[jira] [Updated] (IGNITE-11655) [ML]: OneHotEncoder returns more columns than expected

2020-01-14 Thread Alexey Zinoviev (Jira) 


 [ 
https://issues.apache.org/jira/browse/IGNITE-11655?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Alexey Zinoviev updated IGNITE-11655:
-
Summary: [ML]: OneHotEncoder returns more columns than expected  (was: ML: 
OneHotEncoder returns more columns than expected)

> [ML]: OneHotEncoder returns more columns than expected
> --
>
> Key: IGNITE-11655
> URL: https://issues.apache.org/jira/browse/IGNITE-11655
> Project: Ignite
>  Issue Type: Bug
>  Components: ml
>Affects Versions: 2.7
>Reporter: Anton Dmitriev
>Assignee: Alexey Zinoviev
>Priority: Critical
> Fix For: 2.8
>
>  Time Spent: 20m
>  Remaining Estimate: 0h
>
> OneHotEncoder returns more columns than expected (two values that might be 
> encoded using two columns encoded using 3 columns). The following example 
> demonstrates the problem:
> {code:java}
> Map training = new HashMap<>();
> training.put(0, new Object[]{42.0});
> training.put(1, new Object[]{43.0});
> training.put(2, new Object[]{42.0});
> EncoderTrainer trainer = new EncoderTrainer Object[]>()
> .withEncoderType(EncoderType.ONE_HOT_ENCODER)
> .withEncodedFeature(0);
> IgniteBiFunction processor = trainer.fit(training, 
> 1, (k, v) -> v);
> Vector res = processor.apply(1, new Object[]{42.0});
> System.out.println(Arrays.toString(res.asArray()));
> >>> [0.0, 1.0, 0.0]
> {code}



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

[jira] [Updated] (IGNITE-11655) [ML]: OneHotEncoder returns more columns than expected

2020-01-14 Thread Alexey Zinoviev (Jira) 


 [ 
https://issues.apache.org/jira/browse/IGNITE-11655?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Alexey Zinoviev updated IGNITE-11655:
-
Ignite Flags: Release Notes Required
Release Note: OneHotEncoder returns more columns than expected

> [ML]: OneHotEncoder returns more columns than expected
> --
>
> Key: IGNITE-11655
> URL: https://issues.apache.org/jira/browse/IGNITE-11655
> Project: Ignite
>  Issue Type: Bug
>  Components: ml
>Affects Versions: 2.7
>Reporter: Anton Dmitriev
>Assignee: Alexey Zinoviev
>Priority: Critical
> Fix For: 2.8
>
>  Time Spent: 20m
>  Remaining Estimate: 0h
>
> OneHotEncoder returns more columns than expected (two values that might be 
> encoded using two columns encoded using 3 columns). The following example 
> demonstrates the problem:
> {code:java}
> Map training = new HashMap<>();
> training.put(0, new Object[]{42.0});
> training.put(1, new Object[]{43.0});
> training.put(2, new Object[]{42.0});
> EncoderTrainer trainer = new EncoderTrainer Object[]>()
> .withEncoderType(EncoderType.ONE_HOT_ENCODER)
> .withEncodedFeature(0);
> IgniteBiFunction processor = trainer.fit(training, 
> 1, (k, v) -> v);
> Vector res = processor.apply(1, new Object[]{42.0});
> System.out.println(Arrays.toString(res.asArray()));
> >>> [0.0, 1.0, 0.0]
> {code}



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

[jira] [Updated] (IGNITE-11655) ML: OneHotEncoder returns more columns than expected

2019-10-10 Thread Maxim Muzafarov (Jira) 


 [ 
https://issues.apache.org/jira/browse/IGNITE-11655?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Maxim Muzafarov updated IGNITE-11655:
-
Fix Version/s: 2.8

