Integrating LGT/DLT into ETS Base #280

edwinnglabs · 2020-11-09T02:35:59Z

Description

A significant refactor of ETS related models. To make models more extensible, we want to create a base named as ETS to build core logic such as smoothing parameters and attributes, regression etc.

Fixes # (issue)

Type of change

How Has This Been Tested?

unit tests on ETS
unit tests different position of columns of regressor matrices
compare predictions of LGT and DLT against master
unit tests for LGT/DLT negative regressors test cases

* fix regressor matrix extraction * unit test for cases with mixed pos&reg regressors

edwinnglabs · 2020-11-11T00:26:05Z

@steveyang90 this should be ready for some initial review. Want to hear your input before updating doc string and tutorials.

steveyang90 · 2020-11-11T03:04:19Z

At a high level this makes sense and is in line with what I had in mind. It'll take me a little while to go through the details.

As I also mentioned, I'm working on a PR right now for a linear regression, which also incorporates a redesign to push up a common base class. I agree with the general design pattern here, but I'm leaning more towards having an abstract shared class, rather than a concrete. For now I think the general design here is fine though.

I'll wait until we wrap up this PR to incorporate that though so we can merge one thing at a time

steveyang90

@edwinnglabs line by line comments are a little hard on this PR so i'll be writing a series of comments here. Overall, I think the refactor is good and aligned with how we previously discussed!

A few things, it appears there are a number of methods left in LGTBase that are identical to the methods that are now pushed up to ETS and can be removed. Let me know if there's a reason for this.

To name a few:

BaseLGT.fit()
BaseLGT._prepent_date_column()
BaseLGT._set_aggregate_posteriors()

Not sure if that list is exhaustive or not, but you can do a diff comparison between the methods in LGT and ETS and remove any that are identical

Same for DLT, but I think there are fewer there.

steveyang90 · 2020-11-14T03:48:08Z

This one is just a note to keep track in the future: redundant regression methods between DLT and LGT will either be handled in #275 or in a follow up PR

steveyang90 · 2020-11-14T03:51:45Z

Also I think _get_regressor_matrix() in BaseETS is not meant to be there, since there is not regression context in ETS

edwinnglabs · 2020-12-04T22:52:19Z

@steveyang90 i feel quite safe now for having the new unit tests added and have this PR passed them. I suggest you do a quick final review before we merge this since it is impacting a lot of lines.

steveyang90 · 2020-12-04T23:54:33Z

@edwinnglabs I just merged #303 into dev. That one contains the new unit test that ensures reproducibility for both fit and predict. I think since it'd be a good idea to rebase to dev and make sure that the test runs here as well to ensure that that is still working.

In addition, I only wrote that test for LGT. I think it's worthwhile adding it for DLT and ETS in this PR before merging as well since this is a huge change.

… dev-refactor-ets

steveyang90

Almost there! Some small last bits of clean up left in the comments and then we should be good to merge

steveyang90 · 2020-12-05T07:21:29Z

orbit/models/lgt.py

+        """
+        super()._set_static_data_attributes()
+        # TODO: hacky fix
+        # self._set_init_values()


@edwinnglabs Can we confirm and remove these commented lines to avoid confusion

steveyang90 · 2020-12-05T07:24:57Z

orbit/models/lgt.py

-            init_values_callable = lambda: init_values_function(seasonality)  # noqa
-            self._init_values = init_values_callable
+    @staticmethod
+    def _get_regressor_matrix(df, rr_col, pr_col, nr_col):


I don't think this is used anywhere. If that is the case, let's remove to avoid confusion since we preserve regression order using self._regressor_col

steveyang90 · 2020-12-05T07:36:36Z

orbit/models/dlt.py

+                items=self._regular_regressor_col, ).values
+
+    @staticmethod
+    def _get_regressor_matrix(df, rr_col, pr_col, nr_col):


Same comment as in LGT. Let's get rid of this if we're not using it

- refine/remove comments - remove unused methods

steveyang90 · 2020-12-05T20:43:33Z

LGTM!

