zoukankan      html  css  js  c++  java
  • xgboost 简单测试



    #
    coding=utf8 import pandas as pd from sklearn.model_selection import train_test_split from sklearn.feature_extraction import DictVectorizer from xgboost import XGBClassifier titanic = pd.read_csv('./DataSets/Titanic/train.csv') X = titanic[['Pclass', 'Age', 'Sex']] y = titanic['Survived']
    X[
    'Age'].fillna(X['Age'].mean(), inplace=True) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=33) vec = DictVectorizer(separator=False) X_train = vec.fit_transform(X_train.to_dict(orient='record')) #print X_train.to_dict(orient='record') X_test = vec.transform(X_test.to_dict(orient='record')) xgbc = XGBClassifier() xgbc.fit(X_train, y_train) print 'The accuracy of eXtreme Gradient Boosting Classifier on testing set:', xgbc.score(X_test, y_test)

    #coding=utf8
    
    import pandas as pd
    from sklearn.model_selection import train_test_split
    from sklearn.feature_extraction import DictVectorizer
    from xgboost import XGBClassifier
    from sklearn.model_selection import GridSearchCV
    titanic = pd.read_csv('./DataSets/Titanic/train.csv')
    X = titanic[['Pclass', 'Age', 'Sex']]
    y = titanic['Survived']
    
    X['Age'].fillna(X['Age'].mean(), inplace=True)
    
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=33)
    vec = DictVectorizer(separator=False)
    X_train = vec.fit_transform(X_train.to_dict(orient='record'))
    #print X_train.to_dict(orient='record')
    X_test = vec.transform(X_test.to_dict(orient='record'))
    xgbc = XGBClassifier()
    
    params = {'max_depth':range(2, 7), 'n_estimators':range(100, 1100, 200), 'learning_rate':[0.05, 0.1, 0.25, 0.5, 1.0]}
    gs = GridSearchCV(xgbc, params, n_jobs=-1, cv=5, verbose=1)
    gs.fit(X_train, y_train)
    #print 'The accuracy of eXtreme Gradient Boosting Classifier on testing set:', gs.score(X_test, y_test)
    
    print gs.best_score_
    print gs.best_params_

  • 相关阅读:
    MySQL表行数查询最佳实践
    mysqldump备份表中有大字段失败的排错过程
    μC/OSⅡ在C8051F060上的移植及其应用
    OSSchedLock()函数透析
    32位与64位区别
    【Cesium】Animation显示系统时间
    【Cesium】根据经纬度计算距离
    【Cesium】 鼠标拾取椭球、地形、模型坐标点(经度+纬度+高程)
    【Python学习】Selenium模拟浏览器抓取数据
    【Cesium】polygon中的height和extrudedHeight的区别
  • 原文地址:https://www.cnblogs.com/TMatrix52/p/7686536.html
Copyright © 2011-2022 走看看