Machine Learning with Python for Everyone

8. More Classification Methods

In [1]:

Click here to view code image

# setup
from mlwpy import *
%matplotlib inline

iris = datasets.load_iris()

# standard iris dataset
tts = skms.train_test_split(iris.data, iris.target,
                            test_size=.33, random_state=21)
(iris_train_ftrs, iris_test_ftrs,
 iris_train_tgt,  iris_test_tgt) = tts

# one-class variation
useclass = 1
tts_1c = skms.train_test_split(iris.data, iris.target==useclass,
                               test_size=.33, random_state = 21)
(iris_1c_train_ftrs, iris_1c_test_ftrs,
 iris_1c_train_tgt,  iris_1c_test_tgt) = tts_1c

8.1 Revisiting Classification

So far, we’ve discussed two classifiers: Naive Bayes (NB) and k-Nearest Neighbors (k-NN). I want to add to our classification toolkit—but first, I want to revisit what is happening ...