Benjamin Trent benwtrent
🏠
benwtrent
/ helpers.py
Created
January 31, 2023 16:09
Some helpers around loading and testing BEIR data sets with elasticsearch
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import loaders | |
| from sentence_transformers import SentenceTransformer | |
| # Load queries, qrels, etc. and create embeddings for the queries | |
| queries = loaders.load_jsonl(jsonl_path=Path("./data/queries.jsonl")) | |
| embedding_model = SentenceTransformer(model_id, device="mps") | |
| query_embeddings = embedding_model.encode([d['text'] for d in queries]) | |
| query_embeddings = query_embeddings.tolist() | |
| query_and_embeddings = [dict(item, **{'embedding': embedding}) for (item, embedding) in zip(queries, query_embeddings)] | |
| qrels = loaders.load_beir_qrels(qrels_file=Path("./data/qrels/test.tsv")) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ------------------------------------------------------ | |
| _______ __ _____ | |
| / ____(_)___ ____ _/ / / ___/_________ ________ | |
| / /_ / / __ \/ __ `/ / \__ \/ ___/ __ \/ ___/ _ \ | |
| / __/ / / / / / /_/ / / ___/ / /__/ /_/ / / / __/ | |
| /_/ /_/_/ /_/\__,_/_/ /____/\___/\____/_/ \___/ | |
| ------------------------------------------------------ | |
| | Metric | Task | Baseline | Contender | Diff | Unit | Diff % | | |
| |--------------------------------------------------------------:|---------------------------------------------:|---------------:|---------------:|-------------:|-------:|---------:| |
benwtrent
/ PyLucene95Codec.java
Created
November 16, 2022 19:37
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| package org.apache.pylucene.codecs; | |
| import org.apache.lucene.codecs.lucene95.Lucene95Codec; | |
| import org.apache.lucene.codecs.KnnVectorsFormat; | |
| public class PyLucene95Codec extends Lucene95Codec { | |
| private long pythonObject; | |
| public void pythonExtension(long pythonObject){ | |
| this.pythonObject = pythonObject; |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| package org.apache.pylucene.codecs; | |
| import org.apache.lucene.codecs.lucene94.Lucene94Codec; | |
| import org.apache.lucene.codecs.KnnVectorsFormat; | |
| public class PyLucene94Codec extends Lucene94Codec { | |
| private long pythonObject; | |
| public void pythonExtension(long pythonObject){ | |
| this.pythonObject = pythonObject; |
benwtrent
/ lucenepyknn.py
Created
October 18, 2022 19:27
Ann Benchmark's integration using Lucene KNN.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| ann-benchmarks interface for Apache Lucene. | |
| """ | |
| import sklearn.preprocessing | |
| import numpy as np | |
| from struct import Struct | |
| import lucene |
benwtrent
/ EntropyBenchmark.java
Created
November 10, 2020 16:39
Benchmark for calculating the entropy for a string.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import org.openjdk.jmh.annotations.Benchmark; | |
| import org.openjdk.jmh.annotations.BenchmarkMode; | |
| import org.openjdk.jmh.annotations.Fork; | |
| import org.openjdk.jmh.annotations.Level; | |
| import org.openjdk.jmh.annotations.Measurement; | |
| import org.openjdk.jmh.annotations.Mode; | |
| import org.openjdk.jmh.annotations.OutputTimeUnit; | |
| import org.openjdk.jmh.annotations.Param; | |
| import org.openjdk.jmh.annotations.Scope; | |
| import org.openjdk.jmh.annotations.Setup; |
benwtrent
/ datafeed_config.json
Last active
October 15, 2020 12:53
Calculating the percent true and using it in a job
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "indices" : [ | |
| "kibana_sample_data_flights" | |
| ], | |
| "query" : { | |
| "bool" : { | |
| "must" : [ | |
| { | |
| "match_all" : { } | |
| } |
benwtrent
/ lat_lon fix
Created
August 12, 2020 17:19
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| PUT users/_mapping | |
| { | |
| "properties": { | |
| "geo.location.point": { | |
| "type": "geo_point" | |
| } | |
| } | |
| } | |
| POST users/_update_by_query |
benwtrent
/ es-commands.es
Created
June 26, 2020 11:39
helpful actions to support anomalous behavior by geo area
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ### | |
| # transform definition | |
| ### | |
| { | |
| "id" : "count_by_grid_15", | |
| "source" : { | |
| "index" : [ | |
| "gtfs*" | |
| ], | |
| "query" : { |
benwtrent
/ MultiThreadedStatsAccumulatorBenchmark.java
Created
June 18, 2020 15:08
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| package org.elasticsearch.benchmark.ml; | |
| import org.openjdk.jmh.annotations.Benchmark; | |
| import org.openjdk.jmh.annotations.BenchmarkMode; | |
| import org.openjdk.jmh.annotations.Fork; | |
| import org.openjdk.jmh.annotations.Level; | |
| import org.openjdk.jmh.annotations.Measurement; | |
| import org.openjdk.jmh.annotations.Mode; | |
| import org.openjdk.jmh.annotations.OutputTimeUnit; | |
| import org.openjdk.jmh.annotations.Param; |