In [1]:

    

from sklearn import datasets


    

In [2]:

    

iris = datasets.load_iris()


    

In [3]:

    

# by analogy of f(x) = y
X = iris.data  # array([[ 5.1,  3.5,  1.4,  0.2], [ 4.9,  3. ,  1.4,  0.2]])
y = iris.target  # array([0, 0])


    

In [4]:

    

from sklearn.cross_validation import train_test_split


    

In [5]:

    

# 0.5 means use half of data for testing
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)


    

In [6]:

    

from sklearn import tree


    

In [7]:

    

my_classifier = tree.DecisionTreeClassifier()


    

In [8]:

    

my_classifier.fit(X_train, y_train)


    

    
Out[8]:





DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
            min_samples_split=2, min_weight_fraction_leaf=0.0,
            presort=False, random_state=None, splitter='best')

In [9]:

    

predictions = my_classifier.predict(X_test)  # array([2, 0, 2])


    

In [10]:

    

from sklearn.metrics import accuracy_score


    

In [11]:

    

accuracy_score(y_test, predictions)


    

    
Out[11]:





0.95999999999999996

In [14]:

    

from sklearn.neighbors import KNeighborsClassifier
my_classifier = KNeighborsClassifier()


    

In [15]:

    

my_classifier.fit(X_train, y_train)
predictions = my_classifier.predict(X_test)  # array([2, 0, 2])
accuracy_score(y_test, predictions)


    

    
Out[15]:





0.92000000000000004

In [ ]: