使用神经网络做二分类预测

不想整理代码了。先给个结果图：

train 0 loss: 1838.0616
train 100 loss: 1441.5283
train 200 loss: 1299.4546
train 300 loss: 934.36536
train 400 loss: 506.06702
train 500 loss: 322.9782
train 600 loss: 271.5825
train 700 loss: 360.091
train 800 loss: 237.25177
train 900 loss: 332.97592
train 1000 loss: 117.5983
train 1100 loss: 173.39397
train 1200 loss: 51.26674
train 1300 loss: 82.82826
train 1400 loss: 74.705734
train 1500 loss: 113.63321
train 1600 loss: 71.29809
train 1700 loss: 38.41456
train 1800 loss: 82.75247
train 1900 loss: 44.553272
test 0,accuracy:0.953125,auc: (0.0, 0.9708618)
test 1,accuracy:0.9375,auc: (0.9708618, 0.96028894)
test 2,accuracy:0.9609375,auc: (0.96028894, 0.9594982)
test 3,accuracy:0.953125,auc: (0.9594982, 0.96195656)
test 4,accuracy:0.9375,auc: (0.96195656, 0.9627208)

loss这么大，结果这么准确。我也搞不懂是怎么肥事呀。

                                                     

AUC也没什么问题。暂时认为是好的吧。

下面是源码dataUtil用来对数据预处理：

import pandas as pd
import numpy as np
def load_csv(filename):
    data=pd.read_csv(filename)
    data = data.drop(data.columns[39:], axis=1)
    return data
def toInt(y):
    return int(y)
def split_x_y(data):
    keys=data.keys().tolist()
    y=data["Label"]
    keys.remove("Label")
    x=data[keys]
    return (x.values,y.values)
def max_min_nomalize(X):
    keys=X.keys().tolist()
    keys.remove("Index")
    keys.remove("Label")
    #keys.remove("Gender")
    #keys=["BMI","JiGan","ShouSuoYa","ShuZhangYa"]
    #删掉JiGan为-1的人
    #X = X[X["JiGan"].isin([-1.0]) == False]
    for key in keys:
        #normalize_col=(X[key]-(X[key].max()+X[key].min())/2)/(X[key].max()-X[key].min())
        #测试1：用mean来normolize
        normalize_col = (X[key] - X[key].mean()) / (X[key].max() - X[key].min())
        X = X.drop(key, axis=1)
        X[key]=normalize_col
    return X

if __name__=="__main__":
    pd.set_option('display.max_rows', 500)
    pd.set_option('display.max_columns', 500)
    pd.set_option('display.width', 500)
    data=load_csv("./data/patient_data.csv")
    #print(data.head())
    print(data.info())
    print(data.describe())
    print(data.count())
    #print(data["Label"].value_counts())
    #data=data[data["JiGan"].isin([-1.0])==False]
   # print(data)
    #print(data)
    #print(data.describe())
    #x=max_min_nomalize(data)
    # for key in data.keys().tolist():
    #     print("********************************************************{}**********************************".format(key))
    #     print(data[key].value_counts())
    #data=load_csv("F:\workspaces\pycharm\Patient\data\patient_data.csv")
    #data=max_min_nomalize(data)
    #print(data.head())

dataUtil