xgboost实现

def draw_result(filename):    import numpy as np    from scipy import interp    import matplotlib.pyplot as plt    from matplotlib.pyplot import savefig    import xgboost as xgb    from sklearn.cross_validation import train_test_split    from sklearn.cross_validation import cross_val_score    from sklearn import cross_validation    from sklearn.metrics import roc_curve, auc    from sklearn.cross_validation import StratifiedKFold    %pylab inline    matplotlib.style.use('ggplot')        # setup parameters for xgboost    param = {}    # use softmax multi-class classification    param['objective'] = 'binary:logistic'              #多分类：'multi:softprob'#     param['eval_metric '] = 'auc' #校验数据所需要的评价指标    param['eta'] = 0.03  #通常最后设置eta为0.01~0.2#     param['min_child_weight']=0.5 #孩子节点中最小的样本权重和。如果一个叶子节点的样本权重和小于min_child_weight则拆分过程结束。#     param['alpha '] =0 #默认0，L1正则惩罚系数，当数据维度极高时可以使用，使得算法运行更快。#     param['lambda '] =0 #默认0，L2 正则的惩罚系数#     param['scale_pos_weight'] = 0 #默认0，大于0的取值可以处理类别不平衡的情况。帮助模型更快收敛    param['max_depth'] = 6  #通常取值：3-10#     param['colsample_bytree '] =1 #默认为1，在建立树时对特征随机采样的比例。#     param['subsample']=1 #默认为1，用于训练模型的子样本占整个样本集合的比例。#     param['max_delta_step']=3  #通常不需要设置这个值，但在使用logistics 回归时，若类别极度不平衡，则调整该参数可能有效果    param['silent'] = 1  #取0时表示打印出运行时信息，取1时表示以缄默方式运行，不打印运行时的信息。#     param['nthread'] = 4  #如果你希望以最大速度运行，建议不设置这个参数，模型将自动获得最大线程#     param['num_class'] = 2  #多分类时需设置    num_round = 300  #提升迭代的个数    try:        import cPickle as pickle    except:        import pickle

#从.npz文件中加载数据    with np.load(filename) as data:        positive = data['positiveSample']        negative = data['negSample']    X = np.concatenate((positive,negative))    y1 = np.ones((len(positive),1))    y2 = np.zeros((len(negative),1))    y = []    for i in range(len(positive)):        y.append(1)    for i in range(len(negative)):        y.append(0)     y=np.array(y)    # Classification and ROC analysis    #分类，做ROC分析    # Run classifier with cross-validation and plot ROC curves    #使用6折交叉验证，并且画ROC曲线    cv = StratifiedKFold(y, n_folds=6)    mean_tpr = 0.0    mean_fpr = np.linspace(0, 1, 100)    all_tpr = []        for i, (train, test) in enumerate(cv):        xg_train = xgb.DMatrix( X[train], label=y[train])        xg_test = xgb.DMatrix(X[test], label=y[test])        watchlist = [ (xg_train,'train'), (xg_test, 'test') ]        bst = xgb.train(param, xg_train, num_round, watchlist)  #,early_stopping_rounds=100                probas_ = bst.predict( xg_test )#         ylabel = np.argmax(probas_, axis=1)                fpr, tpr, thresholds = roc_curve(y[test], probas_)  #probas_[:, 1]        mean_tpr += interp(mean_fpr, fpr, tpr)#对mean_tpr在mean_fpr处进行插值，通过scipy包调用interp()函数        mean_tpr[0] = 0.0 #初始处为0        roc_auc = auc(fpr, tpr)        #画图，只需要plt.plot(fpr,tpr),变量roc_auc只是记录auc的值，通过auc()函数能计算出来        plt.plot(fpr, tpr, lw=1, label='ROC fold %d (area = %0.6f)' % (i, roc_auc))    #画对角线    plt.plot([0, 1], [0, 1], '--', color=(0.6, 0.6, 0.6), label='Luck')    mean_tpr /= len(cv) #在mean_fpr100个点，每个点处插值插值多次取平均    mean_tpr[-1] = 1.0 #坐标最后一个点为（1,1）    mean_auc = auc(mean_fpr, mean_tpr)#计算平均AUC值    #画平均ROC曲线    plt.plot(mean_fpr, mean_tpr, 'k--',label='Mean ROC (area = %0.6f)' % mean_auc, lw=2)    plt.xlim([-0.05, 1.05])    plt.ylim([-0.05, 1.05])    plt.xlabel('False Positive Rate')    plt.ylabel('True Positive Rate')    plt.title('Receiver operating characteristic example')    plt.legend(loc="lower right")    plt.savefig('data/mimic3.jpg',dpi=600)  #保存图片    plt.show()    draw_result("file.npz")