常规特性¶

质数¶

In [36]:
from math import sqrt
def is_prime(n):
    if n == 1:
        return False
    for i in range(2, int(sqrt(n))+1):
        if n % i == 0:
            return False
    return True
print(is_prime(4))
print(is_prime(5))

False
True

斐波那契数列¶

递归¶

In [42]:
def normal_fibo(n):
    if n <= 2:
        return 1
    else:
        return normal_fibo(n-1) + normal_fibo(n-2)
# 前十
for n in range(10):
    print(n, normal_fibo(n))
# 第n
%time normal_fibo(35)

0 1
1 1
2 1
3 2
4 3
5 5
6 8
7 13
8 21
9 34
CPU times: user 2.23 s, sys: 0 ns, total: 2.23 s
Wall time: 2.39 s
Out[42]:
9227465

递归缓存¶

In [43]:
from functools import cache
@cache
def cached_fibo(n):
    if n <= 2:
        return 1
    else:
        return cached_fibo(n - 1) + cached_fibo(n-2)
# 前10
for n in range(10):
    print(n, cached_fibo(n))
# 第n
%time cached_fibo(35)

0 1
1 1
2 1
3 2
4 3
5 5
6 8
7 13
8 21
9 34
CPU times: user 27 µs, sys: 0 ns, total: 27 µs
Wall time: 30 µs
Out[43]:
9227465

合并和分组聚合¶

字符串离散化¶

In [81]:
import pandas as pd
file_path = './test.csv'
df = pd.read_csv(file_path)
print(type(df))
print(df.shape)
print(df['type'].head(3))
# 统计分类的列表
temp_list = df['type'].str.split(',').to_list()
# 分类列表
genre_list = list(set([i for j in temp_list for i in j]))

print(temp_list[0])
import numpy as np
# 构造全为0的数组
zeros_df = pd.DataFrame(np.zeros((df.shape[0], len(genre_list))),columns=genre_list)
for i in range(df.shape[0]):#行
    zeros_df.loc[i, temp_list[i]] = 1 
    
print(zeros_df.head(3))
# 统计和
genre_cnt = zeros_df.sum(axis=0)
print(genre_cnt)

genre_cnt = genre_cnt.sort_values()

_x = genre_cnt.index
_y = genre_cnt.values
import matplotlib.pyplot as plt
plt.figure(figsize=(20, 8), dpi=30)
plt.bar(range(len(_x)), _y)
plt.xticks(range(len(_x)), _x)
plt.show()

<class 'pandas.core.frame.DataFrame'>
(5, 2)
0    a,b,c
1    a,f,x
2    x,b,m
Name: type, dtype: object
['a', 'b', 'c']
     x    y    a    c    f    m    b
0  0.0  0.0  1.0  1.0  0.0  0.0  1.0
1  1.0  0.0  1.0  0.0  1.0  0.0  0.0
2  1.0  0.0  0.0  0.0  0.0  1.0  1.0
x    2.0
y    1.0
a    3.0
c    3.0
f    2.0
m    1.0
b    3.0
dtype: float64
No description has been provided for this image

数据合并¶

In [89]:
import pandas as pd
import numpy as np
df1 = pd.DataFrame(np.ones((2,4)), index=['A','B'], columns=list('abcd'))
print(df1)
df2 = pd.DataFrame(np.zeros((3,3)), index=['A','B','C'], columns=list('xyz'))
print(df2)
print(df2.join(df1))
print(df1.join(df2))

     a    b    c    d
A  1.0  1.0  1.0  1.0
B  1.0  1.0  1.0  1.0
     x    y    z
A  0.0  0.0  0.0
B  0.0  0.0  0.0
C  0.0  0.0  0.0
     x    y    z    a    b    c    d
A  0.0  0.0  0.0  1.0  1.0  1.0  1.0
B  0.0  0.0  0.0  1.0  1.0  1.0  1.0
C  0.0  0.0  0.0  NaN  NaN  NaN  NaN
     a    b    c    d    x    y    z
A  1.0  1.0  1.0  1.0  0.0  0.0  0.0
B  1.0  1.0  1.0  1.0  0.0  0.0  0.0
In [91]:
df3 = pd.DataFrame(np.zeros((3,3)), columns=list('fax'))
print(df3)
print(df1.merge(df3, on='a'))

     f    a    x
0  0.0  0.0  0.0
1  0.0  0.0  0.0
2  0.0  0.0  0.0
Empty DataFrame
Columns: [a, b, c, d, f, x]
Index: []
In [92]:
df3.loc[1, "a"]  = 1
print(df1.merge(df3, on='a'))

     a    b    c    d    f    x
0  1.0  1.0  1.0  1.0  0.0  0.0
1  1.0  1.0  1.0  1.0  0.0  0.0
In [94]:
df3 = pd.DataFrame(np.arange(9).reshape(3,3), columns=list('fax'))
print(df3)
print(df1.merge(df3, on='a'))

   f  a  x
0  0  1  2
1  3  4  5
2  6  7  8
     a    b    c    d  f  x
0  1.0  1.0  1.0  1.0  0  2
1  1.0  1.0  1.0  1.0  0  2
In [95]:
df1.loc["A",'a'] = 100
print(df1.merge(df3, on='a'))

     a    b    c    d  f  x
0  1.0  1.0  1.0  1.0  0  2
In [96]:
print(df1.merge(df3, on='a', how='outer'))

       a    b    c    d    f    x
0    1.0  1.0  1.0  1.0  0.0  2.0
1    4.0  NaN  NaN  NaN  3.0  5.0
2    7.0  NaN  NaN  NaN  6.0  8.0
3  100.0  1.0  1.0  1.0  NaN  NaN
In [97]:
print(df1.merge(df3, on='a', how='left'))

       a    b    c    d    f    x
0  100.0  1.0  1.0  1.0  NaN  NaN
1    1.0  1.0  1.0  1.0  0.0  2.0
In [98]:
print(df1.merge(df3, on='a', how='right'))

     a    b    c    d  f  x
0  1.0  1.0  1.0  1.0  0  2
1  4.0  NaN  NaN  NaN  3  5
2  7.0  NaN  NaN  NaN  6  8