Commit Graph

Select branches

Hide Pull Requests

Adding-GitHub-actions-workflow

UpdateDocAndVersion

Weight0samplesError

add_kernels

add_multiclass

add_subspaces

codeql-analysis

combinatorial_explosion

complete-source-comments

context-scaling#31

enhance-partition

entropy_function

graphviz

gridsearch

master

mypy-static-type

new_predict_proba

ovo-#36

package_doc_#7

predict_proba

selectKBest-#17

#10

#16

#19

#20

#22

#23

#25

#28

#29

#30

#32

#33

#34

#35

#37

#40

#42

#44

#47

#48

#49

#5

#52

#53

#55

#56

#58

#9

0.9.rc3

0.9rc1

0.9rc2

0.9rc4

0.9rc5

0.9rc6

1.0

1.0rc1

1.1

1.2

v1.2.1

v1.2.2

v1.2.3

v1.2.4

v1.3.0

v1.3.1

v1.3.2

v1.4.0

Mono Color

• 82f7352f9a Fix python version & os Ricardo Montañana 2021-01-11 12:00:32 +01:00
• 8359e442e5 lock scikit-learn version to 0.23.2 fix github actions workflow Ricardo Montañana 2021-01-10 20:05:36 +01:00
• 673081cdc5 Add main workflow action Ricardo Montañana Gómez 2021-01-10 14:24:16 +01:00
• 36816074ff Combinatorial explosion (#19) Ricardo Montañana Gómez 2021-01-10 13:32:22 +01:00
• 6896f76ca9 Generates 5 random subspaces at most combinatorial_explosion Ricardo Montañana 2020-12-11 11:32:54 +01:00
• 3f01234ebf Remove itertools combinations from subspaces Ricardo Montañana 2020-12-10 14:14:42 +01:00
• 475ad7e752 Fix mistakes in function comments Ricardo Montañana 2020-11-11 19:14:36 +01:00
• 1c869e154e Enhance partition (#16) 0.9rc6 Ricardo Montañana Gómez 2020-11-03 11:36:05 +01:00
• ddc0fe15b8 Fix mistake in computing multiclass node belief Set default criterion for split to entropy instead of gini Set default max_iter to 1e5 instead of 1e3 change up-down criterion to match SVC multiclass Fix impurity method of splitting nodes Update jupyter Notebooks enhance-partition Ricardo Montañana 2020-11-01 17:37:17 +01:00
• c593b55bec Complete implementation of splitter_type = impurity with tests Remove max_distance & min_distance splitter types Ricardo Montañana 2020-10-17 16:56:15 +02:00
• 044918f834 #15 First approach Create impurity function in Stree (consistent name, same criteria as other splitter parameter) Create test for the new function Update init test Update test splitter parameters Rename old impurity function to partition_impurity Ricardo Montañana 2020-10-15 17:51:20 +02:00
• d1e30a3372 Refactor predict and score and make mypy --strict mypy-static-type Ricardo Montañana 2020-07-01 18:37:10 +02:00
• f5706c3159 Update version and notebooks 0.9rc5 Ricardo Montañana 2020-06-28 10:44:29 +02:00
• fa001f97a4 First Approach Ricardo Montañana 2020-06-28 02:46:20 +02:00
• be552fdd6c Add test for getting 3 feature_sets in Splitter Add ensemble notebook Ricardo Montañana 2020-06-28 02:45:08 +02:00
• 5e3a8e3ec5 Change adaboost notebook Ricardo Montañana 2020-06-27 23:34:15 +02:00
• 554ec03c32 Get only 3 sets for best split Fix flaky test in Splitter_test Ricardo Montañana 2020-06-27 18:29:40 +02:00
• 4b7e4a3fb0 better solution to the sklearn bagging problem Add better tests enhance .coveragerc Ricardo Montañana 2020-06-26 11:22:45 +02:00
• 76723993fd Solve Warning class label not found when bagging Ricardo Montañana 2020-06-25 13:07:50 +02:00
• ecd0b86f4d Solve the mistake of min and max distance The split criteria functions min and max distance return classes while max_samples return distances positives and negatives to hyperplane of the class with more samples in node Ricardo Montañana 2020-06-17 00:13:52 +02:00
• 3e52a4746c Fix entroy and information_gain functions Ricardo Montañana 2020-06-16 13:56:02 +02:00
