cas-pml/ML/unterlagen/03_decisiontree.ipynb

data prep

In [2]:

from sklearn import datasets
iris = datasets.load_iris()

data understanding

In [3]:

print(iris.data.size)
print(iris.target.size)

600
150

In [4]:

print(iris.data)

[[ 5.1  3.5  1.4  0.2]
 [ 4.9  3.   1.4  0.2]
 [ 4.7  3.2  1.3  0.2]
 [ 4.6  3.1  1.5  0.2]
 [ 5.   3.6  1.4  0.2]
 [ 5.4  3.9  1.7  0.4]
 [ 4.6  3.4  1.4  0.3]
 [ 5.   3.4  1.5  0.2]
 [ 4.4  2.9  1.4  0.2]
 [ 4.9  3.1  1.5  0.1]
 [ 5.4  3.7  1.5  0.2]
 [ 4.8  3.4  1.6  0.2]
 [ 4.8  3.   1.4  0.1]
 [ 4.3  3.   1.1  0.1]
 [ 5.8  4.   1.2  0.2]
 [ 5.7  4.4  1.5  0.4]
 [ 5.4  3.9  1.3  0.4]
 [ 5.1  3.5  1.4  0.3]
 [ 5.7  3.8  1.7  0.3]
 [ 5.1  3.8  1.5  0.3]
 [ 5.4  3.4  1.7  0.2]
 [ 5.1  3.7  1.5  0.4]
 [ 4.6  3.6  1.   0.2]
 [ 5.1  3.3  1.7  0.5]
 [ 4.8  3.4  1.9  0.2]
 [ 5.   3.   1.6  0.2]
 [ 5.   3.4  1.6  0.4]
 [ 5.2  3.5  1.5  0.2]
 [ 5.2  3.4  1.4  0.2]
 [ 4.7  3.2  1.6  0.2]
 [ 4.8  3.1  1.6  0.2]
 [ 5.4  3.4  1.5  0.4]
 [ 5.2  4.1  1.5  0.1]
 [ 5.5  4.2  1.4  0.2]
 [ 4.9  3.1  1.5  0.1]
 [ 5.   3.2  1.2  0.2]
 [ 5.5  3.5  1.3  0.2]
 [ 4.9  3.1  1.5  0.1]
 [ 4.4  3.   1.3  0.2]
 [ 5.1  3.4  1.5  0.2]
 [ 5.   3.5  1.3  0.3]
 [ 4.5  2.3  1.3  0.3]
 [ 4.4  3.2  1.3  0.2]
 [ 5.   3.5  1.6  0.6]
 [ 5.1  3.8  1.9  0.4]
 [ 4.8  3.   1.4  0.3]
 [ 5.1  3.8  1.6  0.2]
 [ 4.6  3.2  1.4  0.2]
 [ 5.3  3.7  1.5  0.2]
 [ 5.   3.3  1.4  0.2]
 [ 7.   3.2  4.7  1.4]
 [ 6.4  3.2  4.5  1.5]
 [ 6.9  3.1  4.9  1.5]
 [ 5.5  2.3  4.   1.3]
 [ 6.5  2.8  4.6  1.5]
 [ 5.7  2.8  4.5  1.3]
 [ 6.3  3.3  4.7  1.6]
 [ 4.9  2.4  3.3  1. ]
 [ 6.6  2.9  4.6  1.3]
 [ 5.2  2.7  3.9  1.4]
 [ 5.   2.   3.5  1. ]
 [ 5.9  3.   4.2  1.5]
 [ 6.   2.2  4.   1. ]
 [ 6.1  2.9  4.7  1.4]
 [ 5.6  2.9  3.6  1.3]
 [ 6.7  3.1  4.4  1.4]
 [ 5.6  3.   4.5  1.5]
 [ 5.8  2.7  4.1  1. ]
 [ 6.2  2.2  4.5  1.5]
 [ 5.6  2.5  3.9  1.1]
 [ 5.9  3.2  4.8  1.8]
 [ 6.1  2.8  4.   1.3]
 [ 6.3  2.5  4.9  1.5]
 [ 6.1  2.8  4.7  1.2]
 [ 6.4  2.9  4.3  1.3]
 [ 6.6  3.   4.4  1.4]
 [ 6.8  2.8  4.8  1.4]
 [ 6.7  3.   5.   1.7]
 [ 6.   2.9  4.5  1.5]
 [ 5.7  2.6  3.5  1. ]
 [ 5.5  2.4  3.8  1.1]
 [ 5.5  2.4  3.7  1. ]
 [ 5.8  2.7  3.9  1.2]
 [ 6.   2.7  5.1  1.6]
 [ 5.4  3.   4.5  1.5]
 [ 6.   3.4  4.5  1.6]
 [ 6.7  3.1  4.7  1.5]
 [ 6.3  2.3  4.4  1.3]
 [ 5.6  3.   4.1  1.3]
 [ 5.5  2.5  4.   1.3]
 [ 5.5  2.6  4.4  1.2]
 [ 6.1  3.   4.6  1.4]
 [ 5.8  2.6  4.   1.2]
 [ 5.   2.3  3.3  1. ]
 [ 5.6  2.7  4.2  1.3]
 [ 5.7  3.   4.2  1.2]
 [ 5.7  2.9  4.2  1.3]
 [ 6.2  2.9  4.3  1.3]
 [ 5.1  2.5  3.   1.1]
 [ 5.7  2.8  4.1  1.3]
 [ 6.3  3.3  6.   2.5]
 [ 5.8  2.7  5.1  1.9]
 [ 7.1  3.   5.9  2.1]
 [ 6.3  2.9  5.6  1.8]
 [ 6.5  3.   5.8  2.2]
 [ 7.6  3.   6.6  2.1]
 [ 4.9  2.5  4.5  1.7]
 [ 7.3  2.9  6.3  1.8]
 [ 6.7  2.5  5.8  1.8]
 [ 7.2  3.6  6.1  2.5]
 [ 6.5  3.2  5.1  2. ]
 [ 6.4  2.7  5.3  1.9]
 [ 6.8  3.   5.5  2.1]
 [ 5.7  2.5  5.   2. ]
 [ 5.8  2.8  5.1  2.4]
 [ 6.4  3.2  5.3  2.3]
 [ 6.5  3.   5.5  1.8]
 [ 7.7  3.8  6.7  2.2]
 [ 7.7  2.6  6.9  2.3]
 [ 6.   2.2  5.   1.5]
 [ 6.9  3.2  5.7  2.3]
 [ 5.6  2.8  4.9  2. ]
 [ 7.7  2.8  6.7  2. ]
 [ 6.3  2.7  4.9  1.8]
 [ 6.7  3.3  5.7  2.1]
 [ 7.2  3.2  6.   1.8]
 [ 6.2  2.8  4.8  1.8]
 [ 6.1  3.   4.9  1.8]
 [ 6.4  2.8  5.6  2.1]
 [ 7.2  3.   5.8  1.6]
 [ 7.4  2.8  6.1  1.9]
 [ 7.9  3.8  6.4  2. ]
 [ 6.4  2.8  5.6  2.2]
 [ 6.3  2.8  5.1  1.5]
 [ 6.1  2.6  5.6  1.4]
 [ 7.7  3.   6.1  2.3]
 [ 6.3  3.4  5.6  2.4]
 [ 6.4  3.1  5.5  1.8]
 [ 6.   3.   4.8  1.8]
 [ 6.9  3.1  5.4  2.1]
 [ 6.7  3.1  5.6  2.4]
 [ 6.9  3.1  5.1  2.3]
 [ 5.8  2.7  5.1  1.9]
 [ 6.8  3.2  5.9  2.3]
 [ 6.7  3.3  5.7  2.5]
 [ 6.7  3.   5.2  2.3]
 [ 6.3  2.5  5.   1.9]
 [ 6.5  3.   5.2  2. ]
 [ 6.2  3.4  5.4  2.3]
 [ 5.9  3.   5.1  1.8]]

