机器学习测试笔记（29）——找到最佳模型及参数

顾翔

发布于 2021-03-03 07:24:12

48400

代码可运行

文章被收录于专栏：啄木鸟软件测试啄木鸟软件测试

运行总次数：0

代码可运行

顾老师新书《全栈软件测试工程师宝典》

https://item.m.jd.com/product/10023427978355.html

以前两本书的网上购买地址：

《软件测试技术实战设计、工具及管理》：

https://item.jd.com/34295655089.html

《基于Django的电子商务网站》：

https://item.jd.com/12082665.html

1构造函数

from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
class Better:
def __init__(self,data):
              self.n_jobs = 2
              self.data = data
              self.prams=[{'reg':[LinearRegression()],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__n_jobs":[self.n_jobs]},
                               {'reg':[LogisticRegression()],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__n_jobs":[self.n_jobs]},
                               {'reg':[Ridge()],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__alpha":[1,0.1,0.001,0.0001]},
                               {'reg':[Lasso()],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__alpha":[1,0.1,0.001,0.0001]},
                                {'reg':[ElasticNet()],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__alpha":[0.1,0.5,1,5,10],"reg__l1_ratio":[0.1,0.5,0.9]},
                               {'reg':[RandomForestClassifier()],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__n_estimators":[4,5,6,7],"reg__random_state":[2,3,4,5],"reg__n_jobs":[self.n_jobs],"reg__random_state":[range(0,200)]},
                               {'reg':[RandomForestRegressor()],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__n_estimators":[4,5,6,7],"reg__random_state":[2,3,4,5],"reg__n_jobs":[self.n_jobs],"reg__random_state":[range(0,200)]},
                               {'reg':[DecisionTreeClassifier()],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__max_depth":[1,3,5,7],"reg__random_state":[range(1,200)]},
                               {'reg':[DecisionTreeRegressor()],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__max_depth":[1,3,5,7],"reg__random_state":[range(1,200)]},
                               {'reg':[KNeighborsClassifier()],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__n_jobs":[self.n_jobs]},
                               {'reg':[KNeighborsRegressor()],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__n_jobs":[self.n_jobs]},
                               {'reg':[BernoulliNB()],'scaler':[StandardScaler(),MinMaxScaler(),None]},
                               {'reg':[GaussianNB()],'scaler':[StandardScaler(),MinMaxScaler(),None]},
                               {'reg':[MultinomialNB()],'scaler':[MinMaxScaler()]},
                               {'reg':[SVC(max_iter=10000)],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__kernel":["linear","rbf","sigmoid","poly"],"reg__gamma":[0.01,0.1,1,5,10],"reg__C":[1.0,3.0,5.0]},
                               {'reg':[SVR(max_iter=100000)],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__kernel":["linear","rbf","sigmoid","poly"],"reg__gamma":[0.01,0.1,1,5,10],"reg__C":[1.0,3.0,5.0]},
                               {'reg':[LinearSVC(max_iter=100000)],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__C":[1.0,3.0,5.0]},
                               {'reg':[LinearSVR(max_iter=100000)],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__C":[1.0,3.0,5.0]},
                               {'reg':[AdaBoostClassifier()],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__random_state":[range(1,200)]},
                               {'reg':[AdaBoostRegressor()],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__random_state":[range(1,200)]},
                               {'reg':[VotingClassifier(estimators=[('log_clf',LogisticRegression()),('svm_clf', SVC(probability=True)),('dt_clf',DecisionTreeClassifier(random_state=666))])],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__voting":["hard","soft"],"reg__n_jobs":[self.n_jobs]},
                               {'reg':[LinearDiscriminantAnalysis(n_components=2)],'scaler':[StandardScaler(),MinMaxScaler(),None]},
                               {'reg':[MLPClassifier(max_iter=100000)],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__activation":["relu","tanh","identity","logistic"],"reg__alpha":[0.0001,0.001,0.01,1],"reg__hidden_layer_sizes":[(1),(50,),(100,),(1,1),(50,50),(100,100)]},
                               {'reg':[MLPRegressor(max_iter=100000)],'scaler':[StandardScaler(),MinMaxScaler(),None],"reg__activation":["relu","tanh","identity","logistic"],"reg__alpha":[0.0001,0.001,0.01,1],"reg__hidden_layer_sizes":[(1),(50,),(100,),(1,1),(50,50),(100,100)]}

2 找到最佳模型及参数

def Get_Better_Algorithm_and_Parameter(self):
              warnings.filterwarnings("ignore")
if self.data =="iris":
                     random_state= 40
              elif self.data =="wine":
                     random_state= 23
              elif self.data =="breast_cancer":
                     random_state= 41
              elif self.data =="diabetes":
                     random_state= 80
              elif self.data =="boston":
                     random_state= 67
else:
                     random_state= 0
              ML =Machine_Learn()
              X,y =ML.get_data(self.data)
              X_train, X_test,y_train, y_test = train_test_split(X, y,random_state=random_state)
              pipe =Pipeline([('scaler',StandardScaler()),('reg',LinearRegression())])
              shuffle_split =ShuffleSplit(test_size=.2,train_size=.7,n_splits=10)
              grid =GridSearchCV(pipe,self.prams,cv=shuffle_split)
              grid.fit(X_train,y_train)
print("最佳模型是：{}".format(grid.best_params_))
print("模型最佳训练得分：{:.2%}".format(grid.best_score_))
print("模型最佳测试得分：{:.2%}".format(grid.score(X_test,y_test)))

3 调用

better =Better("iris")
better.Get_Better_Algorithm_and_Parameter()

输出

最佳模型是：{'reg': MLPClassifier(alpha=1,hidden_layer_sizes=(100, 100), max_iter=100000), 'reg__activation': 'relu','reg__alpha': 1, 'reg__hidden_layer_sizes': (100, 100), 'scaler':MinMaxScaler()}
模型最佳训练得分：78.70%
模型最佳测试得分：84.21%