sklearn Decision tree

from sklearn import datasets
from sklearn import tree
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# ------ Load iris -----------
iris = datasets.load_iris()
X = iris.data
y = iris.target

# ----- Build decision tree classifier ------------
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 100)
dt = tree.DecisionTreeClassifier(criterion='entropy', max_depth=5)
dt.fit(X_train, y_train)

y_pred = dt.predict(X_test)
print("Accuracy is ", accuracy_score(y_test,y_pred)*100)

# ---- plot decision tree -----------

# plot tree in .dot file
dotfile = open("dt.dot", 'w')
tree.export_graphviz(dt, out_file=dotfile, feature_names=iris.feature_names, class_names=iris.target_names,  filled=True)
dotfile.close()

# set graphviz path 
import os
os.environ["PATH"] += os.pathsep + 'C:/Program Files (x86)/Graphviz2.38/bin/'

# convert the .dot to .png
from subprocess import check_call
check_call(['dot','-Tpng','dt.dot','-o','dt.png'])

# convert the .dot to .pdf file
import graphviz
g = graphviz.Source(open('dt.dot').read()) #  returns a graphviz.files.Source object
g.render()
g.view()
sklearn Decision tree

Updated: 12 April, 2018