* remove enum34 dependency (#301) * add test_lgt_full_reproducibility (#303) * Integrating LGT/DLT into ETS Base (#280) * first draft of ets * ets temp * refresh banner and icon * read me link * more banners * testing new dim of banner * Predict fix (#281) * fix regressor matrix extraction * unit test for cases with mixed pos&reg regressors * adding logo and some style for tutorial and docs * favicon * refactoring DLT onto ets * refine DLT and pass all unit tests * passed all unit tests * unit test fix * fixed unit test * add test_ets.py * Additional refinement on ETS Refactoring (#296) * fixed some OO duplicated methods -[x] remove duplicated modules as suggested -[x] remove `_get_regresso_matrix()` as suggested * docstring update * removing fit method in lgt * add negative regressor test cases * add negative regressor test * Update test_lgt.py * updated the test data and tests logic * fixed numerical issues due to initialization * minor * bug fix * Update conftest.py * Create iclaims.example.csv * temp * Create orbit-adhoc-test[TEST].ipynb * fixed regression issue * Delete orbit-adhoc-test[TEST].ipynb * removing negative test for lgt * add test_lgt_full_reproducibility (#303) * introducing * small fix on refactoring ets - refine/remove comments - remove unused methods Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> Co-authored-by: Yifeng Wu <yifeng.wu@uber.com> Co-authored-by: Steve Yang <steven.s.yang@gmail.com> * Create RELEASE.md (#307) * utility for hyper-parameter tuning (#324) * utility for hyper-parameter tuning * minor * demo for hyper tuning * Organize Plotting functions and enhancement (#327) * Tutorial Update - diagnostics/backtest plotting (#332) * add ploting tutorials * back test tutorial * back test tutorial * fix commets * suppress warnings * quick fix * badge update * Update tutorials notebooks (#329) * Update tutorials notebooks * add the notebook and dataset for regression * push the new icalim dataset * update the regression notebook and modify the data load function * update for regression tutorials * regression notebook * Update regression.ipynb * notebooks update * refine verbiage; regression change * minor cosmetics * remove log transform since it's done in new iclaims data * remove log transform since it's done in the new iclaims data * filter first then standardize * filter first then standardize Co-authored-by: Edwin Ng <edwinng@uber.com> Co-authored-by: Zhishi Wang <zhishiw@uber.com> Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> * fix data url in load_iclaims() (#337) * fix data url in load_iclaims() * update the tutorials catalogue to reflect the changes; fix typos * Minor updates in tutorial notebooks (#339) * fix tutorials notebook * update title level in regression notebook * Feat pickle fix (#342) * first pickle fix attempt * better attempt by using initializer creating an initializer class to tackle problem of #340 fixed #40 * ETS Initializer add ets initializer and change some wording from stan to generic * change wording from stan to generic [minor] minor wording * Add deprecating warnings for LGT model with regressor (#341) * add deprecation warning for LGT regression * remove wrong notebook * remove wrong notebook * minor cosmetic change (#343) * Dev unit test (#348) * validation for global_trend_option and regression_penalty * unit test for fixed sm input and regression penalty * unit test for fixed sm input * validation for global_trend_option and regression_penalty * unit test for fixed sm input and regression penalty * warning message * more smoothing input tests * more smoothing input tests * change level_sm_input lower bound to 0.001 from 0 * raise error message for level_sm_input lower than 0.0001 * Docstring inheritance (#351) * add docstring inheritance * add example jupyter notebook * add requirements * minor changes * minor formatting * add lower bound for common substring * Update stan_estimator.py * Update docstring_inheritance_check.ipynb * Update backtest.py Co-authored-by: Edwin Ng <edwinng@uber.com> * iclaims data de-meaning (#352) * pumping version to 1.0.11 pumping version to 1.0.11 * bug fix for following sphinx in README.rst * Update setup.py Co-authored-by: CrossNox <ijmermet@gmail.com> Co-authored-by: Steve Yang <steven.s.yang@gmail.com> Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> Co-authored-by: Yifeng Wu <yifeng.wu@uber.com> Co-authored-by: ppstacy <ppstacy@gmail.com> Co-authored-by: Zhishi Wang <zhishiw@uber.com>

