数据科学和人工智能技术笔记十九、数据整理（1）

2019年5月18日 167次阅读来源: ApacheCN_飞龙

十九、数据整理（1）

作者：Chris Albon
译者：飞龙
协议：CC BY-NC-SA 4.0

在 Pandas 中通过分组应用函数

import pandas as pd

# 创建示例数据帧
data = {'Platoon': ['A','A','A','A','A','A','B','B','B','B','B','C','C','C','C','C'],
       'Casualties': [1,4,5,7,5,5,6,1,4,5,6,7,4,6,4,6]}
df = pd.DataFrame(data)
df

	Casualties	Platoon
0	1	A
1	4	A
2	5	A
3	7	A
4	5	A
5	5	A
6	6	B
7	1	B
8	4	B
9	5	B
10	6	B
11	7	C
12	4	C
13	6	C
14	4	C
15	6	C

# 按照 df.platoon 对 df 分组
# 然后将滚动平均 lambda 函数应用于 df.casualties
df.groupby('Platoon')['Casualties'].apply(lambda x:x.rolling(center=False,window=2).mean())

'''
0     NaN
1     2.5
2     4.5
3     6.0
4     6.0
5     5.0
6     NaN
7     3.5
8     2.5
9     4.5
10    5.5
11    NaN
12    5.5
13    5.0
14    5.0
15    5.0
dtype: float64
'''

在 Pandas 中向分组应用操作

# 导入模块
import pandas as pd

# 创建数据帧
raw_data = {'regiment': ['Nighthawks', 'Nighthawks', 'Nighthawks', 'Nighthawks', 'Dragoons', 'Dragoons', 'Dragoons', 'Dragoons', 'Scouts', 'Scouts', 'Scouts', 'Scouts'], 
        'company': ['1st', '1st', '2nd', '2nd', '1st', '1st', '2nd', '2nd','1st', '1st', '2nd', '2nd'], 
        'name': ['Miller', 'Jacobson', 'Ali', 'Milner', 'Cooze', 'Jacon', 'Ryaner', 'Sone', 'Sloan', 'Piger', 'Riani', 'Ali'], 
        'preTestScore': [4, 24, 31, 2, 3, 4, 24, 31, 2, 3, 2, 3],
        'postTestScore': [25, 94, 57, 62, 70, 25, 94, 57, 62, 70, 62, 70]}
df = pd.DataFrame(raw_data, columns = ['regiment', 'company', 'name', 'preTestScore', 'postTestScore'])
df

	regiment	company	name	preTestScore	postTestScore
0	Nighthawks	1st	Miller	4	25
1	Nighthawks	1st	Jacobson	24	94
2	Nighthawks	2nd	Ali	31	57
3	Nighthawks	2nd	Milner	2	62
4	Dragoons	1st	Cooze	3	70
5	Dragoons	1st	Jacon	4	25
6	Dragoons	2nd	Ryaner	24	94
7	Dragoons	2nd	Sone	31	57
8	Scouts	1st	Sloan	2	62
9	Scouts	1st	Piger	3	70
10	Scouts	2nd	Riani	2	62
11	Scouts	2nd	Ali	3	70

# 创建一个 groupby 变量，按团队（regiment）对 preTestScores 分组
groupby_regiment = df['preTestScore'].groupby(df['regiment'])
groupby_regiment

# <pandas.core.groupby.SeriesGroupBy object at 0x113ddb550>

“这个分组变量现在是GroupBy对象。除了分组的键df ['key1']的一些中间数据之外，它实际上还没有计算任何东西。我们的想法是，该对象具有将所有操作应用于每个分组所需的所有信息。” — PyDA

使用list()显示分组的样子。

list(df['preTestScore'].groupby(df['regiment']))

'''
[('Dragoons', 4     3
  5     4
  6    24
  7    31
  Name: preTestScore, dtype: int64), ('Nighthawks', 0     4
  1    24
  2    31
  3     2
  Name: preTestScore, dtype: int64), ('Scouts', 8     2
  9     3
  10    2
  11    3
  Name: preTestScore, dtype: int64)] 
'''

df['preTestScore'].groupby(df['regiment']).describe()

	count	mean	std	min	25%	50%	75%	max
regiment
Dragoons	4.0	15.50	14.153916	3.0	3.75	14.0	25.75	31.0
Nighthawks	4.0	15.25	14.453950	2.0	3.50	14.0	25.75	31.0
Scouts	4.0	2.50	0.577350	2.0	2.00	2.5	3.00	3.0

# 每个团队的 preTestScore 均值
groupby_regiment.mean()

'''
regiment
Dragoons      15.50
Nighthawks    15.25
Scouts         2.50
Name: preTestScore, dtype: float64 
'''

df['preTestScore'].groupby([df['regiment'], df['company']]).mean()

'''
regiment    company
Dragoons    1st         3.5
            2nd        27.5
Nighthawks  1st        14.0
            2nd        16.5
Scouts      1st         2.5
            2nd         2.5
Name: preTestScore, dtype: float64 
'''

df['preTestScore'].groupby([df['regiment'], df['company']]).mean().unstack()

company	1st	2nd
regiment
Dragoons	3.5	27.5
Nighthawks	14.0	16.5
Scouts	2.5	2.5

# 按团队和公司（company）对整个数据帧分组
df.groupby(['regiment', 'company']).mean()

		preTestScore	postTestScore
regiment	company
Dragoons	1st	3.5	47.5
2nd	27.5	75.5
Nighthawks	1st	14.0	59.5
2nd	16.5	59.5
Scouts	1st	2.5	66.0
2nd	2.5	66.0

# 每个团队和公司的观测数量
df.groupby(['regiment', 'company']).size()

'''
regiment    company
Dragoons    1st        2
            2nd        2
Nighthawks  1st        2
            2nd        2
Scouts      1st        2
            2nd        2
dtype: int64 
'''

