the python elasticsearch , elasticsearch dsl packages are life-saver and
got me converted to ES.
Now I am trying to use elasticsearch dsl package to create pivot tables in
ES but am having hard time figuring out how to chain the buckets
programmatically.
while chaining the buckets / metrics manually works, to chain them
programmatically seems impossible
here is an example
from elasticsearch import Elasticsearch
from elasticsearch_dsl import Search as dsl_search, A, Q, F
# create client
es = Elasticsearch('localhost:9200')
# data : from the definitive guide, slighlty modified
#data from the definitive guide
xData = [
{'doc_id' : 1, 'price' : 10000, 'color' : 'red', 'make' : 'honda',
'sold' : '2014-10-28', 'city': 'ROME', 'insurance': 'y'},
{'doc_id' : 2, 'price' : 20000, 'color' : 'red', 'make' : 'honda',
'sold' : '2014-11-05', 'city': 'ROME', 'insurance': 'n'},
{'doc_id' : 3, 'price' : 30000, 'color' : 'green', 'make' : 'ford',
'sold' : '2014-05-18', 'city': 'Berlin', 'insurance': 'y'},
{'doc_id' : 4, 'price' : 15000, 'color' : 'blue', 'make' : 'toyota',
'sold' : '2014-07-02', 'city': 'Berlin', 'insurance': 'n'},
{'doc_id' : 5, 'price' : 12000, 'color' : 'green', 'make' : 'toyota',
'sold' : '2014-08-19', 'city': 'Berlin', 'insurance': 'n'},
{'doc_id' : 6, 'price' : 20000, 'color' : 'red', 'make' : 'honda',
'sold' : '2014-11-05', 'city': 'Paris', 'insurance': 'n'},
{'doc_id' : 7, 'price' : 80000, 'color' : 'red', 'make' : 'bmw',
'sold' : '2014-01-01', 'city': 'Paris', 'insurance': 'y'},
{'doc_id' : 8, 'price' : 25000, 'color' : 'blue', 'make' : 'ford',
'sold' : '2014-02-12', 'city': 'Paris', 'insurance': 'y'}]
#create a mapping
my_mapping = {
'my_example': {
'properties': {
'doc_id': {'type': 'integer'},
'price': {'type': 'integer'},
'color': {'type': 'string', 'index': 'not_analyzed'},
'make': {'type': 'string', 'index': 'not_analyzed'},
'city': {'type': 'string', 'index': 'not_analyzed'},
'insurance': {'type': 'string', 'index': 'not_analyzed'},
'sold': {'type': 'date'}
}}}
#create an index and add the mapping
if es.indices.exists('my_index_test'):
es.indices.delete(index="my_index_test")
es.indices.create('my_index_test')
# mapping for the document type
if es.indices.exists_type(index = 'my_index_test', doc_type = 'my_example'):
es.indices.delete_mapping(index='my_index_test',doc_type='my_example')
es.indices.put_mapping(index='my_index_test',doc_type='my_example',body=my_mapping)
# indexing
for xRow in xData:
es.index(index = 'my_index',
doc_type= 'my_example',
id = xRow['doc_id'],
body = xRow
)
### MANUALLY CHAINING WORKS
a = A('terms', field = 'color')
b = A('terms', field = 'make')
c = A('terms', field = 'city')
s1 = dsl_search(es, index = 'my_index', doc_type= 'my_example')
s1.aggs.bucket('xColor', a).bucket('xMake', b).bucket('xCity', c)\
.metric('xMyPriceSum', 'sum', field = 'price')\
.metric('xMyPriceAvg', 'avg', field = 'price')
resp = s1.execute()
#get results
q1 = resp.aggregations
q1
#### but not PROGRAMMATICALLY
# Programmatically chaining
xVarBuckets = [{'field': 'color', 'label': 'xColor'},
{'field': 'make', 'label': 'xMake'},
{'field': 'city', 'label': 'xCity'}]
xVar_Metrics = [{'field': 'price', 'agg_function': 'sum', 'label':
'xMyPriceSum'},
{'field': 'price', 'agg_function': 'avg', 'label':
'xMyPriceAvg'}]
s2 = None
s2 = dsl_search(es, index = 'my_index', doc_type = 'my_example')
#add buckets
for xBucketVar in xVarBuckets:
xAgg = A('terms', field= xBucketVar['field'])
s2.aggs.bucket(xBucketVar['label'], xAgg)
resp2 = s2.execute()
#get results
q2 = resp2.aggregations
I guess it has to do with the fact that the newly create bucket is
overwritten by the new bucket, but how can append the new bucket to the
previous one
Any help appreciated
--
You received this message because you are subscribed to the Google Groups
"elasticsearch" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to elasticsearch+unsubscr...@googlegroups.com.
To view this discussion on the web visit
https://groups.google.com/d/msgid/elasticsearch/fa471fcf-9ed7-49f9-9e34-4cbefb90abb8%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
