DadaWhale之task01-数据初步探索

import numpy as np
import pandas as pd

#相对路径
train = pd.read_csv("train.csv") # ../上级文件夹
test = pd.read_csv("test.csv") 

#绝对路径
train = pd.read_csv(r‘C:\Users\63509\Desktop\titanic’)

#查看当前工作目录
import os
os.getcwd()

'C:\\Users\\63509\\DataWhale'

• read_csv: 从文件、URL、文件型对下中加载带分隔符的数据。默认分隔符为逗号

• read_table: 从文件、URL、文件型对下中加载带分隔符的数据。默认分隔符为制表符

TSV 是Tab-separated values的缩写，即制表符分隔值。
相对来说CSV，Comma-separated values（逗号分隔值）更常见一些。

1.逐块读取

1.只想读取几行，避免读取整个文件，通过 nrows进行指定：
pd.read_csv(path, nrows=5)
2.逐块读取文件，需要设置chunksize(行数)
pd.read_csv(path, chunksize=1000)

train_01 = pd.read_csv("train.csv", nrows=5)
train_01

	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/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35	0	0	373450	8.0500	NaN	S

train_02 = pd.read_csv("train.csv", chunksize=1000)
train_02

<pandas.io.parsers.TextFileReader at 0x21f3ad9f9d0>

train.rename(columns={"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"}, inplace=True)
train.head()

'''
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)
'''

	乘客ID	是否幸存	乘客等级(1/2/3等舱位)	乘客姓名	性别	年龄	堂兄弟/妹个数	父母与小孩个数	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

train.set_index("乘客ID", inplace=True)
train.head()

	是否幸存	乘客等级(1/2/3等舱位)	乘客姓名	性别	年龄	堂兄弟/妹个数	父母与小孩个数	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

2.初步观察

train.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   乘客等级(1/2/3等舱位)  891 non-null    int64  
 2   乘客姓名            891 non-null    object 
 3   性别              891 non-null    object 
 4   年龄              714 non-null    float64
 5   堂兄弟/妹个数         891 non-null    int64  
 6   父母与小孩个数         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

train.shape

(891, 11)

train.describe()

	是否幸存	乘客等级(1/2/3等舱位)	年龄	堂兄弟/妹个数	父母与小孩个数	票价
count	891.000000	891.000000	714.000000	891.000000	891.000000	891.000000
mean	0.383838	2.308642	29.699118	0.523008	0.381594	32.204208
std	0.486592	0.836071	14.526497	1.102743	0.806057	49.693429
min	0.000000	1.000000	0.420000	0.000000	0.000000	0.000000
25%	0.000000	2.000000	20.125000	0.000000	0.000000	7.910400
50%	0.000000	3.000000	28.000000	0.000000	0.000000	14.454200
75%	1.000000	3.000000	38.000000	1.000000	0.000000	31.000000
max	1.000000	3.000000	80.000000	8.000000	6.000000	512.329200

train.head(10)

	是否幸存	乘客等级(1/2/3等舱位)	乘客姓名	性别	年龄	堂兄弟/妹个数	父母与小孩个数	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

train.tail(15)

	是否幸存	乘客等级(1/2/3等舱位)	乘客姓名	性别	年龄	堂兄弟/妹个数	父母与小孩个数	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

train.isnull()

	是否幸存	乘客等级(1/2/3等舱位)	乘客姓名	性别	年龄	堂兄弟/妹个数	父母与小孩个数	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
...	...	...	...	...	...	...	...	...	...	...	...
887	False	False	False	False	False	False	False	False	False	True	False
888	False	False	False	False	False	False	False	False	False	False	False
889	False	False	False	False	True	False	False	False	False	True	False
890	False	False	False	False	False	False	False	False	False	False	False
891	False	False	False	False	False	False	False	False	False	True	False

891 rows × 11 columns

#哪些列有缺失值
train.isnull().any()

是否幸存              False
乘客等级(1/2/3等舱位)    False
乘客姓名              False
性别                False
年龄                 True
堂兄弟/妹个数           False
父母与小孩个数           False
船票信息              False
票价                False
客舱                 True
登船港口               True
dtype: bool

3.保存数据

train.to_csv("train_chinese.csv")
```## 标题