# 按团队对数据帧分组，对于每个团队，
for name, group in df.groupby('regiment'): 
    # 打印团队名称
    print(name)
    # 打印它的数据
    print(group)


'''
Dragoons
   regiment company    name  preTestScore  postTestScore
4  Dragoons     1st   Cooze             3             70
5  Dragoons     1st   Jacon             4             25
6  Dragoons     2nd  Ryaner            24             94
7  Dragoons     2nd    Sone            31             57
Nighthawks
     regiment company      name  preTestScore  postTestScore
0  Nighthawks     1st    Miller             4             25
1  Nighthawks     1st  Jacobson            24             94
2  Nighthawks     2nd       Ali            31             57
3  Nighthawks     2nd    Milner             2             62
Scouts
   regiment company   name  preTestScore  postTestScore
8    Scouts     1st  Sloan             2             62
9    Scouts     1st  Piger             3             70
10   Scouts     2nd  Riani             2             62
11   Scouts     2nd    Ali             3             70 
'''

按列分组：

特别是在这种情况下：按列对数据类型（即axis = 1）分组，然后使用list()查看该分组的外观。

list(df.groupby(df.dtypes, axis=1))

'''
[(dtype('int64'),     preTestScore  postTestScore
  0              4             25
  1             24             94
  2             31             57
  3              2             62
  4              3             70
  5              4             25
  6             24             94
  7             31             57
  8              2             62
  9              3             70
  10             2             62
  11             3             70),
 (dtype('O'),       regiment company      name
  0   Nighthawks     1st    Miller
  1   Nighthawks     1st  Jacobson
  2   Nighthawks     2nd       Ali
  3   Nighthawks     2nd    Milner
  4     Dragoons     1st     Cooze
  5     Dragoons     1st     Jacon
  6     Dragoons     2nd    Ryaner
  7     Dragoons     2nd      Sone
  8       Scouts     1st     Sloan
  9       Scouts     1st     Piger
  10      Scouts     2nd     Riani
  11      Scouts     2nd       Ali)] 

df.groupby('regiment').mean().add_prefix('mean_')

	mean_preTestScore	mean_postTestScore
regiment
Dragoons	15.50	61.5
Nighthawks	15.25	59.5
Scouts	2.50	66.0

# 创建获取分组状态的函数
def get_stats(group):
    return {'min': group.min(), 'max': group.max(), 'count': group.count(), 'mean': group.mean()}

bins = [0, 25, 50, 75, 100]
group_names = ['Low', 'Okay', 'Good', 'Great']
df['categories'] = pd.cut(df['postTestScore'], bins, labels=group_names)

df['postTestScore'].groupby(df['categories']).apply(get_stats).unstack()

	count	max	mean	min
categories
Good	8.0	70.0	63.75	57.0
Great	2.0	94.0	94.00	94.0
Low	2.0	25.0	25.00	25.0
Okay	0.0	NaN	NaN	NaN

在 Pandas 数据帧上应用操作

# 导入模型
import pandas as pd
import numpy as np

data = {'name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'], 
        'year': [2012, 2012, 2013, 2014, 2014], 
        'reports': [4, 24, 31, 2, 3],
        'coverage': [25, 94, 57, 62, 70]}
df = pd.DataFrame(data, index = ['Cochice', 'Pima', 'Santa Cruz', 'Maricopa', 'Yuma'])
df

	coverage	name	reports	year
Cochice	25	Jason	4	2012
Pima	94	Molly	24	2012
Santa Cruz	57	Tina	31	2013
Maricopa	62	Jake	2	2014
Yuma	70	Amy	3	2014

# 创建大写转换的 lambda 函数
capitalizer = lambda x: x.upper()

将capitalizer函数应用于name列。

apply()可以沿数据帧的任意轴应用函数。

df['name'].apply(capitalizer)

'''
Cochice       JASON
Pima          MOLLY
Santa Cruz     TINA
Maricopa       JAKE
Yuma            AMY
Name: name, dtype: object 
'''

将capitalizer lambda 函数映射到序列name中的每个元素。

map()对序列的每个元素应用操作。

df['name'].map(capitalizer)

'''
Cochice       JASON
Pima          MOLLY
Santa Cruz     TINA
Maricopa       JAKE
Yuma            AMY
Name: name, dtype: object 
'''

将平方根函数应用于整个数据帧中的每个单元格。

applymap()将函数应用于整个数据帧中的每个元素。

# 删除字符串变量，以便 applymap() 可以运行
df = df.drop('name', axis=1)

# 返回数据帧每个单元格的平方根
df.applymap(np.sqrt)

	coverage	reports	year
Cochice	5.000000	2.000000	44.855323
Pima	9.695360	4.898979	44.855323
Santa Cruz	7.549834	5.567764	44.866469
Maricopa	7.874008	1.414214	44.877611
Yuma	8.366600	1.732051	44.877611

在数据帧上应用函数。

# 创建叫做 times100 的函数
def times100(x):
    # 如果 x 是字符串，
    if type(x) is str:
        # 原样返回它
        return x
    # 如果不是，返回它乘上 100
    elif x:
        return 100 * x
    # 并留下其它东西
    else:
        return

df.applymap(times100)

	coverage	reports	year
Cochice	2500	400	201200
Pima	9400	2400	201200
Santa Cruz	5700	3100	201300
Maricopa	6200	200	201400
Yuma	7000	300	201400

向 Pandas 数据帧赋予新列

import pandas as pd

# 创建空数据帧
df = pd.DataFrame()

# 创建一列
df['name'] = ['John', 'Steve', 'Sarah']

# 查看数据帧
df

	name
0	John
1	Steve
2	Sarah

# 将一个新列赋予名为 age 的 df，它包含年龄列表
df.assign(age = [31, 32, 19])

	name	age
0	John	31
1	Steve	32
2	Sarah	19

将列表拆分为大小为 N 的分块

在这个片段中，我们接受一个列表并将其分解为大小为 n 的块。在处理具有最大请求大小的 API 时，这是一种非常常见的做法。

这个漂亮的函数由 Ned Batchelder 贡献，发布于 StackOverflow。

# 创建名称列表
first_names = ['Steve', 'Jane', 'Sara', 'Mary','Jack','Bob', 'Bily', 'Boni', 'Chris','Sori', 'Will', 'Won','Li']