In [3]:

print(iris.target)

[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2
 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
 2 2]

In [4]:

print(iris.feature_names)
print(iris.target_names)

['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']
['setosa' 'versicolor' 'virginica']

In [5]:

import matplotlib.pyplot as plt
plt.hist(iris.target, bins=(0,1,2,3), edgecolor='black')
plt.show()

In [7]:

X = iris.data[:, :2]  # we only take the first two features.
y = iris.target
plt.figure(2, figsize=(8, 6))
plt.clf()
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.Set1, edgecolor='k')
plt.xlabel('Sepal length')
plt.ylabel('Sepal width')
plt.xticks(())
plt.yticks(())
plt.show()

train model

In [9]:

from sklearn.tree import DecisionTreeClassifier
classifier = DecisionTreeClassifier()
classifier.fit(iris.data[:-1], iris.target[:-1])  # use all but the last sample for training

Out [9]:

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

use model for prediction

In [11]:

print("predicted",classifier.predict(iris.data[-1:]),"vs. real",iris.target[-1:])

predicted [2] vs. real [2]

export model for visual inspection

In [12]:

from sklearn import tree
tree.export_graphviz(classifier,out_file='tree.dot', 
                         feature_names=iris.feature_names,  
                         class_names=iris.target_names,  
                         filled=True, rounded=True,  
                         special_characters=True)         

In [ ]: