Xueqing Liu
2a8decdc50
fix the post-processing bug in NER ( #534 )
...
* fix conll bug
* update DataCollatorForAuto
* adding label_list comments
2022-05-10 17:22:57 -04:00
Xueqing Liu
c1e1299855
fixing use_ray in automl.py ( #531 )
...
* fixing use_ray
2022-05-02 08:05:23 -07:00
Xueqing Liu
ca35fa969f
refactoring TransformersEstimator to support default and custom_hp ( #511 )
...
* refactoring TransformersEstimator to support default and custom_hp
* handling starting_points not in search space
* addressing starting point more than max_iter
* fixing upper < lower bug
2022-04-28 14:06:29 -04:00
Qingyun Wu
6c16e47e42
Bug fix and add documentation for metric_constraints ( #498 )
...
* metric constraint documentation
* update link
* update notebook
* fix a bug in adding 'time_total_s' to result
* use the default multiple factor from config file
* update notebook
* format
* improve test
* revise test budget for macos
* bug fix in adding time_total_s
* increase performance check budget
* revise test
* update notebook
* uncomment test
* remove redundancy
* clear output
* remove n_jobs
* remove constraint in notebook
* increase budget
* revise test
* add python version
* use getattr
* improve code robustness
Co-authored-by: Qingyun Wu <qxw5138@psu.edu>
2022-03-26 21:11:45 -04:00
Chi Wang
7eb7b46ea9
version number and doc ( #497 )
...
* version number
* add missing tasks in documentation
* update node-forge version
2022-03-25 17:32:37 -07:00
Xueqing Liu
5f97532986
adding evaluation ( #495 )
...
* adding automl.score
* fixing the metric name in train_with_config
* adding pickle after score
* fixing a bug in automl.pickle
2022-03-25 17:00:08 -04:00
Xueqing Liu
af423463c3
fixing bug for ner ( #463 )
...
* fixing bug for ner
* removing global var
* adding class for trial counter
* adding notebook
* adding use_ray dict
* updating documentation for nlp
2022-03-20 22:03:02 -04:00
Qingyun Wu
f6ae1331f5
metric constraints in flaml.automl ( #479 )
...
* metric constraints
* revise docstr
* fix docstr
* improve docstr
* Update flaml/automl.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* Update flaml/automl.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* Update flaml/automl.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* docstr
Co-authored-by: Qingyun Wu <qxw5138@psu.edu>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2022-03-12 00:39:35 -05:00
Kevin Chen
f9eda0cc40
update documentation for time series forecasting ( #472 )
...
* update automl.py
- documentation update
* update test_forecast.py
* update model.py
* update automl_time_series_forecast.ipynb
* update time series forecast website examples
Signed-off-by: Kevin Chen <chenkevin.8787@gmail.com>
2022-03-08 11:21:18 -08:00
Chi Wang
df01031cfe
Zero-shot AutoML ( #468 )
...
* Prepare for release
Co-authored-by: Moe Kayali <t-moekayali@microsoft.com>
* bug fix
* improve doc and code quality
Co-authored-by: Qingyun Wu
2022-03-01 15:39:09 -08:00
Chi Wang
e3e737c71a
make AutoML.classes_ an array ( #467 )
...
* remove .tolist()
* docstr
2022-02-25 22:13:41 -08:00
Qingyun Wu
05f9065ade
Docstr update ( #460 )
...
* parallel tuning docstr
* update n_concurrent_trials docstr
* n_jobs default
* parallel tuning in tune docstr
2022-02-15 09:41:53 -08:00
Chi Wang
9e88f22167
fix a bug when using ray & update ray on aml ( #455 )
...
* fix a bug when using ray & update ray on aml
When using with_parameters(), the config argument must be the first argument in the trainable function.
* make training function runnable standalone
2022-02-11 20:14:10 -08:00
Chi Wang
8a44dd4318
data in csv ( #430 )
...
* data in csv
* support ray ObjectRef #365
* use object store to store data when using ray
* make lgbm tuning example a test
* homepage title
2022-01-30 19:36:41 -08:00
Chi Wang
6960a833ec
Gpu support for xgboost ( #442 )
...
* xgboost gpu support
* test xgboost gpu
* test sparse data
* add xgboost test
* remove ray.init to avoid pytest error
2022-01-30 13:02:18 -08:00
Kevin Chen
81f54026c9
Support time series forecasting for discrete target variable ( #416 )
...
* support 'ts_forecast_classification' task to forecast discrete values
* update test_forecast.py
- add test for forecasting discrete values
* update test_model.py
* pre-commit changes
2022-01-24 18:39:36 -08:00
Chi Wang
6a7caa6a3d
max_iter < 2 -> no search; sign in metric constraints; test and example for forecasting ( #415 )
...
