[ML-49316] Support MonthMid and MonthEnd for DeepAR #160
Conversation
This file contains hidden or 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
| num_months = 24 | ||
|
|
||
| # Starting from end day of January 2020 | ||
| base_dates = pd.date_range( |
There was a problem hiding this comment.
How is it starting on the last ay of Jan 2020?
There was a problem hiding this comment.
see line 228, by specifying freq='M', it is by default the end of the month
There was a problem hiding this comment.
I see. Can you add a comment on the line below?
| @@ -18,6 +18,50 @@ | |||
| import pandas as pd | |||
|
|
|||
|
|
|||
| def validate_and_generate_index(df: pd.DataFrame, time_col: str, frequency: str): | |||
| """ | |||
| Generate a complete time index for the given DataFrame based on the specified frequency. | |||
There was a problem hiding this comment.
Thanks for the detailed function description!
maggiewang-db
approved these changes
Jan 31, 2025
| num_months = 24 | ||
|
|
||
| # Starting from end day of January 2020 | ||
| base_dates = pd.date_range( |
There was a problem hiding this comment.
I see. Can you add a comment on the line below?
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Outdated suggestions cannot be applied.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.
This PR fixes the bug that when user dataset has monthly frequency and the day of the month is not the first day, DeepAR will fail. The bug results from this line,
freqis "MS" so the generated new_index_full will always be the first day of month. So this line,will generate a df with all rows in target column to be NaN.
To fix the bug, this PR introduces
validate_and_generate_index, to generate a complete time index for the given DataFrame based on the specified frequency. If it is monthly frequency, it will generate the index based on the given day of month, also detect if it is the end of month.pd.date_range(total_min, total_max, freq=frequency)To test the function,
Run the below command locally
Month start: notebook
Month mid: notebook
Month end: notebook