yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2025-09-15 11:16:13 +00:00
Code Issues Packages Projects Releases Wiki Activity
678 Commits 200 Branches 127 Tags
Commit Graph

678 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Xueqing Liu
4814091d87
remove redundant imports (#426) 
* remove redundant imports

* getting ride of hf dataset
 2022-01-24 14:24:14 -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
Chi Wang
38ad31ea25
remove FLAML sample size from config (#418) 2022-01-22 22:59:44 -08:00
Antoni Baum
113539545c
Use Ray _BackwardsCompatibleNumpyRng if possible (#421) 2022-01-22 22:14:49 -08:00
Chi Wang
4e8b6b98b0 bump flaml version to 0.9.6 2022-01-22 17:15:52 -08:00
Chi Wang
d2b2f98a0d bump version of node-fetch to 3.1.1 in website/ 2022-01-22 17:15:52 -08:00
Chi Wang
66bbe782ee Bump nanoid from 3.1.30 to 3.2.0 in /website 2022-01-22 08:58:53 -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
Z.sk
bb6cd73fb5
Merge pull request #3 from microsoft/main 
update
 2022-01-18 09:30:36 +08:00
Xueqing Liu
3ef758cd7b
reducing AutoConfig.from_pretrained (#411) 
* reducing AutoConfig.from_pretrained
 2022-01-17 11:44:11 -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
a6d70efff7
Bump shelljs from 0.8.4 to 0.8.5 in /website (#402) 2022-01-16 09:41:11 -08:00
Xueqing Liu
cb9c7b0d16
adding logging of training loss (#406) 
* reducing AutoTokenizer load to only once

* fixing early stop bug
 2022-01-16 09:07:31 -08:00
Qingyun Wu
8f0737c57c
update browser icon (#407) 
* update ico
 2022-01-15 14:44:42 -08:00
Qingyun Wu
ac16c31000
Logo (#399) 
* add logo

* update link to file

* Update README.md

* del png

* update website logo

* update icon

Co-authored-by: Qingyun Wu <qxw5138@psu.edu>
Co-authored-by: 张少坤 <zhangshaokun@fuzhi.ai>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
 2022-01-14 21:32:04 -08:00
Xueqing Liu
31645187f3
Update flaml/nlp/README.md (#404) 2022-01-14 17:55:38 -08:00
Xueqing Liu
dda4ac90a1
moving intermediate_results logging from model.py to huggingface/trainer.py (#403) 
* replacing val_loss with automl_metric
 2022-01-14 17:26:10 -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
Z.sk
d7ff258b89
Merge pull request #2 from microsoft/main 
update
 2022-01-14 23:07:06 +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
Chi Wang
8e72904b9e
postcss version update (#385) 2022-01-12 22:24:17 -08:00
Xueqing Liu
f41f1c2198
Logging multiple checkpoints (#394) 2022-01-12 19:50:39 -08:00
liususan091219
303d40c76c set verbose for transformers 2022-01-11 21:42:27 -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
bd66e40296
fixing load best model at the end (#389) 2022-01-11 10:47:53 -08:00
Z.sk
b66930e4f0
Merge pull request #1 from microsoft/main 
update
 2022-01-11 08:32:50 +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
Chi Wang
8593a3fe27
citation file (#364) 2022-01-04 15:13:14 -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
oberonbot
9c00e4272a
Finish the Multiple Choice Classification (#367) 
* adding multiple choice

* update test cases (hard coded)

* merged common code in predict_proba and predict in TransformersEstimator
 2022-01-02 20:12:34 -05:00
Chi Wang
2f5d6169d3
example update (#359) 
update some examples for consistencies with others.
 2021-12-25 16:13:39 -08:00
Xueqing Liu
b2900f4b22
fixing custom metric (#357) 
* fixing the error for custom metric
 2021-12-24 16:23:09 -05:00
Rui Zhuang
c6c0c29769
Simplify lgbm example (#358) 
* simplify lgbm examples

* provide link to lgbm example script.

* simply lgbm example in the example script.

Co-authored-by: Chi Wang <wang.chi@microsoft.com>
 2021-12-23 23:05:14 -08:00
Xueqing Liu
dcfd218108
Fixing the bug in custom metric (#356) 
* fixing the bug for custom metric
 2021-12-23 18:44:53 -05:00
Chi Wang
300f286667
azureml + ray (#344) 
* examples and documentation about how to use azureml + ray
 2021-12-23 13:37:07 -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
a340dbc554 url update for doc edit 2021-12-18 15:00:54 -08:00
Chi Wang
f3fc35c438 version update 2021-12-16 18:38:19 -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
Z.sk
7b24662dca
Makes the evaluation_function could receive the incumbent best result as input in Tune (#339) 
* update tune function

* pass incumbent result to the training function

* Update test/tune/test_record_incumbent.py

* Update flaml/searcher/search_thread.py

* Update flaml/searcher/blendsearch.py

* Update flaml/tune/tune.py

* add constant variable

Co-authored-by: 张少坤 <zhangshaokun@fuzhi.ai>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
 2021-12-15 21:12:47 -08:00
Chi Wang
228b00cbee
use cfo in tune.run if bs is not installed (#334) 
Use cfo in tune.run if bs is not installed and issue a warning.
 2021-12-12 21:10:06 -08:00
Chi Wang
434586e2e2
train at least one iter when not trained (#336) 
* train at least one iter when not trained

* bump version to 0.9.1
 2021-12-12 20:05:18 -08:00
Xueqing Liu
1a3e01c352
adding HF metrics (#335) 
* adding nlp metrics

* fix ndcg
 2021-12-10 12:32:49 -05:00