Rishabh/sqlite fixes #195
Merged
Rishabh/sqlite fixes #195
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
…were made by customers from the USA last week`
wendy-aw
reviewed
Jul 2, 2024
| @@ -19,7 +19,7 @@ broker,sqlite,instructions_date_join,"SELECT strftime('%Y-%m', sbCustJoinDate) A | |||
| CR = customer rank by total transaction amount, where the top customer has the highest amount. | |||
| PMCS = per month customer signups. PMAT = per month average transaction amount. Truncate date to month for aggregation. | |||
| TAC = Total Active Customers who joined after a specified date" | |||
| broker,sqlite,instructions_date_join,"SELECT COUNT(DISTINCT sb.sbTxId) AS num_transactions, SUM(sb.sbTxAmount) AS total_transaction_amount FROM sbTransaction AS sb JOIN sbCustomer AS sc ON sb.sbTxCustId = sc.sbCustId WHERE LOWER(sc.sbCustCountry) = 'usa' AND sb.sbTxDateTime >= DATE('now', '-7 days', 'weekday 0', '-6 days') AND sb.sbTxDateTime <= DATE('now', '-7 days', 'weekday 0');",How many transactions were made by customers from the USA last week (exclusive of the current week)? Return the number of transactions and total transaction amount.,"Last week = DATE('now', '-7 days', 'weekday 1', '-7 days') to before DATE('now', '-7 days', 'weekday 1'). Always join transactions with customers before using the transactions table.","To analyze stock performance, join the daily price and ticker tables and calculate price change To get the total transaction amount per customer, join the customer and transaction tables, group by customer, and sum the transaction amounts. Last week = DATE('now', '-7 days', 'weekday 1', '-7 days') to before DATE('now', '-7 days', 'weekday 1'). Always join transactions with customers before using the transactions table. To get the success rate of transactions per customer, join customer and transaction tables, group by customer, and calculate the percentage of successful transactions" | |||
| broker,sqlite,instructions_date_join,"SELECT COUNT(DISTINCT sb.sbTxId) AS num_transactions, SUM(sb.sbTxAmount) AS total_transaction_amount FROM sbTransaction AS sb JOIN sbCustomer AS sc ON sb.sbTxCustId = sc.sbCustId WHERE LOWER(sc.sbCustCountry) = 'usa' AND sb.sbTxDateTime >= DATE('now', '-7 days', 'weekday 1', '-7 days') AND sb.sbTxDateTime <= DATE('now', '-7 days', 'weekday 1');",How many transactions were made by customers from the USA last week (exclusive of the current week)? Return the number of transactions and total transaction amount.,"Last week = DATE('now', '-7 days', 'weekday 1', '-7 days') to before DATE('now', '-7 days', 'weekday 1'). Always join transactions with customers before using the transactions table.","To analyze stock performance, join the daily price and ticker tables and calculate price change To get the total transaction amount per customer, join the customer and transaction tables, group by customer, and sum the transaction amounts. Last week = DATE('now', '-7 days', 'weekday 1', '-7 days') to before DATE('now', '-7 days', 'weekday 1'). Always join transactions with customers before using the transactions table. To get the success rate of transactions per customer, join customer and transaction tables, group by customer, and calculate the percentage of successful transactions" | |||
There was a problem hiding this comment.
Whoops sorry for not matching the query to the instructions even though they are semantically similar. Good catch 🙏
wendy-aw
reviewed
Jul 2, 2024
| @@ -137,7 +137,7 @@ derm_treatment,sqlite,keywords_aggregate,SELECT AVG(weight_kg) AS caw FROM patie | |||
| CAW = cohort average weight in kilograms | |||
| To calculate the D7D100PIR, subtract the average PASI score at the beginning of the period from the average at the end, divide by the initial average, and multiply by 100 | |||
| The Defined Daily Dose (DDD) is calculated as the total consumed medication divided by the treatment duration" | |||
| derm_treatment,sqlite,keywords_ratio,"SELECT d.drug_name, AVG(t.tot_drug_amt / NULLIF((t.end_dt - t.start_dt), 0)) AS ddd FROM treatments AS t JOIN drugs AS d ON t.drug_id = d.drug_id WHERE NOT t.end_dt IS NULL GROUP BY d.drug_name;",Calculate the average DDD for each drug. Return the drug name and average DDD value.,"DDD (defined daily dose) = total drug amount consumed during one treatment / total days of treatment (end - start date in days), where end date is not null","DDD (defined daily dose) = total drug amount consumed during one treatment / total days of treatment (end - start date in days). To find the average weight of patients treated with a specific drug, first join patients with treatments on patient_id, then filter by the drug name. To identify doctors who have prescribed a certain drug type and their respective locations, first join doctors with treatments on doc_id, then filter by the drug type. To calculate the total number of adverse events reported for treatments involving certain drug types, first join treatments with adverse_events on treatment_id, then filter by the drug type." | |||
| derm_treatment,sqlite,keywords_ratio,"SELECT d.drug_name, AVG(t.tot_drug_amt / NULLIF((JULIANDAY(t.end_dt) - JULIANDAY(t.start_dt)), 0)) AS ddd FROM treatments AS t JOIN drugs AS d ON t.drug_id = d.drug_id WHERE NOT t.end_dt IS NULL GROUP BY d.drug_name;",Calculate the average DDD for each drug. Return the drug name and average DDD value.,"DDD (defined daily dose) = total drug amount consumed during one treatment / total days of treatment (end - start date in days), where end date is not null","DDD (defined daily dose) = total drug amount consumed during one treatment / total days of treatment (end - start date in days). To find the average weight of patients treated with a specific drug, first join patients with treatments on patient_id, then filter by the drug name. To identify doctors who have prescribed a certain drug type and their respective locations, first join doctors with treatments on doc_id, then filter by the drug type. To calculate the total number of adverse events reported for treatments involving certain drug types, first join treatments with adverse_events on treatment_id, then filter by the drug type." | |||
There was a problem hiding this comment.
Ahh thanks for this. Missed out on this date sub
wendy-aw
approved these changes
Jul 2, 2024
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.
Fixed some questions. Also an additional prompt for the LoRA models to deal with the loss of attention with LoRA models, and be better aligned with the prompt used while training.
This is a temporary solution until our LoRA models are trained with the same prompt as our current
prompt_cot.md