# -*- coding: utf-8 -*-

 """

 Created on Sat Sep  1 11:54:48 2018

 @author: zhen

     交叉验证

 """

 import numpy as np

 from sklearn import datasets

 from sklearn.linear_model import LogisticRegression

 from sklearn.model_selection import GridSearchCV

 import matplotlib.pyplot as plt

 iris = datasets.load_iris()

 x = iris['data'][:, 3:]

 y = iris['target']

 def report(results, n_top=3):

     for i in range(1, n_top + 1):

         candidates = np.flatnonzero(results['rank_test_score'] == i)

         for candidate in candidates:

             print("Model with rank: {0}".format(i))

             print("Mean validation score: {0:.3f} (std: {1:.3f})".format(

                    results['mean_test_score'][candidate],

                    results['std_test_score'][candidate]))

             print("Parameters: {0}".format(results['params'][candidate]))

             print("")

 param_grid = {"tol":[1e-4, 1e-3,1e-2], "C":[0.4, 0.6, 0.8]}

 log_reg = LogisticRegression(multi_class='ovr', solver='sag')

 # 采用3折交叉验证

 grid_search = GridSearchCV(log_reg, param_grid=param_grid, cv=3)

 grid_search.fit(x, y)

 report(grid_search.cv_results_)

 x_new = np.linspace(0, 3, 1000).reshape(-1, 1)

 y_proba = grid_search.predict_proba(x_new)

 y_hat = grid_search.predict(x_new)

 plt.plot(x_new, y_proba[:, 2], 'g-', label='Iris-Virginica')

 plt.plot(x_new, y_proba[:, 1], 'r-', label='Iris-Versicolour')

 plt.plot(x_new, y_proba[:, 0], 'b-', label='Iris-Setosa')

 plt.show()

 print(grid_search.predict([[1.7], [1.5]]))