* max_iter < 2 -> no search
* use_ray in test
* eval_method in ts example
* check sign of constraints
* test metric constraint sign
2022-01-23 01:24:15 -08:00
Xueqing Liu
47d2295fb7
Set use_ray to True for logging to databricks ( #414 )
...
* fixing use_ray bug
2022-01-18 18:37:35 -08:00
MichaelMarien
1c911da9f8
Sklearn api x ( #405 )
...
* changed signature of automl.predict and automl.predict_proba to X
* XGBoostEstimator
* changed signature of Prophet predict to X
* changed signature of ARIMA predict to X
* changed signature of TS_SKLearn_Regressor predict to X
2022-01-16 14:37:56 -08:00
Chi Wang
569908fbe6
fix issues in logging, bug in space.py, constraint sign, and improve code coverage ( #388 )
...
* console log handler
* version update
* doc
* skippable steps
* notebook update
* constraint sign
* doc for constraints
* bug fix: define-by-run and unflatten_hierarchical
* const
* handle nested space in indexof()
* test grid search
* test suggestion
* model test
* >1 ckpts
* always increase iter count
* log total # iterations
* security patch
* make iter_per_learner consistent
2022-01-14 13:39:09 -08:00
Xueqing Liu
c1b5cb5348
fixing default metric for regression + change verbosity for transformers ( #397 )
...
* fixing default metric for regression + change verbosity for transformers
* fixing per_device_train_batch_size
* Update flaml/automl.py for gpu_per_trial
2022-01-13 21:08:51 -08:00
Xueqing Liu
f41f1c2198
Logging multiple checkpoints ( #394 )
2022-01-12 19:50:39 -08:00
Kevin Chen
99667dad5f
Regression forecast debug ( #391 )
...
* update automl.py
- fix bug with removing "catboost"
2022-01-11 13:16:59 -08:00
Xueqing Liu
c54c1246c6
fixing auto metric bug ( #387 )
2022-01-07 16:25:58 -08:00
Kevin Chen
d4273669e6
Time series forecasting with sklearn regressors ( #362 )
...
* add sklearn regressors as learners for ts_forecast task
* add direct forecasting strategy
warnings and errors for duplicate rows and missing values
- add preprocess for sklearn time series forecast
update automl.py
update test/test_forecast.py
* update model.py and test_forecast.py for cv eval_method
* add "hcrystalball" dependency in setup.py
* update automl.py
- add _validate_ts_data function for abstraction
- include xgb_limitdepth as a learner
* update model.py
- update search space for sklearn ts regressors
* update automl.py and test_forecast.py for numpy array inputs
* add documentations to model.py
* add documentation for removing catboost regressor
* update automl.py
- _validate_ts_data() function
Signed-off-by: Kevin Chen <chenkevin.8787@gmail.com>
2022-01-06 23:12:38 -08:00
Chi Wang
612668e8ed
serialize TransformerEstimator ( #381 )
...
* serialize TransformerEstimator
* check has_attr
* custom metric needs trainer
* skip test on mac
2022-01-06 10:28:19 -08:00
Chi Wang
cd9740f022
Fix several issues for nlp tasks ( #380 )
...
* num cpu issue #378 ;
* temp fix for ray issue #379 ;
* transformers version.
2022-01-05 13:49:12 -08:00
Xueqing Liu
207b6935d9
adding token classification ( #376 )
...
* adding ner
2022-01-03 13:44:10 -05:00
Chi Wang
8602def1c4
logging ( #371 )
...
* query logged runs
* mlflow log when using ray
* key check for newer version of ray #363
* catch importerror
* log and load AutoML model
* retrain if necessary when ensemble fails
2022-01-02 21:37:19 -08:00
Chi Wang
2f5d6169d3
example update ( #359 )
...
update some examples for consistencies with others.
2021-12-25 16:13:39 -08:00
Chi Wang
baa0359324
doc update ( #352 )
...
* custom splitter
* NLP
* version number
2021-12-22 14:35:13 -08:00
Chi Wang
0b25e89f29
reproducibility for random sampling ( #349 )
...
* reproducibility for random sampling #236
* doc update
2021-12-22 12:12:25 -08:00
Xueqing Liu
ee3162e232
Adding the NLP task summarization ( #346 )
...
* Add test_autohf_summarization.py
* adding seq2seq
* Update flaml/nlp/huggingface/trainer.py
* rouge metrics
Co-authored-by: XinZofStevens <xzhao4346@gmail.com>
Co-authored-by: JinzhuoWu <wujinzhuo0105@gmail.com>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-12-20 14:19:32 -08:00
Chi Wang
efd85b4c86
Deploy a new doc website ( #338 )
...
A new documentation website. And:
* add actions for doc
* update docstr
* installation instructions for doc dev
* unify README and Getting Started
* rename notebook
* doc about best_model_for_estimator #340
* docstr for keep_search_state #340
* DNN
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu>
Co-authored-by: Z.sk <shaokunzhang@psu.edu>
2021-12-16 17:11:33 -08:00
Chia-Chi Hsu
671ccbbe3f
support for customized splitters ( #333 )
...