• a20e45e8e7 Merge pull request #10 from Doctorado-ML/add_subspaces Ricardo Montañana Gómez 2020-06-15 11:30:53 +02:00
• 9334951d1b #2 Cosmetic and style updates add_subspaces Ricardo Montañana 2020-06-15 11:09:11 +02:00
• 736ab7ef20 #2 update benchmark notebook Ricardo Montañana 2020-06-15 10:33:51 +02:00
• c94bc068bd #2 Refactor Stree & create Splitter Add and test splitter parameter Ricardo Montañana 2020-06-15 00:22:57 +02:00
• 502ee72799 #2 Add predict and score support Add a test in features notebook Show max_features in main.py Ricardo Montañana 2020-06-14 14:00:21 +02:00
• f1ee4de37b #2 - Add gini and entropy measures rename get_dataset to load_dataset add features and impurity to __str__ of node Ricardo Montañana 2020-06-14 03:08:55 +02:00
• ae1c199e21 # 2 - add max_features parameters Ricardo Montañana 2020-06-13 17:58:45 +02:00
• 1bfe273a70 Fix problem in _min_distance Remove grapher (moved to another repo) Ricardo Montañana 2020-06-12 00:50:25 +02:00
• 647d21bdb5 Merge pull request #9 from Doctorado-ML/add_multiclass Ricardo Montañana Gómez 2020-06-11 16:30:16 +02:00
• 1d392d534f #6 - Update tests and codecov conf add_multiclass Ricardo Montañana 2020-06-11 13:45:24 +02:00
• f360a2640c #6 - Add multiclass support Removed (by now) predict_proba. Created a notebook in jupyter Added split_criteria parameter with min_distance and max_samples values Refactor _distances Refactor _split_criteria Refactor _reorder_results Ricardo Montañana 2020-06-11 13:10:52 +02:00
• 45510b43bc Merge pull request #5 from Doctorado-ML/add_kernels Ricardo Montañana Gómez 2020-06-09 13:43:31 +02:00
• 286a91a3d7 #3 refactor unneeded code and new test add_kernels Ricardo Montañana 2020-06-09 13:01:01 +02:00
• 5c31c2b2a5 #3 update features notebook Ricardo Montañana 2020-06-09 02:12:56 +02:00
• 7e932de072 #3 Add sample_weights to score, update notebooks Update readme to use new names of notebooks Ricardo Montañana 2020-06-09 01:46:38 +02:00
• 26273e936a #3 Add degree hyperparam and update notebooks Update readme to add new notebooks Ricardo Montañana 2020-06-08 20:16:42 +02:00
• d7c0bc3bc5 #3 Complete multiclass in Stree Add multiclass dimensions management in distances method Add gamma hyperparameter for non linear kernels Ricardo Montañana 2020-06-08 13:54:24 +02:00
• 3a48d8b405 #3 Rewrite some tests & remove use_predictions Remove use_predictions parameter as of now, the model always use it Ricardo Montañana 2020-06-08 01:51:21 +02:00
• 05b462716e #3 First try, change LinearSVC to SVC make a builder start changing tests Ricardo Montañana 2020-06-07 20:26:59 +02:00
• b824229121 #1 Add min_samples_split Fix #1 Ricardo Montañana 2020-06-07 16:12:25 +02:00
• 8ba9b1b6a1 Remove travis ci and set codecov percentage Ricardo Montañana 2020-06-06 19:47:00 +02:00
• 37577849db Fix parameter missing in method overload Ricardo Montañana 2020-06-06 18:18:03 +02:00
• cb10aea36e remove unneed test and cosmetic Ricardo Montañana 2020-06-06 14:20:07 +02:00
• b9f14aec05 #4 Add code coverage & codacy badge Add code coverage configuration in codecov Add some tests Ricardo Montañana 2020-06-06 03:04:18 +02:00
• b4816b2995 Show sample_weight use in test2 notebook Update revision to RC4 Lint Stree grapher 0.9rc4 Ricardo Montañana 2020-05-30 23:59:40 +02:00
• 5e5fea9c6a Document & lint code Ricardo Montañana 2020-05-30 23:10:10 +02:00
• 724a4855fb Adapt some notebooks gridsearch Ricardo Montañana 2020-05-30 11:09:59 +02:00
• a22ae81b54 Refactor split_data adding sample_weight Ricardo Montañana 2020-05-29 18:52:23 +02:00
