python数据处理与分析入门-pandas使用（5）

往期文章：

1. pandas使用1
2. pandas使用2
3. pandas使用3
4. pandas使用4

pandas使用技巧

合并

Pandas在join/merge两中情境下提供了支持多种方式，基于逻辑/集合运算和代数运算来连接Series，DataFrame和Panel对象。

# concat()方法连接数组
df = pd.DataFrame(np.random.randn(8, 4))
print(df)
print("------")

# 拆分成块
pieces = [df[:2], df[3:5], df[6:]]

# 重新连接，可得初始数组
print(pd.concat(pieces))
# 输出
          0         1         2         3
0  0.138889  1.468425  0.033937  0.727453
1 -1.534917  1.880785  1.038571  0.782657
2 -0.758474 -0.889903  1.895584 -0.349080
3  1.195926  0.219143  0.141360 -0.133861
4  1.399775  2.084911  0.370451  0.373722
5  0.602006  0.102370  1.408794  2.076663
6  0.208999  3.121470  0.292169 -0.522401
7 -0.141231  0.146212  0.058596  0.423607
------
          0         1         2         3
0  0.138889  1.468425  0.033937  0.727453
1 -1.534917  1.880785  1.038571  0.782657
3  1.195926  0.219143  0.141360 -0.133861
4  1.399775  2.084911  0.370451  0.373722
6  0.208999  3.121470  0.292169 -0.522401
7 -0.141231  0.146212  0.058596  0.423607

增补

df = pd.DataFrame(np.random.randn(8, 4), columns=['A','B','C','D'])
print(df)
print("------")

# 将索引为3的行增补到整个DataFrame最后
s = df.iloc[3]
print(df.append(s, ignore_index=True))
# 输出
          A         B         C         D
0 -1.691575  1.282698  1.939419  0.459406
1  0.666460 -0.146645  0.672000  1.040926
2  1.031160 -1.248344  0.569695 -0.566937
3  0.833353 -1.453265  0.783527 -0.278597
4 -0.069810  1.577667 -0.052604  0.535070
5 -0.355505  1.752383  0.617767 -0.886470
6  0.239778 -1.342020 -0.966699 -0.183925
7  0.557462  0.134796 -0.766296 -1.665554
------
          A         B         C         D
0 -1.691575  1.282698  1.939419  0.459406
1  0.666460 -0.146645  0.672000  1.040926
2  1.031160 -1.248344  0.569695 -0.566937
3  0.833353 -1.453265  0.783527 -0.278597
4 -0.069810  1.577667 -0.052604  0.535070
5 -0.355505  1.752383  0.617767 -0.886470
6  0.239778 -1.342020 -0.966699 -0.183925
7  0.557462  0.134796 -0.766296 -1.665554
8  0.833353 -1.453265  0.783527 -0.278597

组合

# 新建DataFrame对象df
df = pd.DataFrame({'A' : ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'foo'], 'B' : ['one', 'one', 'two', 'three', 'two', 'two', 'one', 'three'], 'C' : np.random.randn(8), 'D' : np.random.randn(8)})

print(df)
print("------")


# 对'A'列进行合并并应用.sum()函数
print(df.groupby('A').sum())
print("------")


# 对'A', 'B'两列分别合并形成层级结构，再应用.sum()函数
print(df.groupby(['A','B']).sum())
# 输出
     A      B         C         D
0  foo    one -0.198964  0.329690
1  bar    one  0.549832  2.443202
2  foo    two -0.061327 -0.328189
3  bar  three -1.342564  0.973223
4  foo    two -0.756521  0.246364
5  bar    two -0.860024  1.068036
6  foo    one  0.587521 -0.734750
7  foo  three  1.654651 -0.293895
------
            C         D
A                      
bar -1.652756  4.484461
foo  1.225360 -0.780780
------
                  C         D
A   B                        
bar one    0.549832  2.443202
    three -1.342564  0.973223
    two   -0.860024  1.068036
foo one    0.388557 -0.405060
    three  1.654651 -0.293895
    two   -0.817848 -0.081826

重塑

tuples = list(zip(*[
    ['bar', 'bar', 'baz', 'baz', 'foo', 'foo', 'qux', 'qux'],
    ['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']]))

# 多重索引
index = pd.MultiIndex.from_tuples(tuples, names=['first', 'second'])

df = pd.DataFrame(np.random.randn(8, 2), index=index, columns=['A', 'B'])
df2 = df[:4]

print(df2)

print("------")

# .stack()方法将DataFrame的列“压缩”了一级
stacked = df2.stack()

print(stacked)
# 输出
  A         B
first second                    
bar   one     0.441812 -0.404707
      two     1.049489  0.476338
baz   one     0.474724  0.879325
      two     1.771712 -0.486847
------
first  second   
bar    one     A    0.441812
               B   -0.404707
       two     A    1.049489
               B    0.476338
baz    one     A    0.474724
               B    0.879325
       two     A    1.771712
               B   -0.486847
dtype: float64

# 对于已经层次化的，具有多重索引的DataFrame或Series，
# stack()的逆操作是unstack()——默认将最后一级“去层次化”。
print(stacked.unstack())

print("------")

print(stacked.unstack(1))

print("------")

print(stacked.unstack(0))
# 输出
 A         B
first second                    
bar   one     0.441812 -0.404707
      two     1.049489  0.476338
baz   one     0.474724  0.879325
      two     1.771712 -0.486847
------
second        one       two
first                      
bar   A  0.441812  1.049489
      B -0.404707  0.476338
baz   A  0.474724  1.771712
      B  0.879325 -0.486847
------
first          bar       baz
second                      
one    A  0.441812  0.474724
       B -0.404707  0.879325
two    A  1.049489  1.771712
       B  0.476338 -0.486847

更多内容请查看我的gittee仓库 ： Python基础练习