? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?決策樹結合網格搜索交叉驗證

如下是常見的模型評估的指標定義及決策樹結合網格搜索交叉驗證的例子。詳見下文：

混淆矩陣：

準確率:

精準率（預測為正樣本真實也是正例的比值，又稱為查準率）:

召回率(真實為正例的樣本中預測為正例的比值，又稱為查全率)：

F1 Socre （反映模型的穩健型):

###as_matrix import pandas as pd from sklearn import tree from sklearn.tree import export_graphviz import graphvizdef decisontreeSimple():filename= '../input/sales_data.xls'data = pd.read_excel(filename,index_col=u'序號')##print(data)data[data == u'好'] = 1data[data==u'是'] = 1data[data==u'高'] = 1data[data!=1] = -1x= data.iloc[:,:3].values.astype(int)y= data.iloc[:,3].values.astype(int)import sklearn.model_selection as cross_validationtrain_data, test_data, train_target, test_target = cross_validation.train_test_split(x, y, test_size=0.3,train_size=0.7,random_state=67897) # 劃分訓練集和測試集from sklearn.tree import DecisionTreeClassifier as DTCdtc = DTC(criterion='entropy')dtc.fit(train_data, train_target)'''train_est = dtc.predict(train_data) # 用模型預測訓練集的結果train_est_p = dtc.predict_proba(train_data)[:, 1] # 用模型預測訓練集的概率test_est = dtc.predict(test_data) # 用模型預測測試集的結果test_est_p = dtc.predict_proba(test_data)[:, 1] # 用模型預測測試集的概率res_pd = pd.DataFrame({'test_target': test_target, 'test_est': test_est, 'test_est_p': test_est_p}).T # 查看測試集預測結果與真實結果對比pd.set_option('precision', 2)pd.set_option('max_colwidth', 20)pd.set_option('display.max_columns', 20)print(res_pd)import sklearn.metrics as metricsprint(metrics.confusion_matrix(test_target, test_est, labels=[0, 1])) # 混淆矩陣print(metrics.classification_report(test_target, test_est)) # 計算評估指標print(pd.DataFrame(list(zip(data.columns, dtc.feature_importances_)))) # 變量重要性指標 '''import sklearn.metrics as metricsfrom sklearn.model_selection import GridSearchCVimport matplotlib.pyplot as pltimport sklearn.tree as treeparam_grid = {'criterion': ['entropy','gini'],'max_depth': [3, 4, 5, 6, 7, 8],'min_samples_split': [4,5,6,7,8,9, 12, 16, 20, 24]}clf = tree.DecisionTreeClassifier(criterion='entropy')clfcv = GridSearchCV(estimator=clf, param_grid=param_grid,scoring='roc_auc', cv=4)clfcv.fit(train_data, train_target)# %%# 查看模型預測結果train_est = clfcv.predict(train_data) # 用模型預測訓練集的結果train_est_p = clfcv.predict_proba(train_data)[:, 1] # 用模型預測訓練集的概率test_est = clfcv.predict(test_data) # 用模型預測測試集的結果test_est_p = clfcv.predict_proba(test_data)[:, 1] # 用模型預測測試集的概率# %%fpr_test, tpr_test, th_test = metrics.roc_curve(test_target, test_est_p)fpr_train, tpr_train, th_train = metrics.roc_curve(train_target, train_est_p)plt.figure(figsize=[6, 6])plt.plot(fpr_test, tpr_test, color='blue')plt.plot(fpr_train, tpr_train, color='red')plt.title('ROC curve')plt.show()print(clfcv.best_params_)clf = tree.DecisionTreeClassifier(criterion='entropy', max_depth=3, min_samples_split=6) # 當前支持計算信息增益和GINIclf.fit(train_data, train_target) # 使用訓練數據建模'''from sklearn.tree import export_graphvizfrom sklearn.externals.six import StringIOx = pd.DataFrame(x)print(x)with open("../output/tree.dot",'w') as f:f= export_graphviz(dtc,feature_names=x.columns,out_file=f)'''x = pd.DataFrame(x,columns=[u"weather",u"weekend",u"promotion"])#x = pd.DataFrame(x)dot_data = export_graphviz(dtc,feature_names=x.columns,out_file=None)graph = graphviz.Source(dot_data)''' dot文件里追加中文字體支持,需要手動編輯該文件graph [bb="0,0,712,365"];下面追加edge[fontname = "SimHei"];node[fontname = "SimHei"];'''##graph.render(filename="../output/tree",format="dot",cleanup="False")##直接轉PDF會有亂碼##graph.render(filename="../output/tree",format="pdf",cleanup="False")'''或者直接執行，但是需要先dot配置環境變量'''import osos.system('dot -Tpdf "../output/tree33.dot" -o "../output/tree33.pdf"')'''或者直接執行'''#with open("../output/tree.dot",'w') as f:# f = export_graphviz(dtc,feature_names=x.columns,out_file=f)with open("../output/tree33.dot",'w') as f:f = export_graphviz(clf,feature_names=x.columns,out_file=f)##代碼參考至<<Python機器學習及實踐_從零開始通往KAGGLE競賽之路>> def decisontreeTitanic():##titanic=pd.read_csv('http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt')titanic = pd.read_csv('../input/titanic.txt')print("行數:"+str(titanic.shape[0])+"\t"+"列數:"+str(titanic.shape[1])+"\t"+"行數："+str(len(titanic))+"\t"+"總數:"+str(titanic.size))'''row.names pclass survived name age embarked home.dest room ticket boat sex序號 乘客等級 獲救情況 姓名 年齡 登船港口 目的地 房間號 船票信息 票價 性別'''#print(titanic[:7])#print(titanic.info())X = titanic[['pclass','age','sex']]y = titanic['survived']print(X[X['age'].notnull()]['age'].sum()/X[X['age'].notnull()].shape[0]) #19745.9166/636#X=X['age'].fillna(X['age'].mean(),inplace=True)#cc1 = X['age'].fillna(age_mean, inplace=True)#print(cc1)#X.info()X= X.copy() #要先拷貝，然后再進行fillna操作。