Skip to content

Commit b951cc4

Browse files
author
Github Actions
committed
Arlind Kadra: Fixing issues with imbalanced datasets (#197)
1 parent 2ded7ae commit b951cc4

19 files changed

+445
-183
lines changed

‎refactor_development_regularization_cocktails/_downloads/2f0f54a9831653ac5c12ee0e06324a62/basics_tabular_jupyter.zip

0 Bytes
Binary file not shown.

‎refactor_development_regularization_cocktails/_downloads/8ef6602cf8ed40221edd89244fb031af/basics_tabular_python.zip

0 Bytes
Binary file not shown.

‎refactor_development_regularization_cocktails/_downloads/b38295cf56f02b1c4547385a8f389f90/advanced_tabular_python.zip

0 Bytes
Binary file not shown.

‎refactor_development_regularization_cocktails/_downloads/df038041811db9bd567de83692a8f994/advanced_tabular_jupyter.zip

0 Bytes
Binary file not shown.

‎refactor_development_regularization_cocktails/_sources/advanced_tabular/example_custom_configuration_space.rst.txt

Lines changed: 33 additions & 29 deletions
Original file line numberDiff line numberDiff line change
@@ -46,7 +46,7 @@ the search. Currently, there are two changes that can be made to the space:-
4646

4747
.. code-block:: none
4848
49-
<smac.runhistory.runhistory.RunHistory object at 0x7fd5a9342610> [TrajEntry(train_perf=2147483648, incumbent_id=1, incumbent=Configuration:
49+
<smac.runhistory.runhistory.RunHistory object at 0x7fc41b387d00> [TrajEntry(train_perf=2147483648, incumbent_id=1, incumbent=Configuration:
5050
data_loader:batch_size, Value: 32
5151
encoder:__choice__, Value: 'OneHotEncoder'
5252
feature_preprocessor:__choice__, Value: 'NoFeaturePreprocessor'
@@ -87,7 +87,7 @@ the search. Currently, there are two changes that can be made to the space:-
8787
trainer:StandardTrainer:use_stochastic_weight_averaging, Value: True
8888
trainer:StandardTrainer:weighted_loss, Constant: 1
8989
trainer:__choice__, Value: 'StandardTrainer'
90-
, ta_runs=0, ta_time_used=0.0, wallclock_time=0.0018794536590576172, budget=0), TrajEntry(train_perf=0.14035087719298245, incumbent_id=1, incumbent=Configuration:
90+
, ta_runs=0, ta_time_used=0.0, wallclock_time=0.0019719600677490234, budget=0), TrajEntry(train_perf=0.14035087719298245, incumbent_id=1, incumbent=Configuration:
9191
data_loader:batch_size, Value: 32
9292
encoder:__choice__, Value: 'OneHotEncoder'
9393
feature_preprocessor:__choice__, Value: 'NoFeaturePreprocessor'
@@ -128,20 +128,19 @@ the search. Currently, there are two changes that can be made to the space:-
128128
trainer:StandardTrainer:use_stochastic_weight_averaging, Value: True
129129
trainer:StandardTrainer:weighted_loss, Constant: 1
130130
trainer:__choice__, Value: 'StandardTrainer'
131-
, ta_runs=1, ta_time_used=12.235623836517334, wallclock_time=13.70586609840393, budget=5.555555555555555)]
132-
{'accuracy': 0.8497109826589595}
133-
| | Preprocessing | Estimator | Weight |
134-
|---:|:------------------------------------------------------------------|:-------------------------------------------------------------|---------:|
135-
| 0 | None | KNNClassifier | 0.3 |
136-
| 1 | None | CatBoostClassifier | 0.28 |
137-
| 2 | None | RFClassifier | 0.1 |
138-
| 3 | None | SVC | 0.08 |
139-
| 4 | SimpleImputer,OneHotEncoder,StandardScaler,NoFeaturePreprocessing | no embedding,MLPBackbone,FullyConnectedHead,nn.Sequential | 0.08 |
140-
| 5 | None | ExtraTreesClassifier | 0.06 |
141-
| 6 | None | LGBMClassifier | 0.04 |
142-
| 7 | SimpleImputer,OneHotEncoder,StandardScaler,NoFeaturePreprocessing | no embedding,MLPBackbone,FullyConnectedHead,nn.Sequential | 0.04 |
143-
| 8 | SimpleImputer,OneHotEncoder,NoScaler,PolynomialFeatures | no embedding,ResNetBackbone,FullyConnectedHead,nn.Sequential | 0.02 |
144-
<smac.runhistory.runhistory.RunHistory object at 0x7fd58e3e22e0> [TrajEntry(train_perf=2147483648, incumbent_id=1, incumbent=Configuration:
131+
, ta_runs=1, ta_time_used=14.711710453033447, wallclock_time=16.210379123687744, budget=5.555555555555555)]
132+
{'accuracy': 0.8439306358381503}
133+
| | Preprocessing | Estimator | Weight |
134+
|---:|:------------------------------------------------------------------|:----------------------------------------------------------|---------:|
135+
| 0 | None | RFClassifier | 0.32 |
136+
| 1 | None | KNNClassifier | 0.2 |
137+
| 2 | None | CatBoostClassifier | 0.16 |
138+
| 3 | None | SVC | 0.12 |
139+
| 4 | None | ExtraTreesClassifier | 0.08 |
140+
| 5 | None | LGBMClassifier | 0.04 |
141+