# 创建叫做 chunks 的函数，有两个参数 l 和 n
def chunks(l, n):
    # 对于长度为 l 的范围中的项目 i
    for i in range(0, len(l), n):
        # 创建索引范围
        yield l[i:i+n]

# 从函数 chunks 的结果创建一个列表
list(chunks(first_names, 5))

'''
[['Steve', 'Jane', 'Sara', 'Mary', 'Jack'],
 ['Bob', 'Bily', 'Boni', 'Chris', 'Sori'],
 ['Will', 'Won', 'Li']] 
'''

在 Pandas 中使用正则表达式将字符串分解为列

# 导入模块
import re
import pandas as pd

# 创建带有一列字符串的数据帧
data = {'raw': ['Arizona 1 2014-12-23       3242.0',
                'Iowa 1 2010-02-23       3453.7',
                'Oregon 0 2014-06-20       2123.0',
                'Maryland 0 2014-03-14       1123.6',
                'Florida 1 2013-01-15       2134.0',
                'Georgia 0 2012-07-14       2345.6']}
df = pd.DataFrame(data, columns = ['raw'])
df

	raw
0	Arizona 1 2014-12-23 3242.0
1	Iowa 1 2010-02-23 3453.7
2	Oregon 0 2014-06-20 2123.0
3	Maryland 0 2014-03-14 1123.6
4	Florida 1 2013-01-15 2134.0
5	Georgia 0 2012-07-14 2345.6

# df['raw'] 的哪些行包含 'xxxx-xx-xx'？
df['raw'].str.contains('....-..-..', regex=True)

'''
0    True
1    True
2    True
3    True
4    True
5    True
Name: raw, dtype: bool 
'''

# 在 raw 列中，提取字符串中的单个数字
df['female'] = df['raw'].str.extract('(\d)', expand=True)
df['female']

'''
0    1
1    1
2    0
3    0
4    1
5    0
Name: female, dtype: object 
'''

# 在 raw 列中，提取字符串中的 xxxx-xx-xx
df['date'] = df['raw'].str.extract('(....-..-..)', expand=True)
df['date']

'''
0    2014-12-23
1    2010-02-23
2    2014-06-20
3    2014-03-14
4    2013-01-15
5    2012-07-14
Name: date, dtype: object 
'''

# 在 raw 列中，提取字符串中的 ####.##
df['score'] = df['raw'].str.extract('(\d\d\d\d\.\d)', expand=True)
df['score']

'''
0    3242.0
1    3453.7
2    2123.0
3    1123.6
4    2134.0
5    2345.6
Name: score, dtype: object 
'''

# 在 raw 列中，提取字符串中的单词
df['state'] = df['raw'].str.extract('([A-Z]\w{0,})', expand=True)
df['state']

'''
0     Arizona
1        Iowa
2      Oregon
3    Maryland
4     Florida
5     Georgia
Name: state, dtype: object 
'''

df

	raw	female	date	score	state
0	Arizona 1 2014-12-23 3242.0	1	2014-12-23	3242.0	Arizona
1	Iowa 1 2010-02-23 3453.7	1	2010-02-23	3453.7	Iowa
2	Oregon 0 2014-06-20 2123.0	0	2014-06-20	2123.0	Oregon
3	Maryland 0 2014-03-14 1123.6	0	2014-03-14	1123.6	Maryland
4	Florida 1 2013-01-15 2134.0	1	2013-01-15	2134.0	Florida
5	Georgia 0 2012-07-14 2345.6	0	2012-07-14	2345.6	Georgia

由两个数据帧贡献列

# 导入库
import pandas as pd

# 创建数据帧
dataframe_one = pd.DataFrame()
dataframe_one['1'] = ['1', '1', '1']
dataframe_one['B'] = ['b', 'b', 'b']

# 创建第二个数据帧
dataframe_two = pd.DataFrame()
dataframe_two['2'] = ['2', '2', '2']
dataframe_two['B'] = ['b', 'b', 'b']

# 将每个数据帧的列转换为集合，
# 然后找到这两个集合的交集。
# 这将是两个数据帧共享的列的集合。
set.intersection(set(dataframe_one), set(dataframe_two))

# {'B'}

从多个列表构建字典

# 创建官员名称的列表
officer_names = ['Sodoni Dogla', 'Chris Jefferson', 'Jessica Billars', 'Michael Mulligan', 'Steven Johnson']

# 创建官员军队的列表
officer_armies = ['Purple Army', 'Orange Army', 'Green Army', 'Red Army', 'Blue Army']

# 创建字典，它是两个列表的 zip
dict(zip(officer_names, officer_armies))

'''
{'Chris Jefferson': 'Orange Army',
 'Jessica Billars': 'Green Army',
 'Michael Mulligan': 'Red Army',
 'Sodoni Dogla': 'Purple Army',
 'Steven Johnson': 'Blue Army'} 
'''

将 CSV 转换为 Python 代码来重建它

# 导入 pandas 包
import pandas as pd

# 将 csv 文件加载为数据帧
df_original = pd.read_csv('http://vincentarelbundock.github.io/Rdatasets/csv/datasets/iris.csv')
df = pd.read_csv('http://vincentarelbundock.github.io/Rdatasets/csv/datasets/iris.csv')

# 打印创建数据帧的代码
print('==============================')
print('RUN THE CODE BELOW THIS LINE')
print('==============================')
print('raw_data =', df.to_dict(orient='list'))
print('df = pd.DataFrame(raw_data, columns = ' + str(list(df_original)) + ')')