* remove enum34 dependency (#301) * add test_lgt_full_reproducibility (#303) * Integrating LGT/DLT into ETS Base (#280) * first draft of ets * ets temp * refresh banner and icon * read me link * more banners * testing new dim of banner * Predict fix (#281) * fix regressor matrix extraction * unit test for cases with mixed pos&reg regressors * adding logo and some style for tutorial and docs * favicon * refactoring DLT onto ets * refine DLT and pass all unit tests * passed all unit tests * unit test fix * fixed unit test * add test_ets.py * Additional refinement on ETS Refactoring (#296) * fixed some OO duplicated methods -[x] remove duplicated modules as suggested -[x] remove `_get_regresso_matrix()` as suggested * docstring update * removing fit method in lgt * add negative regressor test cases * add negative regressor test * Update test_lgt.py * updated the test data and tests logic * fixed numerical issues due to initialization * minor * bug fix * Update conftest.py * Create iclaims.example.csv * temp * Create orbit-adhoc-test[TEST].ipynb * fixed regression issue * Delete orbit-adhoc-test[TEST].ipynb * removing negative test for lgt * add test_lgt_full_reproducibility (#303) * introducing * small fix on refactoring ets - refine/remove comments - remove unused methods Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> Co-authored-by: Yifeng Wu <yifeng.wu@uber.com> Co-authored-by: Steve Yang <steven.s.yang@gmail.com> * Create RELEASE.md (#307) * utility for hyper-parameter tuning (#324) * utility for hyper-parameter tuning * minor * demo for hyper tuning * Organize Plotting functions and enhancement (#327) * Tutorial Update - diagnostics/backtest plotting (#332) * add ploting tutorials * back test tutorial * back test tutorial * fix commets * suppress warnings * quick fix * badge update * Update tutorials notebooks (#329) * Update tutorials notebooks * add the notebook and dataset for regression * push the new icalim dataset * update the regression notebook and modify the data load function * update for regression tutorials * regression notebook * Update regression.ipynb * notebooks update * refine verbiage; regression change * minor cosmetics * remove log transform since it's done in new iclaims data * remove log transform since it's done in the new iclaims data * filter first then standardize * filter first then standardize Co-authored-by: Edwin Ng <edwinng@uber.com> Co-authored-by: Zhishi Wang <zhishiw@uber.com> Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> * fix data url in load_iclaims() (#337) * fix data url in load_iclaims() * update the tutorials catalogue to reflect the changes; fix typos * Minor updates in tutorial notebooks (#339) * fix tutorials notebook * update title level in regression notebook * Feat pickle fix (#342) * first pickle fix attempt * better attempt by using initializer creating an initializer class to tackle problem of #340 fixed #40 * ETS Initializer add ets initializer and change some wording from stan to generic * change wording from stan to generic [minor] minor wording * Add deprecating warnings for LGT model with regressor (#341) * add deprecation warning for LGT regression * remove wrong notebook * remove wrong notebook * minor cosmetic change (#343) * Dev unit test (#348) * validation for global_trend_option and regression_penalty * unit test for fixed sm input and regression penalty * unit test for fixed sm input * validation for global_trend_option and regression_penalty * unit test for fixed sm input and regression penalty * warning message * more smoothing input tests * more smoothing input tests * change level_sm_input lower bound to 0.001 from 0 * raise error message for level_sm_input lower than 0.0001 * Docstring inheritance (#351) * add docstring inheritance * add example jupyter notebook * add requirements * minor changes * minor formatting * add lower bound for common substring * Update stan_estimator.py * Update docstring_inheritance_check.ipynb * Update backtest.py Co-authored-by: Edwin Ng <edwinng@uber.com> * iclaims data de-meaning (#352) * pumping version to 1.0.11 pumping version to 1.0.11 * bug fix for following sphinx in README.rst * Update setup.py * pumping version * Update README.rst * Update README.rst * Update README.rst * Update README.rst * readme refine * Provide Inference for MAP and Aggregated Estimator (#359) * Create .readthedocs.yml. * Rename .readthedocs.yml. to .readthedocs.yml * Update .readthedocs.yml * Dev tutorials update (#362) * tutorials update for master branch * Update conf.py * Update __init__.py * tutorial update * notebook update * Update lgt.ipynb * update * notebook * Update pyro_basic.ipynb * temp * Provide Inference for MAP and Aggregated Estimator (#359) * Update pyro_basic.ipynb * update of notebooks * tutorial update and proof-reading * cell number update * notebook minor update * relabel notebook under exampels/ * file ext * new tab and more updates * readme tone change & link fix * typo fix * minor fix Co-authored-by: Zhishi Wang <zhishiw@uber.com> * Update .readthedocs.yml * Update .readthedocs.yml * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb Co-authored-by: CrossNox <ijmermet@gmail.com> Co-authored-by: Steve Yang <steven.s.yang@gmail.com> Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> Co-authored-by: Yifeng Wu <yifeng.wu@uber.com> Co-authored-by: ppstacy <ppstacy@gmail.com> Co-authored-by: Zhishi Wang <zhishiw@uber.com>

