动手学数据分析——Task01_数据加载

前言

这是一门诞生于datawhale的课程，学习它的时候搭配datawhale所配备其他资源会更好，项目地址：https://github.com/datawhalechina/hands-on-data-analysis
数据集下载：https://www.kaggle.com/c/titanic/overview

import os
os.getcwd()

tip：相对路径载入报错时，尝试使用os.getcwd()查看当前工作目录

'C:\\Users\\lyj\\Desktop\\pyproject\\动手学数据分析_datawhale\\第一章_数据加载'

1.加载数据

1.1载入数据

1.1.1 导入相关库

import numpy as np
import pandas as pd

df = pd.read_csv('../titanic/train.csv')

df.head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

思考：以下几个问题

• 知道数据加载的方法后，pd.read_csv()和pd.read_table()的不同，如果想让他们效果一样，需要怎么做？
• 了解一下’.tsv’和’.csv’的不同，如何加载这两个数据集
• 不同的数据格式:eg:csv,tsv,xlsx的读取方式

由此可知，read_csv和read_table都是是加载带分隔符的数据，每一个分隔符作为一个数据的标志，
但二者读出来的数据格式还是不一样的，read_table是以制表符 \t 作为数据的标志，也就是以行为单位进行存储。

• read_table读取看看效果

# 默认分隔符是'\t'
tabel_df = pd.read_table('../titanic/train.csv')

tabel_df.head()

	PassengerId,Survived,Pclass,Name,Sex,Age,SibSp,Parch,Ticket,Fare,Cabin,Embarked
0	1,0,3,"Braund, Mr. Owen Harris",male,22,1,0,A/...
1	2,1,1,"Cumings, Mrs. John Bradley (Florence Br...
2	3,1,3,"Heikkinen, Miss. Laina",female,26,0,0,S...
3	4,1,1,"Futrelle, Mrs. Jacques Heath (Lily May ...
4	5,0,3,"Allen, Mr. William Henry",male,35,0,0,3...

table_df2 = pd.read_table('../titanic/train.csv',sep = ',')

table_df2.head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

TSV与CSV的区别：

• (1）从名称上即可知道，TSV是用制表符（Tab,’\t’）作为字段值的分隔符；CSV是用半角逗号（’,’）作为字段值的分隔符；
• 2）IANA规定的标准TSV格式，字段值之中是不允许出现制表符的。

关于xlxs类型文件的读取可以参考blog:https://blog.csdn.net/sinat_28576553/article/details/81275650

1.1.2每1000行为一个数据模块，逐块读取

chunker = pd.read_csv('../titanic/train.csv',chunksize = 1000)

• q:什么是逐块读取呢？为什么要逐块读取呢？
• a:有chunksize参数可以进行逐块加载。经测试，它的本质就是将文本分成若干块，每次处理chunksize行的数据，最终返回一个TextParser对象
  
  对该对象进行迭代遍历，可以完成逐块统计的合并处理

chunker

for piece in chunker:
    print(piece.head())

   PassengerId  Survived  Pclass  \
0            1         0       3   
1            2         1       1   
2            3         1       3   
3            4         1       1   
4            5         0       3   

                                                Name     Sex   Age  SibSp  \
0                            Braund, Mr. Owen Harris    male  22.0      1   
1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   
2                             Heikkinen, Miss. Laina  female  26.0      0   
3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   
4                           Allen, Mr. William Henry    male  35.0      0   

   Parch            Ticket     Fare Cabin Embarked  
0      0         A/5 21171   7.2500   NaN        S  
1      0          PC 17599  71.2833   C85        C  
2      0  STON/O2. 3101282   7.9250   NaN        S  
3      0            113803  53.1000  C123        S  
4      0            373450   8.0500   NaN        S  

1.1.3将表头改为中文，索引改为乘客id

PassengerId => 乘客ID

Survived => 是否幸存

Pclass => 乘客等级(1/2/3等舱位)

Name => 乘客姓名

Sex => 性别

Age => 年龄

SibSp => 堂兄弟/妹个数

Parch => 父母与小孩个数

Ticket => 船票信息

Fare => 票价

Cabin => 客舱

Embarked => 登船港口

data_path = '../titanic/train.csv'
df = pd.read_csv(data_path,names=['乘客ID','是否幸存','仓位等级','姓名','性别','年龄','兄弟姐妹个数','父母子女个数','船票信息','票价','客舱','登船港口'],index_col='乘客ID',header=0)

df.head()

	是否幸存	仓位等级	姓名	性别	年龄	兄弟姐妹个数	父母子女个数	船票信息	票价	客舱	登船港口
乘客ID
1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