'''
==============================
RUN THE CODE BELOW THIS LINE
==============================
raw_data = {'Sepal.Length': [5.0999999999999996, 4.9000000000000004, 4.7000000000000002, 4.5999999999999996, 5.0, 5.4000000000000004, 4.5999999999999996, 5.0, 4.4000000000000004, 4.9000000000000004, 5.4000000000000004, 4.7999999999999998, 4.7999999999999998, 4.2999999999999998, 5.7999999999999998, 5.7000000000000002, 5.4000000000000004, 5.0999999999999996, 5.7000000000000002, 5.0999999999999996, 5.4000000000000004, 5.0999999999999996, 4.5999999999999996, 5.0999999999999996, 4.7999999999999998, 5.0, 5.0, 5.2000000000000002, 5.2000000000000002, 4.7000000000000002, 4.7999999999999998, 5.4000000000000004, 5.2000000000000002, 5.5, 4.9000000000000004, 5.0, 5.5, 4.9000000000000004, 4.4000000000000004, 5.0999999999999996, 5.0, 4.5, 4.4000000000000004, 5.0, 5.0999999999999996, 4.7999999999999998, 5.0999999999999996, 4.5999999999999996, 5.2999999999999998, 5.0, 7.0, 6.4000000000000004, 6.9000000000000004, 5.5, 6.5, 5.7000000000000002, 6.2999999999999998, 4.9000000000000004, 6.5999999999999996, 5.2000000000000002, 5.0, 5.9000000000000004, 6.0, 6.0999999999999996, 5.5999999999999996, 6.7000000000000002, 5.5999999999999996, 5.7999999999999998, 6.2000000000000002, 5.5999999999999996, 5.9000000000000004, 6.0999999999999996, 6.2999999999999998, 6.0999999999999996, 6.4000000000000004, 6.5999999999999996, 6.7999999999999998, 6.7000000000000002, 6.0, 5.7000000000000002, 5.5, 5.5, 5.7999999999999998, 6.0, 5.4000000000000004, 6.0, 6.7000000000000002, 6.2999999999999998, 5.5999999999999996, 5.5, 5.5, 6.0999999999999996, 5.7999999999999998, 5.0, 5.5999999999999996, 5.7000000000000002, 5.7000000000000002, 6.2000000000000002, 5.0999999999999996, 5.7000000000000002, 6.2999999999999998, 5.7999999999999998, 7.0999999999999996, 6.2999999999999998, 6.5, 7.5999999999999996, 4.9000000000000004, 7.2999999999999998, 6.7000000000000002, 7.2000000000000002, 6.5, 6.4000000000000004, 6.7999999999999998, 5.7000000000000002, 5.7999999999999998, 6.4000000000000004, 6.5, 7.7000000000000002, 7.7000000000000002, 6.0, 6.9000000000000004, 5.5999999999999996, 7.7000000000000002, 6.2999999999999998, 6.7000000000000002, 7.2000000000000002, 6.2000000000000002, 6.0999999999999996, 6.4000000000000004, 7.2000000000000002, 7.4000000000000004, 7.9000000000000004, 6.4000000000000004, 6.2999999999999998, 6.0999999999999996, 7.7000000000000002, 6.2999999999999998, 6.4000000000000004, 6.0, 6.9000000000000004, 6.7000000000000002, 6.9000000000000004, 5.7999999999999998, 6.7999999999999998, 6.7000000000000002, 6.7000000000000002, 6.2999999999999998, 6.5, 6.2000000000000002, 5.9000000000000004], 'Petal.Width': [0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.40000000000000002, 0.29999999999999999, 0.20000000000000001, 0.20000000000000001, 0.10000000000000001, 0.20000000000000001, 0.20000000000000001, 0.10000000000000001, 0.10000000000000001, 0.20000000000000001, 0.40000000000000002, 0.40000000000000002, 0.29999999999999999, 0.29999999999999999, 0.29999999999999999, 0.20000000000000001, 0.40000000000000002, 0.20000000000000001, 0.5, 0.20000000000000001, 0.20000000000000001, 0.40000000000000002, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.40000000000000002, 0.10000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.10000000000000001, 0.20000000000000001, 0.20000000000000001, 0.29999999999999999, 0.29999999999999999, 0.20000000000000001, 0.59999999999999998, 0.40000000000000002, 0.29999999999999999, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 1.3999999999999999, 1.5, 1.5, 1.3, 1.5, 1.3, 1.6000000000000001, 1.0, 1.3, 1.3999999999999999, 1.0, 1.5, 1.0, 1.3999999999999999, 1.3, 1.3999999999999999, 1.5, 1.0, 1.5, 1.1000000000000001, 1.8, 1.3, 1.5, 1.2, 1.3, 1.3999999999999999, 1.3999999999999999, 1.7, 1.5, 1.0, 1.1000000000000001, 1.0, 1.2, 1.6000000000000001, 1.5, 1.6000000000000001, 1.5, 1.3, 1.3, 1.3, 1.2, 1.3999999999999999, 1.2, 1.0, 1.3, 1.2, 1.3, 1.3, 1.1000000000000001, 1.3, 2.5, 1.8999999999999999, 2.1000000000000001, 1.8, 2.2000000000000002, 2.1000000000000001, 1.7, 1.8, 1.8, 2.5, 2.0, 1.8999999999999999, 2.1000000000000001, 2.0, 2.3999999999999999, 2.2999999999999998, 1.8, 2.2000000000000002, 2.2999999999999998, 1.5, 2.2999999999999998, 2.0, 2.0, 1.8, 2.1000000000000001, 1.8, 1.8, 1.8, 2.1000000000000001, 1.6000000000000001, 1.8999999999999999, 2.0, 2.2000000000000002, 1.5, 1.3999999999999999, 2.2999999999999998, 2.3999999999999999, 1.8, 1.8, 2.1000000000000001, 2.3999999999999999, 2.2999999999999998, 1.8999999999999999, 2.2999999999999998, 2.5, 2.2999999999999998, 1.8999999999999999, 2.0, 2.2999999999999998, 1.8], 'Petal.Length': [1.3999999999999999, 1.3999999999999999, 