• ed98054f0d First approach Added max_depth, tol, weighted samples Ricardo Montañana 2020-05-29 12:46:10 +02:00
• e95bd9697a Make Stree a sklearn estimator Added check_estimator in notebook test2 Added a Stree test with check_estimator 0.9.rc3 Ricardo Montañana 2020-05-25 19:51:39 +02:00
• 5956cd0cd2 Update google colab setup in notebooks Undate save_all in grapher to make dest. folder if it doesn't exist 0.9rc2 Ricardo Montañana 2020-05-24 20:13:27 +02:00
• 27b278860d Fix install from scratch 0.9rc1 Ricardo Montañana 2020-05-24 18:47:55 +02:00
• d5d723c67f update setup.py to include tests suite Ricardo Montañana 2020-05-23 23:59:03 +02:00
• 77f10281c1 Make project python package friendly - Add setup.py - Move classes to module files - Move tests folder inside module folder Ricardo Montañana 2020-05-23 23:40:33 +02:00
• ac1483ae1d update requirements to alllow maptlot widget Ricardo Montañana 2020-05-23 00:05:58 +02:00
• e51690ed95 Implement grapher and notebook to test it Ricardo Montañana 2020-05-22 19:42:13 +02:00
• a4595f5815 Update notebooks and readme with cosmetic changes Ricardo Montañana 2020-05-20 18:11:57 +02:00
• 316f84cc63 Fix precision issues in tests executed in Travis Ricardo Montañana 2020-05-20 15:02:31 +02:00
• 6e35628c85 Grapher working Ricardo Montañana 2020-05-20 14:26:55 +02:00
• c0ef71f139 first approx to grapher Ricardo Montañana 2020-05-20 12:32:17 +02:00
• 6ebd0f9be3 integrate iterator in Stree predict_proba Ricardo Montañana 2020-05-19 18:19:23 +02:00
• 95a6901f47 Cosmetics and Siterator Ricardo Montañana 2020-05-19 16:38:59 +02:00
• 68512b3d75 test results & fix single predict_proba Ricardo Montañana 2020-05-18 17:08:05 +02:00
• 382ae921ab Second try, finished? Ricardo Montañana 2020-05-18 12:55:00 +02:00
• e52cbbb192 First approach to Platt scaling Ricardo Montañana 2020-05-18 11:51:27 +02:00
• 86a9ef2f3a update travis config to notify by mail failures Ricardo Montañana 2020-05-17 19:10:42 +02:00
• 3cd004350d Fix failing tests Ricardo Montañana 2020-05-17 18:55:33 +02:00
• 91af875062 Fix issues in notebooks Ricardo Montañana 2020-05-17 18:36:28 +02:00
• 9f30627e47 Fix main and small issues in notebook test Ricardo Montañana 2020-05-17 18:06:03 +02:00
• d997bc3460 Add model comparison to notebook test Ricardo Montañana 2020-05-17 16:17:57 +02:00
• ad51d0b36b Update readme, add travis config Ricardo Montañana 2020-05-17 00:13:29 +02:00
• ebae3cb316 updt jupyter notebook to fix download of dataset Ricardo Montañana 2020-05-16 22:21:40 +02:00
• 6a8ef288ce add _linear_function to Stree First try to implement predict_proba with sigmoid based on Platt Ricardo Montañana 2020-05-16 20:34:03 +02:00
• 80b5cf8e72 Implement predict & predict_proba optimization Ricardo Montañana 2020-05-15 23:35:33 +02:00
• e56b955b92 Implement predict_proba with test. Fix tree overload with dataset in nodes only needed in tests Ricardo Montañana 2020-05-14 18:42:17 +02:00
• e3ae3a3a6c Add C param in constructor and creditcard dataset Ricardo Montañana 2020-05-14 10:48:39 +02:00
• 8f71eeb316 Implement predict and score methods & tests Ricardo Montañana 2020-05-13 12:42:09 +02:00
• c4de782a3f compute predictor and store model in node Ricardo Montañana 2020-05-13 00:12:05 +02:00
• 371257c121 Implement split data with or without using predictions & some tests Ricardo Montañana 2020-05-12 17:36:16 +02:00
• b9ea24696f Working tree with samples and first test Ricardo Montañana 2020-05-10 14:25:58 +02:00
• 2ca25fd656 Initial commit Ricardo Montañana Gómez 2020-05-09 23:01:30 +02:00