Gluonts change #279
Open
Gluonts change #279
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
This tutorial contains an example with multiple indexes and subsequent tampering to the data in order to show resiliency and a real life use case of TC applied on cryptocurrency prices up to 2021.
Fix to the issue raised on empty dataframe, resulting from an inner merge where the existing dataframe that accumulated results and the newer one had diferent indices. A subsequent issue must be raised to either: 1 report a single model failure (on index matching) 2 fix the moirai discrepancy (only model that showed this issue)
… the title suggested
…These involve a specific edge case where ds are too close to the granularity received by the gluons packages; the idea is to dephase by a repeated (more than 80%) time value in order to normalize the whole index, while preserving the previously detected stationality (and of course, the data within). The forecasting is then done and the time index fixed. Another important addition is that whenever this funcionality is harnessed, the user receives notification through the console, so no blackboxing is done when shifting ds column to make it compatible with gluonts
Collaborator
|
Just took a quick look, are these prints intended to be present? Or just something from testing that you forgot to remove? |
Contributor
Author
|
Hello, yes, you're right. Accidental prints from testing. Removed! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Hello!
After diving into the whole, why does Moirai behave weird on the crypto example I noticed that this dataset in particular was hanging in an edge case for Gluonts handling. I gave it a fix by auditing the possibility of a useful timeshift (while preserving the detected seasonality) to make it Gluonts friendly and de-shift this change prior to emitting the forecast. This is through full disclosure with the user.
Feel free to let me know if it needs any form of further work or fixing.