OrgLion-ML/golearn
1
0
Fork 0
mirror of https://github.com/sjwhitworth/golearn.git synced 2025-05-01 22:18:10 +08:00
Code Issues Releases Wiki Activity
468 Commits 10 Branches 0 Tags
Commit Graph

109 Commits

Author SHA1 Message Date
ss8651twtw
b7662dc784 Add test cases for mat 2018-06-16 22:11:59 +08:00
Richard Townsend
2428dfa7de Fix various other little errors 2018-03-24 00:20:45 +00:00
Richard Townsend
ff52c013eb Update gonum to latest version 
Should fix #200 and #205
 2018-03-24 00:19:35 +00:00
Charles N
e9a8d4a005 Fix #169 wrong Mutex Lock 2018-03-14 13:13:17 +00:00
Richard Townsend
57aa61698c base: CREAT => CREATE 2018-01-28 22:55:17 +00:00
Richard Townsend
a3dab5ec13 base: try to correct 'no such file or directory' error 2018-01-28 16:36:21 +00:00
Richard Townsend
e2279995c1 Fixing all tests 2018-01-28 16:22:33 +00:00
Richard Townsend
f722f2e59d trees: implement serialization 2018-01-27 18:00:52 +00:00
Etienne Bruines
7a6fa54353 Made versions of CSV-readers w/ io.ReadSeeker 
Each method now ontains a -FromReader counterpart
such that it'll allow use of those helper-methods
even when someone does not have his data in a physical
file. The original methods make use of those -FromReader
methods.

The reader is being reset (Seek(0, 0)) before every method-
specific read, to ensure it's reading from the start of the
reader.

