Kei Minagawa

我同意@Demi Lune。

我更改了操作码 male_only() 和 female_only() __init__() 方法,因为我认为您不想调用 pd.read_csv() 方法每次创建新对象时。所以 仅限男性() 仅限女性() 方法总是返回新对象,它不会影响其他对象。

import pandas as pd

# Added for creating file on memory.
import io
csv = '''Person,Sex,Score
p1,M,1
p2,M,2
p3,M,3
p4,F,4
p5,F,5
p6,F,6'''
file = io.StringIO(csv)

class MyData:
    def __init__ (self, file=None, data=None):
        import pandas as pd
        if file:
            self.data = pd.read_csv(file)
        else:
            self.data = data
        self.Person = self.data['Person']
        self.Sex = self.data['Sex']
        self.Score = self.data['Score']

    def copy_d(self):
        return MyData(data=self.data.copy())

    def male_only(self):
        d = self.copy_d()
        d.data = self.data[self.Sex=="M"]
        d.Person = self.Person[self.Sex=="M"]
        d.Score = self.Score[self.Sex=="M"]
        d.Sex = self.Sex[self.Sex=="M"]
        return d

    def female_only(self):
        d = self.copy_d()
        d.data = self.data[self.Sex=="F"]
        d.Person = self.Person[self.Sex=="F"]
        d.Score = self.Score[self.Sex=="F"]
        d.Sex = self.Sex[self.Sex=="F"]
        return d

d = MyData(file)
print(d.female_only().data)
#   Person Sex  Score
# 3     p4   F      4
# 4     p5   F      5
# 5     p6   F      6

print(d.male_only().data)
#   Person Sex  Score
# 0     p1   M      1
# 1     p2   M      2
# 2     p3   M      3

print(d.data)
#   Person Sex  Score
# 0     p1   M      1
# 1     p2   M      2
# 2     p3   M      3
# 3     p4   F      4
# 4     p5   F      5
# 5     p6   F      6

但如果你只是在用 pandas.DataFrame ,另一种方法是使用bare . 首先,在大多数情况下, 熊猫.DataFrame Person , Sex Score 因为它已经存在于DATAFRAM对象中。

即:

import pandas as pd
import numpy as np
df = pd.DataFrame(np.eye(3,3), columns=['Person', 'Sex', 'Score'])

# `df` already has these properteis.
df.Person
df.Sex
df.Score
# In [986]: df.Person
# Out[986]: 
# 0    1.0
# 1    0.0
# 2    0.0
# Name: Person, dtype: float64

# In [987]: df.Sex
# Out[987]: 
# 0    0.0
# 1    1.0
# 2    0.0
# Name: Sex, dtype: float64

# In [988]: df.Score
# Out[988]: 
# 0    0.0
# 1    0.0
# 2    1.0
# Name: Score, dtype: float64

所以,你的 仅限男性() 仅限女性() 方法的编写方式如下。

import pandas as pd

# Added for creating file on memory.
import io
csv = '''Person,Sex,Score
p1,M,1
p2,M,2
p3,M,3
p4,F,4
p5,F,5
p6,F,6'''
file = io.StringIO(csv)

def male_only(df):
    return df[df.Sex=='M']

def female_only(df):
    return df[df.Sex=='F']

df = pd.read_csv(file)
male_only(df)
# In [1034]: male_only(df)
# Out[1037]: 
#   Person Sex  Score
# 0     p1   M      1
# 1     p2   M      2
# 2     p3   M      3

female_only(df)
# In [1038]: female_only(df)
# Out[1041]: 
#   Person Sex  Score
# 3     p4   F      4
# 4     p5   F      5
# 5     p6   F      6

我希望它能帮助你。