• 以上是在读取的时候就进行重命名，还有什么方法吗？
• ①对全部列重命名 df.columns = [‘a1’, ‘b1’, ‘c1’, ‘d1’]
• ②对部分列重命名 df.rename(columns={‘a’: ‘A’})

old_df = pd.read_csv(data_path)

old_df.head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

old_df.columns = ['乘客ID','是否幸存','仓位等级','姓名','性别','年龄','兄弟姐妹个数','父母子女个数','船票信息','票价','客舱','登船港口']

old_df.head()

	乘客ID	是否幸存	仓位等级	姓名	性别	年龄	兄弟姐妹个数	父母子女个数	船票信息	票价	客舱	登船港口
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

对部分列重命名，此时是新生成了一个新的dataframe,如果想替换原有df，则需要设置inplace = True

df1 = pd.read_csv(data_path)
df1.head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

df1.rename( columns={'PassengerId': '乘客id'}).head()

	乘客id	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

1.2.观察数据

1.2.1查看数据的基本信息

df = pd.read_csv(data_path,names=['乘客ID','是否幸存','仓位等级','姓名','性别','年龄','兄弟姐妹个数','父母子女个数','船票信息','票价','客舱','登船港口'],header = 0)

df.info()

RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
乘客ID      891 non-null int64
是否幸存      891 non-null int64
仓位等级      891 non-null int64
姓名        891 non-null object
性别        891 non-null object
年龄        714 non-null float64
兄弟姐妹个数    891 non-null int64
父母子女个数    891 non-null int64
船票信息      891 non-null object
票价        891 non-null float64
客舱        204 non-null object
登船港口      889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 83.6+ KB

可以看到数据的一些信息，包括dtype，还可以发现一些缺失值

1.2.2观察表格前10行的数据和后15行的数据

df.head(10)

	乘客ID	是否幸存	仓位等级	姓名	性别	年龄	兄弟姐妹个数	父母子女个数	船票信息	票价	客舱	登船港口
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S
5	6	0	3	Moran, Mr. James	male	NaN	0	0	330877	8.4583	NaN	Q
6	7	0	1	McCarthy, Mr. Timothy J	male	54.0	0	0	17463	51.8625	E46	S
7	8	0	3	Palsson, Master. Gosta Leonard	male	2.0	3	1	349909	21.0750	NaN	S
8	9	1	3	Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)	female	27.0	0	2	347742	11.1333	NaN	S
9	10	1	2	Nasser, Mrs. Nicholas (Adele Achem)	female	14.0	1	0	237736	30.0708	NaN	C

df.tail(15)

	乘客ID	是否幸存	仓位等级	姓名	性别	年龄	兄弟姐妹个数	父母子女个数	船票信息	票价	客舱	登船港口
876	877	0	3	Gustafsson, Mr. Alfred Ossian	male	20.0	0	0	7534	9.8458	NaN	S
877	878	0	3	Petroff, Mr. Nedelio	male	19.0	0	0	349212	7.8958	NaN	S
878	879	0	3	Laleff, Mr. Kristo	male	NaN	0	0	349217	7.8958	NaN	S
879	880	1	1	Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)	female	56.0	0	1	11767	83.1583	C50	C
880	881	1	2	Shelley, Mrs. William (Imanita Parrish Hall)	female	25.0	0	1	230433	26.0000	NaN	S
881	882	0	3	Markun, Mr. Johann	male	33.0	0	0	349257	7.8958	NaN	S
882	883	0	3	Dahlberg, Miss. Gerda Ulrika	female	22.0	0	0	7552	10.5167	NaN	S
883	884	0	2	Banfield, Mr. Frederick James	male	28.0	0	0	C.A./SOTON 34068	10.5000	NaN	S
884	885	0	3	Sutehall, Mr. Henry Jr	male	25.0	0	0	SOTON/OQ 392076	7.0500	NaN	S
885	886	0	3	Rice, Mrs. William (Margaret Norton)	female	39.0	0	5	382652	29.1250	NaN	Q
886	887	0	2	Montvila, Rev. Juozas	male	27.0	0	0	211536	13.0000	NaN	S
887	888	1	1	Graham, Miss. Margaret Edith	female	19.0	0	0	112053	30.0000	B42	S
888	889	0	3	Johnston, Miss. Catherine Helen "Carrie"	female	NaN	1	2	W./C. 6607	23.4500	NaN	S
889	890	1	1	Behr, Mr. Karl Howell	male	26.0	0	0	111369	30.0000	C148	C
890	891	0	3	Dooley, Mr. Patrick	male	32.0	0	0	370376	7.7500	NaN	Q

1.2.3判断数据是否为空，为空的地方返回True,其余地方返回False

df.isnull().head()