1.3, 1.5, 1.3999999999999999, 1.7, 1.3999999999999999, 1.5, 1.3999999999999999, 1.5, 1.5, 1.6000000000000001, 1.3999999999999999, 1.1000000000000001, 1.2, 1.5, 1.3, 1.3999999999999999, 1.7, 1.5, 1.7, 1.5, 1.0, 1.7, 1.8999999999999999, 1.6000000000000001, 1.6000000000000001, 1.5, 1.3999999999999999, 1.6000000000000001, 1.6000000000000001, 1.5, 1.5, 1.3999999999999999, 1.5, 1.2, 1.3, 1.3999999999999999, 1.3, 1.5, 1.3, 1.3, 1.3, 1.6000000000000001, 1.8999999999999999, 1.3999999999999999, 1.6000000000000001, 1.3999999999999999, 1.5, 1.3999999999999999, 4.7000000000000002, 4.5, 4.9000000000000004, 4.0, 4.5999999999999996, 4.5, 4.7000000000000002, 3.2999999999999998, 4.5999999999999996, 3.8999999999999999, 3.5, 4.2000000000000002, 4.0, 4.7000000000000002, 3.6000000000000001, 4.4000000000000004, 4.5, 4.0999999999999996, 4.5, 3.8999999999999999, 4.7999999999999998, 4.0, 4.9000000000000004, 4.7000000000000002, 4.2999999999999998, 4.4000000000000004, 4.7999999999999998, 5.0, 4.5, 3.5, 3.7999999999999998, 3.7000000000000002, 3.8999999999999999, 5.0999999999999996, 4.5, 4.5, 4.7000000000000002, 4.4000000000000004, 4.0999999999999996, 4.0, 4.4000000000000004, 4.5999999999999996, 4.0, 3.2999999999999998, 4.2000000000000002, 4.2000000000000002, 4.2000000000000002, 4.2999999999999998, 3.0, 4.0999999999999996, 6.0, 5.0999999999999996, 5.9000000000000004, 5.5999999999999996, 5.7999999999999998, 6.5999999999999996, 4.5, 6.2999999999999998, 5.7999999999999998, 6.0999999999999996, 5.0999999999999996, 5.2999999999999998, 5.5, 5.0, 5.0999999999999996, 5.2999999999999998, 5.5, 6.7000000000000002, 6.9000000000000004, 5.0, 5.7000000000000002, 4.9000000000000004, 6.7000000000000002, 4.9000000000000004, 5.7000000000000002, 6.0, 4.7999999999999998, 4.9000000000000004, 5.5999999999999996, 5.7999999999999998, 6.0999999999999996, 6.4000000000000004, 5.5999999999999996, 5.0999999999999996, 5.5999999999999996, 6.0999999999999996, 5.5999999999999996, 5.5, 4.7999999999999998, 5.4000000000000004, 5.5999999999999996, 5.0999999999999996, 5.0999999999999996, 5.9000000000000004, 5.7000000000000002, 5.2000000000000002, 5.0, 5.2000000000000002, 5.4000000000000004, 5.0999999999999996], 'Species': ['setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica'], 'Sepal.Width': [3.5, 3.0, 3.2000000000000002, 3.1000000000000001, 3.6000000000000001, 3.8999999999999999, 3.3999999999999999, 3.3999999999999999, 2.8999999999999999, 3.1000000000000001, 3.7000000000000002, 3.3999999999999999, 3.0, 3.0, 4.0, 4.4000000000000004, 3.8999999999999999, 3.5, 3.7999999999999998, 3.7999999999999998, 3.3999999999999999, 3.7000000000000002, 3.6000000000000001, 3.2999999999999998, 3.3999999999999999, 3.0, 3.3999999999999999, 3.5, 3.3999999999999999, 3.2000000000000002, 3.1000000000000001, 3.3999999999999999, 4.0999999999999996, 4.2000000000000002, 3.1000000000000001, 3.2000000000000002, 3.5, 3.6000000000000001, 3.0, 3.3999999999999999, 3.5, 2.2999999999999998, 3.2000000000000002, 3.5, 3.7999999999999998, 3.0, 3.7999999999999998, 3.2000000000000002, 3.7000000000000002, 3.2999999999999998, 3.2000000000000002, 3.2000000000000002, 3.1000000000000001, 2.2999999999999998, 2.7999999999999998, 2.7999999999999998, 3.2999999999999998, 2.3999999999999999, 2.8999999999999999, 2.7000000000000002, 2.0, 3.0, 2.2000000000000002, 2.8999999999999999, 2.8999999999999999, 3.1000000000000001, 3.0, 2.7000000000000002, 2.2000000000000002, 2.5, 3.2000000000000002, 2.7999999999999998, 2.5, 2.7999999999999998, 2.8999999999999999, 3.0, 2.7999999999999998, 3.0, 2.8999999999999999, 2.6000000000000001, 2.3999999999999999, 2.3999999999999999, 2.7000000000000002, 2.7000000000000002, 3.0, 3.3999999999999999, 3.1000000000000001, 2.2999999999999998, 3.0, 2.5, 2.6000000000000001, 3.0, 2.6000000000000001, 2.2999999999999998, 2.7000000000000002, 3.0, 2.8999999999999999, 2.8999999999999999, 2.5, 2.7999999999999998, 3.2999999999999998, 2.7000000000000002, 3.0, 2.8999999999999999, 3.0, 3.0, 2.5, 2.8999999999999999, 2.5, 3.6000000000000001, 3.2000000000000002, 2.7000000000000002, 3.0, 2.5, 2.7999999999999998, 3.2000000000000002, 3.0, 3.7999999999999998, 2.6000000000000001, 2.2000000000000002, 3.2000000000000002, 2.7999999999999998, 2.7999999999999998, 2.7000000000000002, 3.2999999999999998, 3.2000000000000002, 2.7999999999999998, 3.0, 2.7999999999999998, 3.0, 2.7999999999999998, 3.7999999999999998, 2.7999999999999998, 2.7999999999999998, 2.6000000000000001, 3.0, 3.3999999999999999, 3.1000000000000001, 3.0, 3.1000000000000001, 3.1000000000000001, 3.1000000000000001, 2.7000000000000002, 3.2000000000000002, 3.2999999999999998, 3.0, 2.5, 3.0, 3.3999999999999999, 3.0], 'Unnamed: 0': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150]}
'''

