【阿里天池-医学影像报告异常检测】3 机器学习模型训练及集成学习Baseline开源

谁践踏了优雅 2022-11-15 01:09 108阅读 0赞

# 引言 #

采用机器学习分类算法XGBClassifier、LGBMClassifier、LogisticRegression集成学习线上得到0.83+的准确率  
开源源码：[https://github.com/823316627bandeng/TIANCHI-2021-AI-Compition][https_github.com_823316627bandeng_TIANCHI-2021-AI-Compition]

# 模型实现 #

（1）导入包

import os
    import numpy as np
    import pandas as pd
    from sklearn.linear_model import LogisticRegression
    from sklearn.multiclass import OneVsRestClassifier
    from sklearn.multioutput import ClassifierChain, ClassifierMixin, MultiOutputClassifier
    from iterstrat.ml_stratifiers import MultilabelStratifiedKFold, MultilabelStratifiedShuffleSplit
    from sklearn.preprocessing import StandardScaler
    from xgboost import XGBClassifier
    from lightgbm import LGBMClassifier
    from mlxtend.classifier import StackingClassifier
    from utils import *
    import os
    import pickle
    os.environ["CUDA_VISIBLE_DEVICES"] = "0"

（2）准备数据

#加载数据
    label= np.array(pd.read_csv('./data/label.csv'))
    #train_sampel = pd.read_csv('./data/train_sample_500.csv')
    train_sampel = pd.read_csv('./data/train_sample.csv')
    test_sampel = pd.read_csv('./data/test_sample.csv')
    #test_sampel = pd.read_csv('./data/test_sample_500.csv')
    #数据归一化
    stdScalar = StandardScaler()
    train_df = stdScalar.fit_transform(np.float_(train_sampel))
    test_df = stdScalar.fit_transform(np.float_(test_sampel))
    
    
    losslist = []
    nfold = 5
    kf = MultilabelStratifiedKFold(n_splits=nfold, shuffle=True, random_state=2020)
    lr_oof = np.zeros(label.shape)
    # 存储测试集的概率
    probility = np.zeros((len(test_df), label.shape[1]))
    i = 0
    model_type = 'ensemble'
    # model_type ='single'
    # K折交叉划分训练
    for train_index, valid_index in kf.split(train_df, label):
        print("\nFold {}".format(i + 1))
        X_train, label_train = train_df[train_index], label[train_index]
        X_valid, label_valid = train_df[valid_index], label[valid_index]
        # 三个模型
        clf1 = OneVsRestClassifier(XGBClassifier(eval_metric= 'mlogloss',use_label_encoder=False,n_estimators=150))
        clf2 = LGBMClassifier()
        clf3 = LogisticRegression(max_iter =500, n_jobs=20)
    	# 集成学习方法1
        if model_type == 'ensemble':
            model = OneVsRestClassifier(EnsembleVoteClassifier(clfs=[clf1, clf2, clf3],weights=[2, 1, 1], voting='soft', verbose=2))
        # 集成学习方法2
        elif model_type == 'stacking':
            lr = LogisticRegression()
            base = StackingClassifier(classifiers=[clf1, clf2, clf3],use_probas=True,average_probas=False, meta_classifier=lr,verbose=2)
            model = OneVsRestClassifier(base)
        else:
        # 单模型训练
            model = OneVsRestClassifier(XGBClassifier(eval_metric= 'mlogloss',use_label_encoder=False,n_estimators=150))
        
        model.fit(X_train, label_train)
    	# 预测结果
        lr_oof[valid_index] = model.predict_proba(X_valid,)
        # 计算mlogloss
        loss = Mutilogloss(label_valid[:,:-1,], lr_oof[valid_index][:,:-1,])
        losslist.append(loss)
        # 多个flod预测结果叠加
        probility += model.predict_proba(test_df) / nfold
        i += 1
        print(losslist)
        
    print(np.mean(losslist))
    print()
    
    # 保存存提交数据
    submit_dir='submits/'
    if not os.path.exists(submit_dir): os.makedirs(submit_dir)
    str_w=''
    with open(submit_dir+'machine_model_submit.csv','w') as f:
        for i in range(len(probility)):
            list_to_str = [str(x) for x in list(probility[i])][0:-1]
            liststr = " ".join(list_to_str)
            str_w+=str(i)+'|'+','+'|'+liststr+'\n'
        str_w=str_w.strip('\n')
        f.write(str_w)
    print()

[https_github.com_823316627bandeng_TIANCHI-2021-AI-Compition]: https://github.com/823316627bandeng/TIANCHI-2021-AI-Compition