Skip to content
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

Week1 - PR #1

Open
wants to merge 9 commits into
base: main
Choose a base branch
from
Open

Week1 - PR #1

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
c7c93cf
Adding xgb_train implementation
sdwaraki Oct 20, 2023
0bd0e0c
completing steps until 4a
sdwaraki Oct 20, 2023
7cc5e6a
Adding rescore query
sdwaraki Oct 20, 2023
2cc3af7
Steps until 4f
sdwaraki Oct 21, 2023
cd87327
Adding main query weight to rescore query
sdwaraki Oct 21, 2023
bf267a1
Adding new features and updating the feature log query
sdwaraki Oct 21, 2023
6d481b4
Fixing the extract logged features
sdwaraki Oct 22, 2023
39c3e6c
Adding more features into the featureset
sdwaraki Oct 23, 2023
042c9c6
Trying out some new features
sdwaraki Oct 23, 2023
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
Binary file modified opensearch/ltr_toy_model.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
280 changes: 280 additions & 0 deletions week1/conf/ltr_featureset.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,286 @@
"name": "{{keywords}}"
}
}
},
{
"name": "manufacturer_phrase_match",
"params": [
"keywords"
],
"template_language": "mustache",
"template": {
"match_phrase": {
"manufacturer": {
"query": "{{keywords}}",
"slop": 6
}
}
}
},
{
"name": "dept_phrase_match",
"params": [
"keywords"
],
"template_language": "mustache",
"template": {
"match_phrase": {
"department": {
"query": "{{keywords}}",
"slop": 6
}
}
}
},
{
"name": "category_path_phrase_match",
"params": [
"keywords"
],
"template_language": "mustache",
"template": {
"match_phrase": {
"categoryPath": {
"query": "{{keywords}}",
"slop": 6
}
}
}
},
{
"name": "class_phrase_match",
"params": [
"keywords"
],
"template_language": "mustache",
"template": {
"match_phrase": {
"class": {
"query": "{{keywords}}",
"slop": 6
}
}
}
},
{
"name": "name_phrase_match",
"params": [
"keywords"
],
"template_language": "mustache",
"template": {
"match_phrase": {
"name": {
"query": "{{keywords}}",
"slop": 6
}
}
}
},
{
"name": "customer_review_avg",
"template_language": "mustache",
"template": {
"function_score": {
"functions": [
{
"field_value_factor": {
"field": "customerReviewAverage",
"missing": 4.0
}
}
],
"query": {
"match_all": {}
}
}
}
},
{
"name": "customer_review_count",
"template_language": "mustache",
"template": {
"function_score": {
"functions": [
{
"field_value_factor": {
"field": "customerReviewCount",
"missing": 9
}
}
],
"query": {
"match_all": {}
}
}
}
},
{
"name": "artist_name_phrase_match",
"params": [
"keywords"
],
"template_language": "mustache",
"template": {
"match_phrase": {
"artistName": {
"query": "{{keywords}}",
"slop": 6
}
}
}
},
{
"name": "short_description_phrase_match",
"params": [
"keywords"
],
"template_language": "mustache",
"template": {
"match_phrase": {
"shortDescription": {
"query": "{{keywords}}",
"slop": 6
}
}
}
},
{
"name": "long_description_phrase_match",
"params": [
"keywords"
],
"template_language": "mustache",
"template": {
"match_phrase": {
"longDescription": {
"query": "{{keywords}}",
"slop": 6
}
}
}
},
{
"name": "salesRankShortTerm",
"template_language": "mustache",
"template": {
"function_score": {
"functions": [
{
"filter": {
"exists": {
"field": "salesRankShortTerm"
}
},
"gauss": {
"salesRankShortTerm": {
"origin": "1.0",
"offset": "100",
"scale": "10000",
"decay": "0.1"
}
}
},
{
"filter": {
"bool": {
"must_not": {
"exists": {
"field": "salesRankShortTerm"
}
}
}
},
"script_score": {
"script": "if (doc['salesRankShortTerm'] == null || doc['salesRankShortTerm'].size() == 0 ){return 0.0}"
}
}
],
"query": {
"match_all": {}
}
}
}
},
{
"name": "in_store_availability",
"template_language": "mustache",
"template": {
"function_score": {
"query": { "match_all": {} },
"functions": [
{
"filter": { "match": { "inStoreAvailability": "true" } },
"weight": 1
},
{
"weight": 0
}
],
"score_mode": "max",
"min_score": 0
}
}
},
{
"name": "online_availability",
"template_language": "mustache",
"template": {
"function_score": {
"query": { "match_all": {} },
"functions": [
{
"filter": { "match": { "onlineAvailability": "true" } },
"weight": 1
},
{
"weight": 0
}
],
"score_mode": "max",
"min_score": 0
}
}
},
{
"name": "on_sale",
"template_language": "mustache",
"template": {
"function_score": {
"query": { "match_all": {} },
"functions": [
{
"filter": { "match": { "onSale": "true" } },
"weight": 1
},
{
"weight": 0
}
],
"score_mode": "max",
"min_score": 0
}
}
},
{
"name": "digital",
"template_language": "mustache",
"template": {
"function_score": {
"query": { "match_all": {} },
"functions": [
{
"filter": { "match": { "digital": "true" } },
"weight": 1
},
{
"weight": 0
}
],
"score_mode": "max",
"min_score": 0
}
}
}
]
}
Expand Down
37 changes: 37 additions & 0 deletions week1/test/week1test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@

hits=[
{
'_index': 'searchml_ltr',
'_id': 'doc_e',
'_score': 0.0,
'_source': {
'id': 'doc_e',
'title': 'Pigs in a Blanket and Other Recipes',
'price': '27.50',
'in_stock': True,
'body': "Pigs in a blanket aren't as cute as you would think given it's a food and not actual pigs wrapped in blankets.",
'category': 'instructional'
},
'fields': {
'_ltrlog': [
{
'log_entry': [
{'name': 'title_query', 'value': 1.1272218},
{'name': 'body_query', 'value': 2.2908108},
{'name': 'price_func', 'value': 27.5}
]

}
]
},
'matched_queries': ['logged_featureset']
}
]

log_entries = hits[0]['fields']['_ltrlog'][0]['log_entry']

print(log_entries)

for entry in log_entries:
if entry['name'] == "title_query" :
print(entry['value'])
1 change: 0 additions & 1 deletion week1/utilities/build_ltr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -327,7 +327,6 @@
#############
if args.xgb:
# Defaults

bst, xgb_params = xgbu.train(args.xgb, args.xgb_rounds, args.xgb_conf)
print("Dumping out model using feature map: %s" % args.xgb_feat_map)
model = bst.get_dump(fmap=("%s/%s" % (output_dir, args.xgb_feat_map)), dump_format='json')
Expand Down
Loading