机器学习sklearn利用GridSearchCV进行超参数优化后的SVM分类

# -*- coding: utf-8 -*-
'''
SVM分类:最优超参数GridSearchCV优化后的SVM分类
'''

import numpy as np
import sklearn.model_selection as ms
import sklearn.svm as svm
import sklearn.metrics as sm
import matplotlib.pyplot as plt

'''***************************数据集：start************************************'''
x, y = [], []
with open('multiple2.txt', 'r') as f:
    for line in f.readlines():
        data = [float(substr) for substr in line.split(',')]
        x.append(data[:-1])
        y.append(data[-1])
x = np.array(x)
y = np.array(y, dtype=int)
train_x, test_x, train_y, test_y = ms.train_test_split(x, y, test_size=0.25, random_state=7)
'''***************************数据集：end**************************************'''



'''***************************超参数优化及GridSearchCV属性：start*******************************'''
# 最优超参数组合列表
params = [
        {'kernel': ['linear'], 'C': [1, 10, 100, 100]},
        {'kernel': ['poly'], 'C': [1], 'degree': [2, 3]},
        {'kernel': ['rbf'], 'C': [1, 10, 100, 100], 'gamma':[1, 0.1, 0.01, 0.001]}
        ]

model = ms.GridSearchCV(svm.SVC(probability=True), 
                        params, 
                        refit=True,
                        return_train_score=True,        # 后续版本需要指定True才有score方法  
                        cv=5)
model.fit(train_x, train_y)

# GridSearchCV的属性
print('Attrabutes:vvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvv')
print('cv_results_:',model.cv_results_.keys())
print('Desc:',model.cv_results_['params'][2], model.cv_results_['mean_train_score'][2], 
      model.cv_results_['mean_test_score'][2],model.cv_results_['rank_test_score'][2])
print('best_estimator_:',model.best_estimator_) 
print('best_params_:',model.best_params_) 
print('best_params_:', model.cv_results_['params'][model.best_index_])
print('best_score_:',model.best_score_)
print('scorer_:',model.scorer_)
print('n_splits_:',model.n_splits_)
'''
        #   params                       mean_train_score    mean_test_score      rank_test_score
        # {'C': 100, 'kernel': 'linear'} 0.6877777777777778  0.6577777777777778   17

        # cv_results_: 类似如下output
        # |         {'param_kernel': masked_array(data = ['poly', 'poly', 'rbf', 'rbf'],
        # |                                       mask = [False False False False]...)
        # |          'param_gamma': masked_array(data = [-- -- 0.1 0.2],
        # |                                      mask = [ True  True False False]...),
        # |          'param_degree': masked_array(data = [2.0 3.0 -- --],
        # |                                       mask = [False False  True  True]...),
        # |          'split0_test_score'  : [0.8, 0.7, 0.8, 0.9],
        # |          'split1_test_score'  : [0.82, 0.5, 0.7, 0.78],
        # |          'mean_test_score'    : [0.81, 0.60, 0.75, 0.82],
        # |          'std_test_score'     : [0.02, 0.01, 0.03, 0.03],
        # |          'rank_test_score'    : [2, 4, 3, 1],
        # |          'split0_train_score' : [0.8, 0.9, 0.7],
        # |          'split1_train_score' : [0.82, 0.5, 0.7],
        # |          'mean_train_score'   : [0.81, 0.7, 0.7],
        # |          'std_train_score'    : [0.03, 0.03, 0.04],
        # |          'mean_fit_time'      : [0.73, 0.63, 0.43, 0.49],
        # |          'std_fit_time'       : [0.01, 0.02, 0.01, 0.01],
        # |          'mean_score_time'    : [0.007, 0.06, 0.04, 0.04],
        # |          'std_score_time'     : [0.001, 0.002, 0.003, 0.005],
        # |          'params'             : [{'kernel': 'poly', 'degree': 2}, ...],
        # |          }

        # best_estimator_: 
        #SVC(C=1, cache_size=200, class_weight=None, coef0=0.0,
        #    decision_function_shape='ovr', degree=3, gamma=1, kernel='rbf',
        #    max_iter=-1, probability=True, random_state=None, shrinking=True,
        #    tol=0.001, verbose=False)

        # model.cv_results_['mean_test_score'] 与 model.cv_results_['params']对应数据的平均值
        for param, score in zip(model.cv_results_['params'],model.cv_results_['mean_test_score']): 
            print(param, score)
            #{'C': 1, 'kernel': 'linear'} 0.6577777777777778
            # ...
            #{'C': 1, 'gamma': 1, 'kernel': 'rbf'} 0.9511111111111111
            # ...
'''
'''***************************超参数优化及GridSearchCV属性：start*******************************'''



