05pandas读取excel csv txt文件

pandas丨数据读取与保存

• 读取excel文件: pandas.read_excel()
• 保存excel文件: pandas.to_excel()

pandas.read_excel(io, sheet_name=0, header=0, names=None, index_col=None, usecols=None,
squeeze=False, dtype=None, engine=None, converters=None, true_values=None,
false_values=None, skiprows=None, nrows=None, na_values=None, keep_default_na=True,
verbose=False, parse_dates=False, date_parser=None, thousands=None, comment=None,
skip_footer=0, skipfooter=0, convert_float=True, mangle_dupe_cols=True, **kwds)

#查看帮助文件
import pandas as pd
help(pd.read_excel)

Help on function read_excel in module pandas.io.excel._base:

read_excel(io, sheet_name=0, header=0, names=None, index_col=None, usecols=None, squeeze=False, dtype=None, engine=None, converters=None, true_values=None, false_values=None, skiprows=None, nrows=None, na_values=None, keep_default_na=True, na_filter=True, verbose=False, parse_dates=False, date_parser=None, thousands=None, comment=None, skipfooter=0, convert_float=True, mangle_dupe_cols=True)
    Read an Excel file into a pandas DataFrame.
    
    Supports `xls`, `xlsx`, `xlsm`, `xlsb`, `odf`, `ods` and `odt` file extensions
    read from a local filesystem or URL. Supports an option to read
    a single sheet or a list of sheets.

• 常用参数：
  • io：excel的路径,选中文件，鼠标右键，在"属性"中找到文件位置，再补充上文件名称，则为完整路径。注意反斜杠方向 ★★★★★
  • sheet_name：工作表的名称。当不输入时，默认读取第一个工作表
• 不常用参数
  • index_col ：指定某一列为索引。index_col=1
  • names ：列名称,传入list数据
  • header: 指定行作为列名,默认为第1行。header=[1,2]多级索引
  • usecols: 读取指定列。usecols = [“A”,“B”]
  • skiprows: 忽略前几行

pd.read_excel()常用参数

io

要读取文件所在的位置

• 字符串
• 注意 \ 和 / 的区别

# 读取文件
# 导入pandas工具包
import pandas as pd

# 方式1 ★★★
data1 = pd.read_excel('C:/Users/yyz/Desktop/python数据分析基础/data/泰坦尼克数据.xlsx')
data1.head()

	乘客ID	是否存活	票类	姓名	性别	年龄	乘客兄弟姐妹个数	乘客父母/孩子的个数	票号	票价	仓位	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

data2 = pd.read_excel('C:\\Users\\yyz\\Desktop\\python数据分析基础\\data\\泰坦尼克数据.xlsx')

data3 = pd.read_excel(r'C:\Users\yyz\Desktop\python数据分析基础\data\泰坦尼克数据.xlsx')

data3.head()

	乘客ID	是否存活	票类	姓名	性别	年龄	乘客兄弟姐妹个数	乘客父母/孩子的个数	票号	票价	仓位	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

# 方式2 ★★★
# 导入os工具包
import os
# 设置默认路径，当读取此文件夹下的文件时，直接输入文件名称就可以
os.chdir('C:/Users/yyz/Desktop/python数据分析基础/data/')

data4 = pd.read_excel('泰坦尼克数据.xlsx')

data4.head()

	乘客ID	是否存活	票类	姓名	性别	年龄	乘客兄弟姐妹个数	乘客父母/孩子的个数	票号	票价	仓位	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

sheet_name

读取的工作表,可以是工作表名称, 也可以是工作表所在的位置,0 表示第1个.

• 格式: 整数或者是字符串

# 方式1 ★★★
data5 = pd.read_excel('泰坦尼克数据.xlsx',sheet_name='Sheet1')
data5.head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
1	32	1	1	Spencer, Mrs. William Augustus (Marie Eugenie)	female	NaN	1	0	PC 17569	146.5208	B78	C
2	53	1	1	Harper, Mrs. Henry Sleeper (Myna Haxtun)	female	49.0	1	0	PC 17572	76.7292	D33	C
3	98	1	1	Greenfield, Mr. William Bertram	male	23.0	0	1	PC 17759	63.3583	D10 D12	C
4	195	1	1	Brown, Mrs. James Joseph (Margaret Tobin)	female	44.0	0	0	PC 17610	27.7208	B4	C

