数据来源：

参考文献：《机器学习Python实战》魏贞原

博文目的：复习

工具：Geany

#导入类库

from pandas import read_csv                                    #读数据

from pandas.plotting import scatter_matrix            #画散点图from pandas import set_option                                #设置打印数据精确度import numpy as npimport matplotlib.pyplot as plt                                #画图from sklearn.preprocessing import Normalizer            #数据预处理：归一化from sklearn.preprocessing import StandardScaler     #数据预处理：正态化

from sklearn.preprocessing import MinMaxScaler      #数据预处理：调整数据尺度

from sklearn.model_selection import train_test_split        #分离数据集from sklearn.model_selection import cross_val_score       #计算算法准确度from sklearn.model_selection import KFold                        #交叉验证from sklearn.model_selection import GridSearchCV        #机器学习算法的参数优化方法：网格优化法from sklearn.linear_model import LinearRegression        #线性回归from sklearn.linear_model import Lasso                           #套索回归from sklearn.linear_model import ElasticNet                    #弹性网络回归from sklearn.linear_model import LogisticRegression     #逻辑回归算法from sklearn.discriminant_analysis import LinearDiscriminantAnalysis            #线性判别分析from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis      #二次判别分析from sklearn.tree import DecisionTreeRegressor        #决策树回归                                       from sklearn.tree import DecisionTreeClassifier         #决策树分类from sklearn.neighbors import KNeighborsRegressor    #KNN回归

from sklearn.neighbors import KNeighborsClassifier        #KNN分类

from sklearn.naive_bayes import GaussianNB    #贝叶斯分类器from sklearn.svm import SVR    #支持向量机 回归from sklearn.svm import SVC    #支持向量机 分类from sklearn.pipeline import Pipeline    #pipeline能够将从数据转换到评估模型的整个机器学习流程进行自动化处理from sklearn.ensemble import RandomForestRegressor        #随即森林回归from sklearn.ensemble import RandomForestClassifier        #随即森林分类from sklearn.ensemble import GradientBoostingRegressor    #随即梯度上升回归from sklearn.ensemble import GradientBoostingClassifier    #随机梯度上分类from sklearn.ensemble import ExtraTreesRegressor        #极端树回归from sklearn.ensemble import ExtraTreesClassifier        #极端树分类from sklearn.ensemble import AdaBoostRegressor        #AdaBoost回归from sklearn.ensemble import AdaBoostClassifier        #AdaBoost分类

from sklearn.metrics import mean_squared_error        #

from sklearn.metrics import accuracy_score                #分类准确率

from sklearn.metrics import confusion_matrix        #混淆矩阵

from sklearn.metrics import classification_report    #分类报告

#导入数据

filename = 'wine.csv'data = read_csv(filename, header=None, delimiter=',')#数据理解print(data.shape)#print(data.dtypes)#print(data.corr(method='pearson'))#print(data.describe())#print(data.groupby(0).size())

#数据可视化:直方图、散点图、密度图、关系矩阵图

#直方图

#data.hist()

#plt.show()

#密度图

#data.plot(kind='density', subplots=True, layout=(4,4), sharex=False, sharey=False)

#plt.show()

#散点图

#scatter_matrix(data)

#plt.show()

#关系矩阵图

#fig = plt.figure()

#ax = fig.add_subplot(111)#cax = ax.matshow(data.corr(), vmin=-1, vmax=1)#fig.colorbar(cax)#plt.show()