> ML: OneHotEncoder returns more columns than expected
> 
>
> Key: IGNITE-11655
> URL: https://issues.apache.org/jira/browse/IGNITE-11655
> Project: Ignite
>  Issue Type: Bug
>  Components: ml
>Affects Versions: 2.7
>Reporter: Anton Dmitriev
>Assignee: Alexey Zinoviev
>Priority: Critical
> Fix For: 2.8
>
>  Time Spent: 20m
>  Remaining Estimate: 0h
>
> OneHotEncoder returns more columns than expected (two values that might be 
> encoded using two columns encoded using 3 columns). The following example 
> demonstrates the problem:
> {code:java}
> Map training = new HashMap<>();
> training.put(0, new Object[]{42.0});
> training.put(1, new Object[]{43.0});
> training.put(2, new Object[]{42.0});
> EncoderTrainer trainer = new EncoderTrainer Object[]>()
> .withEncoderType(EncoderType.ONE_HOT_ENCODER)
> .withEncodedFeature(0);
> IgniteBiFunction processor = trainer.fit(training, 
> 1, (k, v) -> v);
> Vector res = processor.apply(1, new Object[]{42.0});
> System.out.println(Arrays.toString(res.asArray()));
> >>> [0.0, 1.0, 0.0]
> {code}



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

[jira] [Updated] (IGNITE-11655) ML: OneHotEncoder returns more columns than expected

2019-03-29 Thread Aleksey Zinoviev (JIRA) 


 [ 
https://issues.apache.org/jira/browse/IGNITE-11655?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Aleksey Zinoviev updated IGNITE-11655:
--
Priority: Critical  (was: Major)

> ML: OneHotEncoder returns more columns than expected
> 
>
> Key: IGNITE-11655
> URL: https://issues.apache.org/jira/browse/IGNITE-11655
> Project: Ignite
>  Issue Type: Bug
>  Components: ml
>Affects Versions: 2.7
>Reporter: Anton Dmitriev
>Assignee: Aleksey Zinoviev
>Priority: Critical
>
> OneHotEncoder returns more columns than expected (two values that might be 
> encoded using two columns encoded using 3 columns). The following example 
> demonstrates the problem:
> {code:java}
> Map training = new HashMap<>();
> training.put(0, new Object[]{42.0});
> training.put(1, new Object[]{43.0});
> training.put(2, new Object[]{42.0});
> EncoderTrainer trainer = new EncoderTrainer Object[]>()
> .withEncoderType(EncoderType.ONE_HOT_ENCODER)
> .withEncodedFeature(0);
> IgniteBiFunction processor = trainer.fit(training, 
> 1, (k, v) -> v);
> Vector res = processor.apply(1, new Object[]{42.0});
> System.out.println(Arrays.toString(res.asArray()));
> >>> [0.0, 1.0, 0.0]
> {code}



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

[jira] [Updated] (IGNITE-11655) ML: OneHotEncoder returns more columns than expected

2019-03-29 Thread Anton Dmitriev (JIRA) 


 [ 
https://issues.apache.org/jira/browse/IGNITE-11655?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Anton Dmitriev updated IGNITE-11655:

Description: 
OneHotEncoder returns more columns than expected (two values that might be 
encoded using two columns encoded using 3 columns). The following example 
demonstrates the problem:


{code:java}
Map training = new HashMap<>();
training.put(0, new Object[]{42.0});
training.put(1, new Object[]{43.0});
 training.put(2, new Object[]{42.0});

EncoderTrainer trainer = new EncoderTrainer()
.withEncoderType(EncoderType.ONE_HOT_ENCODER)
.withEncodedFeature(0);

IgniteBiFunction processor = trainer.fit(training, 
1, (k, v) -> v);
Vector res = processor.apply(1, new Object[]{42.0});
System.out.println(Arrays.toString(res.asArray()));

>>> [0.0, 1.0, 0.0]
{code}


  was:
OneHotEncoder returns more columns than expected (two values that might be 
encoded using two columns encoded using 3 columns). The following example 
demonstrates the problem:


{code:java}
Map training = new HashMap<>();
training.put(0, new Object[]{42.0});
training.put(1, new Object[]{43.0});
 training.put(2, new Object[]{42.0});

 EncoderTrainer trainer = new EncoderTrainer()
.withEncoderType(EncoderType.ONE_HOT_ENCODER)
.withEncodedFeature(0);

IgniteBiFunction processor = trainer.fit(training, 
1, (k, v) -> v);
Vector res = processor.apply(1, new Object[]{42.0});
System.out.println(Arrays.toString(res.asArray()));