# 方式2
data6 = pd.read_excel('泰坦尼克数据.xlsx',sheet_name=1)
data6.head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
1	32	1	1	Spencer, Mrs. William Augustus (Marie Eugenie)	female	NaN	1	0	PC 17569	146.5208	B78	C
2	53	1	1	Harper, Mrs. Henry Sleeper (Myna Haxtun)	female	49.0	1	0	PC 17572	76.7292	D33	C
3	98	1	1	Greenfield, Mr. William Bertram	male	23.0	0	1	PC 17759	63.3583	D10 D12	C
4	195	1	1	Brown, Mrs. James Joseph (Margaret Tobin)	female	44.0	0	0	PC 17610	27.7208	B4	C

pd.read_excel()不常用参数

index_col

指定哪一列为索引, 默认不设置

• 格式:字符串或者字符串构成的列表

data7 = pd.read_excel('泰坦尼克数据.xlsx',index_col='乘客ID')
data7

	是否存活	票类	姓名	性别	年龄	乘客兄弟姐妹个数	乘客父母/孩子的个数	票号	票价	仓位	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
...	...	...	...	...	...	...	...	...	...	...	...
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

891 rows × 11 columns

names

指定列名

• 格式: 列表

data8 = pd.read_excel('泰坦尼克数据.xlsx',
                      names=['变量1','变量2','变量3','变量4','变量5','变量6','变量7','变量8','变量9','变量10','变量11','变量12'])

data8.head()

	变量1	变量2	变量3	变量4	变量5	变量6	变量7	变量8	变量9	变量10	变量11	变量12
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

# 更改列名一般用DataFrame中columns属性★★★
data8.columns = ['乘客ID', '是否存活', '票类', '姓名', '性别', '年龄', '乘客兄弟姐妹个数',
                 '乘客父母/孩子的个数', '票号','票价', '仓位', '登船港口']

data8.head()

	乘客ID	是否存活	票类	姓名	性别	年龄	乘客兄弟姐妹个数	乘客父母/孩子的个数	票号	票价	仓位	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

usecols

选择要读取的列

• 格式: 列表

data7 = pd.read_excel('泰坦尼克数据.xlsx',usecols=['姓名','性别','年龄'])
data7.head()

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

# 方式二★★★
data8 = pd.read_excel('泰坦尼克数据.xlsx')[['姓名','性别','年龄']]  # 注意是两个中括号
data8.head()

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

header

设置列名所在的行

• 格式: 整数或者 None

data9 = pd.read_excel('泰坦尼克数据.xlsx',header=1)
data9.head()

	1	0	3	Braund, Mr. Owen Harris	male	22	1.1	0.1	A/5 21171	7.25	Unnamed: 10	S
0	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
1	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
2	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
3	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S
4	6	0	3	Moran, Mr. James	male	NaN	0	0	330877	8.4583	NaN	Q

data10 = pd.read_excel('泰坦尼克数据.xlsx',header=None)
data10.head()

	0	1	2	3	4	5	6	7	8	9	10	11
0	乘客ID	是否存活	票类	姓名	性别	年龄	乘客兄弟姐妹个数	乘客父母/孩子的个数	票号	票价	仓位	登船港口
1	1	0	3	Braund, Mr. Owen Harris	male	22	1	0	A/5 21171	7.25	NaN	S
2	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38	1	0	PC 17599	71.2833	C85	C
3	3	1	3	Heikkinen, Miss. Laina	female	26	0	0	STON/O2. 3101282	7.925	NaN	S
4	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35	1	0	113803	53.1	C123	S

skiprows

忽略前几行:当前几行为空行或者其他不需要读取的数据时使用

data11 = pd.read_excel(r'C:\Users\yyz\Desktop\python数据分析基础\data\泰坦尼克数据.xlsx',
                      skiprows=1)
data11.head()

	1	0	3	Braund, Mr. Owen Harris	male	22	1.1	0.1	A/5 21171	7.25	Unnamed: 10	S
0	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
1	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
2	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
3	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S
4	6	0	3	Moran, Mr. James	male	NaN	0	0	330877	8.4583	NaN	Q

pd.to_excel()常用参数

# 导入pandas工具包，并简写为pd
import pandas as pd
# 读取数据
data1 = pd.read_excel('C:/Users/yyz/Desktop/python数据分析基础/data/泰坦尼克数据.xlsx')

data1.head()

	乘客ID	是否存活	票类	姓名	性别	年龄	乘客兄弟姐妹个数	乘客父母/孩子的个数	票号	票价	仓位	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

data1.info()

RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
 #   Column      Non-Null Count  Dtype  
---  ------      --------------  -----  
 0   乘客ID        891 non-null    int64  
 1   是否存活        891 non-null    int64  
 2   票类          891 non-null    int64  
 3   姓名          891 non-null    object 
 4   性别          891 non-null    object 
 5   年龄          714 non-null    float64
 6   乘客兄弟姐妹个数    891 non-null    int64  
 7   乘客父母/孩子的个数  891 non-null    int64  
 8   票号          891 non-null    object 
 9   票价          891 non-null    float64
 10  仓位          204 non-null    object 
 11  登船港口        889 non-null    object 
dtypes: float64(2), int64(5), object(5)
memory usage: 83.7+ KB

