|
9 | 9 | "name": "Improve Search Algorithm with Popularity Data Integration"
|
10 | 10 | },
|
11 | 11 | {
|
12 |
| - "description": "Plan out search algorithm changes to incorporate image metadata generated via AWS Rekognition.", |
13 |
| - "gid": "1154270978154720", |
14 |
| - "name": "Plan search algorithm changes for new metadata [AWS Grant]" |
15 |
| - }, |
16 |
| - { |
17 |
| - "description": "Improve data processing infrastructure in the Catalog by parallelizing loading and moving storage of data files from providers to S3.", |
18 |
| - "gid": "1153114910798065", |
19 |
| - "name": "Catalog Infrastructure Improvements" |
20 |
| - }, |
21 |
| - { |
22 |
| - "description": "Update Catalog schema to include new metadata generated through AWS Rekognition.", |
23 |
| - "gid": "1154270978154717", |
24 |
| - "name": "Implement architecture for schema for new metadata [AWS Grant]" |
25 |
| - }, |
| 12 | + "description": "Move our data cleaning code from the ingestion step of the API to the initial data processing step of the Catalog to eliminate unnecessary repetitive data cleaning.", |
| 13 | + "gid": "1167425798148805", |
| 14 | + "name": "Move data cleaning pipeline from API to Catalog" |
| 15 | + } |
| 16 | + ] |
| 17 | + }, |
| 18 | + { |
| 19 | + "name": "Q3 2020", |
| 20 | + "tasks": [ |
26 | 21 | {
|
27 |
| - "description": "Develop metrics for and select a set of ~100 million high quality images for which we'll generate additional metadata through AWS Rekognition.", |
28 |
| - "gid": "1154270978154715", |
29 |
| - "name": "Image Selection for Rekognition [AWS Grant]" |
| 22 | + "description": "Designing and prototyping an upcoming user interface for searching for audio on CC Search.", |
| 23 | + "gid": "1163392248010945", |
| 24 | + "name": "Design Sprint: Audio UI for CC Search" |
30 | 25 | },
|
31 | 26 | {
|
32 | 27 | "description": "Manage Catalog deployment and provisioning entirely through infrastructure as code.",
|
|
39 | 34 | "name": "Improve Documentation for Community Contributors"
|
40 | 35 | },
|
41 | 36 | {
|
42 |
| - "description": "Move our data cleaning code from the ingestion step of the API to the initial data processing step of the Catalog to eliminate unnecessary repetitive data cleaning.", |
43 |
| - "gid": "1167425798148805", |
44 |
| - "name": "Move data cleaning pipeline from API to Catalog" |
| 37 | + "description": "Plan out search algorithm changes to incorporate image metadata generated via AWS Rekognition.", |
| 38 | + "gid": "1154270978154720", |
| 39 | + "name": "Plan search algorithm changes for new metadata [AWS Grant]" |
45 | 40 | },
|
46 | 41 | {
|
47 |
| - "description": "Designing and prototyping an upcoming user interface for searching for audio on CC Search.", |
48 |
| - "gid": "1163392248010945", |
49 |
| - "name": "Design Sprint: Audio UI for CC Search" |
50 |
| - } |
51 |
| - ] |
52 |
| - }, |
53 |
| - { |
54 |
| - "name": "Q3 2020", |
55 |
| - "tasks": [ |
| 42 | + "description": "Update Catalog schema to include new metadata generated through AWS Rekognition.", |
| 43 | + "gid": "1154270978154717", |
| 44 | + "name": "Implement architecture for schema for new metadata [AWS Grant]" |
| 45 | + }, |
56 | 46 | {
|
57 | 47 | "description": "Improve how and where we explain licenses, and consider ways to make it easier for reusers to understand and comply with license requirements.",
|
58 | 48 | "gid": "1147666754358269",
|
|
88 | 78 | "gid": "1171015130050099",
|
89 | 79 | "name": "Audio Support and Integration"
|
90 | 80 | },
|
| 81 | + { |
| 82 | + "description": "Develop metrics for and select a set of ~100 million high quality images for which we'll generate additional metadata through AWS Rekognition.", |
| 83 | + "gid": "1154270978154715", |
| 84 | + "name": "Image Selection for Rekognition [AWS Grant]" |
| 85 | + }, |
91 | 86 | {
|
92 | 87 | "description": "Update our Common Crawl provider infrastructure to:\n(1) use Apache Airflow instead of AWS tools like Data Pipeline & Glue for processing data\n(2) unify provider processing to use the same base classes as API providers",
|
93 | 88 | "gid": "1167425798148813",
|
|
0 commit comments