def _model(self):
if self.family == GAUSSIAN_:
reg = LinearRegression()
elif self.family == BINOMIAL_:
reg = GeneralizedLinearRegression(family="binomial", link="logit")
else:
raise NotImplementedError("Family '{}' not implemented".format(
self.family))
reg.setLabelCol(self.response)
reg.setMaxIter(self.__max_iter)
return reg
# In[18]:
lr.setPredictionCol("Predicted_PE") .setLabelCol("PE")
# We will also configure two parameters, which a re customary to the linear
# regression
# - the maximum number of iterations to 100
# - the regularization parameter to 0.1
# In[19]:
lr.setMaxIter(100) .setRegParam(0.1)
# ## Part 8 Create a pipeline
#
# Next, to create a workflow that puts together the vectorization and the Linear
# Regression learner, we can create an ML Pipeline that stitch together the two
# trasnformations we created before
# In[25]:
lrPipeline = Pipeline()
lrPipeline.setStages([vectorizer, lr])
