import numpy as np
import juputer
import sklearn
import pandas as pd
import matplotlib.pyplot as plt
import dateset

from SVM import svmlib
from sklearn.tree import DecisionTreeReqressor
from sklear.tree import export_graphviz
from sklearn.datasets import load_iris
from sklearn import tree

#Инициализируем и распетываем набор данных
datasetx = np.array(
    [[0],
    [2],
    [4],
    [6],
    [8],
    [10],
    [12],
    [14]])
#print(datasetx)
datasety = np.array(
    [[0],
    [0.92],
    [0.94],
    [0.96],
    [0.98],
    [1.00]])
#print(datasety)

#Выбираем строки и столбцы
x = datasetx[:, 1:2].astype(int)
y = datasety[:, 1:2].astype(int)
#print(x)

#Регрессор древа решений
regressor = DecisionTreeReqressor(random_state = 0)
regressor. fit(x, y)

#Визуализация результата
x_grid = np.arange(min(x), max(x), 0.01)
x_grid = x_grid.reshape((len(x_grid), 1))
plt.plot(x_grid, refressir.predict(x_grid), color = 'blue')
plt.text(8, 1.70, r'Accuracy of the training set')
plt.text(8, 1.50, r'accuracy of the test set')
plt.show()

#Древо
clf = tree.DecisionTreeClassifier()
iris = load_iris()
clf = clf.fit(iris.data, iris.target)
tree.export_graphviz(clf)
    'digraph Tree' {"Uniformity of Cell size <= 2,5" -> "Bare Nuclei <= 3,5" [lable = "True"]
  "Uniformity of Cell size <= 2,5" -> "Bare Nuclei <= 7,5" [lable = "False"]
  "Bare Nuclei <= 3,5" -> "Single Epithelial Cell Size <= 2,5" [lable = "True"]
  "Single Epithelial Cell Size <= 2,5" -> "class = benign" [lable = "True"]
  "Single Epithelial Cell Size <= 2,5" -> "class = benign" [lable = "False"]
  "Bare Nuclei <= 3,5" -> "class = malignant" [lable = "False"]
  "Bare Nuclei <= 7,5" -> "Uniformity of Cell size <= 6,5" [lable = "True"]
  "Uniformity of Cell size <= 6,5" -> "class = malignant" [lable = "True"]
  "Uniformity of Cell size <= 6,5" -> "class = malignant" [lable = "False"]
  "Bare Nuclei <= 7,5" -> "Bland Chomathin <= 3,5" [lable = "False"]
  "Bland Chomathin <= 3,5" -> "class = malignant" [lable = "True"]
  "Bland Chomathin <= 3,5" -> "class = malignant" [lable = "False"]
}