	乘客ID	是否幸存	仓位等级	姓名	性别	年龄	兄弟姐妹个数	父母子女个数	船票信息	票价	客舱	登船港口
0	False	False	False	False	False	False	False	False	False	False	True	False
1	False	False	False	False	False	False	False	False	False	False	False	False
2	False	False	False	False	False	False	False	False	False	False	True	False
3	False	False	False	False	False	False	False	False	False	False	False	False
4	False	False	False	False	False	False	False	False	False	False	True	False

df.isnull().sum()

乘客ID        0
是否幸存        0
仓位等级        0
姓名          0
性别          0
年龄        177
兄弟姐妹个数      0
父母子女个数      0
船票信息        0
票价          0
客舱        687
登船港口        2
dtype: int64

由上可知，客舱缺失值非常多，占了总数据的3/4以上

1.2.4保存我们做出的改变的数据

df.to_csv('train_chinese.csv')

2.pandas基础

2.1认识Series和dataframe

sdata = {'Ohio':35000,'Texas':71000,'Oregon':16000,'Utah':5000}
example = pd.Series(sdata)

example

Ohio      35000
Oregon    16000
Texas     71000
Utah       5000
dtype: int64

data = {'state':list(range(10)),'year':list(range(2010,2020)),'pop':[1.1,2.2,3.3,4.4,5.5,6.6,7.7,8.8,9.9,0.0]}

df = pd.DataFrame(data)

df

	pop	state	year
0	1.1	0	2010
1	2.2	1	2011
2	3.3	2	2012
3	4.4	3	2013
4	5.5	4	2014
5	6.6	5	2015
6	7.7	6	2016
7	8.8	7	2017
8	9.9	8	2018
9	0.0	9	2019

df['pop']

0    1.1
1    2.2
2    3.3
3    4.4
4    5.5
5    6.6
6    7.7
7    8.8
8    9.9
9    0.0
Name: pop, dtype: float64

实际上dataframe的每一列都是Series类型

2.2查看数据

df = pd.read_csv(data_path)

df.columns

Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',
       'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'],
      dtype='object')

test_data_path = '../titanic/test.csv'
test_df = pd.read_csv(test_data_path)

test_df.head()

	PassengerId	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	892	3	Kelly, Mr. James	male	34.5	0	0	330911	7.8292	NaN	Q
1	893	3	Wilkes, Mrs. James (Ellen Needs)	female	47.0	1	0	363272	7.0000	NaN	S
2	894	2	Myles, Mr. Thomas Francis	male	62.0	0	0	240276	9.6875	NaN	Q
3	895	3	Wirz, Mr. Albert	male	27.0	0	0	315154	8.6625	NaN	S
4	896	3	Hirvonen, Mrs. Alexander (Helga E Lindqvist)	female	22.0	1	1	3101298	12.2875	NaN	S

test_df.columns

Index(['PassengerId', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp', 'Parch',
       'Ticket', 'Fare', 'Cabin', 'Embarked'],
      dtype='object')

2.3删除某几列

• ①del df[]
• ②df.drop([],axis = 1)

del df['Name']

df.head()

	PassengerId	Survived	Pclass	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	male	35.0	0	0	373450	8.0500	NaN	S

df.drop(['Age'],axis = 1).head(2)#使用inplace关键字才是真正删除

	PassengerId	Survived	Pclass	Sex	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	male	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	female	1	0	PC 17599	71.2833	C85	C

2.4筛选的逻辑

2.4.1以‘age’为筛选条件，显示年龄在10岁以下的乘客信息

df[df['Age']<10].head(2)

	PassengerId	Survived	Pclass	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
7	8	0	3	male	2.0	3	1	349909	21.075	NaN	S
10	11	1	3	female	4.0	1	1	PP 9549	16.700	G6	S

2.4.2以‘Age’为条件，将年龄在10岁以上和50岁以下的乘客信息显示出来，并将这个数据命名为midage

midage = df[(df['Age']>10)&(df['Age']<50)]

midage.head(2)

	PassengerId	Survived	Pclass	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	female	38.0	1	0	PC 17599	71.2833	C85	C

2.4.3将midage的数据中第100行中的‘Pclass’和‘Sex’的数据显示出来

midage

# index需要重新设置
midage = midage.reset_index(drop = True)
midage.head()

	PassengerId	Survived	Pclass	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	male	35.0	0	0	373450	8.0500	NaN	S

midage.loc[[100],['Pclass','Sex']]

	Pclass	Sex
100	2	male

取值时里面用[]包含才是dataframe，否则取出来就是Series

midage.loc[100,['Pclass','Sex']]

Pclass       2
Sex       male
Name: 100, dtype: object

2.4.4将midage的数据中第100行,105,108中的‘Pclass’和‘Sex’和’Name’的数据显示出来

midage.loc[[100,105,108],['Pclass','Sex','Name']]#Name这列在上面被删除了

	Pclass	Sex	Name
100	2	male	NaN
105	3	male	NaN
108	3	male	NaN

2.4.5将midage的数据中第100行,105,108中的‘Pclass’和‘Sex’的数据显示出来，使用iloc

midage.head()