* remove enum34 dependency (#301) * add test_lgt_full_reproducibility (#303) * Integrating LGT/DLT into ETS Base (#280) * first draft of ets * ets temp * refresh banner and icon * read me link * more banners * testing new dim of banner * Predict fix (#281) * fix regressor matrix extraction * unit test for cases with mixed pos&reg regressors * adding logo and some style for tutorial and docs * favicon * refactoring DLT onto ets * refine DLT and pass all unit tests * passed all unit tests * unit test fix * fixed unit test * add test_ets.py * Additional refinement on ETS Refactoring (#296) * fixed some OO duplicated methods -[x] remove duplicated modules as suggested -[x] remove `_get_regresso_matrix()` as suggested * docstring update * removing fit method in lgt * add negative regressor test cases * add negative regressor test * Update test_lgt.py * updated the test data and tests logic * fixed numerical issues due to initialization * minor * bug fix * Update conftest.py * Create iclaims.example.csv * temp * Create orbit-adhoc-test[TEST].ipynb * fixed regression issue * Delete orbit-adhoc-test[TEST].ipynb * removing negative test for lgt * add test_lgt_full_reproducibility (#303) * introducing * small fix on refactoring ets - refine/remove comments - remove unused methods Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> Co-authored-by: Yifeng Wu <yifeng.wu@uber.com> Co-authored-by: Steve Yang <steven.s.yang@gmail.com> * Create RELEASE.md (#307) * utility for hyper-parameter tuning (#324) * utility for hyper-parameter tuning * minor * demo for hyper tuning * Organize Plotting functions and enhancement (#327) * Tutorial Update - diagnostics/backtest plotting (#332) * add ploting tutorials * back test tutorial * back test tutorial * fix commets * suppress warnings * quick fix * badge update * Update tutorials notebooks (#329) * Update tutorials notebooks * add the notebook and dataset for regression * push the new icalim dataset * update the regression notebook and modify the data load function * update for regression tutorials * regression notebook * Update regression.ipynb * notebooks update * refine verbiage; regression change * minor cosmetics * remove log transform since it's done in new iclaims data * remove log transform since it's done in the new iclaims data * filter first then standardize * filter first then standardize Co-authored-by: Edwin Ng <edwinng@uber.com> Co-authored-by: Zhishi Wang <zhishiw@uber.com> Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> * fix data url in load_iclaims() (#337) * fix data url in load_iclaims() * update the tutorials catalogue to reflect the changes; fix typos * Minor updates in tutorial notebooks (#339) * fix tutorials notebook * update title level in regression notebook * Feat pickle fix (#342) * first pickle fix attempt * better attempt by using initializer creating an initializer class to tackle problem of #340 fixed #40 * ETS Initializer add ets initializer and change some wording from stan to generic * change wording from stan to generic [minor] minor wording * Add deprecating warnings for LGT model with regressor (#341) * add deprecation warning for LGT regression * remove wrong notebook * remove wrong notebook * minor cosmetic change (#343) * Dev unit test (#348) * validation for global_trend_option and regression_penalty * unit test for fixed sm input and regression penalty * unit test for fixed sm input * validation for global_trend_option and regression_penalty * unit test for fixed sm input and regression penalty * warning message * more smoothing input tests * more smoothing input tests * change level_sm_input lower bound to 0.001 from 0 * raise error message for level_sm_input lower than 0.0001 * Docstring inheritance (#351) * add docstring inheritance * add example jupyter notebook * add requirements * minor changes * minor formatting * add lower bound for common substring * Update stan_estimator.py * Update docstring_inheritance_check.ipynb * Update backtest.py Co-authored-by: Edwin Ng <edwinng@uber.com> * iclaims data de-meaning (#352) * pumping version to 1.0.11 pumping version to 1.0.11 * bug fix for following sphinx in README.rst * Update setup.py * pumping version * Update README.rst * Update README.rst * Update README.rst * Update README.rst * readme refine * Provide Inference for MAP and Aggregated Estimator (#359) * Create .readthedocs.yml. * Rename .readthedocs.yml. to .readthedocs.yml * Update .readthedocs.yml * Dev tutorials update (#362) * tutorials update for master branch * Update conf.py * Update __init__.py * tutorial update * notebook update * Update lgt.ipynb * update * notebook * Update pyro_basic.ipynb * temp * Provide Inference for MAP and Aggregated Estimator (#359) * Update pyro_basic.ipynb * update of notebooks * tutorial update and proof-reading * cell number update * notebook minor update * relabel notebook under exampels/ * file ext * new tab and more updates * readme tone change & link fix * typo fix * minor fix Co-authored-by: Zhishi Wang <zhishiw@uber.com> * Update .readthedocs.yml * Update .readthedocs.yml * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update README.md Co-authored-by: CrossNox <ijmermet@gmail.com> Co-authored-by: Steve Yang <steven.s.yang@gmail.com> Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> Co-authored-by: Yifeng Wu <yifeng.wu@uber.com> Co-authored-by: ppstacy <ppstacy@gmail.com> Co-authored-by: Zhishi Wang <zhishiw@uber.com>

