DW_数分任务1

import numpy as np 
import pandas as pd
import os

df = pd.read_csv('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

# 查看当前路径
os.getcwd()

'C:\\Users\\royryanwang\\Desktop\\DW数分'

pd.read_table('train.csv')

	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...
...	...
886	887,0,2,"Montvila, Rev. Juozas",male,27,0,0,21...
887	888,1,1,"Graham, Miss. Margaret Edith",female,...
888	889,0,3,"Johnston, Miss. Catherine Helen ""Car...
889	890,1,1,"Behr, Mr. Karl Howell",male,26,0,0,11...
890	891,0,3,"Dooley, Mr. Patrick",male,32,0,0,3703...

891 rows × 1 columns

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

<pandas.io.parsers.TextFileReader at 0x22317586f48>

将表头改成中文，索引改为乘客ID

df = pd.read_csv('train.csv', 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

dataframe 更改行列名的其他方法

from pandas import DataFrame, Series
data = DataFrame({"a":[1, 2, 3, 4], "b":[4, 5, 6, 7]})
data.columns = ["c", "d"]#直接在原数据上修改

from pandas import DataFrame, Series
data = DataFrame({"a":[1, 2, 3, 4], "b":[4, 5, 6, 7]})
data.rename(columns={"a":"c", "b":"d"})#在原表上修改

	c	d
0	1	4
1	2	5
2	3	6
3	4	7

from pandas import DataFrame, Series
data = DataFrame({"a":[1, 2, 3, 4], "b":[4, 5, 6, 7]})
data.insert(0, 'c', data.pop('a'))#先删除再插入，并且重新命名
data.insert(1, 'd', data.pop('b'))

# 将第1行和第2行的行名更改为aa,bb
d={'one':{'a':1,'b':2,'c':3,'d':4},'two':{'a':5,'b':6,'c':7,'d':8},'three':{'a':9,'b':10,'c':11,'d':12}}
df=pd.DataFrame(d)
print(df)

df.rename(index={'a':'aa','b':'bb'},inplace=True)
print(df)

   one  two  three
a    1    5      9
b    2    6     10
c    3    7     11
d    4    8     12
    one  two  three
aa    1    5      9
bb    2    6     10
c     3    7     11
d     4    8     12

查看数据的基本信息

df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 891 entries, 1 to 891
Data columns (total 11 columns):
 #   Column   Non-Null Count  Dtype  
---  ------   --------------  -----  
 0   是否幸存     891 non-null    int64  
 1   仓位等级     891 non-null    int64  
 2   姓名       891 non-null    object 
 3   性别       891 non-null    object 
 4   年龄       714 non-null    float64
 5   兄弟姐 妹个数  891 non-null    int64  
 6   父母子女个数   891 non-null    int64  
 7   船票信息     891 non-null    object 
 8   票价       891 non-null    float64
 9   客舱       204 non-null    object 
 10  登船港口     889 non-null    object 
dtypes: float64(2), int64(4), object(5)
memory usage: 83.5+ KB

观察表格前10行的数据和后15行的数据

df.head(10)

	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
6	0	3	Moran, Mr. James	male	NaN	0	0	330877	8.4583	NaN	Q
7	0	1	McCarthy, Mr. Timothy J	male	54.0	0	0	17463	51.8625	E46	S
8	0	3	Palsson, Master. Gosta Leonard	male	2.0	3	1	349909	21.0750	NaN	S
9	1	3	Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)	female	27.0	0	2	347742	11.1333	NaN	S
10	1	2	Nasser, Mrs. Nicholas (Adele Achem)	female	14.0	1	0	237736	30.0708	NaN	C

df.tail(15)

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

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()

	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	False	False	False	False	False	False	False	False	False	True	False
2	False	False	False	False	False	False	False	False	False	False	False
3	False	False	False	False	False	False	False	False	False	True	False
4	False	False	False	False	False	False	False	False	False	False	False
5	False	False	False	False	False	False	False	False	False	True	False

对于一个数据，还可以从哪些方面来观察？

可以从数据本身去看，比如对于此数据，我们可以分别统计仓位各等级有多少人，男女各有多少人，平均年龄是多少，平均兄弟姐妹，父母子女个数，票价。

1、分组groupby
Pandas中最为常用和有效的分组函数。

1）按列分组

注意以下使用groupby()函数生成的group1是一个中间分组变量，为GroupBy类型。

既可依据单个列名’key1’进行为分组，也可依据多个列名[‘key1’,‘key2’]进行分组。

2）按分组统计
在分组group1、group2上应用size()、sum()、count()等统计函数，能分别统计分组数量、不同列的分组和、不同列的分组数量。

详情参加此CSDN 博客 https://blog.csdn.net/elecjack/article/details/50760736

# 先按仓位等级分组看幸存人数
group_level = df.groupby('仓位等级')

group_level.sum()

	是否幸存	年龄	兄弟姐 妹个数	父母子女个数	票价
仓位等级
1	136	7111.42	90	77	18177.4125
2	87	5168.83	74	70	3801.8417
3	119	8924.92	302	193	6714.6951

# 按性别分组看幸存人数
group_gender = df.groupby('性别').sum()
group_gender

	是否幸存	仓位等级	年龄	兄弟姐 妹个数	父母子女个数	票价
性别
female	233	678	7286.00	218	204	13966.6628
male	109	1379	13919.17	248	136	14727.2865

# 求年龄平均值
print(df["年龄"].mean())

29.69911764705882

# 求父母子女个数平均值
print(df["父母子女个数"].mean())

0.38159371492704824

加载并做出改变的数据，在工作目录下保存为一 个新文件train_chinese.csv

df.to_csv('train_chinese.csv')