1. 生成Series数据

import pandas as pd
import numpy as np
ser = pd.Series(np.random.randint(1, 10, 4))
print(ser)
0    9
1    8
2    3
3    8
dtype: int32

2. 求幂

print(np.exp(ser))
0    8103.083928
1    2980.957987
2      20.085537
3    2980.957987
dtype: float64

3. 生成DataFrame数据1

df = pd.DataFrame(np.random.randint(1, 10, (2, 3)), columns=['a', 'b', 'c'])
print(df)
   a  b  c
0  5  1  2
1  8  9  2

4. 做乘除运算并取一个sin

print(np.sin(df*np.pi/4))
              a         b    c
0 -7.071068e-01  0.707107  1.0
1 -2.449294e-16  0.707107  1.0

5. 随机生成特定条件的DataFrame数据

A = pd.DataFrame(np.random.randint(1, 10, (3, 4)))
print(A)
   0  1  2  3
0  9  2  3  9
1  3  9  3  3
2  7  1  1  1

6. 索引对齐

A = pd.Series([2, 4, 6], index=[0, 1, 2])
B = pd.Series([1, 3, 5], index=[1, 2, 3])
print(A)
print(B)
print(A+B)  # 任何缺失用NaN填充
0    2
1    4
2    6
dtype: int64
1    1
2    3
3    5
dtype: int64
0    NaN
1    5.0
2    9.0
3    NaN
dtype: float64

7. 不同索引值数据相加

print(A.add(B, fill_value=0))
0    2.0
1    5.0
2    9.0
3    5.0
dtype: float64

8. 不同布局DataFrame数据相加

A = pd.DataFrame(np.random.randint(1, 10, (2, 3)))
B = pd.DataFrame(np.random.randint(1, 10, (3, 4)))
print("A=\n", A)
print("B=\n", B)
print(A+B)
A=
   0  1  2
0  1  6  8
1  4  8  6
B=
   0  1  2  3
0  5  6  5  8
1  3  4  9  1
2  5  2  4  9
     0     1     2   3
0  6.0  12.0  13.0 NaN
1  7.0  12.0  15.0 NaN
2  NaN   NaN   NaN NaN

9. 指定列表为索引值

指定索引值，直接用列表，可以自动分开加到里面

A = pd.DataFrame(np.random.randint(1, 10, (2, 2)), columns=list("AB"))
B = pd.DataFrame(np.random.randint(1, 10, (3, 3)), columns=list("BAC"))
print("A=\n", A)
print("B=\n", B)
A=
    A  B
0  4  9
1  2  4
B=
    B  A  C
0  1  1  1
1  4  1  2
2  1  8  7

10. 计算均值

print('A的均值', np.mean(A.values))
A的均值 4.75

11. 均值填充缺失值

print(A.add(B))
print(A.add(B, fill_value=np.mean(A.values)))  # 将A的均值填充到缺失值里面去相加
     A     B   C
0  5.0  10.0 NaN
1  3.0   8.0 NaN
2  NaN   NaN NaN
       A      B      C
0   5.00  10.00   5.75
1   3.00   8.00   6.75
2  12.75   5.75  11.75

12. 按行来减

A = np.random.randint(1, 10, (3, 4))
print("A=\n", A)
print(A-A[0])
A=
 [[3 7 4 4]
 [8 3 7 6]
 [6 6 2 6]]
[[ 0  0  0  0]
 [ 5 -4  3  2]
 [ 3 -1 -2  2]]

13. 将ndarray转换为DataFrame并指定列名

df = pd.DataFrame(A, columns=list('QUWE'))
print(df)
   Q  U  W  E
0  3  7  4  4
1  8  3  7  6
2  6  6  2  6

14. 按列计算，用的是DataFrame里面的减函数

print(df.subtract(df['U'], axis=0))
   Q  U  W  E
0 -4  0 -3 -3
1  5  0  4  3
2  0  0 -4  0

15. 隐式索引

取第0行,限定步长为2

half = df.iloc[0, ::2]
print(half)
Q    3
W    4
Name: 0, dtype: int32