| 6 | SimpleImputer,OneHotEncoder,StandardScaler,NoFeaturePreprocessing | no embedding,MLPBackbone,FullyConnectedHead,nn.Sequential | 0.04 |
142+
| 7 | SimpleImputer,OneHotEncoder,StandardScaler,NoFeaturePreprocessing | no embedding,MLPBackbone,FullyConnectedHead,nn.Sequential | 0.04 |
143+
<smac.runhistory.runhistory.RunHistory object at 0x7fc419b097c0> [TrajEntry(train_perf=2147483648, incumbent_id=1, incumbent=Configuration:
145144
data_loader:batch_size, Value: 32
146145
encoder:__choice__, Value: 'NoEncoder'
147146
feature_preprocessor:__choice__, Value: 'NoFeaturePreprocessor'
@@ -180,7 +179,7 @@ the search. Currently, there are two changes that can be made to the space:-
180179
trainer:StandardTrainer:use_stochastic_weight_averaging, Value: True
181180
trainer:StandardTrainer:weighted_loss, Constant: 1
182181
trainer:__choice__, Value: 'StandardTrainer'
183-
, ta_runs=0, ta_time_used=0.0, wallclock_time=0.0016574859619140625, budget=0), TrajEntry(train_perf=0.15204678362573099, incumbent_id=1, incumbent=Configuration:
182+
, ta_runs=0, ta_time_used=0.0, wallclock_time=0.0016453266143798828, budget=0), TrajEntry(train_perf=0.15204678362573099, incumbent_id=1, incumbent=Configuration:
184183
data_loader:batch_size, Value: 32
185184
encoder:__choice__, Value: 'NoEncoder'
186185
feature_preprocessor:__choice__, Value: 'NoFeaturePreprocessor'
@@ -219,17 +218,22 @@ the search. Currently, there are two changes that can be made to the space:-
219218
trainer:StandardTrainer:use_stochastic_weight_averaging, Value: True
220219
trainer:StandardTrainer:weighted_loss, Constant: 1
221220
trainer:__choice__, Value: 'StandardTrainer'
222-
, ta_runs=1, ta_time_used=8.074149131774902, wallclock_time=9.542329788208008, budget=5.555555555555555)]
223-
{'accuracy': 0.838150289017341}
224-
| | Preprocessing | Estimator | Weight |
225-
|---:|:--------------------------------------------------------------|:-------------------------------------------------------------------|---------:|
226-
| 0 | SimpleImputer,NoEncoder,MinMaxScaler,NoFeaturePreprocessing | no embedding,ShapedResNetBackbone,FullyConnectedHead,nn.Sequential | 0.52 |
227-
| 1 | SimpleImputer,NoEncoder,Normalizer,KernelPCA | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.26 |
228-
| 2 | None | CatBoostClassifier | 0.1 |
229-
| 3 | None | RFClassifier | 0.04 |
230-
| 4 | SimpleImputer,NoEncoder,StandardScaler,NoFeaturePreprocessing | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.04 |
231-
| 5 | SimpleImputer,NoEncoder,Normalizer,PolynomialFeatures | no embedding,ResNetBackbone,FullyConnectedHead,nn.Sequential | 0.02 |
232-
| 6 | None | SVC | 0.02 |
221+
, ta_runs=1, ta_time_used=9.260286808013916, wallclock_time=10.778798341751099, budget=5.555555555555555)]
222+
{'accuracy': 0.8439306358381503}
223+
| | Preprocessing | Estimator | Weight |
224+
|---:|:--------------------------------------------------------------|:----------------------------------------------------------------|---------:|
225+
| 0 | None | CatBoostClassifier | 0.28 |
226+
| 1 | None | KNNClassifier | 0.18 |
227+
| 2 | None | SVC | 0.12 |
228+
| 3 | SimpleImputer,NoEncoder,Normalizer,PolynomialFeatures | no embedding,ResNetBackbone,FullyConnectedHead,nn.Sequential | 0.1 |
229+
| 4 | None | ExtraTreesClassifier | 0.08 |
230+
| 5 | SimpleImputer,NoEncoder,StandardScaler,NoFeaturePreprocessing | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.06 |
231+
| 6 | None | RFClassifier | 0.04 |
232+
| 7 | SimpleImputer,NoEncoder,StandardScaler,NoFeaturePreprocessing | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.04 |
233+
| 8 | SimpleImputer,NoEncoder,StandardScaler,NoFeaturePreprocessing | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.04 |
234+
| 9 | SimpleImputer,NoEncoder,StandardScaler,PolynomialFeatures | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.02 |
235+
| 10 | SimpleImputer,NoEncoder,StandardScaler,PolynomialFeatures | no embedding,ShapedMLPBackbone,FullyConnectedHead,nn.Sequential | 0.02 |
236+
| 11 | None | LGBMClassifier | 0.02 |
233237
234238
235239
@@ -358,7 +362,7 @@ the search. Currently, there are two changes that can be made to the space:-
358362
359363
.. rst-class:: sphx-glr-timing
360364

361-
**Total running time of the script:** ( 11 minutes 38.872 seconds)
365+
**Total running time of the script:** ( 11 minutes 35.768 seconds)
362366

363367

364368
.. _sphx_glr_download_advanced_tabular_example_custom_configuration_space.py:

0 commit comments

Comments
 (0)