* remove enum34 dependency (#301) * add test_lgt_full_reproducibility (#303) * Integrating LGT/DLT into ETS Base (#280) * first draft of ets * ets temp * refresh banner and icon * read me link * more banners * testing new dim of banner * Predict fix (#281) * fix regressor matrix extraction * unit test for cases with mixed pos&reg regressors * adding logo and some style for tutorial and docs * favicon * refactoring DLT onto ets * refine DLT and pass all unit tests * passed all unit tests * unit test fix * fixed unit test * add test_ets.py * Additional refinement on ETS Refactoring (#296) * fixed some OO duplicated methods -[x] remove duplicated modules as suggested -[x] remove `_get_regresso_matrix()` as suggested * docstring update * removing fit method in lgt * add negative regressor test cases * add negative regressor test * Update test_lgt.py * updated the test data and tests logic * fixed numerical issues due to initialization * minor * bug fix * Update conftest.py * Create iclaims.example.csv * temp * Create orbit-adhoc-test[TEST].ipynb * fixed regression issue * Delete orbit-adhoc-test[TEST].ipynb * removing negative test for lgt * add test_lgt_full_reproducibility (#303) * introducing * small fix on refactoring ets - refine/remove comments - remove unused methods Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> Co-authored-by: Yifeng Wu <yifeng.wu@uber.com> Co-authored-by: Steve Yang <steven.s.yang@gmail.com> * Create RELEASE.md (#307) * utility for hyper-parameter tuning (#324) * utility for hyper-parameter tuning * minor * demo for hyper tuning * Organize Plotting functions and enhancement (#327) * Tutorial Update - diagnostics/backtest plotting (#332) * add ploting tutorials * back test tutorial * back test tutorial * fix commets * suppress warnings * quick fix * badge update * Update tutorials notebooks (#329) * Update tutorials notebooks * add the notebook and dataset for regression * push the new icalim dataset * update the regression notebook and modify the data load function * update for regression tutorials * regression notebook * Update regression.ipynb * notebooks update * refine verbiage; regression change * minor cosmetics * remove log transform since it's done in new iclaims data * remove log transform since it's done in the new iclaims data * filter first then standardize * filter first then standardize Co-authored-by: Edwin Ng <edwinng@uber.com> Co-authored-by: Zhishi Wang <zhishiw@uber.com> Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> * fix data url in load_iclaims() (#337) * fix data url in load_iclaims() * update the tutorials catalogue to reflect the changes; fix typos * Minor updates in tutorial notebooks (#339) * fix tutorials notebook * update title level in regression notebook * Feat pickle fix (#342) * first pickle fix attempt * better attempt by using initializer creating an initializer class to tackle problem of #340 fixed #40 * ETS Initializer add ets initializer and change some wording from stan to generic * change wording from stan to generic [minor] minor wording * Add deprecating warnings for LGT model with regressor (#341) * add deprecation warning for LGT regression * remove wrong notebook * remove wrong notebook * minor cosmetic change (#343) * Dev unit test (#348) * validation for global_trend_option and regression_penalty * unit test for fixed sm input and regression penalty * unit test for fixed sm input * validation for global_trend_option and regression_penalty * unit test for fixed sm input and regression penalty * warning message * more smoothing input tests * more smoothing input tests * change level_sm_input lower bound to 0.001 from 0 * raise error message for level_sm_input lower than 0.0001 * Docstring inheritance (#351) * add docstring inheritance * add example jupyter notebook * add requirements * minor changes * minor formatting * add lower bound for common substring * Update stan_estimator.py * Update docstring_inheritance_check.ipynb * Update backtest.py Co-authored-by: Edwin Ng <edwinng@uber.com> * iclaims data de-meaning (#352) * pumping version to 1.0.11 pumping version to 1.0.11 * bug fix for following sphinx in README.rst * Update setup.py Co-authored-by: CrossNox <ijmermet@gmail.com> Co-authored-by: Steve Yang <steven.s.yang@gmail.com> Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> Co-authored-by: Yifeng Wu <yifeng.wu@uber.com> Co-authored-by: ppstacy <ppstacy@gmail.com> Co-authored-by: Zhishi Wang <zhishiw@uber.com>

