Add embeddings for a few economics indicators #4971
Conversation
This file contains 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
chejennifer
reviewed
Feb 21, 2025
| @@ -3387,6 +3387,7 @@ sdg/ER_PTD_FRHWTR,Average proportion of Freshwater Key Biodiversity Areas covere | |||
| sdg/ER_PTD_MTN,Average proportion of Mountain Key Biodiversity Areas covered by protected areas | |||
| sdg/ER_PTD_TERR,Average proportion of Terrestrial Key Biodiversity Areas covered by protected areas | |||
| sdg/ER_RSK_LST,Red List Index | |||
| sdg/FP_CPI_TOTL_ZG,"Annual inflation, consumer prices;Annual inflation rate as measured by the consumer price index;Percentage change in the cost to the average consumer of acquiring a basket of goods and services that may be fixed or changed at specified intervals, such as yearly;Annual inflation rate consumer price index" | |||
There was a problem hiding this comment.
the first description "Annual inflation, consumer prices", the second description "annual inflation rate as measured by the consumer price index" and the last description "annual inflation rate consumer price index" are all quite similar, are they all needed? Last year when we did an overhaul on the embeddings, the goal was to have one good distinct description per variable, maybe 2 if necessary
| @@ -3602,7 +3603,11 @@ worldBank/4_1_SHARE_RE_IN_ELECTRICITY,Renewable electricity share of total elect | |||
| worldBank/EG_ELC_ACCS_RU_ZS,percentage of rural population with access to electricity | |||
| worldBank/EG_ELC_ACCS_UR_ZS,percentage of urban population with access to electricity | |||
| worldBank/EG_ELC_ACCS_ZS,percentage of population with access to electricity | |||
| worldBank/FR_INR_DPST,"Deposit interest rate;Deposit interest rate is the rate paid by commercial or similar banks for demand, time, or savings deposits" | |||
There was a problem hiding this comment.
also, not sure if the description of what a deposit interest rate is is necessary? the more sentences we add, the harder it is to have variables be in distinct embedding spaces
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add embeddings to base for a few economic indicators.
Attached reports with diffs below.
SV Index Differ.pdf
NL Eval Playground - Data Commons.pdf