# -*- coding：utf-8 -*-
# time ：2019/4/18 13:33
# author: 毛利
from sklearn.model_selection import train_test_split
import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn import datasets
from sklearn import tree
from sklearn.metrics import accuracy_score
import pydotplus
iris = datasets.load_iris()
iris_feature = '花萼長度', '花萼寬度', '花瓣長度', '花瓣寬度'
iris_feature_E = 'sepal length', 'sepal width', 'petal length', 'petal width'
iris_class = 'Iris-setosa', 'Iris-versicolor', 'Iris-virginica'
x = pd.DataFrame(iris['data'])[[0,1]]
y = pd.Series(iris[ 'target'])
x_train,x_test,y_train,y_test = train_test_split(x,y)
model = DecisionTreeClassifier()
model.fit(x_train,y_train)
y_train_pred = model.predict(x_train)
print('訓(xùn)練集正確率：', accuracy_score(y_train, y_train_pred))
data = tree.export_graphviz(model, out_file='iris.dot', feature_names= iris_feature_E[0:2], class_names=iris_class,filled=True, rounded=True, special_characters=True)
graph = pydotplus.graph_from_dot_data(data)
graph.write_pdf('iris.pdf')
with open('iris.png', 'wb') as f:f.write(graph.create_png())、import numpy as np
from sklearn.tree import DecisionTreeClassifier
import pydotplus
from sklearn import treeX = np.array([[2, 2],[2, 1],[2, 3],[1, 2],[1, 1],[3, 3]])y = np.array([0, 1, 1, 1, 0, 1])plt.style.use('fivethirtyeight')
plt.rcParams['font.size'] = 18
plt.figure(figsize=(8, 8))# Plot each point as the label
for x1, x2, label in zip(X[:, 0], X[:, 1], y):plt.text(x1, x2, str(label), fontsize=40, color='g',ha='center', va='center')plt.grid(None)
plt.xlim((0, 3.5))
plt.ylim((0, 3.5))
plt.xlabel('x1', size=20)
plt.ylabel('x2', size=20)
plt.title('Data', size=24)
# plt.show()dec_tree = DecisionTreeClassifier()
print(dec_tree)
dec_tree.fit(X, y)
print(dec_tree.score(X,y))
# Export as dot
dot_data = tree.export_graphviz(dec_tree, out_file=None,feature_names=['x1', 'x2'],class_names=['0', '1'],filled=True, rounded=True,special_characters=True)
graph = pydotplus.graph_from_dot_data(dot_data)
with open('1.png', 'wb') as f:f.write(graph.create_png())
這是export_graphviz源代碼加快理解
def export_graphviz(decision_tree, out_file=SENTINEL, max_depth=None,feature_names=None, class_names=None, label='all',filled=False, leaves_parallel=False, impurity=True,node_ids=False, proportion=False, rotate=False,rounded=False, special_characters=False, precision=3):"""Export a decision tree in DOT format.This function generates a GraphViz representation of the decision tree,which is then written into `out_file`. Once exported, graphical renderingscan be generated using, for example::$ dot -Tps tree.dot -o tree.ps (PostScript format)$ dot -Tpng tree.dot -o tree.png (PNG format)The sample counts that are shown are weighted with any sample_weights thatmight be present.Read more in the :ref:`User Guide <tree>`.Parameters----------decision_tree : decision tree classifierThe decision tree to be exported to GraphViz.out_file : file object or string, optional (default='tree.dot')Handle or name of the output file. If ``None``, the result isreturned as a string. This will the default from version 0.20.max_depth : int, optional (default=None)The maximum depth of the representation. If None, the tree is fullygenerated.feature_names : list of strings, optional (default=None)Names of each of the features.class_names : list of strings, bool or None, optional (default=None)Names of each of the target classes in ascending numerical order.Only relevant for classification and not supported for multi-output.If ``True``, shows a symbolic representation of the class name.label : {'all', 'root', 'none'}, optional (default='all')Whether to show informative labels for impurity, etc.Options include 'all' to show at every node, 'root' to show only atthe top root node, or 'none' to not show at any node.filled : bool, optional (default=False)When set to ``True``, paint nodes to indicate majority class forclassification, extremity of values for regression, or purity of nodefor multi-output.leaves_parallel : bool, optional (default=False)When set to ``True``, draw all leaf nodes at the bottom of the tree.impurity : bool, optional (default=True)When set to ``True``, show the impurity at each node.node_ids : bool, optional (default=False)When set to ``True``, show the ID number on each node.proportion : bool, optional (default=False)When set to ``True``, change the display of 'values' and/or 'samples'to be proportions and percentages respectively.rotate : bool, optional (default=False)When set to ``True``, orient tree left to right rather than top-down.rounded : bool, optional (default=False)When set to ``True``, draw node boxes with rounded corners and useHelvetica fonts instead of Times-Roman.special_characters : bool, optional (default=False)When set to ``False``, ignore special characters for PostScriptcompatibility.precision : int, optional (default=3)Number of digits of precision for floating point in the values ofimpurity, threshold and value attributes of each node.Returns-------dot_data : stringString representation of the input tree in GraphViz dot format.Only returned if ``out_file`` is None... versionadded:: 0.18