X['age'].fillna(X['age'].mean(), inplace=True)print(X[:20])from sklearn.model_selection import train_test_splitX_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.01,random_state=33)print(X_test)from sklearn.feature_extraction import DictVectorizervec = DictVectorizer(sparse=False)##轉換特征后，類別型特征都被剝離出單獨的特征，數值型的保持不變X_train = vec.fit_transform(X_train.to_dict(orient='record'))print(vec.feature_names_)X_test = vec.fit_transform(X_test.to_dict(orient='record'))from sklearn.tree import DecisionTreeClassifierdtc = DecisionTreeClassifier()dtc.fit(X_train,y_train)y_predict = dtc.predict(X_test)#y_pd = pd.concat(pd.DataFrame([X_test]),pd.DataFrame([y_predict]),axis=1)print(y_predict)print(type(y_predict))#import numpy as np#print(np.concatenate((X_test,y_predict),axis=1))X_test_df = pd.DataFrame(X_test)y_predict_df = pd.DataFrame(y_predict)print("################")#print(pd.concat([X_test_df,y_predict_df],axis=0))'''print(X_test.ndim )print(y_predict.ndim)'''''' 如果對所有字段都應用這個規則，可以沿用如下寫法for column in list(X.columns[X.isnull().sum() > 0]):mean_val = X[column].mean()X[column].fillna(mean_val, inplace=True)'''###模型評估from sklearn.metrics import classification_reportprint(dtc.score(X_test,y_test))print(classification_report(y_predict,y_test,target_names=['died','survived']))def irisdt():from sklearn import treefrom sklearn import model_selectionfrom sklearn.datasets import load_iris#from sklearn.grid_search import GridSearchCVfrom sklearn.model_selection import GridSearchCVfrom sklearn.metrics import classification_reportimport matplotlib.pyplot as pltiris = load_iris()x = iris.datay = iris.targetX_train, X_test, y_train, y_test = model_selection \.train_test_split(x, y, test_size=0.2,random_state=123456)parameters = {'criterion': ['gini', 'entropy'],'max_depth': range(1,30),#[1, 2, 3, 4, 5, 6, 7, 8,9,10],'max_leaf_nodes': [2,3,4, 5, 6, 7, 8, 9] #最大葉節點數}dtree = tree.DecisionTreeClassifier()grid_search = GridSearchCV(dtree, parameters, scoring='accuracy', cv=5)grid_search.fit(x, y)print(grid_search.best_estimator_) # 查看grid_search方法print(grid_search.best_score_) # 正確率print(grid_search.best_params_) # 最佳 參數組合dtree = tree.DecisionTreeClassifier(criterion='gini', max_depth=3)dtree.fit(X_train, y_train)pred = dtree.predict(X_test)print(pred)print(y_test)print(classification_report(y_test, pred,target_names=['setosa', 'versicolor', 'virginica']))print(dtree.predict([[6.9,3.3,5.6,2.4]]))#預測屬于哪個分類print(dtree.predict_proba([[6.9,3.3,5.6,2.4]])) # 預測所屬分類的概率值##print(iris.target)print(list(iris.target_names)) #輸出目標值的元素名稱#print(grid_search.estimator.score(y_test, pred))def irisdecisontree():from sklearn import datasetsiris = datasets.load_iris()X_train = iris.data[:,[0,1]][0:150]y_train = iris.target#print(iris.feature_names)#print(type(X_train))##print(X_train[:,[0,1]][0:150])clf = tree.DecisionTreeClassifier(max_depth=3,criterion='entropy')clf = clf.fit(X_train, y_train)with open("../output/iristree.dot",'w') as f:f = export_graphviz(clf,feature_names=['sepallength','sepalwidth'],out_file=f)import osos.system('dot -Tpdf "../output/iristree.dot" -o "../output/iristree.pdf"')def kfolddemo():'''1 shuffle=True結合random_state=整數 等效于shuffle=False 即出來的順序不變2 驗證集和訓練集的比例大于1:8 小于1:2'''from numpy import arrayfrom sklearn.model_selection import KFold# data sampledata = array([0.1, 0.2, 0.3, 0.4, 0.5,0.6,0.7,0.8,0.9])# prepare cross validationkfold = KFold(n_splits=5, shuffle=True)# enumerate splitsfor train, test in kfold.split(data):print('train: %s, test: %s' % (data[train], data[test]))if __name__ == '__main__':##decisontreeSimple()##decisontreeTitanic()##irisdecisontree()irisdt()##kfolddemo()

