kaggle——泰坦尼克号生死预测

把很久以前做的泰坦尼克号的代码贴出来。

# -*- coding: utf-8 -*-
"""
Created on Fri Mar 30 14:23:12 2017

@author: Yichengfan
"""

import pandas as pd

train = pd.read_csv(r"F:\TS\03_other_parts\Titanic\02_data\train.csv")
test = pd.read_csv(r"F:\TS\03_other_parts\Titanic\02_data\test.csv")

#先分别输出训练集和测试数据的基本信息，这是一个好习惯，可以对数据的规模，
#各个特征的数据类型以及是否缺失等，有一个整体的了解
print(train.info())
print(test.info())
'''
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
PassengerId    891 non-null int64
Survived       891 non-null int64
Pclass         891 non-null int64
Name           891 non-null object
Sex            891 non-null object
Age            714 non-null float64
SibSp          891 non-null int64
Parch          891 non-null int64
Ticket         891 non-null object
Fare           891 non-null float64
Cabin          204 non-null object
Embarked       889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 83.6+ KB
None
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 418 entries, 0 to 417
Data columns (total 11 columns):
PassengerId    418 non-null int64
Pclass         418 non-null int64
Name           418 non-null object
Sex            418 non-null object
Age            332 non-null float64
SibSp          418 non-null int64
Parch          418 non-null int64
Ticket         418 non-null object
Fare           417 non-null float64
Cabin          91 non-null object
Embarked       418 non-null object
dtypes: float64(2), int64(4), object(5)
memory usage: 36.0+ KB
None
'''

selectd_features = ['Pclass','Sex', 'Age', 'Embarked',