import numpy
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn import tree
from sklearn.model_selection import train_test_split
filename = 'diabetes.csv'
raw_data = open(filename, 'rt')
data = numpy.loadtxt(raw_data, delimiter=",", skiprows=1)
print(data.shape)

X = data[:,0:8] #identify columns as data sets
Y = data[:, 9] #identfy last column as target
print(X)
print(Y)
X_train, X_test, Y_train, Y_test = train_test_split(
X, Y, test_size=0.25)
treeClassifier = DecisionTreeClassifier(max_depth=5)
treeClassifier.fit(X_train, Y_train)
with open("treeClassifier.txt", "w") as f:
 f = tree.export_graphviz(treeClassifier, out_file=f)

(768, 10)
[[  6.    148.     72.    ...  33.6     0.627  50.   ]
[  1.     85.     66.    ...  26.6     0.351  31.   ]
[  8.    183.     64.    ...  23.3     0.672  32.   ]
 ...
[  5.    121.     72.    ...  26.2     0.245  30.   ]
[  1.    126.     60.    ...  30.1     0.349  47.   ]
[  1.     93.     70.    ...  30.4     0.315  23.   ]]
[1. 0. 1. 0. 1. 0. 1. 0. 1. 1. 0. 1. 0. 1. 1. 1. 1. 1. 0. 1. 0. 0. 1. 1.
 1. 1. 1. 0. 0. 0. 0. 1. 0. 0. 0. 0. 0. 1. 1. 1. 0. 0. 0. 1. 0. 1. 0. 0.
 1. 0. 0. 0. 0. 1. 0. 0. 1. 0. 0. 0. 0. 1. 0. 0. 1. 0. 1. 0. 0. 0. 1. 0.
 1. 0. 0. 0. 0. 0. 1. 0. 0. 0. 0. 0. 1. 0. 0. 0. 1. 0. 0. 0. 0. 1. 0. 0.
 0. 0. 0. 1. 1. 0. 0. 0. 0. 0. 0. 0. 0. 1. 1. 1. 0. 0. 1. 1. 1. 0. 0. 0.
 1. 0. 0. 0. 1. 1. 0. 0. 1. 1. 1. 1. 1. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1.
 0. 0. 0. 0. 0. 0. 0. 0. 1. 0. 1. 1. 0. 0. 0. 1. 0. 0. 0. 0. 1. 1. 0. 0.
 0. 0. 1. 1. 0. 0. 0. 1. 0. 1. 0. 1. 0. 0. 0. 0. 0. 1. 1. 1. 1. 1. 0. 0.
 1. 1. 0. 1. 0. 1. 1. 1. 0. 0. 0. 0. 0. 0. 1. 1. 0. 1. 0. 0. 0. 1. 1. 1.
 1. 0. 1. 1. 1. 1. 0. 0. 0. 0. 0. 1. 0. 0. 1. 1. 0. 0. 0. 1. 1. 1. 1. 0.
 0. 0. 1. 1. 0. 1. 0. 0. 0. 0. 0. 0. 0. 0. 1. 1. 0. 0. 0. 1. 0. 1. 0. 0.
 1. 0. 1. 0. 0. 1. 1. 0. 0. 0. 0. 0. 1. 0. 0. 0. 1. 0. 0. 1. 1. 0. 0. 1.
 0. 0. 0. 1. 1. 1. 0. 0. 1. 0. 1. 0. 1. 1. 0. 1. 0. 0. 1. 0. 1. 1. 0. 0.
 1. 0. 1. 0. 0. 1. 0. 1. 0. 1. 1. 1. 0. 0. 1. 0. 1. 0. 0. 0. 1. 0. 0. 0.
 0. 1. 1. 1. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1. 0. 0. 0. 0. 0. 1. 1. 1. 0. 1.
 1. 0. 0. 1. 0. 0. 1. 0. 0. 1. 1. 0. 0. 0. 0. 1. 0. 0. 1. 0. 0. 0. 0. 0.
 0. 0. 1. 1. 1. 0. 0. 1. 0. 0. 1. 0. 0. 1. 0. 1. 1. 0. 1. 0. 1. 0. 1. 0.
 1. 1. 0. 0. 0. 0. 1. 1. 0. 1. 0. 1. 0. 0. 0. 0. 1. 1. 0. 1. 0. 1. 0. 0.
 0. 0. 0. 1. 0. 0. 0. 0. 1. 0. 0. 1. 1. 1. 0. 0. 1. 0. 0. 1. 0. 0. 0. 1.
 0. 0. 1. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1. 0. 0. 0. 0. 0. 0. 0. 1. 0. 0. 0.
 1. 0. 0. 0. 1. 1. 0. 0. 0. 0. 0. 0. 0. 1. 0. 0. 0. 0. 1. 0. 0. 0. 1. 0.
 0. 0. 1. 0. 0. 0. 1. 0. 0. 0. 0. 1. 1. 0. 0. 0. 0. 0. 0. 1. 0. 0. 0. 0.
 0. 0. 0. 0. 0. 0. 0. 1. 0. 0. 0. 1. 1. 1. 1. 0. 0. 1. 1. 0. 0. 0. 0. 0.
 0. 0. 0. 0. 0. 0. 0. 0. 1. 1. 0. 0. 0. 0. 0. 0. 0. 1. 0. 0. 0. 0. 0. 0.
 0. 1. 0. 1. 1. 0. 0. 0. 1. 0. 1. 0. 1. 0. 1. 0. 1. 0. 0. 1. 0. 0. 1. 0.
 0. 0. 0. 1. 1. 0. 1. 0. 0. 0. 0. 1. 1. 0. 1. 0. 0. 0. 1. 1. 0. 0. 0. 0.
 0. 0. 0. 0. 0. 0. 1. 0. 0. 0. 0. 1. 0. 0. 1. 0. 0. 0. 1. 0. 0. 0. 1. 1.
 1. 0. 0. 0. 0. 0. 0. 1. 0. 0. 0. 1. 0. 1. 1. 1. 1. 0. 1. 1. 0. 0. 0. 0.
 0. 0. 0. 1. 1. 0. 1. 0. 0. 1. 0. 1. 0. 0. 0. 0. 0. 1. 0. 1. 0. 1. 0. 1.
 1. 0. 0. 0. 0. 1. 1. 0. 0. 0. 1. 0. 1. 1. 0. 0. 1. 0. 0. 1. 1. 0. 0. 1.
 0. 0. 1. 0. 0. 0. 0. 0. 0. 0. 1. 1. 1. 0. 0. 0. 0. 0. 0. 1. 1. 0. 0. 1.
 0. 0. 1. 0. 1. 1. 1. 0. 0. 1. 1. 1. 0. 1. 0. 1. 0. 1. 0. 0. 0. 0. 1. 0.]

tree.export_graphviz(treeClassifier, out_file=f)

tree.export_graphviz(treeClassifier, class_names=['0', '1'], out_file=f)

import graphviz
import numpy as np
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree
from sklearn.model_selection import train_test_split

np.random.seed(42)
X = np.random.random((100, 8))
Y = np.random.randint(2, size=100)
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25)
tree_classifier = DecisionTreeClassifier(max_depth=5)
tree_classifier.fit(X_train, Y_train)

dot_data = tree.export_graphviz(tree_classifier, class_names=['0', '1'], out_file=None)
graph = graphviz.Source(dot_data)
graph

tree.export_graphviz(treeClassifier, class_names=['0', '1'],
                     filled=True, rounded=True, out_file=f)