'''**************************优化模型的分类预测：start**************************'''
# 选取最优参数的模型来测试模型
model_best = model.best_estimator_
pred_test_y = model_best.predict(test_x)
#print(sm.classification_report(test_y, pred_test_y))

# 已知输入未知输出的待分类数据集
prob_x = np.array([[2, 1.5],[8, 9], [4.8, 5.2], [4,4],[2.5,7],[7.6,2],[5.4, 5.9]])
# 最优模型预测分类
pred_prob_y = model_best.predict(prob_x)
#[1 1 0 0 1 1 0]

# 待分类点分到k类的置信概率
probs = model_best.predict_proba(prob_x)
print(probs)
#  0类的prob         1类的prob
#[[1.03714141e-06 9.99998963e-01]
# [1.08965069e-05 9.99989103e-01]
# [9.87823056e-01 1.21769441e-02]
# [6.04905412e-01 3.95094588e-01]
# [7.29711067e-02 9.27028893e-01]
# [5.77669737e-07 9.99999422e-01]
# [9.71139698e-01 2.88603024e-02]]

# 样本点到分割超平面的函数距离
print(model_best.decision_function(prob_x))  
#[ 0.89437297  0.57872334 -1.12141003 -0.29460761  0.73701418  1.03644923 -1.11770644]
'''**************************优化模型的分类预测：end****************************'''


'''******************************绘图区：start**********************************'''
plt.figure('The Best HyperParametre', facecolor='lightgray')
plt.title('The Best Hyperparametre', fontsize=14)
plt.xlabel('x', fontsize=14)
plt.ylabel('y', fontsize=14)
plt.tick_params(labelsize=10)

# pcolormap
l, r, h = x[:, 0].min() - 1, x[:, 0].max() + 1, 0.005
b, t, v = x[:, 1].min() - 1, x[:, 1].max() + 1, 0.005
grid_x = np.meshgrid(np.arange(l, r, h), np.arange(b, t, v))
flat_x = np.c_[grid_x[0].ravel(), grid_x[1].ravel()]
flat_y = model_best.predict(flat_x)
grid_y = flat_y.reshape(grid_x[0].shape)
plt.pcolormesh(grid_x[0], grid_x[1], grid_y, cmap='gray')

# 已知训练集的分类散点图
c0, c1 = y==0, y==1                                                             # 掩码
plt.scatter(x[c0][:, 0], x[c0][:, 1], c='b', s=30)                              # y=0的点用蓝色点表示
plt.scatter(x[c1][:, 0], x[c1][:, 1], c='r', s=30)                              # y=1的点用红色表示

# 最优模型预测的已知输入未知输出的分类散点图
C0, C1 = pred_prob_y==0, pred_prob_y==1
plt.scatter(prob_x[C0][:, 0], prob_x[C0][:, 1], c='y', s=30, marker='D')        # 预测值为0类的点用黄色表示，
plt.scatter(prob_x[C1][:, 0], prob_x[C1][:, 1], c='purple', s=30, marker='D')   # 预测值为1类的点用紫色表示，

for i in range(len(probs[C0])):
    plt.annotate(
            '{}% {}%'.format(round(probs[C0][:, 0][i],2)*100, round(probs[C0][:, 1][i],2)*100),
            xy=(prob_x[C0][:, 0][i], prob_x[C0][:, 1][i]),                      # 预测为0类的点坐标
            xytext=(12, -12),textcoords='offset points',
            horizontalalignment='left',
            verticalalignment='top',
            fontsize=9,
            bbox={'boxstyle':'round, pad=0.6','fc':'deepskyblue', 'alpha':0.8}) # 框参数设置
for i in range(len(probs[C1])):
    plt.annotate(
            '{}% {}%'.format(round(probs[C1][:, 0][i], 2)*100, round(probs[C1][:, 1][i], 2)*100),
            xy=(prob_x[C1][:, 0][i], prob_x[C1][:, 1][i]),                      # 预测为1类的点坐标
            xytext=(12, -12),textcoords='offset points',
            horizontalalignment='left',
            verticalalignment='top',
            fontsize=9,
            bbox={'boxstyle':'round, pad=0.6','fc':'green', 'alpha':0.4})
plt.show()
'''******************************绘图区：end************************************'''