df = pd.DataFrame(raw_data, columns = ['Unnamed: 0', 'Sepal.Length', 'Sepal.Width', 'Petal.Length', 'Petal.Width', 'Species']) 

# 如果你打算检查结果
# 1\. 输入此单元格中上面单元格生成的代码
raw_data = {'Petal.Width': [0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.40000000000000002, 0.29999999999999999, 0.20000000000000001, 0.20000000000000001, 0.10000000000000001, 0.20000000000000001, 0.20000000000000001, 0.10000000000000001, 0.10000000000000001, 0.20000000000000001, 0.40000000000000002, 0.40000000000000002, 0.29999999999999999, 0.29999999999999999, 0.29999999999999999, 0.20000000000000001, 0.40000000000000002, 0.20000000000000001, 0.5, 0.20000000000000001, 0.20000000000000001, 0.40000000000000002, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.40000000000000002, 0.10000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.10000000000000001, 0.20000000000000001, 0.20000000000000001, 0.29999999999999999, 0.29999999999999999, 0.20000000000000001, 0.59999999999999998, 0.40000000000000002, 0.29999999999999999, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 1.3999999999999999, 1.5, 1.5, 1.3, 1.5, 1.3, 1.6000000000000001, 1.0, 1.3, 1.3999999999999999, 1.0, 1.5, 1.0, 1.3999999999999999, 1.3, 1.3999999999999999, 1.5, 1.0, 1.5, 1.1000000000000001, 1.8, 1.3, 1.5, 1.2, 1.3, 1.3999999999999999, 1.3999999999999999, 1.7, 1.5, 1.0, 1.1000000000000001, 1.0, 1.2, 1.6000000000000001, 1.5, 1.6000000000000001, 1.5, 1.3, 1.3, 1.3, 1.2, 1.3999999999999999, 1.2, 1.0, 1.3, 1.2, 1.3, 1.3, 1.1000000000000001, 1.3, 2.5, 1.8999999999999999, 2.1000000000000001, 1.8, 2.2000000000000002, 2.1000000000000001, 1.7, 1.8, 1.8, 2.5, 2.0, 1.8999999999999999, 2.1000000000000001, 2.0, 2.3999999999999999, 2.2999999999999998, 1.8, 2.2000000000000002, 2.2999999999999998, 1.5, 2.2999999999999998, 2.0, 2.0, 1.8, 2.1000000000000001, 1.8, 1.8, 1.8, 2.1000000000000001, 1.6000000000000001, 1.8999999999999999, 2.0, 2.2000000000000002, 1.5, 1.3999999999999999, 2.2999999999999998, 2.3999999999999999, 1.8, 1.8, 2.1000000000000001, 2.3999999999999999, 2.2999999999999998, 1.8999999999999999, 2.2999999999999998, 2.5, 2.2999999999999998, 1.8999999999999999, 2.0, 2.2999999999999998, 1.8], 'Sepal.Width': [3.5, 3.0, 3.2000000000000002, 3.1000000000000001, 3.6000000000000001, 3.8999999999999999, 3.3999999999999999, 3.3999999999999999, 2.8999999999999999, 3.1000000000000001, 3.7000000000000002, 3.3999999999999999, 3.0, 3.0, 4.0, 4.4000000000000004, 3.8999999999999999, 3.5, 3.7999999999999998, 3.7999999999999998, 3.3999999999999999, 3.7000000000000002, 3.6000000000000001, 3.2999999999999998, 3.3999999999999999, 3.0, 3.3999999999999999, 3.5, 3.3999999999999999, 3.2000000000000002, 3.1000000000000001, 3.3999999999999999, 4.0999999999999996, 4.2000000000000002, 3.1000000000000001, 3.2000000000000002, 3.5, 3.6000000000000001, 3.0, 3.3999999999999999, 3.5, 2.2999999999999998, 3.2000000000000002, 3.5, 3.7999999999999998, 3.0, 3.7999999999999998, 3.2000000000000002, 3.7000000000000002, 3.2999999999999998, 3.2000000000000002, 3.2000000000000002, 3.1000000000000001, 2.2999999999999998, 2.7999999999999998, 2.7999999999999998, 3.2999999999999998, 2.3999999999999999, 2.8999999999999999, 2.7000000000000002, 2.0, 3.0, 2.2000000000000002, 2.8999999999999999, 2.8999999999999999, 3.1000000000000001, 3.0, 2.7000000000000002, 2.2000000000000002, 2.5, 3.2000000000000002, 2.7999999999999998, 2.5, 2.7999999999999998, 2.8999999999999999, 3.0, 2.7999999999999998, 3.0, 2.8999999999999999, 2.6000000000000001, 2.3999999999999999, 2.3999999999999999, 2.7000000000000002, 2.7000000000000002, 3.0, 3.3999999999999999, 3.1000000000000001, 2.2999999999999998, 3.0, 2.5, 2.6000000000000001, 3.0, 2.6000000000000001, 2.2999999999999998, 2.7000000000000002, 3.0, 2.8999999999999999, 2.8999999999999999, 2.5, 2.7999999999999998, 3.2999999999999998, 2.7000000000000002, 3.0, 2.8999999999999999, 3.0, 3.0, 2.5, 2.8999999999999999, 2.5, 3.6000000000000001, 3.2000000000000002, 2.7000000000000002, 3.0, 2.5, 2.7999999999999998, 3.2000000000000002, 3.0, 3.7999999999999998, 2.6000000000000001, 2.2000000000000002, 3.2000000000000002, 2.7999999999999998, 2.7999999999999998, 2.7000000000000002, 3.2999999999999998, 3.2000000000000002, 2.7999999999999998, 3.0, 2.7999999999999998, 3.0, 2.7999999999999998, 3.7999999999999998, 2.7999999999999998, 2.7999999999999998, 2.6000000000000001, 3.0, 3.3999999999999999, 3.1000000000000001, 3.0, 3.1000000000000001, 3.1000000000000001, 3.1000000000000001, 2.7000000000000002, 3.2000000000000002, 3.2999999999999998, 3.0, 2.5, 3.0, 3.3999999999999999, 3.0], 'Species': ['setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica'], 'Unnamed: 0': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150], 'Sepal.Length': [5.0999999999999996, 4.9000000000000004, 4.7000000000000002, 4.5999999999999996, 5.0, 5.4000000000000004, 