Re: [ML] Training with bias

[Daniel Siegmann]

Yes, that's what I was looking for. Thanks.

On Tue, Apr 12, 2016 at 9:28 AM, Nick Pentreath 
wrote:

> Are you referring to fitting the intercept term? You can use
> lr.setFitIntercept (though it is true by default):
>
> scala> lr.explainParam(lr.fitIntercept)
> res27: String = fitIntercept: whether to fit an intercept term (default:
> true)
>
> On Mon, 11 Apr 2016 at 21:59 Daniel Siegmann 
> wrote:
>
>> I'm trying to understand how I can add a bias when training in Spark. I
>> have only a vague familiarity with this subject, so I hope this question
>> will be clear enough.
>>
>> Using liblinear a bias can be set - if it's >= 0, there will be an
>> additional weight appended in the model, and predicting with that model
>> will automatically append a feature for the bias.
>>
>> Is there anything similar in Spark, such as for logistic regression? The
>> closest thing I can find is MLUtils.appendBias, but this seems to
>> require manual work on both the training and scoring side. I was hoping for
>> something that would just be part of the model.
>>
>>
>> ~Daniel Siegmann
>>
>

Re: [ML] Training with bias

[Nick Pentreath]

Are you referring to fitting the intercept term? You can use
lr.setFitIntercept (though it is true by default):

scala> lr.explainParam(lr.fitIntercept)
res27: String = fitIntercept: whether to fit an intercept term (default:
true)

On Mon, 11 Apr 2016 at 21:59 Daniel Siegmann 
wrote:

> I'm trying to understand how I can add a bias when training in Spark. I
> have only a vague familiarity with this subject, so I hope this question
> will be clear enough.
>
> Using liblinear a bias can be set - if it's >= 0, there will be an
> additional weight appended in the model, and predicting with that model
> will automatically append a feature for the bias.
>
> Is there anything similar in Spark, such as for logistic regression? The
> closest thing I can find is MLUtils.appendBias, but this seems to require
> manual work on both the training and scoring side. I was hoping for
> something that would just be part of the model.
>
>
> ~Daniel Siegmann
>

[ML] Training with bias

[Daniel Siegmann]

I'm trying to understand how I can add a bias when training in Spark. I
have only a vague familiarity with this subject, so I hope this question
will be clear enough.

Using liblinear a bias can be set - if it's >= 0, there will be an
additional weight appended in the model, and predicting with that model
will automatically append a feature for the bias.

Is there anything similar in Spark, such as for logistic regression? The
closest thing I can find is MLUtils.appendBias, but this seems to require
manual work on both the training and scoring side. I was hoping for
something that would just be part of the model.

~Daniel Siegmann