pandas 初识（三）

import pandas as pd
import numpy as np

df = pd.DataFrame({"a": ["aa", np.NAN, np.NAN], "b": [3, np.NAN, 2]})

>>> df.a.isnull().any()
True

>>> df.a.isnull().all()
True

>>> df.c.apply(None if x == np.nan else x)  # 错误的方式，x的类型不是np.nan活着np.NAN, 任何类型都有可能。所以这种判断时可用

>>> df = df.where(df.notnull(), None)
>>> print(df)
>>> print(df.isnull())
      a     b     c
0    aa        None
1  None  None  None
2  None  None  None
       a      b     c
0  False  False  True
1   True   True  True
2   True   True  True

import pandas as pd
import numpy as np

df = pd.DataFrame({‘key1‘: [‘a‘, ‘a‘, ‘b‘, ‘b‘, ‘a‘], ‘key2‘: [‘one‘, ‘two‘, ‘one‘, ‘two‘, ‘one‘],
                   ‘data1‘: np.random.randn(5), ‘data2‘: np.random.randn(5)})

print(df)
print("*********")

class_key = ["key1", "key2"]
# class_key = ["key1"]  # 如果 class_key 是一个元素或者字符串，这class_ 为字符串
for class_, group in df.groupby(class_key):
    print("______________")
    print(class_)
    print(group)

  key1 key2     data1     data2
0    a  one  1.237276 -0.813727
1    a  two  0.508972 -1.336699
2    b  one -0.343635  0.714680
3    b  two  2.433797  0.417454
4    a  one  1.215114  2.646685
*********
______________
(‘a‘, ‘one‘)
  key1 key2     data1     data2
0    a  one  1.237276 -0.813727
4    a  one  1.215114  2.646685
______________
(‘a‘, ‘two‘)
  key1 key2     data1     data2
1    a  two  0.508972 -1.336699
______________
(‘b‘, ‘one‘)
  key1 key2     data1    data2
2    b  one -0.343635  0.71468
______________
(‘b‘, ‘two‘)
  key1 key2     data1     data2
3    b  two  2.433797  0.417454

import pandas as pd
import numpy as np

a = pd.DataFrame({‘A‘: [1, 2, 3], ‘B‘: [4, 5, 6], ‘C‘: [7, 8, 9]})
print(a)

# a.colums = ["a", "b", "c"] # 错误的写法
a.rename(columns={‘A‘: ‘a‘, ‘C‘: ‘c‘}, inplace=True)
print(a)

   A  B  C
0  1  4  7
1  2  5  8
2  3  6  9
   a  B  c
0  1  4  7
1  2  5  8
2  3  6  9