4.5999999999999996, 5.0, 4.4000000000000004, 4.9000000000000004, 5.4000000000000004, 4.7999999999999998, 4.7999999999999998, 4.2999999999999998, 5.7999999999999998, 5.7000000000000002, 5.4000000000000004, 5.0999999999999996, 5.7000000000000002, 5.0999999999999996, 5.4000000000000004, 5.0999999999999996, 4.5999999999999996, 5.0999999999999996, 4.7999999999999998, 5.0, 5.0, 5.2000000000000002, 5.2000000000000002, 4.7000000000000002, 4.7999999999999998, 5.4000000000000004, 5.2000000000000002, 5.5, 4.9000000000000004, 5.0, 5.5, 4.9000000000000004, 4.4000000000000004, 5.0999999999999996, 5.0, 4.5, 4.4000000000000004, 5.0, 5.0999999999999996, 4.7999999999999998, 5.0999999999999996, 4.5999999999999996, 5.2999999999999998, 5.0, 7.0, 6.4000000000000004, 6.9000000000000004, 5.5, 6.5, 5.7000000000000002, 6.2999999999999998, 4.9000000000000004, 6.5999999999999996, 5.2000000000000002, 5.0, 5.9000000000000004, 6.0, 6.0999999999999996, 5.5999999999999996, 6.7000000000000002, 5.5999999999999996, 5.7999999999999998, 6.2000000000000002, 5.5999999999999996, 5.9000000000000004, 6.0999999999999996, 6.2999999999999998, 6.0999999999999996, 6.4000000000000004, 6.5999999999999996, 6.7999999999999998, 6.7000000000000002, 6.0, 5.7000000000000002, 5.5, 5.5, 5.7999999999999998, 6.0, 5.4000000000000004, 6.0, 6.7000000000000002, 6.2999999999999998, 5.5999999999999996, 5.5, 5.5, 6.0999999999999996, 5.7999999999999998, 5.0, 5.5999999999999996, 5.7000000000000002, 5.7000000000000002, 6.2000000000000002, 5.0999999999999996, 5.7000000000000002, 6.2999999999999998, 5.7999999999999998, 7.0999999999999996, 6.2999999999999998, 6.5, 7.5999999999999996, 4.9000000000000004, 7.2999999999999998, 6.7000000000000002, 7.2000000000000002, 6.5, 6.4000000000000004, 6.7999999999999998, 5.7000000000000002, 5.7999999999999998, 6.4000000000000004, 6.5, 7.7000000000000002, 7.7000000000000002, 6.0, 6.9000000000000004, 5.5999999999999996, 7.7000000000000002, 6.2999999999999998, 6.7000000000000002, 7.2000000000000002, 6.2000000000000002, 6.0999999999999996, 6.4000000000000004, 7.2000000000000002, 7.4000000000000004, 7.9000000000000004, 6.4000000000000004, 6.2999999999999998, 6.0999999999999996, 7.7000000000000002, 6.2999999999999998, 6.4000000000000004, 6.0, 6.9000000000000004, 6.7000000000000002, 6.9000000000000004, 5.7999999999999998, 6.7999999999999998, 6.7000000000000002, 6.7000000000000002, 6.2999999999999998, 6.5, 6.2000000000000002, 5.9000000000000004], 'Petal.Length': [1.3999999999999999, 1.3999999999999999, 1.3, 1.5, 1.3999999999999999, 1.7, 1.3999999999999999, 1.5, 1.3999999999999999, 1.5, 1.5, 1.6000000000000001, 1.3999999999999999, 1.1000000000000001, 1.2, 1.5, 1.3, 1.3999999999999999, 1.7, 1.5, 1.7, 1.5, 1.0, 1.7, 1.8999999999999999, 1.6000000000000001, 1.6000000000000001, 1.5, 1.3999999999999999, 1.6000000000000001, 1.6000000000000001, 1.5, 1.5, 1.3999999999999999, 1.5, 1.2, 1.3, 1.3999999999999999, 1.3, 1.5, 1.3, 1.3, 1.3, 1.6000000000000001, 1.8999999999999999, 1.3999999999999999, 1.6000000000000001, 1.3999999999999999, 1.5, 1.3999999999999999, 4.7000000000000002, 4.5, 4.9000000000000004, 4.0, 4.5999999999999996, 4.5, 4.7000000000000002, 3.2999999999999998, 4.5999999999999996, 3.8999999999999999, 3.5, 4.2000000000000002, 4.0, 4.7000000000000002, 3.6000000000000001, 4.4000000000000004, 4.5, 4.0999999999999996, 4.5, 3.8999999999999999, 4.7999999999999998, 4.0, 4.9000000000000004, 4.7000000000000002, 4.2999999999999998, 4.4000000000000004, 4.7999999999999998, 5.0, 4.5, 3.5, 3.7999999999999998, 3.7000000000000002, 3.8999999999999999, 5.0999999999999996, 4.5, 4.5, 4.7000000000000002, 4.4000000000000004, 4.0999999999999996, 4.0, 4.4000000000000004, 4.5999999999999996, 4.0, 3.2999999999999998, 4.2000000000000002, 4.2000000000000002, 4.2000000000000002, 4.2999999999999998, 3.0, 4.0999999999999996, 6.0, 5.0999999999999996, 5.9000000000000004, 5.5999999999999996, 5.7999999999999998, 6.5999999999999996, 4.5, 6.2999999999999998, 5.7999999999999998, 6.0999999999999996, 5.0999999999999996, 5.2999999999999998, 5.5, 5.0, 5.0999999999999996, 5.2999999999999998, 5.5, 6.7000000000000002, 6.9000000000000004, 5.0, 5.7000000000000002, 4.9000000000000004, 6.7000000000000002, 4.9000000000000004, 5.7000000000000002, 6.0, 4.7999999999999998, 4.9000000000000004, 5.5999999999999996, 5.7999999999999998, 6.0999999999999996, 6.4000000000000004, 5.5999999999999996, 5.0999999999999996, 5.5999999999999996, 6.0999999999999996, 5.5999999999999996, 5.5, 4.7999999999999998, 5.4000000000000004, 5.5999999999999996, 5.0999999999999996, 5.0999999999999996, 5.9000000000000004, 5.7000000000000002, 5.2000000000000002, 5.0, 5.2000000000000002, 5.4000000000000004, 5.0999999999999996]}
df = pd.DataFrame(raw_data, columns = ['Unnamed: 0', 'Sepal.Length', 'Sepal.Width', 'Petal.Length', 'Petal.Width', 'Species'])