>>> [0.0, 1.0, 0.0]
{code}



> ML: OneHotEncoder returns more columns than expected
> 
>
> Key: IGNITE-11655
> URL: https://issues.apache.org/jira/browse/IGNITE-11655
> Project: Ignite
>  Issue Type: Bug
>  Components: ml
>Affects Versions: 2.7
>Reporter: Anton Dmitriev
>Priority: Major
>
> OneHotEncoder returns more columns than expected (two values that might be 
> encoded using two columns encoded using 3 columns). The following example 
> demonstrates the problem:
> {code:java}
> Map training = new HashMap<>();
> training.put(0, new Object[]{42.0});
> training.put(1, new Object[]{43.0});
>  training.put(2, new Object[]{42.0});
> EncoderTrainer trainer = new EncoderTrainer Object[]>()
> .withEncoderType(EncoderType.ONE_HOT_ENCODER)
> .withEncodedFeature(0);
> IgniteBiFunction processor = trainer.fit(training, 
> 1, (k, v) -> v);
> Vector res = processor.apply(1, new Object[]{42.0});
> System.out.println(Arrays.toString(res.asArray()));
> >>> [0.0, 1.0, 0.0]
> {code}



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

[jira] [Updated] (IGNITE-11655) ML: OneHotEncoder returns more columns than expected

2019-03-29 Thread Anton Dmitriev (JIRA) 


 [ 
https://issues.apache.org/jira/browse/IGNITE-11655?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Anton Dmitriev updated IGNITE-11655:

Description: 
OneHotEncoder returns more columns than expected (two values that might be 
encoded using two columns encoded using 3 columns). The following example 
demonstrates the problem:


{code:java}
Map training = new HashMap<>();
training.put(0, new Object[]{42.0});
training.put(1, new Object[]{43.0});
training.put(2, new Object[]{42.0});

EncoderTrainer trainer = new EncoderTrainer()
.withEncoderType(EncoderType.ONE_HOT_ENCODER)
.withEncodedFeature(0);

IgniteBiFunction processor = trainer.fit(training, 
1, (k, v) -> v);
Vector res = processor.apply(1, new Object[]{42.0});
System.out.println(Arrays.toString(res.asArray()));

>>> [0.0, 1.0, 0.0]
{code}


  was:
OneHotEncoder returns more columns than expected (two values that might be 
encoded using two columns encoded using 3 columns). The following example 
demonstrates the problem:


{code:java}
Map training = new HashMap<>();
training.put(0, new Object[]{42.0});
training.put(1, new Object[]{43.0});
 training.put(2, new Object[]{42.0});

EncoderTrainer trainer = new EncoderTrainer()
.withEncoderType(EncoderType.ONE_HOT_ENCODER)
.withEncodedFeature(0);

IgniteBiFunction processor = trainer.fit(training, 
1, (k, v) -> v);
Vector res = processor.apply(1, new Object[]{42.0});
System.out.println(Arrays.toString(res.asArray()));

>>> [0.0, 1.0, 0.0]
{code}



> ML: OneHotEncoder returns more columns than expected
> 
>
> Key: IGNITE-11655
> URL: https://issues.apache.org/jira/browse/IGNITE-11655
> Project: Ignite
>  Issue Type: Bug
>  Components: ml
>Affects Versions: 2.7
>Reporter: Anton Dmitriev
>Priority: Major
>
> OneHotEncoder returns more columns than expected (two values that might be 
> encoded using two columns encoded using 3 columns). The following example 
> demonstrates the problem:
> {code:java}
> Map training = new HashMap<>();
> training.put(0, new Object[]{42.0});
> training.put(1, new Object[]{43.0});
> training.put(2, new Object[]{42.0});
> EncoderTrainer trainer = new EncoderTrainer Object[]>()
> .withEncoderType(EncoderType.ONE_HOT_ENCODER)
> .withEncodedFeature(0);
> IgniteBiFunction processor = trainer.fit(training, 
> 1, (k, v) -> v);
> Vector res = processor.apply(1, new Object[]{42.0});
> System.out.println(Arrays.toString(res.asArray()));
> >>> [0.0, 1.0, 0.0]
> {code}



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

[jira] [Updated] (IGNITE-11655) ML: OneHotEncoder returns more columns than expected

2019-03-29 Thread Anton Dmitriev (JIRA) 


 [ 
https://issues.apache.org/jira/browse/IGNITE-11655?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Anton Dmitriev updated IGNITE-11655:

Description: 
OneHotEncoder returns more columns than expected (two values that might be 
encoded using two columns encoded using 3 columns). The following example 
demonstrates the problem:


{code:java}
Map training = new HashMap<>();

training.put(0, new Object[]{42.0});
training.put(1, new Object[]{43.0});
training.put(2, new Object[]{42.0});

EncoderTrainer trainer = new EncoderTrainer()
.withEncoderType(EncoderType.ONE_HOT_ENCODER)
.withEncodedFeature(0);

IgniteBiFunction processor = trainer.fit(training, 
1, (k, v) -> v);
Vector res = processor.apply(1, new Object[]{42.0});
System.out.println(Arrays.toString(res.asArray()));

>>> [0.0, 1.0, 0.0]
{code}


  was:
OneHotEncoder returns more columns than expected (two values that might be 
encoded using two columns encoded using 3 columns). The following example 
demonstrates the problem:


{code:java}
Map training = new HashMap<>();
training.put(0, new Object[]{42.0});
training.put(1, new Object[]{43.0});
training.put(2, new Object[]{42.0});

EncoderTrainer trainer = new EncoderTrainer()
.withEncoderType(EncoderType.ONE_HOT_ENCODER)
.withEncodedFeature(0);

IgniteBiFunction processor = trainer.fit(training, 
1, (k, v) -> v);
Vector res = processor.apply(1, new Object[]{42.0});
System.out.println(Arrays.toString(res.asArray()));

>>> [0.0, 1.0, 0.0]
{code}



> ML: OneHotEncoder returns more columns than expected
> 
>
> Key: IGNITE-11655
> URL: https://issues.apache.org/jira/browse/IGNITE-11655
> Project: Ignite
>  Issue Type: Bug
>  Components: ml
>Affects Versions: 2.7
>Reporter: Anton Dmitriev
>Priority: Major
>
> OneHotEncoder returns more columns than expected (two values that might be 
> encoded using two columns encoded using 3 columns). The following example 
> demonstrates the problem:
> {code:java}
> Map training = new HashMap<>();
> training.put(0, new Object[]{42.0});
> training.put(1, new Object[]{43.0});
> training.put(2, new Object[]{42.0});
> EncoderTrainer trainer = new EncoderTrainer Object[]>()
> .withEncoderType(EncoderType.ONE_HOT_ENCODER)
> .withEncodedFeature(0);
> IgniteBiFunction processor = trainer.fit(training, 
> 1, (k, v) -> v);
> Vector res = processor.apply(1, new Object[]{42.0});
> System.out.println(Arrays.toString(res.asArray()));
> >>> [0.0, 1.0, 0.0]
> {code}



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

[jira] [Updated] (IGNITE-11655) ML: OneHotEncoder returns more columns than expected

2019-03-29 Thread Anton Dmitriev (JIRA) 


 [ 
https://issues.apache.org/jira/browse/IGNITE-11655?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Anton Dmitriev updated IGNITE-11655:

Description: 
OneHotEncoder returns more columns than expected (two values that might be 
encoded using two columns encoded using 3 columns). The following example 
demonstrates the problem:


{code:java}
Map training = new HashMap<>();
training.put(0, new Object[]{42.0});
training.put(1, new Object[]{43.0});
 training.put(2, new Object[]{42.0});

 EncoderTrainer trainer = new EncoderTrainer()
.withEncoderType(EncoderType.ONE_HOT_ENCODER)
.withEncodedFeature(0);

IgniteBiFunction processor = trainer.fit(training, 
1, (k, v) -> v);
Vector res = processor.apply(1, new Object[]{42.0});
System.out.println(Arrays.toString(res.asArray()));

>>> [0.0, 1.0, 0.0]
{code}


  was:
OneHotEncoder returns more columns than expected (two values that might be 
encoded using two columns encoded using 3 columns). The following example 
demonstrates the problem:

Map training = new HashMap<>();
training.put(0, new Object[]{42.0});
training.put(1, new Object[]{43.0});
training.put(2, new Object[]{42.0});

EncoderTrainer trainer = new EncoderTrainer()
.withEncoderType(EncoderType.ONE_HOT_ENCODER)
.withEncodedFeature(0);

IgniteBiFunction processor = 
trainer.fit(training, 1, (k, v) -> v);

