【机器学习 sklearn】XGBclassifier 超参数寻优

代码片段

# encoding: utf-8import sysreload(sys)sys.setdefaultencoding('utf-8')import pandas as pdtrain = pd.read_csv('train.csv')test = pd.read_csv('test.csv')# print train.info()# print test.info()selected_features = ['Pclass', 'Sex', 'Age', 'Embarked', 'SibSp', 'Parch','Fare']X_train = train[selected_features]X_test = test[selected_features]y_train = train['Survived']#############缺失值处理#########print X_train['Embarked'].value_counts()print X_test['Embarked'].value_counts()X_train['Embarked'].fillna('S', inplace=True)X_test['Embarked'].fillna('S', inplace=True)X_train['Age'].fillna(X_train['Age'].mean(), inplace=True)X_test['Age'].fillna(X_test['Age'].mean(), inplace=True)X_test['Fare'].fillna(X_test['Fare'].mean(), inplace=True)###检查# print X_train.info()# print X_test.info()#####特征向量化############from sklearn.feature_extraction import DictVectorizerdict_vec = DictVectorizer(sparse=False)###########归一化和标准化#################X_train = dict_vec.fit_transform(X_train.to_dict(orient='record'))X_test = dict_vec.transform(X_test.to_dict(orient='record'))from sklearn.ensemble import RandomForestClassifierrfc = RandomForestClassifier()from xgboost import XGBClassifierxgbc = XGBClassifier()from sklearn.model_selection import cross_val_scoreprint cross_val_score(rfc, X_train, y_train, cv=5).mean()cross_val_score(xgbc, X_train, y_train, cv=5).mean()rfc.fit(X_train,y_train)rfc_y_predict = rfc.predict(X_test)rfc_submission = pd.DataFrame({'PassengerId': test['PassengerId'], 'Survived': rfc_y_predict})# rfc_submission.to_csv('rfc_submission.csv', index=False)xgbc.fit(X_train, y_train)xgbc_y_predict = xgbc.predict(X_test)xgbc_submission = pd.DataFrame({'PassengerId': test['PassengerId'], 'Survived': xgbc_y_predict})# xgbc_submission.to_csv('xgbc_submission.csv', index=False)from sklearn.grid_search import GridSearchCVparams = {'max_depth':range(2, 7), 'n_estimators':range(100, 1100, 200), 'learning_rate':[0.05, 0.1, 0.25, 0.5, 1.0]}xgbc_best = XGBClassifier()gs = GridSearchCV(xgbc_best, params, n_jobs=-1, cv=5, verbose=1)gs.fit(X_train, y_train)print gs.best_score_print gs.best_params_xgbc_best_y_predict = gs.predict(X_test)xgbc_best_submission = pd.DataFrame({'PassengerId': test['PassengerId'], 'Survived': xgbc_best_y_predict})#xgbc_best_submission.to_csv('xgbc_best_submission.csv', index=False)