Skip to content

Commit db95db3

Browse files
akondasakondas
committed
Implement Keep a changelog format
1 parent e5189df commit db95db3

File tree

1 file changed

+114
-103
lines changed

1 file changed

+114
-103
lines changed

‎CHANGELOG.md‎

Lines changed: 114 additions & 103 deletions
Original file line numberDiff line numberDiff line change
@@ -1,116 +1,127 @@
1-
CHANGELOG
2-
=========
1+
# Changelog
2+
All notable changes to this project will be documented in this file.
33

4-
This changelog references the relevant changes done in PHP-ML library.
4+
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
5+
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
56

6-
* Unreleased
7-
* feature [Dataset] changed the default kernel type in SVC to Kernel::RBF (#267)
8-
* feature [Clustering] added KMeans associative clustering (#262)
9-
* feature [Dataset] added removeColumns function to ArrayDataset (#249)
10-
* feature [Dataset] added a SvmDataset class for SVM-Light (or LibSVM) format files (#237)
11-
* feature [Optimizer] removed $initialTheta property and renamed setInitialTheta method to setTheta (#252)
12-
* change [Imputer] Throw exception when trying to transform without train data (#314)
13-
* enhancement Add performance test for LeastSquares (#263)
14-
* enhancement Micro optimization for matrix multiplication (#255)
15-
* enhancement Throw proper exception (#259, #251)
16-
* fix ensure DataTransformer::testSet samples array is not empty (#204)
17-
* fix optimizer initial theta randomization (#239)
18-
* fix travis build on osx (#281)
19-
* fix SVM locale (non-locale aware) (#288)
20-
* typo, tests, code styles and documentation fixes (#265, #261, #254, #253, #251, #250, #248, #245, #243)
21-
* change [MLPClassifier] return labels in output (#315)
22-
* enhancement Update phpstan to 0.10.5 (#320)
7+
## [0.7.0] - 2018-11-07
8+
### Added
9+
- [Clustering] added KMeans associative clustering (#262)
10+
- [Dataset] added removeColumns function to ArrayDataset (#249)
11+
- [Dataset] added a SvmDataset class for SVM-Light (or LibSVM) format files (#237)
12+
- [Dataset] added Mnist Dataset for MNIST file format (#326)
13+
- [Internal] Add performance test for LeastSquares (#263)
2314

24-
* 0.6.2 (2018-02-22)
25-
* Fix Apriori array keys (#238)
15+
### Changed
16+
- [Internal] implement Keep a Changelog format
17+
- [Classification] changed the default kernel type in SVC to Kernel::RBF (#267)
18+
- [Optimizer] removed $initialTheta property and renamed setInitialTheta method to setTheta (#252)
19+
- [Imputer] Throw exception when trying to transform without train data (#314)
20+
- [Math] Micro optimization for matrix multiplication (#255)
21+
- [Internal] Throw proper exception (#259, #251)
22+
- [MLPClassifier] return labels in output (#315)
23+
- [Internal] Update phpstan to 0.10.5 (#320)
2624

27-
* 0.6.1 (2018-02-18)
28-
* Fix KMeans and EigenvalueDecomposition (#235)
25+
### Fixed
26+
- [SVM] ensure DataTransformer::testSet samples array is not empty (#204)
27+
- [Optimizer] optimizer initial theta randomization (#239)
28+
- [Internal] travis build on osx (#281)
29+
- [SVM] SVM locale (non-locale aware) (#288)
30+
- [Internal] typo, tests, code styles and documentation fixes (#265, #261, #254, #253, #251, #250, #248, #245, #243, #317, #328)
31+
- [Classification] Check if feature exist when predict target in NaiveBayes (#327)
2932

30-
* 0.6.0 (2018-02-16)
31-
* feature [FeatureSelection] implement SelectKBest with scoring functions (#232)
32-
* feature [FeatureSelection] implement VarianceThreshold - simple baseline approach to feature selection. (#228)
33-
* feature [Classification] support probability estimation in SVC (#218)
34-
* feature [NeuralNetwork] configure an Activation Function per hidden layer (#208)
35-
* feature [NeuralNetwork] Ability to update learningRate in MLP (#160)
36-
* feature [Metric] Choose averaging method in classification report (#205)
37-
* enhancement Add phpstan strict rules (#233)
38-
* enhancement Flatten directory structure (#220)
39-
* enhancement Update phpunit/phpunit (#219)
40-
* enhancement Cache dependencies installed with composer on Travis (#215)
41-
* enhancement Add support for coveralls.io (#153)
42-
* enhancement Add phpstan and easy coding standards (#156, #168)
43-
* enhancement Throw exception when libsvm command fails to run (#200, #202)
44-
* enhancement Normalize composer.json and sort packages (#214, #210)
45-
* enhancement Rewrite DBSCAN (#185)
46-
* fix phpunit include tests path (#230)
47-
* fix support of a rule in Apriori (#229)
48-
* fix apriori generates an empty array as a part of the frequent item sets (#224)
49-
* fix backpropagation random error (#157)
50-
* fix logistic regression implementation (#169)
51-
* fix activation functions support (#163)
52-
* fix string representation of integer labels issue in NaiveBayes (#206)
53-
* fix the implementation of conjugate gradient method (#184)
54-
* typo, tests and documentation fixes (#234, #221, #181, #183, #155, #159, #165, #187, #154, #191, #203, #209, #213, #212, #211)
33+
## [0.6.2] - 2018-02-22
34+
### Fixed
35+
- Fix Apriori array keys (#238)
5536