* remove enum34 dependency (#301) * add test_lgt_full_reproducibility (#303) * Integrating LGT/DLT into ETS Base (#280) * first draft of ets * ets temp * refresh banner and icon * read me link * more banners * testing new dim of banner * Predict fix (#281) * fix regressor matrix extraction * unit test for cases with mixed pos&reg regressors * adding logo and some style for tutorial and docs * favicon * refactoring DLT onto ets * refine DLT and pass all unit tests * passed all unit tests * unit test fix * fixed unit test * add test_ets.py * Additional refinement on ETS Refactoring (#296) * fixed some OO duplicated methods -[x] remove duplicated modules as suggested -[x] remove `_get_regresso_matrix()` as suggested * docstring update * removing fit method in lgt * add negative regressor test cases * add negative regressor test * Update test_lgt.py * updated the test data and tests logic * fixed numerical issues due to initialization * minor * bug fix * Update conftest.py * Create iclaims.example.csv * temp * Create orbit-adhoc-test[TEST].ipynb * fixed regression issue * Delete orbit-adhoc-test[TEST].ipynb * removing negative test for lgt * add test_lgt_full_reproducibility (#303) * introducing * small fix on refactoring ets - refine/remove comments - remove unused methods Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> Co-authored-by: Yifeng Wu <yifeng.wu@uber.com> Co-authored-by: Steve Yang <steven.s.yang@gmail.com> * Create RELEASE.md (#307) * utility for hyper-parameter tuning (#324) * utility for hyper-parameter tuning * minor * demo for hyper tuning * Organize Plotting functions and enhancement (#327) * Tutorial Update - diagnostics/backtest plotting (#332) * add ploting tutorials * back test tutorial * back test tutorial * fix commets * suppress warnings * quick fix * badge update * Update tutorials notebooks (#329) * Update tutorials notebooks * add the notebook and dataset for regression * push the new icalim dataset * update the regression notebook and modify the data load function * update for regression tutorials * regression notebook * Update regression.ipynb * notebooks update * refine verbiage; regression change * minor cosmetics * remove log transform since it's done in new iclaims data * remove log transform since it's done in the new iclaims data * filter first then standardize * filter first then standardize Co-authored-by: Edwin Ng <edwinng@uber.com> Co-authored-by: Zhishi Wang <zhishiw@uber.com> Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> * fix data url in load_iclaims() (#337) * fix data url in load_iclaims() * update the tutorials catalogue to reflect the changes; fix typos * Minor updates in tutorial notebooks (#339) * fix tutorials notebook * update title level in regression notebook * Feat pickle fix (#342) * first pickle fix attempt * better attempt by using initializer creating an initializer class to tackle problem of #340 fixed #40 * ETS Initializer add ets initializer and change some wording from stan to generic * change wording from stan to generic [minor] minor wording * Add deprecating warnings for LGT model with regressor (#341) * add deprecation warning for LGT regression * remove wrong notebook * remove wrong notebook * minor cosmetic change (#343) * Dev unit test (#348) * validation for global_trend_option and regression_penalty * unit test for fixed sm input and regression penalty * unit test for fixed sm input * validation for global_trend_option and regression_penalty * unit test for fixed sm input and regression penalty * warning message * more smoothing input tests * more smoothing input tests * change level_sm_input lower bound to 0.001 from 0 * raise error message for level_sm_input lower than 0.0001 * Docstring inheritance (#351) * add docstring inheritance * add example jupyter notebook * add requirements * minor changes * minor formatting * add lower bound for common substring * Update stan_estimator.py * Update docstring_inheritance_check.ipynb * Update backtest.py Co-authored-by: Edwin Ng <edwinng@uber.com> * iclaims data de-meaning (#352) * pumping version to 1.0.11 pumping version to 1.0.11 * bug fix for following sphinx in README.rst * Update setup.py * pumping version * Update README.rst * Update README.rst * Update README.rst * Update README.rst * readme refine * Provide Inference for MAP and Aggregated Estimator (#359) * Create .readthedocs.yml. * Rename .readthedocs.yml. to .readthedocs.yml * Update .readthedocs.yml * Dev tutorials update (#362) * tutorials update for master branch * Update conf.py * Update __init__.py * tutorial update * notebook update * Update lgt.ipynb * update * notebook * Update pyro_basic.ipynb * temp * Provide Inference for MAP and Aggregated Estimator (#359) * Update pyro_basic.ipynb * update of notebooks * tutorial update and proof-reading * cell number update * notebook minor update * relabel notebook under exampels/ * file ext * new tab and more updates * readme tone change & link fix * typo fix * minor fix Co-authored-by: Zhishi Wang <zhishiw@uber.com> * Update .readthedocs.yml * Update .readthedocs.yml * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb Co-authored-by: CrossNox <ijmermet@gmail.com> Co-authored-by: Steve Yang <steven.s.yang@gmail.com> Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> Co-authored-by: Yifeng Wu <yifeng.wu@uber.com> Co-authored-by: ppstacy <ppstacy@gmail.com> Co-authored-by: Zhishi Wang <zhishiw@uber.com>

