使用Titanic 数据集进行数据清洗，并使用ID3决策树与IPOT模型对乘客生存进行预测

1. 数据清洗

代码部分

import numpy as np
import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.feature_extraction import DictVectorizer
from sklearn.model_selection import cross_val_score
from sklearn import metrics
from sklearn.feature_extraction import DictVectorizer

# 数据加载
train_data = pd.read_csv('./train.csv')
test_data = pd.read_csv('./test.csv')
# 数据探索
# 查看train_data信息
#pd.set_option('display.max_columns', None) #显示所有列
print('查看数据信息：列名、非空个数、类型等')
print(train_data.info())
print('-'*30)
print('查看数据摘要')
print(train_data.describe())
print