-
Notifications
You must be signed in to change notification settings - Fork 80
Conversation
# Conflicts: # poetry.lock
🚀 Deployed on https://deploy-preview-875--etna-docs.netlify.app |
Codecov Report
❗ Your organization is not using the GitHub App Integration. As a result you may experience degraded service beginning May 15th. Please install the Github App Integration for your organization. Read more. @@ Coverage Diff @@
## master #875 +/- ##
===========================================
- Coverage 88.50% 50.94% -37.56%
===========================================
Files 192 192
Lines 12151 12146 -5
===========================================
- Hits 10754 6188 -4566
- Misses 1397 5958 +4561
... and 132 files with indirect coverage changes 📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
182f370
to
1745737
Compare
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
View / edit / reply to this conversation on ReviewNB alex-hse-repository commented on 2023-07-05T13:18:13Z
|
View / edit / reply to this conversation on ReviewNB alex-hse-repository commented on 2023-07-05T13:18:14Z The original horizon is actually 365 alex-hse-repository commented on 2023-07-05T13:18:59Z But we can leave this version as well |
View / edit / reply to this conversation on ReviewNB alex-hse-repository commented on 2023-07-05T13:18:15Z May be len(temp_ts.column.get_level_value("feature").unique()) |
View / edit / reply to this conversation on ReviewNB alex-hse-repository commented on 2023-07-05T13:18:16Z Here we need to emphasis that |
View / edit / reply to this conversation on ReviewNB alex-hse-repository commented on 2023-07-05T13:18:16Z It is actually more then 10% better |
View / edit / reply to this conversation on ReviewNB alex-hse-repository commented on 2023-07-05T13:18:17Z Lets limit the number of features |
View / edit / reply to this conversation on ReviewNB alex-hse-repository commented on 2023-07-05T13:18:19Z Too complicated) Try to find the medium article about the mrmr and copy the picture with formula from there |
View / edit / reply to this conversation on ReviewNB alex-hse-repository commented on 2023-07-05T13:18:20Z Try to use alex-hse-repository commented on 2023-07-10T08:12:44Z May you check the results with alex-hse-repository commented on 2023-07-10T08:15:55Z If Mr-Geekman commented on 2023-07-10T08:26:53Z For MRMR both ModelRelevanceTable and StatisticsRelevanceTable works worse than a baseline. I'll write all the results in the next message to compare. Mr-Geekman commented on 2023-07-10T16:23:47Z These are results on my personal laptop. SMAPE baseline: 8.094 Time baseline: 79.353
- SMAPE: 7.416 - Time: 43.722
- SMAPE: 13.262 - Time: 42.955
- SMAPE: 7.197 - Time: 143.238
- SMAPE: 13.262 - Time: 144.947
It seems like bug fix also changed the results for MRMR. alex-hse-repository commented on 2023-07-11T10:59:08Z I guess we can take |
But we can leave this version as well View entire conversation on ReviewNB |
May you check the results with View entire conversation on ReviewNB |
If View entire conversation on ReviewNB |
For MRMR both ModelRelevanceTable and StatisticsRelevanceTable works worse than a baseline. I'll write all the results in the next message to compare. View entire conversation on ReviewNB |
These are results on my personal laptop. SMAPE baseline: 8.094 Time baseline: 79.353
- SMAPE: 7.416 - Time: 43.722
- SMAPE: 13.262 - Time: 42.955
- SMAPE: 7.197 - Time: 143.238
- SMAPE: 13.262 - Time: 144.947
It seems like bug fix also changed the results for MRMR. View entire conversation on ReviewNB |
I guess we can take View entire conversation on ReviewNB |
Before submitting (must do checklist)
Proposed Changes
Closing issues
#712