一、读入titanic.xlsx文件，按照教材示例步骤，完成数据清洗。

titanic数据集包含11个特征，分别是：

Survived:0代表死亡，1代表存活
Pclass:乘客所持票类，有三种值(1,2,3)
Name:乘客姓名
Sex:乘客性别
Age:乘客年龄(有缺失)
SibSp:乘客兄弟姐妹/配偶的个数(整数值)
Parch:乘客父母/孩子的个数(整数值)
Ticket:票号(字符串)
Fare:乘客所持票的价格(浮点数，0-500不等)
Cabin:乘客所在船舱(有缺失)
Embark:乘客登船港口:S、C、Q(有缺失)

import pandas as pd

pd.set_option('display.max_columns', 1000)
pd.set_option('display.width', 1000)
pd.set_option('display.max_colwidth', 1000)

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx'))

titanic.head() print(titanic.head())

import pandas as pd

pd.set_option('display.max_columns', 1000)
pd.set_option('display.width', 1000)
pd.set_option('display.max_colwidth', 1000)

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx')) 
titanic.head()
titanic.drop('embark_town',axis=1,inplace=True) 
titanic.head()
print(titanic.head())

import pandas as pd

pd.set_option('display.max_columns', 1000)
pd.set_option('display.width', 1000)
pd.set_option('display.max_colwidth', 1000)

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx')) 
titanic.head()
titanic.drop('embark_town',axis=1,inplace=True) 
titanic.head()
titanic.duplicated()
print(titanic.duplicated())

import pandas as pd

pd.set_option('display.max_columns', 1000)
pd.set_option('display.width', 1000)
pd.set_option('display.max_colwidth', 1000)

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx'))
titanic.head()
titanic.drop('embark_town',axis=1,inplace=True)
titanic.head()
titanic.drop_duplicates()
titanic.head()
print(titanic.head())

 

import pandas as pd


titanic = pd.DataFrame(pd.read_excel('titanic.xlsx'))
titanic.head()
titanic['age'].isnull().value_counts()
print(titanic['age'].isnull().value_counts())

import pandas as pd

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx'))
titanic.head()
titanic['embarked'].isnull().value_counts() #查看embarked缺失
print(titanic['embarked'].isnull().value_counts())

import pandas as pd

pd.set_option('display.max_columns', 1000)
pd.set_option('display.width', 1000)
pd.set_option('display.max_colwidth', 1000)

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx'))
titanic.head()
titanic.drop('embark_town',axis=1,inplace=True)
titanic.head()
titanic.drop_duplicates()
titanic.head()
titanic['age'] = titanic['age'].fillna(titanic['age'].mean()) #处理age缺失，取平均值
titanic['embarked'] = titanic['embarked'].fillna('S') #处理embarked缺失，取's'
titanic.head()
print(titanic.head())

import pandas as pd

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx'))
titanic.head()
titanic.describe()#异常值处理
print(titanic.describe())

import pandas as pd

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx'))
titanic.head()
titanic.drop('embark_town',axis=1,inplace=True) 
titanic.head()
titanic.replace([512.329200], titanic['fare'].mean()) #修改fare异常值
print(titanic.replace([512.329200], titanic['fare'].mean()))

 

二、对titanic数据集完成以下统计操作

1.统计乘客死亡和存活人数

import pandas as pd

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx'))
titanic.head()
titanic['survived'].value_counts()
print(titanic['survived'].value_counts())

2.统计乘客中男女性别人数

import pandas as pd

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx'))
titanic.head()
titanic['sex'].value_counts() #统计性别人数
print(titanic['sex'].value_counts())

3.统计男女获救的人数

import pandas as pd

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx'))
titanic.head()
titanic.groupby('survived')['sex'].value_counts().unstack()  # 统计获救男女人数
print(titanic.groupby('survived')['sex'].value_counts().unstack())

4.统计乘客所在的船舱等级的人数

import pandas as pd

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx'))
titanic.head()
titanic['pclass'].value_counts() #统计乘客所在的船舱等级的人数
print(titanic['pclass'].value_counts())

5.使用corr（）函数，判断两个属性是否具有相关性，分析舱位的高低和存活率的关系

import pandas as pd

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx'))
titanic.head()
titanic['survived'].corr(titanic['pclass']) #分析舱位的高低和存活率的关系
print(titanic['survived'].corr(titanic['pclass']))

      舱位越高，存活率越低。

6.画出乘客票价与舱位等级的箱体图Boxplot，从图中能够得到哪些结论？

import pandas as pd

titanic = pd.DataFrame(pd.read_excel('titanic.xlsx'))
titanic.head()
titanic.boxplot(['fare'],['pclass'])
print(titanic.boxplot(['fare'],['pclass']))