Vector res = processor.apply(1, new Object[]{42.0});

System.out.println(Arrays.toString(res.asArray()));

>>> [0.0, 1.0, 0.0]


> ML: OneHotEncoder returns more columns than expected
> 
>
> Key: IGNITE-11655
> URL: https://issues.apache.org/jira/browse/IGNITE-11655
> Project: Ignite
>  Issue Type: Bug
>  Components: ml
>Affects Versions: 2.7
>Reporter: Anton Dmitriev
>Priority: Major
>
> OneHotEncoder returns more columns than expected (two values that might be 
> encoded using two columns encoded using 3 columns). The following example 
> demonstrates the problem:
> {code:java}
> Map training = new HashMap<>();
> training.put(0, new Object[]{42.0});
> training.put(1, new Object[]{43.0});
>  training.put(2, new Object[]{42.0});
>  EncoderTrainer trainer = new EncoderTrainer Object[]>()
> .withEncoderType(EncoderType.ONE_HOT_ENCODER)
> .withEncodedFeature(0);
> IgniteBiFunction processor = trainer.fit(training, 
> 1, (k, v) -> v);
> Vector res = processor.apply(1, new Object[]{42.0});
> System.out.println(Arrays.toString(res.asArray()));
> >>> [0.0, 1.0, 0.0]
> {code}



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

[jira] [Updated] (IGNITE-11655) ML: OneHotEncoder returns more columns than expected

2019-03-29 Thread Anton Dmitriev (JIRA) 


 [ 
https://issues.apache.org/jira/browse/IGNITE-11655?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Anton Dmitriev updated IGNITE-11655:

Description: 
OneHotEncoder returns more columns than expected (two values that might be 
encoded using two columns encoded using 3 columns). The following example 
demonstrates the problem:


{code:java}
Map training = new HashMap<>();

training.put(0, new Object[]{42.0});
training.put(1, new Object[]{43.0});
training.put(2, new Object[]{42.0});

EncoderTrainer trainer = new EncoderTrainer()
.withEncoderType(EncoderType.ONE_HOT_ENCODER)
.withEncodedFeature(0);

IgniteBiFunction processor = trainer.fit(training, 
1, (k, v) -> v);
Vector res = processor.apply(1, new Object[]{42.0});

System.out.println(Arrays.toString(res.asArray()));

>>> [0.0, 1.0, 0.0]
{code}


  was:
OneHotEncoder returns more columns than expected (two values that might be 
encoded using two columns encoded using 3 columns). The following example 
demonstrates the problem:


{code:java}
Map training = new HashMap<>();

training.put(0, new Object[]{42.0});
training.put(1, new Object[]{43.0});
training.put(2, new Object[]{42.0});

EncoderTrainer trainer = new EncoderTrainer()
.withEncoderType(EncoderType.ONE_HOT_ENCODER)
.withEncodedFeature(0);

IgniteBiFunction processor = trainer.fit(training, 
1, (k, v) -> v);
Vector res = processor.apply(1, new Object[]{42.0});
System.out.println(Arrays.toString(res.asArray()));

>>> [0.0, 1.0, 0.0]
{code}



> ML: OneHotEncoder returns more columns than expected
> 
>
> Key: IGNITE-11655
> URL: https://issues.apache.org/jira/browse/IGNITE-11655
> Project: Ignite
>  Issue Type: Bug
>  Components: ml
>Affects Versions: 2.7
>Reporter: Anton Dmitriev
>Priority: Major
>
> OneHotEncoder returns more columns than expected (two values that might be 
> encoded using two columns encoded using 3 columns). The following example 
> demonstrates the problem:
> {code:java}
> Map training = new HashMap<>();
> training.put(0, new Object[]{42.0});
> training.put(1, new Object[]{43.0});
> training.put(2, new Object[]{42.0});
> EncoderTrainer trainer = new EncoderTrainer Object[]>()
> .withEncoderType(EncoderType.ONE_HOT_ENCODER)
> .withEncodedFeature(0);
> IgniteBiFunction processor = trainer.fit(training, 
> 1, (k, v) -> v);
> Vector res = processor.apply(1, new Object[]{42.0});
> System.out.println(Arrays.toString(res.asArray()));
> >>> [0.0, 1.0, 0.0]
> {code}



