Skip to content

DATAP-1638: CCDB - Update API to return Matched Company aggregation (CABL-433) #208

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
AnthonyDiaz wants to merge 9 commits into from
Closed

DATAP-1638: CCDB - Update API to return Matched Company aggregation (CABL-433) #208

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
e354bdb
Subject:
Feb 3, 2025
cc82bab
Reverting the size about for _AGG_SIZE_MAP use es_field_name
Feb 5, 2025
4958bd0
Updating the docs_requirements.txt file with needed libraries
Feb 5, 2025
7605497
Correcting field size
Feb 5, 2025
cc5ffb3
remove matched company field in favor of default field. update agg c…
flacoman91 Feb 7, 2025
d74b7ec
Merge commit '4696ee1b50ea2cc4b61e4449cc26db71e84a1de6' into DATAP-16…
flacoman91 Jun 24, 2025
f38224f
restore to 26000 companies
flacoman91 Jun 24, 2025
60785a5
revert url for other environments
flacoman91 Jun 24, 2025
26f15a2
revert defaults.py company count to 6500 max
flacoman91 Jun 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion complaint_search/defaults.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@
]
)

AGG_EXCLUDE_FIELDS = ["company", "zip_code"]
AGG_EXCLUDE_FIELDS = ["zip_code"]

CHUNK_SIZE = 512

Expand Down
25 changes: 15 additions & 10 deletions complaint_search/es_builders.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -339,13 +339,13 @@ class AggregationBuilder(BaseBuilder):
)

_AGG_SIZE_MAP = {
"company.raw": AGG_COMPANY_DEFAULT, # 6500
"company": AGG_COMPANY_DEFAULT, # 6500
"state": AGG_STATE_DEFAULT, # 100
"zip_code": AGG_ZIPCODE_DEFAULT, # 26000
"issue.raw": AGG_ISSUE_DEFAULT, # 200
"sub_issue.raw": AGG_SUBISSUE_DEFAULT, # 250
"product.raw": AGG_PRODUCT_DEFAULT, # 30
"sub_product.raw": AGG_SUBPRODUCT_DEFAULT, # 90
"issue": AGG_ISSUE_DEFAULT, # 200
"sub_issue": AGG_SUBISSUE_DEFAULT, # 250
"product": AGG_PRODUCT_DEFAULT, # 30
"sub_product": AGG_SUBPRODUCT_DEFAULT, # 90
}

def __init__(self):
Expand All @@ -358,19 +358,19 @@ def add_exclude(self, field_name_list):
self.exclude += field_name_list

def build_parent_child_field_agg(
self, agg_heading_name, es_parent_name, es_child_name
self, agg_heading_name, es_parent_name, es_child_name, parent_size, child_size
):

field_agg = {
agg_heading_name: {
"terms": {
"size": self._AGG_SIZE_MAP.get(es_parent_name, 10),
"size": parent_size,
"field": es_parent_name,
},
"aggs": {
es_child_name: {
"terms": {
"size": self._AGG_SIZE_MAP.get(es_child_name, 10),
"size": child_size,
"field": es_child_name,
}
}
Expand Down Expand Up @@ -398,19 +398,24 @@ def build_one(self, field_name):
es_child_name = self._OPTIONAL_FILTERS_PARAM_TO_ES_MAP.get(
self._OPTIONAL_FILTERS_CHILD_MAP.get(field_name)
)
parent_field_size = self._AGG_SIZE_MAP.get(field_name, 10)
child_field_size = self._AGG_SIZE_MAP.get(self._OPTIONAL_FILTERS_CHILD_MAP.get(field_name), 10)

field_aggs["aggs"] = self.build_parent_child_field_agg(
field_name, es_field_name, es_child_name
field_name, es_field_name, es_child_name, parent_field_size, child_field_size
)
else:
field_aggs["aggs"] = {
field_name: {
"terms": {
"size": self._AGG_SIZE_MAP.get(es_field_name, 10),
"size": self._AGG_SIZE_MAP.get(field_name, 10),
"field": es_field_name,
}
}
}

print(f"field_aggs: {field_aggs['aggs']}")

# Create a subset of the filters
incl_subset = {
k: v for k, v in self.include_clauses.items() if k != field_name
Expand Down