decision_tree_pruning

from sklearn import tree
import matplotlib.pyplot as plt
import numpy as np
import ipdb

X = np.random.random([500,2])
Y = []
for x_value in X:
    y_value = 0
    if (x_value[0] > 0.5) and (x_value[1] > 0.5):  # AND "logic"
        y_value = 1

    #parte aleatória
    if np.random.random() > 0.9:
        y_value = not y_value

    Y.append(y_value)

Y = np.array(Y)

X_array = np.asarray(X)

#plt.scatter(np.asarray(X[:,0]),X[:,1],c=Y,cmap='hsv')
#plt.show()

feature_names = ['x1','x2']
target_names = ['falso','verdadeiro']

clf = tree.DecisionTreeClassifier()
#clf = tree.DecisionTreeClassifier(max_depth=2)
#clf = tree.DecisionTreeClassifier(min_samples_split=200)
#clf = tree.DecisionTreeClassifier(min_samples_leaf=100)
#clf = tree.DecisionTreeClassifier(min_impurity_decrease=0.01)

clf = clf.fit(X, Y)



# exportando de forma gráfica
import graphviz
dot_data = tree.export_graphviz(clf, out_file=None, filled=False, rounded=True, impurity=True,
class_names=target_names,
                                feature_names=feature_names
)

graph = graphviz.Source(dot_data)
graph.render("graph")

# exportando de formato texto
r = tree.export_text(clf)
print('\n'+r)