運行結果：

"D:\Program Files\Python37\python.exe" "E:/Decision tree/decisiontree.py"
DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=3,
? ? ? ? ? ? ? ? ? ? ? ?max_features=None, max_leaf_nodes=6,
? ? ? ? ? ? ? ? ? ? ? ?min_impurity_decrease=0.0, min_impurity_split=None,
? ? ? ? ? ? ? ? ? ? ? ?min_samples_leaf=1, min_samples_split=2,
? ? ? ? ? ? ? ? ? ? ? ?min_weight_fraction_leaf=0.0, presort=False,
? ? ? ? ? ? ? ? ? ? ? ?random_state=None, splitter='best')
0.9733333333333334
{'criterion': 'gini', 'max_depth': 3, 'max_leaf_nodes': 6}
[0 2 0 1 0 0 2 2 2 0 1 2 2 0 0 2 1 2 1 0 1 2 1 1 1 2 2 2 1 1]
[0 2 0 1 0 0 2 2 2 0 1 2 2 0 0 2 1 2 1 0 1 2 1 1 1 2 2 2 2 1]
? ? ? ? ? ? ? precision ? ?recall ?f1-score ? support

? ? ? setosa ? ? ? 1.00 ? ? ?1.00 ? ? ?1.00 ? ? ? ? 8
? versicolor ? ? ? 0.90 ? ? ?1.00 ? ? ?0.95 ? ? ? ? 9
? ?virginica ? ? ? 1.00 ? ? ?0.92 ? ? ?0.96 ? ? ? ?13

? ? accuracy ? ? ? ? ? ? ? ? ? ? ? ? ? 0.97 ? ? ? ?30
? ?macro avg ? ? ? 0.97 ? ? ?0.97 ? ? ?0.97 ? ? ? ?30
weighted avg ? ? ? 0.97 ? ? ?0.97 ? ? ?0.97 ? ? ? ?30

[2]
[[0. 0. 1.]]
['setosa', 'versicolor', 'virginica']

Process finished with exit code 0
?

?

總結

以上是生活随笔為你收集整理的决策树结合网格搜索交叉验证的例子的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。