# 数据透视表1：按照性别、登录港口统计人数
result1 = data1.pivot_table('姓名',      # 需要计算统计量的变量（字段）
                            index='性别',   # 行变量,当需要输入多个时 用列表形式 ['','']
                            columns='登船港口', # 列变量,当需要输入多个时 用列表形式 ['','']
                            aggfunc='count', # 需要计算的统计量，'sum','mean','max'等
                            margins=True)   # 是否显示合计

# 数据透视表2：按照性别、票类统计人数
result2 = data1.pivot_table('姓名',
                            index='性别',
                            columns='票类',
                            aggfunc='count',
                            margins=True)   # 是否显示合计

result1.head()

登船港口	C	Q	S	All
性别
female	73	36	203	312
male	95	41	441	577
All	168	77	644	889

result2

票类	1	2	3	All
性别
female	94	76	144	314
male	122	108	347	577
All	216	184	491	891

# 最常用写法
result1.to_excel('C:/Users/yyz/Desktop/保存数据1.xlsx')

# 当索引为数值序列，不期望导出的时候设置index=False
result2.to_excel('C:/Users/yyz/Desktop/保存数据2.xlsx',index=False)

result2.to_excel('C:/Users/yyz/Desktop/保存数据3.xlsx',sheet_name='汇总')

with pd.ExcelWriter('C:/Users/yyz/Desktop/保存数据4.xlsx') as writer:
    result1.to_excel(writer,sheet_name='第1个表')
    result2.to_excel(writer,sheet_name='第2个表')

pandas丨读取csv、txt文件

• 当数据量比较大时, 一般会存储为csv或者txt格式文件;
• 读取方法:pandas.read_csv(), 括号内参数如下:

pandas.read_csv(filepath_or_buffer: Union[str, pathlib.Path, IO[~AnyStr]], sep=’,’, delimiter=None,
header=‘infer’, names=None, index_col=None, usecols=None, squeeze=False, prefix=None,
mangle_dupe_cols=True, dtype=None, engine=None, converters=None, true_values=None,
false_values=None, skipinitialspace=False, skiprows=None, skipfooter=0, nrows=None,
na_values=None, keep_default_na=True, na_filter=True, verbose=False, skip_blank_lines=True,
parse_dates=False, infer_datetime_format=False, keep_date_col=False, date_parser=None,
dayfirst=False, cache_dates=True, iterator=False, chunksize=None, compression=‘infer’,
thousands=None, decimal=b’.’, lineterminator=None, quotechar=’"’, quoting=0, doublequote=True,
escapechar=None, comment=None, encoding=None, dialect=None, error_bad_lines=True,
warn_bad_lines=True, delim_whitespace=False, low_memory=True, memory_map=False,
float_precision=None)

• 常用参数：
  • filepath_or_buffer ：文件路径 ，和读取excel中io参数一样
  • sep ：分隔符，默认逗号,其他特殊符号: ※
    • 回车: \r,
    • 换行: \n,
    • 制表符: \t,
    • 空白字符: \s
    • 多个空白字符: \s+
  • encoding ：一般utf-8 或者 gbk
• 其他参数和pd.read_excel()参数类似

# 查看帮助文档
import pandas as pd
help(pd.read_csv)

Help on function read_csv in module pandas.io.parsers:

read_csv(filepath_or_buffer: Union[str, pathlib.Path, IO[~AnyStr]], sep=',', delimiter=None, header='infer', names=None, index_col=None, usecols=None, squeeze=False, prefix=None, mangle_dupe_cols=True, dtype=None, engine=None, converters=None, true_values=None, false_values=None, skipinitialspace=False, skiprows=None, skipfooter=0, nrows=None, na_values=None, keep_default_na=True, na_filter=True, verbose=False, skip_blank_lines=True, parse_dates=False, infer_datetime_format=False, keep_date_col=False, date_parser=None, dayfirst=False, cache_dates=True, iterator=False, chunksize=None, compression='infer', thousands=None, decimal: str = '.', lineterminator=None, quotechar='"', quoting=0, doublequote=True, escapechar=None, comment=None, encoding=None, dialect=None, error_bad_lines=True, warn_bad_lines=True, delim_whitespace=False, low_memory=True, memory_map=False, float_precision=None)

# 读取csv格式文件
data1 = pd.read_csv('C:/Users/yyz/Desktop/python数据分析基础/data/titanic_train.csv')
data1.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

# 读取txt格式文件:sep参数
data2 = pd.read_csv('C:/Users/yyz/Desktop/python数据分析基础/data/titanic_train.txt',sep='\t')  # 不输入sep参数则无法准确读取
data2.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

data2.sample(10).to_csv('C:/Users/yyz/Desktop/导出txt文件.txt',sep=':')

提升代码速度小技巧

• 微软拼音：设置→常规→开启“中文输入时使用英文标点”
• 搜狗拼音：设置→常用→开启“中文时使用英文标点”

扫码关注微信, 赠送《pandas数据读取与清洗》视频及课程代码!