New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
sklearnserver: ignore converting instances into np.array #1972
sklearnserver: ignore converting instances into np.array #1972
Conversation
e2768cf
to
156a7ce
Compare
@Suresh-Nakkeran Can you help test with the mixed type example with your change? |
6a421f0
to
8f9933e
Compare
@@ -0,0 +1,299 @@ | |||
{ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This should be moved to sklearn v1 examples
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I moved.
from sklearn.base import TransformerMixin | ||
|
||
|
||
class DictToDFTransformer(TransformerMixin): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This file is only used for sklearn pipeline example right?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
yes @yuzisun . It is used only for sklearnserver model test.
Signed-off-by: Suresh Nakkeran <suresh.n@ideas2it.com>
Signed-off-by: Suresh Nakkeran <suresh.n@ideas2it.com>
Signed-off-by: Suresh Nakkeran <suresh.n@ideas2it.com>
Signed-off-by: Suresh Nakkeran <suresh.n@ideas2it.com>
8f9933e
to
572e60d
Compare
@@ -0,0 +1,299 @@ | |||
{ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@Suresh-Nakkeran I have uploaded the model to gs://kfserving-examples/models/sklearn/1.0/mixedtype/model.joblib
, can you help remove the above model.joblib
file(keep the repo small) and add an inferenceservice yaml example file instead ?
predictor: | ||
sklearn: | ||
storageUri: "gs://kfserving-examples/models/sklearn/1.0/mixedtype" | ||
image: "suresh1233/sklearnserver:latest" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
image: "suresh1233/sklearnserver:latest" | |
image: "kserve/sklearnserver:latest" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
or maybe can simply remove the image field as the image is going to be published when 0.8 is released
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
sure @yuzisun
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
updated!
ecfd9fd
to
2ba66e3
Compare
2. multi-datatype renamed to mixedtype Signed-off-by: Suresh Nakkeran <suresh.n@ideas2it.com>
2ba66e3
to
d77bf90
Compare
/retest |
Thanks @Suresh-Nakkeran ! /lgtm |
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: Suresh-Nakkeran, yuzisun The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
To support mix types of input such as pandas data frames, we remove the numpy array conversion in sklearnserver which can be done in transformer if needed.
fixes #1912