* add support for customized splitters
* use the param split_type for feeding generators
* use single API for customized splitter and add test
* when task==TS_FORCAST, always set shuffle=False
* update docstr
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-12-16 16:13:04 -08:00
Xueqing Liu
1a3e01c352
adding HF metrics ( #335 )
...
* adding nlp metrics
* fix ndcg
2021-12-10 12:32:49 -05:00
Qingyun Wu
17b17d084f
tune api for schedulers ( #322 )
...
* revise api and tests
* rename prune_attr
* update finetune notebook
* add scheduler test and notebook
* update tune api for scheduler
* remove scheduler notebook
* Update flaml/tune/tune.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* docstr
* fix imports
* clear notebook output
* fix ray import
* Update flaml/tune/tune.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* improve docstr
* Update flaml/searcher/blendsearch.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* remove redundant import
Co-authored-by: Qingyun Wu <qxw5138@psu.edu>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-12-04 21:52:20 -05:00
Chi Wang
7d269435ae
add save_best_config()
2021-12-04 16:29:52 -08:00
Chi Wang
18230ed22f
pred_time_limit clarification and logging ( #319 )
...
* pred_time_limit clarification
* log prediction time
* handle ChunkedEncodingError in test
2021-12-03 16:02:00 -08:00
Chi Wang
c57954fbbd
include default value in rf search space ( #317 )
...
* include default value in rf search space
* init _mem_per_iter with -1
* bump version to 0.8.2
* docstr for search space's arguments
2021-12-03 09:15:21 -08:00
Chi Wang
1545d5a6d2
skip cv preparation if eval_method is holdout ( #314 )
...
* skip cv preparation if eval_method is holdout
* bump version to 0.8.1
2021-11-28 11:18:55 -08:00
Xueqing Liu
fd136b02d1
bug fix for TransformerEstimator ( #293 )
...
* fix checkpoint naming + trial id for non-ray mode, fix the bug in running test mode, delete all the checkpoints in non-ray mode
* finished testing for checkpoint naming, delete checkpoint, ray, max iter = 1
* adding predict_proba, address PR 293's comments
close #293 #291
2021-11-23 11:26:39 -08:00
Chi Wang
85e21864ce
test -> val; docstr ( #300 )
...
* rename test -> val in custom metric function
* add an example in docstr
resolve #299
2021-11-22 22:17:29 -08:00
Chi Wang
ea6d28d7bd
add max_depth to xgboost search space ( #282 )
...
* add max_depth to xgboost search space
* notebook update
* two learners for xgboost (max_depth or max_leaves)
2021-11-22 21:17:48 -08:00
Chi Wang
d937b03e42
multioutput regression ( #292 )
...
* make AutoML inherit sklearn.base.BaseEstimator such that it can be wrapped in sklearn.multioutput.MultiOutputRegressor for multi-output regression.
* moved and simplified preprocessing code in AutoML.predictI() to _preprocess()
2021-11-22 06:59:42 -08:00
Chi Wang
72caa2172d
model_history, ITER_HP, settings in AutoML(), checkpoint bug fix ( #283 )
...
if save_best_model_per_estimator is False and retrain_final is True, unfit the model after evaluation in HPO.
retrain if using ray.
update ITER_HP in config after a trial is finished.
change prophet logging level.
example and notebook update.
allow settings to be passed to AutoML constructor. Are you planning to add multi-output-regression capability to FLAML #192 Is multi-tasking allowed? #277 can pass the auotml setting to the constructor instead of requiring a derived class.
remove model_history.
checkpoint bug fix.
* model_history meaning save_best_model_per_estimator
* ITER_HP
* example update
* prophet logging level
* comment update in forecast notebook
* print format improvement
* allow settings to be passed to AutoML constructor
* checkpoint bug fix
* time limit for autohf regression test
* skip slow test on macos
* cleanup before del
2021-11-18 09:39:45 -08:00
Qingyun Wu
e9551de3cc
add best_loss_per_estimator
2021-11-17 22:43:20 -08:00
Xueqing Liu
42de3075e9
Make NLP tasks available from AutoML.fit() ( #210 )
...
Sequence classification and regression: "seq-classification" and "seq-regression"
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2021-11-16 11:06:20 -08:00
Chi Wang
92ebd1f7f9
when max_iter=1, skip search only if retrain_final ( #280 )
...
* when max_iter=1, skip search only if retrain_final
* remove nlp
redesign in #210
* minor change in readme example
2021-11-09 21:51:23 -08:00
Chi Wang
0c7bf7219f
Merge branch 'main' into docstr
2021-11-06 21:58:26 -07:00
