Gani Nazirov

Currently when data is transformed as part of pipeline: ```pipeline.transform(data)``` the output is pandas dataframe. It would be good to return a pointer to a IDataView object and realize it...

Speed up scoring in NimbusML

1

Consider this python based prediction server code: # One time setup model = Pipeline() model.load_model('model.zip') # Numerous multiple calls to predict: model.predict(data) ########################## Currently calls to predict(data) always make ML.NET...

In scikit-learn one can do: pca = PCA(n_components=n_digits).fit(data) estimator = KMeans(init=pca.components_, n_clusters=n_digits, n_init=1) Would be great to allow this in NimbusML