56-
* 0.5.0 (2017-11-14)
57-
* general [php] Upgrade to PHP 7.1 (#150)
58-
* general [coding standard] fix imports order and drop unused docs typehints
59-
* feature [NeuralNetwork] Add PReLU activation function (#128)
60-
* feature [NeuralNetwork] Add ThresholdedReLU activation function (#129)
61-
* feature [Dataset] Support CSV with long lines (#119)
62-
* feature [NeuralNetwork] Neural networks partial training and persistency (#91)
63-
* feature Add french stopwords (#92)
64-
* feature New methods: setBinPath, setVarPath in SupportVectorMachine (#73)
65-
* feature Linear Discrimant Analysis (LDA) (#82)
66-
* feature Linear algebra operations, Dimensionality reduction and some other minor changes (#81)
67-
* feature Partial training base (#78)
68-
* feature Add delimiter option for CsvDataset (#66)
69-
* feature LogisticRegression classifier & Optimization methods (#63)
70-
* feature Additional training for SVR (#59)
71-
* optimization Comparison - replace eval (#130)
72-
* optimization Use C-style casts (#124)
73-
* optimization Speed up DataTransformer (#122)
74-
* bug DBSCAN fix for associative keys and array_merge performance optimization (#139)
75-
* bug Ensure user-provided SupportVectorMachine paths are valid (#126)
76-
* bug [DecisionTree] Fix string cast #120 (#121)
77-
* bug fix invalid typehint for subs method (#110)
78-
* bug Fix samples transformation in Pipeline training (#94)
79-
* bug Fix division by 0 error during normalization (#83)
80-
* bug Fix wrong docs references (#79)
37+
## [0.6.1] - 2018-02-18
38+
### Fixed
39+
- Fix KMeans and EigenvalueDecomposition (#235)
8140

82-
* 0.4.0 (2017-02-23)
83-
* feature [Classification] - Ensemble Classifiers : Bagging and RandomForest by Mustafa Karabulut
84-
* feature [Classification] - RandomForest::getFeatureImportances() method by Mustafa Karabulut
85-
* feature [Classification] - Linear classifiers: Perceptron, Adaline, DecisionStump by Mustafa Karabulut
86-
* feature [Classification] - AdaBoost algorithm by Mustafa Karabulut
87-
* bug [Math] - Check if matrix is singular doing inverse by Povilas Susinskas
88-
* optimization - Euclidean optimization by Mustafa Karabulut
41+
## [0.6.0] - 2018-02-16
42+
- feature [FeatureSelection] implement SelectKBest with scoring functions (#232)
43+
- feature [FeatureSelection] implement VarianceThreshold - simple baseline approach to feature selection. (#228)
44+
- feature [Classification] support probability estimation in SVC (#218)
45+
- feature [NeuralNetwork] configure an Activation Function per hidden layer (#208)
46+
- feature [NeuralNetwork] Ability to update learningRate in MLP (#160)
47+
- feature [Metric] Choose averaging method in classification report (#205)
48+
- enhancement Add phpstan strict rules (#233)
49+
- enhancement Flatten directory structure (#220)
50+
- enhancement Update phpunit/phpunit (#219)
51+
- enhancement Cache dependencies installed with composer on Travis (#215)
52+
- enhancement Add support for coveralls.io (#153)
53+
- enhancement Add phpstan and easy coding standards (#156, #168)
54+
- enhancement Throw exception when libsvm command fails to run (#200, #202)
55+
- enhancement Normalize composer.json and sort packages (#214, #210)
56+
- enhancement Rewrite DBSCAN (#185)
57+
- fix phpunit include tests path (#230)
58+
- fix support of a rule in Apriori (#229)
59+
- fix apriori generates an empty array as a part of the frequent item sets (#224)
60+
- fix backpropagation random error (#157)
61+
- fix logistic regression implementation (#169)
62+
- fix activation functions support (#163)
63+
- fix string representation of integer labels issue in NaiveBayes (#206)
64+
- fix the implementation of conjugate gradient method (#184)
65+
- typo, tests and documentation fixes (#234, #221, #181, #183, #155, #159, #165, #187, #154, #191, #203, #209, #213, #212, #211)
8966

