Dataprep integration

[ganik]

pip install dataprep.
dataprep is a data preparation and cleansing package with internals in .NET CLR
We will need to do changes so the code below is possible:

from nimbusml import Pipeline
from nimbusml.datasets import get_dataset
from nimbusml.ensemble import FastTreesBinaryClassifier
from nimbusml.feature_extraction.text import NGramFeaturizer
 
train_data = dataflow(customer—provided--traindata)
test_data = dataflow(customer—provided-testdata)
 
pipeline = Pipeline([ # nimbusml pipeline
    NGramFeaturizer(columns={'Features': ['Text']}),
    FastTreesBinaryClassifier(feature=['Features'], label='Label')
])
 
# fit and predict
pipeline.fit(train_data)
results = pipeline.predict(test_data)

[ganik]

NimbusML Pipeline should accept dataprep dataflow() object same way it accepts FileDataStream.