GitLab

[python] fixed picklability of sklearn models with custom obj and updated docstings for custom obj (#2191)

* refactored joblib test

* fixed picklability of sklearn models with custom obj and updated docstings for custom obj

* pickled model should be able to predict without refitting

* disable default pandas cat features if cat features were explicitly provided

* added assertion for cat features

* ignore pandas ordered categorical columns by default

* fix tests

* fix tests

* added comments

* Update doc string for pred_contrib

See comments at the end of #1969

* Update basic.py

* Update basic.py

* update doc strings

* update equals sign in doc string

* strip whitespace and gen rst

* strip whitespace

* disabled split value histogram for categorical features

* updated test for cat. feature

* updated docs

* added get_split_value_histogram method

* added param for ordinary return value

* Initial attempt to implement appending features in-memory to another data set

The intent is for this to enable munging files together easily, without needing to round-trip via numpy or write multiple copies to disk.
In turn, that enables working more efficiently with data sets that were written separately.

* Implement Dataset.dump_text, and fix small bug in appending of group bin boundaries.

Dumping to text enables us to compare results, without having to worry about issues like features being reordered.

* Add basic tests for validation logic for add_features_from.

* Remove various internal mapping items from dataset text dumps

These are too sensitive to the exact feature order chosen, which is not visible to the user.
Including them in tests appears unnecessary, as the data dumping code should provide enough coverage.

* Add test that add_features_from results in identical data sets according to dump_text.

* Add test that booster behaviour after using add_features_from matches that of training on the full data

This checks:
- That training after add_features_from works at all
- That add_features_from does not cause training to misbehave

* Expose feature_penalty and monotone_types/constraints via get_field

These getters allow us to check that add_features_from does the right thing with these vectors.

* Add tests that add_features correctly handles feature_penalty and monotone_constraints.

* Ensure add_features_from properly frees the added dataset and add unit test for this

Since add_features_from moves the feature group pointers from the added dataset to the dataset being added to, the added dataset is invalid after the call.
We must ensure we do not try and access this handle.

* Remove some obsolete TODOs

* Tidy up DumpTextFile by using a single iterator for each feature

This iterators were also passed around as raw pointers without being freed, which is now fixed.

* Factor out offsetting logic in AddFeaturesFrom

* Remove obsolete TODO

* Remove another TODO

This one is debatable, test code can be a bit messy and duplicate-heavy, factoring it out tends to end badly.
Leaving this for now, will revisit if adding more tests later on becomes a mess.

* Add documentation for newly-added methods.

* Fix whitespace issues identified by pylint.

* Fix a few more whitespace issues.

* Fix doc comments

* Implement deep copying for feature groups.

* Replace awkward std::move usage by emplace_back, and reduce vector size to num_features rather than num_total_features.

* Copy feature groups in addFeaturesFrom, rather than moving them.

* Fix bugs in FeatureGroup copy constructor and ensure source dataset remains usable

* Add reserve to PushVector and PushOffset

* Move definition of Clone into class body

* Fix PR review issues

* Fix for loop increment style.

* Fix test failure

* Some more docstring fixes.

* Remove blank line

* convert datatable to numpy directly

* fix according to comments

* updated more docstrings

* simplified isinstance check

* Update compat.py

* add warnings for override parameters of Dataset

* fix pep8

* add feature_penalty

* refactor

* add R's code

* Update basic.py

* Update basic.py

* fix parameter bug

* Update lgb.Dataset.R

* fix a bug

* added get_data method

* hotfix

* added warning for other data types

* reworked according to review comments

* minor addition to FAQ

* added test

* add pandas_categorical to returned json

* save pandas_categorical to model file

* added regression test

* removed excess conversion to list

* removed deprecated line

* hotfix

* added docstring style test and fixed errors in existing docstrings

* hotfix

* hotfix

* fix grammar

* hotfix

* Fixed some typos in Python API Docs

* FixTypo changed validation set -> sets

* copy old Booster's attributes to new one in refit method

* fixed according to review comment

* raise error in case of null objective

* fix indices type in csr and csc

* fix

* add indexs in shuffle model.

* fix pep

* fix bug

* break extremely large lines in basic.py

* break extremely large lines in callback.py

* break extremely large lines in engine.py

* break extremely large lines in sklearn.py

* hotfixes

* warning on categorical feature with sparse values

* [docs] categorical features note

* pass params to predictor

* hotfix

* added test for pandas label of Dataset

* fix when label type is pandas DataFrame; document possible pandas Series type

* fix ndcg group

* fix ndcg

* pass params to _InnerPredictor in train and cv

* fixed verbosity param description

* treat silent param as Fatal log level

* create Dataset in refit method silently

* do not overwrite verbose param by silent argument

* added possibility to predict numpy array with nrow > max_int32

* save memory more efficient

* better variable name

* added possibility to predict scipy.sparse.csr matrix with nrow > max_int32

* added possibility to predict scipy.sparse.csc matrix with nrow > max_int32

* reworked numpy array case

* added NumberOfTotalModel and NumModelPerIteration to C_API and python-package

* fixed tests

* added tests for current_iteration, num_trees, num_model_per_iteration methods

* break huge line in test

* hotfix

* add support of refit-decay

* add refit into c_api

* add test

* update document

* Update basic.py

* Update test_engine.py

* Update basic.py

* Update test_engine.py

* fix comments

* update test

* fix the comments

* Update test_engine.py

* add start_iteration in model saving

* fix test

* shuffle models ability

* fix bug

* update document

* refine

* Update engine.py

* Update basic.py

* fix comments

* fix comment

* refined num_iteration argument in python

* hotfix

* broadcast info about negative values in categorical features to python package

* update link to categorical_feature parameter