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

[jira] [Updated] (IGNITE-11655) ML: OneHotEncoder returns more columns than expected

2019-03-29 Thread Anton Dmitriev (JIRA) 


 [ 
https://issues.apache.org/jira/browse/IGNITE-11655?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Anton Dmitriev updated IGNITE-11655:

Ignite Flags:   (was: Docs Required)

> ML: OneHotEncoder returns more columns than expected
> 
>
> Key: IGNITE-11655
> URL: https://issues.apache.org/jira/browse/IGNITE-11655
> Project: Ignite
>  Issue Type: Bug
>  Components: ml
>Reporter: Anton Dmitriev
>Priority: Major
>
> OneHotEncoder returns more columns than expected (two values that might be 
> encoded using two columns encoded using 3 columns). The following example 
> demonstrates the problem:
> Map training = new HashMap<>();
> training.put(0, new Object[]{42.0});
> training.put(1, new Object[]{43.0});
> training.put(2, new Object[]{42.0});
> EncoderTrainer trainer = new 
> EncoderTrainer()
> .withEncoderType(EncoderType.ONE_HOT_ENCODER)
> .withEncodedFeature(0);
> IgniteBiFunction processor = 
> trainer.fit(training, 1, (k, v) -> v);
> Vector res = processor.apply(1, new Object[]{42.0});
> System.out.println(Arrays.toString(res.asArray()));
> >>> [0.0, 1.0, 0.0]



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

[jira] [Updated] (IGNITE-11655) ML: OneHotEncoder returns more columns than expected

2019-03-29 Thread Anton Dmitriev (JIRA) 


 [ 
https://issues.apache.org/jira/browse/IGNITE-11655?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Anton Dmitriev updated IGNITE-11655:

Affects Version/s: 2.7

> ML: OneHotEncoder returns more columns than expected
> 
>
> Key: IGNITE-11655
> URL: https://issues.apache.org/jira/browse/IGNITE-11655
> Project: Ignite
>  Issue Type: Bug
>  Components: ml
>Affects Versions: 2.7
>Reporter: Anton Dmitriev
>Priority: Major
>
> OneHotEncoder returns more columns than expected (two values that might be 
> encoded using two columns encoded using 3 columns). The following example 
> demonstrates the problem:
> Map training = new HashMap<>();
> training.put(0, new Object[]{42.0});
> training.put(1, new Object[]{43.0});
> training.put(2, new Object[]{42.0});
> EncoderTrainer trainer = new 
> EncoderTrainer()
> .withEncoderType(EncoderType.ONE_HOT_ENCODER)
> .withEncodedFeature(0);
> IgniteBiFunction processor = 
> trainer.fit(training, 1, (k, v) -> v);
> Vector res = processor.apply(1, new Object[]{42.0});
> System.out.println(Arrays.toString(res.asArray()));
> >>> [0.0, 1.0, 0.0]



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

[jira] [Updated] (IGNITE-11655) ML: OneHotEncoder returns more columns than expected

2019-03-29 Thread Anton Dmitriev (JIRA) 


 [ 
https://issues.apache.org/jira/browse/IGNITE-11655?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Anton Dmitriev updated IGNITE-11655:

Component/s: ml

> ML: OneHotEncoder returns more columns than expected
> 
>
> Key: IGNITE-11655
> URL: https://issues.apache.org/jira/browse/IGNITE-11655
> Project: Ignite
>  Issue Type: Bug
>  Components: ml
>Reporter: Anton Dmitriev
>Priority: Major
>
> OneHotEncoder returns more columns than expected (two values that might be 
> encoded using two columns encoded using 3 columns). The following example 
> demonstrates the problem:
> Map training = new HashMap<>();
> training.put(0, new Object[]{42.0});
> training.put(1, new Object[]{43.0});
> training.put(2, new Object[]{42.0});
> EncoderTrainer trainer = new 
> EncoderTrainer()
> .withEncoderType(EncoderType.ONE_HOT_ENCODER)
> .withEncodedFeature(0);
> IgniteBiFunction processor = 
> trainer.fit(training, 1, (k, v) -> v);
> Vector res = processor.apply(1, new Object[]{42.0});
> System.out.println(Arrays.toString(res.asArray()));
> >>> [0.0, 1.0, 0.0]



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)