Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update training/input data #41

Merged
merged 13 commits into from
Mar 12, 2024
Merged

Update training/input data #41

merged 13 commits into from
Mar 12, 2024

Conversation

dfsnow
Copy link
Member

@dfsnow dfsnow commented Mar 11, 2024

This PR fixes the missing sales situation discovered in ccao-data/data-architecture#334. It:

  • Ingests the (now available) missing sales and adds a marker to them (sv_added_later)
  • Runs a very basic set of sales validation heuristics to flag the new sales
  • Retrains the model using the updated sales sample
  • Updates the Desk Review workbooks with:
    • An indicator (and conditional formatting) for sales that were previously missing from the review sheets
    • A column containing the previous initial model value
    • Columns showing the nominal and percent change from the old model value to the new model value

@dfsnow dfsnow added the bug Something isn't working label Mar 11, 2024
@dfsnow dfsnow self-assigned this Mar 11, 2024
@@ -395,4 +395,4 @@ ratio_study:
# upload
export:
triad_code: "1"
run_id: "2024-02-16-silly-billy"
run_id: "2024-03-11-pensive-manasi"
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is the new final run ID w SHAPs.

@@ -283,7 +283,7 @@
"RemoteUsername": "ccao-data",
"RemoteRepo": "ccao",
"RemoteRef": "master",
"RemoteSha": "6bdb2f2cab811c3450d91726a784804bd8bca971",
"RemoteSha": "fe992f9bb6e75c97a0c8fa742106096adbabb642",
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is just updating the CCAO package to the latest version. It's tangential to this PR.

Copy link
Member

@wrridgeway wrridgeway left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good to me. I didn't take a look at the rendered desk review sheets.

Copy link
Contributor

@jeancochrane jeancochrane left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Some serious duct tape in this one, but I think it's probably the best option if we really can't run another round of sales val.

The workbook looks good too, let's just make sure to correct the number formatting on the Average YoY ∆ % column in the Neighborhood Breakout sheet to a percentage with 1 decimal point before we share the workbooks:

### NOTE ###
# OpenXLSX is not perfect and messes up the macros and formatting on saved
# workbooks. To finish each workbook, you must manually:
# 1. Open the Neighborhood Breakout sheet and ensure that the values are
# all formatted correctly in the pivot table; if not (e.g. if
# `Average of YoY ∆ %` is formatted as a date when it should be a percentage)
# then manually update the formatting by selecting
# PivotTable Fields > Values > {fieldname} > Value Field Settings... >
# Number Format.

@dfsnow dfsnow merged commit 4dcdfa8 into master Mar 12, 2024
4 checks passed
@dfsnow dfsnow deleted the dfsnow/update-input-data branch March 12, 2024 17:58
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants