Cách dùng phương thức .apply() trên DataFrame?
Luyện tập câu hỏi phỏng vấn lập trình bằng Python
Kirill Smirnov
Data Science Consultant, Altran
Bộ dữ liệu
import pandas as pd
scores = pd.read_csv('exams.csv')
scores = scores[['math score', 'reading score', 'writing score']]
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
Mặc định .apply()
df.apply(function)
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
import numpy as np
scores_new = scores.apply(np.sqrt)
print(score_new)
math score reading score writing score
0 8.602325 9.273618 9.055385
1 6.633250 7.000000 7.280110
2 7.348469 6.782330 6.557439
3 9.380832 9.746794 9.591663
4 9.219544 9.000000 9.000000
...
Mặc định .apply()
df.apply(function)
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
import numpy as np
scores_new = scores.apply(np.mean)
print(score_new.head())
math score 65.18
reading score 69.28
writing score 67.96
dtype: float64
type(scores_new)
pandas.core.series.Series
Mặc định .apply()
df.apply(function)
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
function(pd.Series)
kích thước đầu vào $n$
$\rightarrow$ np.sqrt(pd.Series)
$\rightarrow$ kích thước đầu ra $n$
kích thước đầu vào $n$
$\rightarrow$ np.mean(pd.Series)
$\rightarrow$ một giá trị
Mặc định .apply(): hàm tự viết
df.apply(function)
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
def divide_scores(x):
return x / 2
scores_new = scores.apply(divide_scores)
print(scores_new)
math score reading score writing score
0 37.0 43.0 41.0
1 22.0 24.5 26.5
2 27.0 23.0 21.5
3 44.0 47.5 46.0
4 42.5 40.5 40.5
...
Mặc định .apply(): hàm tự viết
df.apply(function)
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
def perfect_score(x):
return 100
scores_new = scores.apply(perfect_score)
print(scores_new)
math score 100
reading score 100
writing score 100
dtype: int64
Biểu thức lambda
def divide_scores(x):
return x / 2
scores_new = scores.apply(divide_scores)
print(scores_new)
math score reading score writing score
0 37.0 43.0 41.0
1 22.0 24.5 26.5
2 27.0 23.0 21.5
3 44.0 47.5 46.0
4 42.5 40.5 40.5
...
def perfect_score(x):
return 100
scores_new = scores.apply(perfect_score)
print(scores_new)
math score 100
reading score 100
writing score 100
dtype: int64
Biểu thức lambda
scores_new = scores.apply(lambda x: x / 2)
print(scores_new)
math score reading score writing score
0 37.0 43.0 41.0
1 22.0 24.5 26.5
2 27.0 23.0 21.5
3 44.0 47.5 46.0
4 42.5 40.5 40.5
...
scores_new = scores.apply(lambda x: 100)
print(scores_new)
math score 100
reading score 100
writing score 100
dtype: int64
Tham số bổ sung: axis
df.apply(function, axis= )
Tham số bổ sung: axis
df.apply(function, axis=0)
Tham số bổ sung: axis
df.apply(function, axis=1)
Tham số bổ sung: axis
df.apply(function, axis= )
axis=0 - áp dụng function theo cột
axis=1 - áp dụng function theo hàng
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
import numpy as np
scores_new = scores.apply(np.mean)
print(score_new.head())
math score 65.18
reading score 69.28
writing score 67.96
dtype: float64
Tham số bổ sung: axis
df.apply(function, axis= )
axis=0 - áp dụng function theo cột
axis=1 - áp dụng function theo hàng
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
import numpy as np
scores_new = scores.apply(np.mean, axis=0)
print(score_new.head())
math score 65.18
reading score 69.28
writing score 67.96
dtype: float64
Tham số bổ sung: axis
df.apply(function, axis= )
axis=0 - áp dụng function theo cột
axis=1 - áp dụng function theo hàng
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
import numpy as np
scores_new = scores.apply(np.mean, axis=1)
print(score_new.head())
0 80.666667
1 48.666667
2 47.666667
3 91.666667
4 82.333333
5 84.000000
6 75.000000
7 70.666667
...
Tham số bổ sung: result_type
df.apply(function, result_type= )
result_type='expand'
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
import numpy
def span(x):
return [np.min(x), np.max(x)]
scores_new = scores.apply(span)
print(scores_new)
math score [27, 100]
reading score [33, 100]
writing score [30, 100]
dtype: object
Tham số bổ sung: result_type
df.apply(function, result_type= )
result_type='expand'
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
import numpy
def span(x):
return [np.min(x), np.max(x)]
scores.apply(span, result_type='expand')
math score reading score writing score
0 27 33 30
1 100 100 100
Tham số bổ sung: result_type
df.apply(function, result_type= )
result_type='expand'
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
import numpy
def span(x):
return [np.min(x), np.max(x)]
scores.apply(span, result_type='expand', axis=1)
0 1
0 74 86
1 44 53
2 43 54
3 88 95
4 81 85
...
Tham số bổ sung: result_type
df.apply(function, result_type= )
result_type='broadcast'
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
import numpy as np
scores_new = scores.apply(np.mean)
print(score_new.head())
math score 65.18
reading score 69.28
writing score 67.96
dtype: float64
Tham số bổ sung: result_type
df.apply(function, result_type= )
result_type='broadcast'
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
import numpy as np
scores.apply(np.mean, result_type='broadcast')
math score reading score writing score
0 65 69 67
1 65 69 67
2 65 69 67
3 65 69 67
4 65 69 67
5 65 69 67
6 65 69 67
7 65 69 67
...
Nhiều đối số trong một hàm
function(pd.Series)
Nhiều đối số trong một hàm
function(pd.Series, arg1, arg2, ..., kwarg1=val1, kwarg2=val2, ...)
def check_mean(x, a, b, inside=True):
mean = np.mean(x)
if inside:
return mean > a and mean < b
else:
return mean < a or mean > b
Áp dụng hàm
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
import numpy as np
scores.apply(check_mean)
TypeError
Tham số bổ sung: args
df.apply(function, args= )
args - [arg1, arg2, ...]
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
import numpy as np
scores.apply(check_mean, args=[67, 70])
math score False
reading score True
writing score True
dtype: bool
Tham số bổ sung: args
df.apply(function, args= )
args - (arg1, arg2, ...)
print(scores.head())
math score reading score writing score
0 74 86 82
1 44 49 53
2 54 46 43
3 88 95 92
4 85 81 81
import numpy as np
scores.apply(
check_mean, args=[67, 70], inside=False
)
math score True
reading score False
writing score False
dtype: bool
Vamos praticar!
Luyện tập câu hỏi phỏng vấn lập trình bằng Python