Test cases are not yet touched, and I'm not sure they should.
 2018-01-27 17:53:44 +00:00
Richard Townsend
e7fee0a2d1 Reformat, fix tests 2017-09-10 21:10:54 +01:00
Richard Townsend
fc110aab48 Fix bad import, reformat 2017-09-10 20:35:34 +01:00
Richard Townsend
44e4c4fbef Naive: serialiation implemented, tests pass 2017-09-10 20:10:53 +01:00
Richard Townsend
e27215052b ensemble: tests pass 2017-09-10 19:30:02 +01:00
Richard Townsend
3e80230d3d meta: passes the tests, seems to be flaky 2017-09-10 18:24:40 +01:00
Richard Townsend
c18d50d217 meta: tests passing 2017-09-10 17:43:17 +01:00
Richard Townsend
768d2cd19f meta: tests are almost passing 2017-09-10 16:59:05 +01:00
Richard Townsend
43f04021af knn: tests now passing 2017-09-09 20:07:56 +01:00
Richard Townsend
72c2005e70 All tests are passing again 2017-09-09 19:58:57 +01:00
Richard Townsend
007af15658 Merging SerializableClassifier with Classifier 2017-09-09 13:38:02 +01:00
Richard Townsend
ead76bdd7e I think I'm going to refocus this whole thing 2017-09-09 12:31:32 +01:00
Richard Townsend
499ac7a493 base: fix unmarshalling attributes, add JSON 2017-08-26 14:56:17 +01:00
Richard Townsend
127a8e9162 base: method to get a SaveableClassifer's metadata 2017-08-26 14:55:12 +01:00
Richard Townsend
e68361c162 Genericize for ensemble use 2017-08-08 12:37:57 +01:00
Richard Townsend
a90ef09781 Remove excessive logging 2017-08-08 12:29:00 +01:00
Richard Townsend
d23619eac2 OK, but with a lot of extra printing 2017-08-07 17:26:11 +01:00
Richard Townsend
3e393cea4c Add a SaveableClassifier interface 2017-08-07 14:50:51 +01:00
Richard Townsend
7b08820152 Adding some new ways of serializing things 2017-08-07 14:43:21 +01:00
Linker Lin
9aa4ee64b5 Update util_attributes.go 
replaced range by []
 2017-02-14 15:08:12 +08:00
Richard Townsend
0f0b4d800b base: fix a failing test case 2016-09-29 11:33:36 +01:00
Richard Townsend
855df3a7fa Merge pull request #135 from Sentimentron/inline-training-data 
Support the use of mat64.Dense as an instance type
 2016-09-29 11:25:16 +01:00
Richard Townsend
7041fc33c7 base: correct handling of class attributes in ParseCSVToTemplatedInstances 2016-07-11 23:16:18 +01:00
Thatcher Peskens
de9a6246fd added String() function to sentimentIron's inline-training-data function 2016-07-06 18:00:30 -07:00
Richard Townsend
de01a2fd10 Merge pull request #138 from anzellai/fix/go-vet-complaints 
Fix go vet complaints
 2016-07-04 13:24:41 +01:00
Philip Gatt
f74483db53 Serialize ARFF to Writer in Addition to a File 2016-06-28 15:52:04 -07:00
Anzel Lai
481da97eca Fix go vet complaints 2016-06-14 00:56:47 +01:00
Richard Townsend
6f7326b6ff neural: check that the new dense instances type works... 2016-05-22 12:58:51 +01:00
Richard Townsend
590d7a8091 base: add a new instances type for mat64 2016-05-22 12:58:50 +01:00
Richard Townsend
986cd230f9 clustering: creates the package and implements DBSCAN 
Verified against scikit-learn's implementation (gen_test.py)
 2015-10-10 20:20:33 +01:00
Stephen Whitworth
092917dee9 Temporarily removing test 2015-01-27 13:24:40 +00:00
Stephen Whitworth
183c672cfe Hopefully, should build now. 2015-01-27 12:32:19 +00:00
Richard Townsend
a250e99644 base: correct some non-deterministic serialisation test behaviour 2015-01-15 22:45:05 +00:00
Stephen Whitworth
353cd38e7c Merge pull request #98 from Sentimentron/dense-staging 
New DenseInstances conversion function
 2014-11-21 13:53:52 +00:00
Stephen Whitworth
7ea42ac80b Merge pull request #101 from Sentimentron/arff-staging 
ARFF import/export, CSV export, lossless serialisation
 2014-11-21 13:53:43 +00:00
Richard Townsend
e30ff6580a ARFF import/export, CSV export, serialisation 
* Only numeric and categorical ARFF attributes are currently supported.
* Only the dense version of the ARFF format is supported.
* Compressed format is .tar.gz file which should allow extensibility.
    * Attributes stored using JSON representations.
* Also offers smarter estimation of the precision of numeric Attributes.
* Also adds support for writing instances to CSV
 2014-11-13 20:09:00 +00:00
Richard Townsend
8fe06e7332 Support for individual class weightings 2014-10-30 23:28:26 +00:00
Richard Townsend
6929052af0 base: conversion to DenseInstances via DenseCopyOf 2014-10-30 22:10:39 +00:00
Richard Townsend
1e888d2a97 base: More general version of equality 2014-10-30 22:02:38 +00:00
Richard Townsend
7ba57fe6df trees: Handling FloatAttributes. 
This patch adds:

	* Gini index and information gain ratio as
           DecisionTree split options;
	* handling for numeric Attributes (split point
           chosen naïvely on the basis of maximum entropy);
	* A couple of additional utility functions in base/
	* A new dataset (see sources.txt) for testing.

Performance on Iris performs markedly without discretisation.
 2014-10-26 17:40:38 +00:00
Richard Townsend
527c6476e1 Optimised version of KNN for Euclidean distances 
This patch also:
   * Completes removal of the edf/ package
   * Corrects an erroneous print statement
   * Introduces two new CSV functions
      * ParseCSVToInstancesTemplated makes sure that
        reading a second CSV file maintains strict Attribute
        compatibility with an existing DenseInstances
      * ParseCSVToInstancesWithAttributeGroups gives more control
        over where Attributes end up in memory, important for
        gaining predictable control over the KNN optimisation
      * Decouples BinaryAttributeGroup from FixedAttributeGroup for
        better casting support
 2014-09-30 23:10:22 +01:00
Jake Pyne
e5da0a8b04 Correct spelling 2014-09-28 01:34:21 +02:00