載入套件

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree
import graphviz 
from sklearn.metrics import classification_report,confusion_matrix

匯入資料

urlprefix = 'https://vincentarelbundock.github.io/Rdatasets/csv/' 
dataname = 'datasets/iris.csv'
iris = pd.read_csv(urlprefix + dataname)
iris = iris.drop("Unnamed: 0", 1)

iris.head()

切割為訓練集與測試集

X = iris.iloc[:, 0:4].values
y = iris.iloc[:, 4].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

建立模型(資料不需標準化)

clf = DecisionTreeClassifier(criterion = "entropy", max_depth=3, random_state=0)
clf = clf.fit(X_train, y_train)

查看結果

print(confusion_matrix(y_test,clf.predict(X_test)))

視覺化呈現

• 存出pdf檔

dot_data = tree.export_graphviz(clf, out_file=None) 
graph = graphviz.Source(dot_data) 
graph.render("iris")

• 直接在jupyter notebook上呈現

dot_data = tree.export_graphviz(clf, out_file=None, 
                                feature_names=list(iris.columns)[:4],  
                                class_names=clf.classes_,  
                                filled=True, rounded=True,  
                                special_characters=True)  
graph = graphviz.Source(dot_data)  
graph