(datetime.strptime(session['fromDate'], format)) * 1000)
if not session['toDate'] is None:
session['toDate'] = long(CrawlerModel.convert_to_epoch(datetime.strptime(session['toDate'], format)) * 1000)
s_fields = {
"tag": "Positive",
"index": es_info['activeCrawlerIndex'],
"doc_type": es_info['docType']
}
pos_terms = [field['term'][0] for field in multifield_term_search(s_fields, self._capTerms, ['term'], self._termsIndex, 'terms', self._es)]
s_fields["tag"]="Negative"
neg_terms = [field['term'][0] for field in multifield_term_search(s_fields, self._capTerms, ['term'], self._termsIndex, 'terms', self._es)]
results = term_search(es_info['mapping']['tag'], ['Relevant'], self._pagesCapTerms, ['url', es_info['mapping']['text']], es_info['activeCrawlerIndex'], es_info['docType'], self._es)
pos_urls = [field["id"] for field in results]
top_terms = []
top_bigrams = []
top_trigrams = []
if session['filter'] is None:
urls = []
if len(pos_urls) > 0:
# If positive urls are available search for more documents like them
results_more_like_pos = get_more_like_this(pos_urls, ['url', es_info['mapping']["text"]], self._pagesCapTerms, es_info['activeCrawlerIndex'], es_info['docType'], self._es)
results.extend(results_more_like_pos)
urls = pos_urls[0:self._pagesCapTerms] + [field['id'] for field in results_more_like_pos]
if not urls:
# If positive urls are not available then get the most recent documents
results = get_most_recent_documents(self._pagesCapTerms, es_info['mapping'], ['url',es_info['mapping']["text"]], session['filter'], es_info['activeCrawlerIndex'], es_info['docType'], self._es)
urls = [field['id'] for field in results]
if len(results) > 0:
text = [field[es_info['mapping']["text"]][0] for field in results]
if len(urls) > 0:
tfidf_all = tfidf.tfidf(urls, pos_tags=self.pos_tags, mapping=es_info['mapping'], es_index=es_info['activeCrawlerIndex'], es_doc_type=es_info['docType'], es=self._es)
if pos_terms:
extract_terms_all = extract_terms.extract_terms(tfidf_all)
[ranked_terms, scores] = extract_terms_all.results(pos_terms)
top_terms = [ term for term in ranked_terms if (term not in neg_terms)]
top_terms = top_terms[0:opt_maxNumberOfTerms]
else:
top_terms = tfidf_all.getTopTerms(opt_maxNumberOfTerms)
if len(text) > 0:
[_,_,_,_,_,_,_,_,top_bigrams, top_trigrams] = get_bigrams_trigrams.get_bigrams_trigrams(text, urls, opt_maxNumberOfTerms+len(neg_terms), self.w2v, self._es)
top_bigrams = [term for term in top_bigrams if term not in neg_terms]
top_trigrams = [term for term in top_trigrams if term not in neg_terms]
else:
s_fields = {
es_info['mapping']["text"]: "(" + session['filter'].replace('"','\"') + ")"
}
if not session['fromDate'] is None:
s_fields[es_info['mapping']["timestamp"]] = "[" + str(session['fromDate']) + " TO " + str(session['toDate']) + "]"
results = multifield_query_search(s_fields, self._pagesCapTerms, ["url", es_info['mapping']["text"]],
es_info['activeCrawlerIndex'],
es_info['docType'],
self._es)
ids = [field['id'] for field in results]
text = [field[es_info['mapping']["text"]][0] for field in results]
urls = [field[es_info['mapping']["url"]][0] for field in results]
top_terms = get_significant_terms(ids, opt_maxNumberOfTerms, mapping=es_info['mapping'], es_index=es_info['activeCrawlerIndex'], es_doc_type=es_info['docType'], es=self._es)
if len(text) > 0:
[_,_,_,_,_,_,_,_,top_bigrams, top_trigrams] = get_bigrams_trigrams.get_bigrams_trigrams(text, urls, opt_maxNumberOfTerms+len(neg_terms), self.w2v, self._es)
top_bigrams = [term for term in top_bigrams if term not in neg_terms]
top_trigrams = [term for term in top_trigrams if term not in neg_terms]
s_fields = {
"tag": "Custom",
"index": es_info['activeCrawlerIndex'],
"doc_type": es_info['docType']
}
custom_terms = [field['term'][0] for field in multifield_query_search(s_fields, 500, ['term'], self._termsIndex, 'terms', self._es)]
top_terms = custom_terms + top_terms
if not top_terms:
return []
pos_freq = {}
if len(pos_urls) > 1:
tfidf_pos = tfidf.tfidf(pos_urls, pos_tags=self.pos_tags, mapping=es_info['mapping'], es_index=es_info['activeCrawlerIndex'], es_doc_type=es_info['docType'], es=self._es)
[_,corpus,ttfs_pos] = tfidf_pos.getTfArray()
total_pos_tf = np.sum(ttfs_pos, axis=0)
total_pos = np.sum(total_pos_tf)
pos_freq={}
for key in top_terms:
try:
pos_freq[key] = (float(total_pos_tf[corpus.index(key)])/total_pos)
except ValueError:
pos_freq[key] = 0
else:
pos_freq = { key: 0 for key in top_terms }
neg_urls = [field['id'] for field in term_search(es_info['mapping']['tag'], ['Irrelevant'], self._pagesCapTerms, ['url'], es_info['activeCrawlerIndex'], es_info['docType'], self._es)]
neg_freq = {}
if len(neg_urls) > 1:
tfidf_neg = tfidf.tfidf(neg_urls, pos_tags=self.pos_tags, mapping=es_info['mapping'], es_index=es_info['activeCrawlerIndex'], es_doc_type=es_info['docType'], es=self._es)
[_,corpus,ttfs_neg] = tfidf_neg.getTfArray()
total_neg_tf = np.sum(ttfs_neg, axis=0)
total_neg = np.sum(total_neg_tf)
neg_freq={}
for key in top_terms:
try:
neg_freq[key] = (float(total_neg_tf[corpus.index(key)])/total_neg)
except ValueError:
neg_freq[key] = 0
else:
neg_freq = { key: 0 for key in top_terms }
terms = []
s_fields = {
"term": "",
"index": es_info['activeCrawlerIndex'],
"doc_type": es_info['docType'],
}
results = []
for term in top_terms:
s_fields["term"] = term
res = multifield_term_search(s_fields, self._capTerms, ['tag', 'term'], self._termsIndex, 'terms', self._es)
results.extend(res)
tags = {result['term'][0]: result['tag'][0] for result in results}
for term in top_terms:
entry = [term, pos_freq[term], neg_freq[term], []]
if tags and not tags.get(term) is None:
entry[3] = tags[term].split(';')
terms.append(entry)
for term in top_bigrams:
entry = [term, 0, 0, []]
terms.append(entry)
for term in top_trigrams:
entry = [term, 0, 0, []]
terms.append(entry)
return terms