درخت تصمیم با پایتون

import numpy as np
from sklearn.model_selection import train_test_split
import os;
path="C:/Users/michaeljgrogan/Documents/a_documents/computing/data science/datasets"
os.chdir(path)
os.getcwd()

Python
#Variables
dataset=np.loadtxt("internetlogit.csv", delimiter=",")
x=dataset[:,0:5]
y=dataset[:,5]

اکنون از np.loadtxt برای بارگذاری داده‌ها در فرمت csv استفاده می‌کنیم.

Python
#Variables
dataset=np.loadtxt("internetlogit.csv", delimiter=",")
x=dataset[:,0:5]
y=dataset[:,5]

Python
from sklearn.tree import DecisionTreeRegressor
X_train, X_test, y_train, y_test = train_test_split(x, y)
tree = DecisionTreeRegressor().fit(X_train,y_train)

print("Training set accuracy: {:.3f}".format(tree.score(X_train, y_train)))
print("Test set accuracy: {:.3f}".format(tree.score(X_test, y_test)))

dtree = tree.predict(x)
dtree

خروجی:

Python
array([  875.,  1792., 27754., 28256.,  4438.,  2102.,  8520.,   500.,
       22997., 26517., 15109., 20956.,  3310.,  3197.,  1211., 18005.,
       22854., 10278.,   739.,  3724.,  4733.,   971.,  6263., 24677.,
...
        8113.,  3166.,  5332.,  2232., 21989.,  5360.,  5837.,  2509.,
        5580.,  5947., 11564.,  5888.,  9130., 16105.,  1593.,  4448.,
       12771., 28511.,  6883.])

percentageerror_tree=((y-dtree)/dtree)*100
percentageerror_tree
np.mean(percentageerror_tree)

pip3 install graphviz
Python
from sklearn.tree import export_graphviz
export_graphviz(tree,out_file="tree.dot")

import graphviz
with open("tree.dot") as f:
    dot_graph = f.read()

graphviz.Source(dot_graph)
dot -Tpdf tree.dot -o tree.pdf