基于机器学习的泰坦尼克号预测

# coding: utf-8

# <h1>Table of Contents<span class="tocSkip"></span></h1>
# <div class="toc"><ul class="toc-item"><li><span><a href="#1.-数据总览" data-toc-modified-id="1.-数据总览-1">1. 数据总览</a></span><ul class="toc-item"><li><span><a href="#1)特征间相关性分析" data-toc-modified-id="1)特征间相关性分析-1.1">1)特征间相关性分析</a></span></li></ul></li><li><span><a href="#7.模型融合及测试" data-toc-modified-id="7.模型融合及测试-2">7.模型融合及测试</a></span><ul class="toc-item"><li><span><a href="#2）依据筛选的特征构建新的训练集和测试集" data-toc-modified-id="2）依据筛选的特征构建新的训练集和测试集-2.1">2）依据筛选的特征构建新的训练集和测试集</a></span></li><li><span><a href="#3）模型融合" data-toc-modified-id="3）模型融合-2.2">3）模型融合</a></span></li></ul></li><li><span><a href="#Final.生成预测结果" data-toc-modified-id="Final.生成预测结果-3">Final.生成预测结果</a></span></li></ul></div>

# In[70]:


import numpy as np   ##保存当前所有环境变量
import dill   
filename= 'Titanic.pkl'  
dill.dump_session(filename) 


# In[1]:


import numpy as np  
import dill  
filename = 'Titanic.pkl'
dill.load_session(filename)  ##读取环境变量


# ## 1. 数据总览

# In[2]:


import numpy as np
import pandas as pd
import matplotlib.pyplot as plt 
import seaborn as sns   ##作图工具


# In[60]:


train_data = pd.read_csv("/Users/lkl/Gtrain.csv")
test_data = pd.read_csv("/Users/lkl/Gtest.csv")
train_data = train_data.drop(['row.names(tT)'], axis=1)
test_data = test_data.drop(['row.names(tT)'], axis=1)


# In[49]:


train_data


# In[47]:


train_data.info()


# In[10]:


train_data['Regulated&