def get_event_state_tweets_count(self,
index="test3",
session="",
words="",
state="confirmed"):
my_connector = Es_connector(index=index)
query = {
"query": {
"bool": {
"must": [{
"match": {
"text": {
"query": words
}
}
}],
"filter": {
"bool": {
"should": [{
"match": {
"session_" + session: state
}
}]
}
}
}
}
}
res = my_connector.count(query)
return res['count']
def get_words_count(self, index="test3", words=""):
my_connector = Es_connector(index=index)
query = {
"query": {
"simple_query_string": {
"fields": ["text"],
"query": words
}
}
}
res = my_connector.count(query)
return res['count']
def get_range_count(self, index, start, end):
my_connector = Es_connector(index=index)
query = {
"query": {
"range": {
"timestamp_ms": {
"gt": str(start),
"lt": str(end)
}
}
}
}
print(query)
res = my_connector.count(query)
return res['count']
def get_words_tweets_count(self, index="test3", session="", words=""):
my_connector = Es_connector(index=index)
query = {
"query": {
"bool": {
"must": [{
"match": {
"text": {
"query": words
}
}
}]
}
}
}
res = my_connector.count(query)
return res['count']
def get_event_tweets_count(self,
index="test3",
main_term="",
related_terms=""):
my_connector = Es_connector(index=index)
terms = []
words = main_term + ' '
for t in related_terms:
terms.append(
{"match": {
"text": {
"query": t['word'],
"boost": t['value']
}
}})
words += t['word'] + " "
terms.append({"match": {"text": {"query": main_term, "boost": 2}}})
query = {"query": {"bool": {"should": terms}}}
res = my_connector.count(query)
return res['count']
def get_event_clusters(self,
index="test3",
main_term="",
related_terms=""):
my_connector = Es_connector(index=index)
terms = []
words = main_term + ' '
for t in related_terms:
terms.append(
{"match": {
"text": {
"query": t['word'],
"boost": t['value']
}
}})
words += t['word'] + " "
terms.append({"match": {"text": {"query": main_term, "boost": 2}}})
# query = {
# "size": 0,
# "query": {
# "bool": {
# "should": terms
# }
# },
# "aggs": {
# "group_by_cluster": {
# "terms": {
# "field": "imagesCluster",
# "size": 200
# }
# }
# }
# }
query = {
"size": 0,
"query": {
"bool": {
"should": terms
}
},
"aggregations": {
"group_by_cluster": {
"terms": {
"field": "imagesCluster",
# "shard_size": 999999999,
"size": 999999
}
}
}
}
# print(query)
res = my_connector.search(query)
# print("Clusters")
# print(res['aggregations']['group_by_cluster']['buckets'])
clusters = res['aggregations']['group_by_cluster']['buckets']
with open(index + '.json') as f:
data = json.load(f)
for cluster in clusters:
# q1 = {
# "_source": [
# "text",
# "imagesCluster"
# ],
# "query": {
# "bool": {
# "should": terms,
# "filter": {
# "bool": {
# "should": [
# {
# "match": {
# "imagesCluster": cluster['key']
# }
# }
# ]
# }
# }
# }
# }
# }
q2 = {"query": {"term": {"imagesCluster": cluster['key']}}}
# cres1 = my_connector.search(q1)
cres = my_connector.count(q2)
# print(cluster['key'])
images = data['duplicates'][cluster['key']]
# print(images[0])
cluster['image'] = images[0]
# cluster['size'] = len(images)
# print(cres)
cluster['size'] = cres['count']
# cluster['size2'] = cres1['hits']['total']
# if cluster['key']==1452:
# print(cluster)
# print(clusters)
return clusters
def get_all_count(self, index="test3"):
my_connector = Es_connector(index=index)
query = {"query": {"match_all": {}}}
res = my_connector.count(query)
return res['count']