plot decision paths from all of the test sample

Question

There is this code obtained from:

How to display the path of a Decision Tree for test samples?

Basically it plots the decision path of a sample over the decision tree plot to know how was a specific prediction made

import pydotplus
from sklearn.datasets import load_iris
from sklearn import tree

clf = tree.DecisionTreeClassifier(random_state=42)
iris = load_iris()

clf = clf.fit(iris.data, iris.target)

dot_data = tree.export_graphviz(clf, out_file=None,
                                feature_names=iris.feature_names,
                                class_names=iris.target_names,
                                filled=True, rounded=True,
                                special_characters=True)
graph = pydotplus.graph_from_dot_data(dot_data)

# empty all nodes, i.e.set color to white and number of samples to zero
for node in graph.get_node_list():
    if node.get_attributes().get('label') is None:
        continue
    if 'samples = ' in node.get_attributes()['label']:
        labels = node.get_attributes()['label'].split('<br/>')
        for i, label in enumerate(labels):
            if label.startswith('samples = '):
                labels[i] = 'samples = 0'
        node.set('label', '<br/>'.join(labels))
        node.set_fillcolor('white')

samples = iris.data[129:130]
decision_paths = clf.decision_path(samples)

for decision_path in decision_paths:
    for n, node_value in enumerate(decision_path.toarray()[0]):
        if node_value == 0:
            continue
        node = graph.get_node(str(n))[0]            
        node.set_fillcolor('green')
        labels = node.get_attributes()['label'].split('<br/>')
        for i, label in enumerate(labels):
            if label.startswith('samples = '):
                labels[i] = 'samples = {}'.format(int(label.split('=')[1]) + 1)

        node.set('label', '<br/>'.join(labels))

filename = 'tree.png'
graph.write_png(filename)

What I want to do is to plot all of the samples decision paths in different plots in my Jupiter notebook. What should I add to the code?

score 0 · Answer 1 · answered Mar 05 '22 at 17:13

As the question doesn't provide concrete expected results, I assume that you want to plot the parts of the decision paths of your classification results.

One of the solutions would be adding one more layer of for loop to achieve it. However, it might affect your program's performance. Hence, use with caution.

import pydotplus
from sklearn.datasets import load_iris
from sklearn import tree

clf = tree.DecisionTreeClassifier(random_state=42)
iris = load_iris()

clf = clf.fit(iris.data, iris.target)

dot_data = tree.export_graphviz(clf, out_file=None,
                                feature_names=iris.feature_names,
                                class_names=iris.target_names,
                                filled=True, rounded=True,
                                special_characters=True)
graph = pydotplus.graph_from_dot_data(dot_data)

# empty all nodes, i.e.set color to white and number of samples to zero
for node in graph.get_node_list():
    if node.get_attributes().get('label') is None:
        continue
    if 'samples = ' in node.get_attributes()['label']:
        labels = node.get_attributes()['label'].split('<br/>')
        for i, label in enumerate(labels):
            if label.startswith('samples = '):
                labels[i] = 'samples = 0'
        node.set('label', '<br/>'.join(labels))
        node.set_fillcolor('white')

# samples = iris.data[129:130]
samples = iris.data[120:130] # <-- Classifying 10 data
decision_paths = clf.decision_path(samples)

for decision_path in decision_paths:
    for path in decision_path.toarray(): # <-- Adding one more layer of for loop to loop each path
    # for n, node_value in enumerate(decision_path.toarray()[0]):
        for n, node_value in enumerate(path):
            if node_value == 0:
                continue
            node = graph.get_node(str(n))[0]
            node.set_fillcolor('green')
            labels = node.get_attributes()['label'].split('<br/>')
            for i, label in enumerate(labels):
                if label.startswith('samples = '):
                    labels[i] = 'samples = {}'.format(int(label.split('=')[1]) + 1)

            node.set('label', '<br/>'.join(labels))

# display it inline
display_png(Image(graph.create_png()))

# or save it as png
filename = 'tree.png'
graph.write_png(filename)

The result:

plot decision paths from all of the test sample

1 Answers1