Computation times#
18:23.710 total execution time for 20 files from all galleries:
Example |
Time |
Mem (MB) |
|---|---|---|
AggJoiner on a credit fraud dataset ( |
03:37.429 |
608.5 |
Various string encoders: a sentiment analysis example ( |
02:57.356 |
1371.1 |
Quick overview of DataOps ( |
02:47.698 |
571.4 |
Multiples tables: building machine learning pipelines with DataOps ( |
02:32.814 |
652.7 |
Tuning DataOps with Optuna ( |
01:05.783 |
727.6 |
Encoding: from a dataframe to a numerical matrix for machine learning ( |
00:47.204 |
577.5 |
Spatial join for flight data: Joining across multiple columns ( |
00:42.137 |
3044.1 |
Interpolation join: infer missing rows when joining two tables ( |
00:39.162 |
2676.8 |
Hyperparameter tuning with DataOps ( |
00:35.036 |
565.3 |
Fuzzy joining dirty tables with the Joiner ( |
00:31.091 |
571.4 |
SquashingScaler: Robust numerical preprocessing for neural networks ( |
00:25.791 |
571.1 |
Using PyTorch (via skorch) in DataOps ( |
00:20.343 |
577.8 |
Getting Started with skrub ( |
00:18.584 |
565.0 |
Subsampling for faster development ( |
00:16.367 |
569.5 |
Handling datetime features with the DatetimeEncoder ( |
00:12.717 |
568.6 |
Use case: developing locally and deploying to production ( |
00:08.1000 |
691.2 |
Sessions in time-based data: Predicting user purchases with the SessionEncoder ( |
00:08.621 |
566.0 |
Hands-On with Column Selection and Transformers ( |
00:08.525 |
565.0 |
Deduplicating misspelled categories ( |
00:05.158 |
565.0 |
Deduplicating misspelled categories ( |
00:02.894 |
565.6 |