一次使用随机森林，罗辑回归，xgboost,及神经网络训练机器学习模型训练和测试分类数据

一次使用多个机器学习模型训练自己的数据

使用sklearn 架构，使用随机森林，逻辑回归，支持向量机，xgboost训练模型，并计算测试数据的准确率和混淆矩阵

1. 随机森林
2. 逻辑回归
3. xgboost
4. 支持向量机
5. 神经网络

import numpy as np
import pandas as pd
import argparse
from time import time
from datetime import datetime
from sklearn.metrics import confusion_matrix as CM # 导入混淆矩阵计算模块
from sklearn.metrics import accuracy_score as ACCS #导入准确率计算模块


parser = argparse.ArgumentParser(description='ML training and testing using RF,SVM,LR with input of matrix and target')
parser.add_argument("allmatrix",help="input all the datamatrix in dataframe")
parser.add_argument("target",help="input label data with np.txt format")
args = parser.parse_args()


#record time costed
def timerecord():
    print("time cost: {}".format(datetime.fromtimestamp(time()-time0).strftime("%M:%S:%f"))) # 记录模型使用时间

# load feature matrix and label
allmatrix = pd.read_csv(args.allmatrix,index_col=0,header=0)
target = np.loadtxt(args.target,dtype='int32')
print("allmatrix shape: {}".format(allmatrix.shape))
print("target shape: {}".format(target.shape))
print("chrom NO.: ",(target==0).sum())
print("plas NO.: ",(target==1).sum())


#随机森林训练
# Random Forest training and cross_validation 
print("random forest training result")
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score

Xtrain,Xtest,Ytrain,Ytest = train_test_split(allmatrix,target,test_size=0.3,random_state=420)
rfc = R