90-
* 0.3.0 (2017-02-04)
91-
* feature [Persistency] - ModelManager - save and restore trained models by David Monllaó
92-
* feature [Classification] - DecisionTree implementation by Mustafa Karabulut
93-
* feature [Clustering] - Fuzzy C Means implementation by Mustafa Karabulut
94-
* other small fixes and code styles refactors
67+
## [0.5.0] - 2017-11-14
68+
- general [php] Upgrade to PHP 7.1 (#150)
69+
- general [coding standard] fix imports order and drop unused docs typehints
70+
- feature [NeuralNetwork] Add PReLU activation function (#128)
71+
- feature [NeuralNetwork] Add ThresholdedReLU activation function (#129)
72+
- feature [Dataset] Support CSV with long lines (#119)
73+
- feature [NeuralNetwork] Neural networks partial training and persistency (#91)
74+
- feature Add french stopwords (#92)
75+
- feature New methods: setBinPath, setVarPath in SupportVectorMachine (#73)
76+
- feature Linear Discrimant Analysis (LDA) (#82)
77+
- feature Linear algebra operations, Dimensionality reduction and some other minor changes (#81)
78+
- feature Partial training base (#78)
79+
- feature Add delimiter option for CsvDataset (#66)
80+
- feature LogisticRegression classifier & Optimization methods (#63)
81+
- feature Additional training for SVR (#59)
82+
- optimization Comparison - replace eval (#130)
83+
- optimization Use C-style casts (#124)
84+
- optimization Speed up DataTransformer (#122)
85+
- bug DBSCAN fix for associative keys and array_merge performance optimization (#139)
86+
- bug Ensure user-provided SupportVectorMachine paths are valid (#126)
87+
- bug [DecisionTree] Fix string cast #120 (#121)
88+
- bug fix invalid typehint for subs method (#110)
89+
- bug Fix samples transformation in Pipeline training (#94)
90+
- bug Fix division by 0 error during normalization (#83)
91+
- bug Fix wrong docs references (#79)
9592

96-
* 0.2.1 (2016-11-20)
97-
* feature [Association] - Apriori algorithm implementation
98-
* bug [Metric] - division by zero
93+
## [0.4.0] - 2017-02-23
94+
- feature [Classification] - Ensemble Classifiers : Bagging and RandomForest by Mustafa Karabulut
95+
- feature [Classification] - RandomForest::getFeatureImportances() method by Mustafa Karabulut
96+
- feature [Classification] - Linear classifiers: Perceptron, Adaline, DecisionStump by Mustafa Karabulut
97+
- feature [Classification] - AdaBoost algorithm by Mustafa Karabulut
98+
- bug [Math] - Check if matrix is singular doing inverse by Povilas Susinskas
99+
- optimization - Euclidean optimization by Mustafa Karabulut
99100

100-
* 0.2.0 (2016-08-14)
101-
* feature [NeuralNetwork] - MultilayerPerceptron and Backpropagation training
101+
## [0.3.0] - 2017-02-04
102+
- feature [Persistency] - ModelManager - save and restore trained models by David Monllaó
103+
- feature [Classification] - DecisionTree implementation by Mustafa Karabulut
104+
- feature [Clustering] - Fuzzy C Means implementation by Mustafa Karabulut
105+
- other small fixes and code styles refactors
102106

103-
* 0.1.2 (2016-07-24)
104-
* feature [Dataset] - FilesDataset - load dataset from files (folder names as targets)
105-
* feature [Metric] - ClassificationReport - report about trained classifier
106-
* bug [Feature Extraction] - fix problem with token count vectorizer array order
107-
* tests [General] - add more tests for specific conditions
107+
## [0.2.1] - 2016-11-20
108+
- feature [Association] - Apriori algorithm implementation
109+
- bug [Metric] - division by zero
108110

109-
* 0.1.1 (2016-07-12)
110-
* feature [Cross Validation] Stratified Random Split - equal distribution for targets in split
111-
* feature [General] Documentation - add missing pages (Pipeline, ConfusionMatrix and TfIdfTransformer) and fix links
111+
## [0.2.0] - 2016-08-14
112+
- feature [NeuralNetwork] - MultilayerPerceptron and Backpropagation training
112113

113-
* 0.1.0 (2016-07-08)
114-
* first develop release
115-
* base tools for Machine Learning: Algorithms, Cross Validation, Preprocessing, Feature Extraction
116-
* bug [General] #7 - PHP-ML doesn't work on Mac
114+
## [0.1.2] - 2016-07-24
115+
- feature [Dataset] - FilesDataset - load dataset from files (folder names as targets)
116+
- feature [Metric] - ClassificationReport - report about trained classifier
117+
- bug [Feature Extraction] - fix problem with token count vectorizer array order
118+
- tests [General] - add more tests for specific conditions
119+
120+
## [0.1.1] - 2016-07-12
121+
- feature [Cross Validation] Stratified Random Split - equal distribution for targets in split
122+
- feature [General] Documentation - add missing pages (Pipeline, ConfusionMatrix and TfIdfTransformer) and fix links
123+
124+
## [0.1.0] - 2016-07-08
125+
- first develop release
126+
- base tools for Machine Learning: Algorithms, Cross Validation, Preprocessing, Feature Extraction
127+
- bug [General] #7 - PHP-ML doesn't work on Mac

0 commit comments

Comments
 (0)