Hi,

As it has been indicated by other members, methods such as
``LocalOutlierFactor`` do not expose a ``predict``  method by design.

However, if you nevertheless would still like to keep experimenting in the
direction of attempting to make predictions on "unseen" data, you could
simply create a sub-class with a ``predict()`` wrapper, as in:
https://gist.github.com/hristog/b6151d21aa38a6c80d80d160b7771ce9

Hristo



> On 10/06/2017 12:53 AM, Lifan Xu wrote:
>
>> Hi,
>>
>>     I was trying to train a model for anomaly detection. I only have the
>> normal data which are all labeled as 1. Here is my code:
>>
>>
>>     clf = sklearn.model_selection.GridSearchCV(sklearn.neighbors.
>> LocalOutlierFactor(),
>>                        parameters,
>>                        scoring="accuracy",
>>                        cv=kfold,
>>                        n_jobs=10)
>>     clf.fit(vectors, labels)
>>
>>
>>     But it complains "AttributeError: 'LocalOutlierFactor' object has no
>> attribute 'predict'".
>>
>>     It looks like LocalOutlierFactor only has fit_predict(), but no
>> predict().
>>
>>     My question is will predict() be implemented?
>>
>>
>>     Thanks!
>>
>> _______________________________________________
>> scikit-learn mailing list
>> scikit-learn@python.org
>> https://mail.python.org/mailman/listinfo/scikit-learn
>>
>
> _______________________________________________
> scikit-learn mailing list
> scikit-learn@python.org
> https://mail.python.org/mailman/listinfo/scikit-learn
>
_______________________________________________
scikit-learn mailing list
scikit-learn@python.org
https://mail.python.org/mailman/listinfo/scikit-learn

Reply via email to