#数据处理：调整数据尺度、归一化、正态化、二值化

array = data.valuesX = array[:, 1:14].astype(float)Y = array[:,0]scaler = MinMaxScaler(feature_range=(0,1)).fit(X)X_m = scaler.transform(X)scaler = Normalizer().fit(X)X_n = scaler.transform(X)scaler = StandardScaler().fit(X)X_s = scaler.transform(X)#分离数据集validation_size = 0.2seed = 7X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=validation_size, random_state=seed)X_m_train, X_m_test, Y_m_train, Y_m_test = train_test_split(X, Y, test_size=validation_size, random_state=seed)X_n_train, X_n_test, Y_n_train, Y_n_test = train_test_split(X, Y, test_size=validation_size, random_state=seed)X_s_train, X_s_test, Y_s_train, Y_s_test = train_test_split(X, Y, test_size=validation_size, random_state=seed)#选择模型：(本例是一个分类问题)#非线性：KNN, SVC, CART, GaussianNB,#线性：KNN, SVR, LR, Lasso, ElasticNet,  LDA, models = {}models['KNN'] = KNeighborsClassifier()models['SVM'] = SVC()models['CART'] = DecisionTreeClassifier()models['GN'] = GaussianNB()#models['LR'] = LinearRegression()#models['Lasso'] = Lasso()#models['EN'] = ElasticNet()models['LDA'] = LinearDiscriminantAnalysis()models['QDA'] = QuadraticDiscriminantAnalysis()#评估模型scoring = 'accuracy'num_folds = 10seed = 7results = []for key in models:    kfold = KFold(n_splits=num_folds, random_state=seed)    cv_results =cross_val_score(models[key], X_train, Y_train, scoring=scoring, cv=kfold)    results.append(cv_results)    print('%s %f(%f)'%(key, cv_results.mean(), cv_results.std()))results_m = []for key in models:    kfold = KFold(n_splits=num_folds, random_state=seed)    cv_results_m =cross_val_score(models[key], X_m_train, Y_m_train, scoring=scoring, cv=kfold)    results_m.append(cv_results_m)    print('调整数据尺度：%s %f(%f)'%(key, cv_results_m.mean(), cv_results_m.std()))results_n = []for key in models:    kfold = KFold(n_splits=num_folds, random_state=seed)    cv_results_n =cross_val_score(models[key], X_n_train, Y_n_train, scoring=scoring, cv=kfold)    results_n.append(cv_results_n)    print('归一化数据：%s %f(%f)'%(key, cv_results_n.mean(), cv_results_n.std()))    results_s = []for key in models:    kfold = KFold(n_splits=num_folds, random_state=seed)    cv_results_s =cross_val_score(models[key], X_s_train, Y_s_train, scoring=scoring, cv=kfold)    results_s.append(cv_results_s)    print('正态化数据：%s %f(%f)'%(key, cv_results_s.mean(), cv_results_s.std()))

#箱线图

#fig = plt.figure()#ax = fig.add_subplot(111)#fig.suptitle('Algorithm Comparison')#plt.boxplot(results)#ax.set_xticklabels(models.keys())#plt.show()#算法优化：LDA

#调参改善算法LinearDiscriminantAnalysis

param_grid = {'solver':['svd', 'lsqr', 'eigen']}

model = LinearDiscriminantAnalysis()kfold = KFold(n_splits=num_folds, random_state=seed)grid = GridSearchCV(estimator=model, param_grid=param_grid, scoring=scoring, cv=kfold)grid_result = grid.fit(X=X_train, y=Y_train)print('最优：%s 使用：%s'%(grid_result.best_score_, grid_result.best_params_))cv_results = zip(grid_result.cv_results_['mean_test_score'], grid_result.cv_results_['std_test_score'], grid_result.cv_results_['params'])for mean, std, params in cv_results:    print('%f(%f) with %r'%(mean, std, params))#算法集成#bagging: 随机森林，极限树；#boosting：ada， 随机梯度上升ensembles = {}ensembles['RF'] = RandomForestClassifier()ensembles['ET'] = ExtraTreesClassifier()ensembles['ADA'] = AdaBoostClassifier()ensembles['GBM'] = GradientBoostingClassifier()results = []for key in ensembles:    kfold = KFold(n_splits=num_folds, random_state=seed)    cv_results =cross_val_score(ensembles[key], X_train, Y_train, scoring=scoring, cv=kfold)    results.append(cv_results)    print('%s %f(%f)'%(key, cv_results.mean(), cv_results.std()))#集成算法调参gbmparam_grid = {'n_estimators':[10,50,100,200,300,400,500,600,700,800,900]}model = GradientBoostingClassifier()kfold = KFold(n_splits=num_folds, random_state=seed)grid = GridSearchCV(estimator=model, param_grid=param_grid, cv=kfold, scoring=scoring)grid_result = grid.fit(X=X_train, y=Y_train)print('最优：%s 使用：%s'%(grid_result.best_score_, grid_result.best_params_))cv_results = zip(grid_result.cv_results_['mean_test_score'], grid_result.cv_results_['std_test_score'], grid_result.cv_results_['params'])for mean, std, params in cv_results:    print('%f(%f) with %r'%(mean, std, params))#训练最终模型model = LinearDiscriminantAnalysis(solver='svd')model.fit(X=X_train, y=Y_train)#评估最终模型predictions = model.predict(X_test)print(accuracy_score(Y_test, predictions))print(confusion_matrix(Y_test, predictions))print(classification_report(Y_test, predictions))