版权声明：博主是初学者，博文可能会有错误，望批评指正！转载请注明本博客地址，谢谢！ https://blog.csdn.net/LieQueov/article/details/80539856
一、说明
本源码主要利用python对于数据进行预处理，包括：
（1）从指定的url中，下载数据文件
（2）使用pandas读取xls文件，填充空缺的数据。
（3）将性别转成二进制编码
（4）对特殊字段进行了one-hot编码
（5）进行数据归一化
（6）按比例将数据分为训练数据和测试数据
（7）构造感知机模型，对生存率进行预测
二、特别注意
训练数据进行尺度变换的函数具体过程不是很清楚，导致测试数据虽然使用相同的变换函数，但是是否进行相同尺度的缩放也不清楚。
三、python源码
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Jun 1 14:52:40 2018
@author: sysu-hgavin
"""
import os
import urllib.request
import numpy as np
import pandas as pd
from sklearn import preprocessing
from keras.models import Sequential
from keras.layers import Dense,Dropout
url = "http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic3.xls"
filepath = "titanic3.xls"
if not os.path.isfile(filepath):
result = urllib.request.urlretrieve(url,filepath)
print("download:",result)
all_df = pd.read_excel(filepath)
cols = ['survived','name','pclass','sex','age','sibsp','parch','fare','embarked']
all_df = all_df[cols]
# delete name
df = all_df.drop(['name'],axis=1)
# check null
df.isnull().sum()
age_mean = df['age'].mean()
df['age'] = df['age'].fillna(age_mean)
fare_mean = df['fare'].mean()
df['fare'] = df['fare'].fillna(fare_mean)
# sex code
df['sex'] = df['sex'].map({'female':0,'male':1}).astype(int)
#embarked code
df_onehot = pd.get_dummies(data=df,columns=['embarked'])
#to array
ndarray = df_onehot.values
label = ndarray[:,0]
data = ndarray[:,1:]
#normalized
minmax_scale = preprocessing.MinMaxScaler(feature_range = (0,1))
scaleddate = minmax_scale.fit_transform(data)
# split data
msk = np.random.rand(len(ndarray))< 0.8
y_train = label[msk]
x_train = scaleddate[msk]
y_test = label[~msk]
x_test = scaleddate[~msk]
#build a model
model = Sequential()
model.add(Dense(units=40,input_dim = 9,kernel_initializer='uniform',activation='relu'))
model.add(Dense(30,activation='relu'))
model.add(Dense(1,activation='sigmoid'))
#train
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])
train_his = model.fit(x_train,y_train,validation_split=0.1,epochs=30,batch_size=32,verbose=2)
scores = model.evaluate(x_test,y_test)