# 查看原始数据帧的前几行
df.head()

	Unnamed: 0	Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
0	1	5.1	3.5	1.4	0.2	setosa
1	2	4.9	3.0	1.4	0.2	setosa
2	3	4.7	3.2	1.3	0.2	setosa
3	4	4.6	3.1	1.5	0.2	setosa
4	5	5.0	3.6	1.4	0.2	setosa

# 查看使用我们的代码创建的，数据帧的前几行
df_original.head()

	Unnamed: 0	Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
0	1	5.1	3.5	1.4	0.2	setosa
1	2	4.9	3.0	1.4	0.2	setosa
2	3	4.7	3.2	1.3	0.2	setosa
3	4	4.6	3.1	1.5	0.2	setosa
4	5	5.0	3.6	1.4	0.2	setosa

将分类变量转换为虚拟变量

# 导入模块
import pandas as pd

# 创建数据帧
raw_data = {'first_name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'], 
        'last_name': ['Miller', 'Jacobson', 'Ali', 'Milner', 'Cooze'], 
        'sex': ['male', 'female', 'male', 'female', 'female']}
df = pd.DataFrame(raw_data, columns = ['first_name', 'last_name', 'sex'])
df

	first_name	last_name	sex
0	Jason	Miller	male
1	Molly	Jacobson	female
2	Tina	Ali	male
3	Jake	Milner	female
4	Amy	Cooze	female

# 从 sex 变量创建一组虚拟变量
df_sex = pd.get_dummies(df['sex'])

# 将虚拟变量连接到主数据帧
df_new = pd.concat([df, df_sex], axis=1)
df_new

	first_name	last_name	sex	female	male
0	Jason	Miller	male	0.0	1.0
1	Molly	Jacobson	female	1.0	0.0
2	Tina	Ali	male	0.0	1.0
3	Jake	Milner	female	1.0	0.0
4	Amy	Cooze	female	1.0	0.0

# 连接新列的替代方案
df_new = df.join(df_sex)
df_new

	first_name	last_name	sex	female	male
0	Jason	Miller	male	0.0	1.0
1	Molly	Jacobson	female	1.0	0.0
2	Tina	Ali	male	0.0	1.0
3	Jake	Milner	female	1.0	0.0
4	Amy	Cooze	female	1.0	0.0

将分类变量转换为虚拟变量

# 导入模块
import pandas as pd
import patsy

# 创建数据帧
raw_data = {'countrycode': [1, 2, 3, 2, 1]} 
df = pd.DataFrame(raw_data, columns = ['countrycode'])
df

	countrycode
0	1
1	2
2	3
3	2
4	1

# 将 countrycode 变量转换为三个二元变量
patsy.dmatrix('C(countrycode)-1', df, return_type='dataframe')

	C(countrycode)[1]	C(countrycode)[2]	C(countrycode)[3]
0	1.0	0.0	0.0
1	0.0	1.0	0.0
2	0.0	0.0	1.0
3	0.0	1.0	0.0
4	1.0	0.0	0.0

将字符串分类变量转换为数字变量

# 导入模块
import pandas as pd

raw_data = {'patient': [1, 1, 1, 2, 2], 
        'obs': [1, 2, 3, 1, 2], 
        'treatment': [0, 1, 0, 1, 0],
        'score': ['strong', 'weak', 'normal', 'weak', 'strong']} 
df = pd.DataFrame(raw_data, columns = ['patient', 'obs', 'treatment', 'score'])
df

	patient	obs	treatment	score
0	1	1	0	strong
1	1	2	1	weak
2	1	3	0	normal
3	2	1	1	weak
4	2	2	0	strong

# 创建一个函数，将 df['score'] 的所有值转换为数字
def score_to_numeric(x):
    if x=='strong':
        return 3
    if x=='normal':
        return 2
    if x=='weak':
        return 1

df['score_num'] = df['score'].apply(score_to_numeric)
df

	patient	obs	treatment	score	score_num
0	1	1	0	strong	3
1	1	2	1	weak	1
2	1	3	0	normal	2
3	2	1	1	weak	1
4	2	2	0	strong	3

    原文作者：ApacheCN_飞龙
    原文地址: https://www.jianshu.com/p/69bb0a7597c7
    本文转自网络文章，转载此文章仅为分享知识，如有侵权，请联系博主进行删除。