Prompt and cleaning updates #211
Merged
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
…lumns_to_keep == 0)
rishsriv
approved these changes
Aug 15, 2024
|
Yea for a while I was actually doubting myself about whether we had these changes made 😅 |
wongjingping
approved these changes
Aug 15, 2024
| @@ -4,7 +4,7 @@ TAC = Total Active Customers who have recently joined | |||
| MoMC = Month-over-month change in average closing price for each ticker. | |||
| ACP = Average Closing Price of tickers over a recent period" | |||
| broker,bigquery,instructions_cte_join,"WITH popular_stocks AS (SELECT t.sbTickerSymbol, COUNT(*) AS tx_count FROM broker.sbTransaction AS tx JOIN broker.sbTicker AS t ON tx.sbTxTickerId = t.sbTickerId WHERE tx.sbTxType = 'buy' AND tx.sbTxDateTime >= CURRENT_DATE - INTERVAL '10' DAY GROUP BY t.sbTickerSymbol) SELECT sbTickerSymbol, tx_count FROM popular_stocks ORDER BY tx_count DESC NULLS FIRST LIMIT 2;",What are the 2 most frequently bought stock ticker symbols in the past 10 days? Return the ticker symbol and number of buy transactions.,"To find the most popular stocks in the past 10 days, join the transaction and ticker tables, filter for buy transactions in the last 10 days, group by ticker and count transactions.","MoMC = month-over-month change in average closing price Weekend days refer to Saturday and Sunday; adjust dates to weeks for aggregation. To find the most popular stocks in the past 10 days, join the transaction and ticker tables, filter for buy transactions in the last 10 days, group by ticker and count transactions. CR = customer rank by total transaction volume, where rank 1 belongs to the customer with the highest volume" | |||
| broker,bigquery,instructions_cte_join,"WITH cust_tx_stats AS (SELECT c.sbCustId, c.sbCustName, COUNT(t.sbTxId) AS total_tx, SUM(CASE WHEN t.sbTxStatus = 'success' THEN 1 ELSE 0 END) AS success_tx FROM broker.sbCustomer AS c JOIN broker.sbTransaction AS t ON c.sbCustId = t.sbTxCustId GROUP BY c.sbCustId, c.sbCustName) SELECT sbCustName, CAST(success_tx AS FLOAT64) / total_tx AS success_rate FROM cust_tx_stats WHERE total_tx >= 5 ORDER BY success_rate NULLS LAST;","For customers with at least 5 total transactions, what is their transaction success rate? Return the customer name and success rate, ordered from lowest to highest success rate.","To get the success rate of transactions per customer, join customer and transaction tables, group by customer, and calculate the percentage of successful transactions.","CR = customer rank by total transaction amount, with different rankings based on transaction amounts MoMC = month-over-month change in average closing price based on previous month's averages for each ticker each month To get the success rate of transactions per customer, join customer and transaction tables, group by customer, and calculate the percentage of successful transactions. Always join transactions with customers before using the transactions table. TAC = Total Active Customers who joined after a certain date" | |||
| broker,bigquery,instructions_cte_join,"WITH cust_tx_stats AS (SELECT c.sbCustId, c.sbCustName, COUNT(t.sbTxId) AS total_tx, SUM(CASE WHEN t.sbTxStatus = 'success' THEN 1 ELSE 0 END) AS success_tx FROM broker.sbCustomer AS c JOIN broker.sbTransaction AS t ON c.sbCustId = t.sbTxCustId GROUP BY c.sbCustId, c.sbCustName) SELECT sbCustName, CAST(success_tx AS FLOAT64) / total_tx * 100 AS success_rate FROM cust_tx_stats WHERE total_tx >= 5 ORDER BY success_rate NULLS LAST;","For customers with at least 5 total transactions, what is their transaction success rate? Return the customer name and success rate, ordered from lowest to highest success rate.","To get the success rate of transactions per customer, join customer and transaction tables, group by customer, and calculate the percentage of successful transactions.","CR = customer rank by total transaction amount, with different rankings based on transaction amounts MoMC = month-over-month change in average closing price based on previous month's averages for each ticker each month To get the success rate of transactions per customer, join customer and transaction tables, group by customer, and calculate the percentage of successful transactions. Always join transactions with customers before using the transactions table. TAC = Total Active Customers who joined after a certain date" | |||
There was a problem hiding this comment.
nit: should we include both variants (with and without *100) since the question doesn't specify the exact format? same for all dialects
There was a problem hiding this comment.
ohh i thought like a whole number (with *100) would be more consistent with the instructions that say "calculate the percentage of successful transactions"
| join_str = f"{col_1} can be joined with {col_2}" | ||
| if join_str not in join_list: | ||
| join_list.append(join_str) | ||
| # add to pruned_join_list if column names are not equal |
There was a problem hiding this comment.
nice heuristic here for pruning join hints!
Comment on lines
+250
to
+251
| join_hints=join_str, | ||
| pruned_join_hints=pruned_join_str, |
There was a problem hiding this comment.
nice thanks for adding these as separate sections!
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.
Just realized this hasn't been pushed to main.