* remove enum34 dependency (#301) * add test_lgt_full_reproducibility (#303) * Integrating LGT/DLT into ETS Base (#280) * first draft of ets * ets temp * refresh banner and icon * read me link * more banners * testing new dim of banner * Predict fix (#281) * fix regressor matrix extraction * unit test for cases with mixed pos&reg regressors * adding logo and some style for tutorial and docs * favicon * refactoring DLT onto ets * refine DLT and pass all unit tests * passed all unit tests * unit test fix * fixed unit test * add test_ets.py * Additional refinement on ETS Refactoring (#296) * fixed some OO duplicated methods -[x] remove duplicated modules as suggested -[x] remove `_get_regresso_matrix()` as suggested * docstring update * removing fit method in lgt * add negative regressor test cases * add negative regressor test * Update test_lgt.py * updated the test data and tests logic * fixed numerical issues due to initialization * minor * bug fix * Update conftest.py * Create iclaims.example.csv * temp * Create orbit-adhoc-test[TEST].ipynb * fixed regression issue * Delete orbit-adhoc-test[TEST].ipynb * removing negative test for lgt * add test_lgt_full_reproducibility (#303) * introducing * small fix on refactoring ets - refine/remove comments - remove unused methods Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> Co-authored-by: Yifeng Wu <yifeng.wu@uber.com> Co-authored-by: Steve Yang <steven.s.yang@gmail.com> * Create RELEASE.md (#307) * utility for hyper-parameter tuning (#324) * utility for hyper-parameter tuning * minor * demo for hyper tuning * Organize Plotting functions and enhancement (#327) * Tutorial Update - diagnostics/backtest plotting (#332) * add ploting tutorials * back test tutorial * back test tutorial * fix commets * suppress warnings * quick fix * badge update * Update tutorials notebooks (#329) * Update tutorials notebooks * add the notebook and dataset for regression * push the new icalim dataset * update the regression notebook and modify the data load function * update for regression tutorials * regression notebook * Update regression.ipynb * notebooks update * refine verbiage; regression change * minor cosmetics * remove log transform since it's done in new iclaims data * remove log transform since it's done in the new iclaims data * filter first then standardize * filter first then standardize Co-authored-by: Edwin Ng <edwinng@uber.com> Co-authored-by: Zhishi Wang <zhishiw@uber.com> Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> * fix data url in load_iclaims() (#337) * fix data url in load_iclaims() * update the tutorials catalogue to reflect the changes; fix typos * Minor updates in tutorial notebooks (#339) * fix tutorials notebook * update title level in regression notebook * Feat pickle fix (#342) * first pickle fix attempt * better attempt by using initializer creating an initializer class to tackle problem of #340 fixed #40 * ETS Initializer add ets initializer and change some wording from stan to generic * change wording from stan to generic [minor] minor wording * Add deprecating warnings for LGT model with regressor (#341) * add deprecation warning for LGT regression * remove wrong notebook * remove wrong notebook * minor cosmetic change (#343) * Dev unit test (#348) * validation for global_trend_option and regression_penalty * unit test for fixed sm input and regression penalty * unit test for fixed sm input * validation for global_trend_option and regression_penalty * unit test for fixed sm input and regression penalty * warning message * more smoothing input tests * more smoothing input tests * change level_sm_input lower bound to 0.001 from 0 * raise error message for level_sm_input lower than 0.0001 * Docstring inheritance (#351) * add docstring inheritance * add example jupyter notebook * add requirements * minor changes * minor formatting * add lower bound for common substring * Update stan_estimator.py * Update docstring_inheritance_check.ipynb * Update backtest.py Co-authored-by: Edwin Ng <edwinng@uber.com> * iclaims data de-meaning (#352) * pumping version to 1.0.11 pumping version to 1.0.11 * bug fix for following sphinx in README.rst * Update setup.py * pumping version * Update README.rst * Update README.rst * Update README.rst * Update README.rst * readme refine * Provide Inference for MAP and Aggregated Estimator (#359) * Create .readthedocs.yml. * Rename .readthedocs.yml. to .readthedocs.yml * Update .readthedocs.yml * Dev tutorials update (#362) * tutorials update for master branch * Update conf.py * Update __init__.py * tutorial update * notebook update * Update lgt.ipynb * update * notebook * Update pyro_basic.ipynb * temp * Provide Inference for MAP and Aggregated Estimator (#359) * Update pyro_basic.ipynb * update of notebooks * tutorial update and proof-reading * cell number update * notebook minor update * relabel notebook under exampels/ * file ext * new tab and more updates * readme tone change & link fix * typo fix * minor fix Co-authored-by: Zhishi Wang <zhishiw@uber.com> * Update .readthedocs.yml * Update .readthedocs.yml * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update regression.ipynb * Update README.md Co-authored-by: CrossNox <ijmermet@gmail.com> Co-authored-by: Steve Yang <steven.s.yang@gmail.com> Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> Co-authored-by: Yifeng Wu <yifeng.wu@uber.com> Co-authored-by: ppstacy <ppstacy@gmail.com> Co-authored-by: Zhishi Wang <zhishiw@uber.com>

* first draft of ets * ets temp * refresh banner and icon * read me link * more banners * testing new dim of banner * Predict fix (#281) * fix regressor matrix extraction * unit test for cases with mixed pos&reg regressors * adding logo and some style for tutorial and docs * favicon * refactoring DLT onto ets * refine DLT and pass all unit tests * passed all unit tests * unit test fix * fixed unit test * add test_ets.py * Additional refinement on ETS Refactoring (#296) * fixed some OO duplicated methods -[x] remove duplicated modules as suggested -[x] remove `_get_regresso_matrix()` as suggested * docstring update * removing fit method in lgt * add negative regressor test cases * add negative regressor test * Update test_lgt.py * updated the test data and tests logic * fixed numerical issues due to initialization * minor * bug fix * Update conftest.py * Create iclaims.example.csv * temp * Create orbit-adhoc-test[TEST].ipynb * fixed regression issue * Delete orbit-adhoc-test[TEST].ipynb * removing negative test for lgt * add test_lgt_full_reproducibility (#303) * introducing * small fix on refactoring ets - refine/remove comments - remove unused methods Co-authored-by: Zhishi Wang <wangzhishi@users.noreply.github.com> Co-authored-by: Yifeng Wu <yifeng.wu@uber.com> Co-authored-by: Steve Yang <steven.s.yang@gmail.com>