	PassengerId	Survived	Pclass	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	male	35.0	0	0	373450	8.0500	NaN	S

midage.iloc[[100,105,108],[2,3]]

	Pclass	Sex
100	2	male
105	3	male
108	3	male

3探索性数据分析

3.1利用Pandas对示例数据进行排序，要求升序

df = pd.DataFrame(np.arange(8).reshape(2,4),index = ['a','b'],columns=['A','B','C','D'])

df

	A	B	C	D
a	0	1	2	3
b	4	5	6	7

df.sort_values(by = ['B'],ascending=True)

	A	B	C	D
a	0	1	2	3
b	4	5	6	7

排序总结

• 让行索引升序排序 df.sort_index()
• 让列索引升序排序df.sort_index(axis = 1)
• 让列索引降序排序df.sort_index(axis= 1,ascending = True)
• 任选两列数据进行排序 df.sort_values(by = [])

3.2对train_data按票价和年龄进行降序排序

train_df = pd.read_csv(data_path)
train_df.head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

train_df.sort_values(by = ['Fare','Age'],ascending = False).head().append(train_df.sort_values(by = ['Fare','Age'],ascending = False).tail())

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
679	680	1	1	Cardeza, Mr. Thomas Drake Martinez	male	36.0	0	1	PC 17755	512.3292	B51 B53 B55	C
258	259	1	1	Ward, Miss. Anna	female	35.0	0	0	PC 17755	512.3292	NaN	C
737	738	1	1	Lesurer, Mr. Gustave J	male	35.0	0	0	PC 17755	512.3292	B101	C
438	439	0	1	Fortune, Mr. Mark	male	64.0	1	4	19950	263.0000	C23 C25 C27	S
341	342	1	1	Fortune, Miss. Alice Elizabeth	female	24.0	3	2	19950	263.0000	C23 C25 C27	S
481	482	0	2	Frost, Mr. Anthony Wood "Archie"	male	NaN	0	0	239854	0.0000	NaN	S
633	634	0	1	Parr, Mr. William Henry Marsh	male	NaN	0	0	112052	0.0000	NaN	S
674	675	0	2	Watson, Mr. Ennis Hastings	male	NaN	0	0	239856	0.0000	NaN	S
732	733	0	2	Knight, Mr. Robert J	male	NaN	0	0	239855	0.0000	NaN	S
815	816	0	1	Fry, Mr. Richard	male	NaN	0	0	112058	0.0000	B102	S

看到前面的富人存活率非常高，但是最后的相对贫穷的基本存活率为0

3.3计算两个dataframe的相加

frame1 = pd.DataFrame(np.arange(100).reshape(10,10),index= list(range(10)),columns=list(range(2010,2020)))

frame2 = pd.DataFrame(np.arange(100,200).reshape(10,10),index= list(range(10)),columns=list(range(2010,2020)))

frame1+frame2

	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019
0	100	102	104	106	108	110	112	114	116	118
1	120	122	124	126	128	130	132	134	136	138
2	140	142	144	146	148	150	152	154	156	158
3	160	162	164	166	168	170	172	174	176	178
4	180	182	184	186	188	190	192	194	196	198
5	200	202	204	206	208	210	212	214	216	218
6	220	222	224	226	228	230	232	234	236	238
7	240	242	244	246	248	250	252	254	256	258
8	260	262	264	266	268	270	272	274	276	278
9	280	282	284	286	288	290	292	294	296	298

3.4计算出船上最大的家族有多少人？

train_df.head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

train_df['family'] = train_df['SibSp']+train_df['Parch']

max(train_df['family'])

10

3.5查看train_data的基本统计数据

del train_df['family']
train_df.describe()

	PassengerId	Survived	Pclass	Age	SibSp	Parch	Fare
count	891.000000	891.000000	891.000000	714.000000	891.000000	891.000000	891.000000
mean	446.000000	0.383838	2.308642	29.699118	0.523008	0.381594	32.204208
std	257.353842	0.486592	0.836071	14.526497	1.102743	0.806057	49.693429
min	1.000000	0.000000	1.000000	0.420000	0.000000	0.000000	0.000000
25%	223.500000	0.000000	2.000000	20.125000	0.000000	0.000000	7.910400
50%	446.000000	0.000000	3.000000	28.000000	0.000000	0.000000	14.454200
75%	668.500000	1.000000	3.000000	38.000000	1.000000	0.000000	31.000000
max	891.000000	1.000000	3.000000	80.000000	8.000000	6.000000	512.329200