first draft of ets

dd2563d

edwinnglabs added refactor Issues to remove tech debt or improve design WIP Someone is aware of this and working in progress labels Nov 9, 2020

edwinnglabs requested a review from steveyang90 November 9, 2020 02:35

edwinnglabs assigned wangzhishi, vincewu51 and edwinnglabs Nov 9, 2020

Edwin Ng and others added 11 commits November 9, 2020 11:12

ets temp

3c1559d

refresh banner and icon

a5a0b2d

read me link

a86b2fe

more banners

502f07f

testing new dim of banner

07fe0df

Predict fix (#281)

b586439

* fix regressor matrix extraction * unit test for cases with mixed pos&reg regressors

adding logo and some style for tutorial and docs

ec6fca7

favicon

d489191

refactoring DLT onto ets

4024e73

refine DLT and pass all unit tests

e536d78

passed all unit tests

9f01cc7

edwinnglabs changed the title ~~first draft of ets~~ Integrating LGT/DLT into ETS Base Nov 10, 2020

Merge branch 'master' into dev-refactor-ets

19aece6

edwinnglabs added the review needed need someone to review label Nov 10, 2020

Edwin Ng added 2 commits November 10, 2020 15:27

unit test fix

05569a7

fixed unit test

ac97014

steveyang90 requested changes Nov 14, 2020

View reviewed changes

vincewu51 added 2 commits November 17, 2020 20:51

add test_ets.py

19a9f49

resolve merge conflict

22c1887

Edwin Ng added 10 commits November 30, 2020 20:46

updated the test data and tests logic

c4db1a1

fixed numerical issues due to initialization

d16905c

minor

661c1fd

bug fix

c272b7d

Update conftest.py

41cee68

Create iclaims.example.csv

4301038

temp

57ce384

Create orbit-adhoc-test[TEST].ipynb

ff641f5

fixed regression issue

d298dc3

Delete orbit-adhoc-test[TEST].ipynb

c929c4c

Edwin Ng and others added 2 commits December 4, 2020 15:31

removing negative test for lgt

6398372

add test_lgt_full_reproducibility (#303)

8664aad

steveyang90 and others added 2 commits December 4, 2020 18:37

Merge branch 'dev-refactor-ets' of https://github.com/uber/orbit into…

78bc049

… dev-refactor-ets

introducing

abd4523

steveyang90 reviewed Dec 5, 2020

View reviewed changes

small fix on refactoring ets

83c7933

- refine/remove comments - remove unused methods

steveyang90 approved these changes Dec 5, 2020

View reviewed changes

edwinnglabs merged commit 0f6ea3e into dev Dec 5, 2020

edwinnglabs deleted the dev-refactor-ets branch December 5, 2020 21:21

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Integrating LGT/DLT into ETS Base #280

Integrating LGT/DLT into ETS Base #280

edwinnglabs commented Nov 9, 2020 •

edited

Loading

edwinnglabs commented Nov 11, 2020

steveyang90 commented Nov 11, 2020

steveyang90 left a comment •

edited

Loading

steveyang90 commented Nov 14, 2020

steveyang90 commented Nov 14, 2020

edwinnglabs commented Dec 4, 2020

steveyang90 commented Dec 4, 2020

steveyang90 left a comment

steveyang90 Dec 5, 2020

steveyang90 Dec 5, 2020

steveyang90 Dec 5, 2020

steveyang90 commented Dec 5, 2020

Integrating LGT/DLT into ETS Base #280

Integrating LGT/DLT into ETS Base #280

Conversation

edwinnglabs commented Nov 9, 2020 • edited Loading

Description

Type of change

How Has This Been Tested?

edwinnglabs commented Nov 11, 2020

steveyang90 commented Nov 11, 2020

steveyang90 left a comment • edited Loading

Choose a reason for hiding this comment

steveyang90 commented Nov 14, 2020

steveyang90 commented Nov 14, 2020

edwinnglabs commented Dec 4, 2020

steveyang90 commented Dec 4, 2020

steveyang90 left a comment

Choose a reason for hiding this comment

steveyang90 Dec 5, 2020

Choose a reason for hiding this comment

steveyang90 Dec 5, 2020

Choose a reason for hiding this comment

steveyang90 Dec 5, 2020

Choose a reason for hiding this comment

steveyang90 commented Dec 5, 2020

edwinnglabs commented Nov 9, 2020 •

edited

Loading

steveyang90 left a comment •

edited

Loading