python数据分析panda库

panda内有两种数据结构，Series（）和DataFrame（）

 >>> a=pd.Series([1,2],index=['a','b'])
 >>> a
 a    1
 b    2
 dtype: int64

 >>> b.index
 RangeIndex(start=0, stop=2, step=1)
 >>> b.values
 array(['b', 'a'], dtype=object)
 >>> a/2
 a    0.5
 b    1.0
 dtype: float64
 >>> 

列表切分选择

>>> s[0:3:2]
a    2
c    6
dtype: int64　　

  s3=pd.Series(arr)  另一种方式生成series
 >>> s3
 0    1
 1    2
 2    3
 3    4
 dtype: int32
 >>> s3=pd.Series(s)
 >>> s3
 a    2
 b    5
 c    6
 d    3
 dtype: int64
 >>> s[s>8]
 Series([], dtype: int64)
 >>> s
 a    2
 b    5
 c    6
 d    3
 dtype: int64
 >>> s[s>3]    找出>3的元素
 b    5
 c    6
 dtype: int64
 >>> np.log(s)    对series直接运用函数
 a    0.693147
 b    1.609438
 c    1.791759
 d    1.098612
 dtype: float64
 >>> s.isin([5,6])     看某些元素是否在series中，boolean值
 a    False
 b     True
 c     True
 d    False
 dtype: bool
 >>> s[s.isin([5,6])]
 b    5
 c    6
 dtype: int64
 >>> s2=pd.Series([5,2,np.NaN,7,np.NaN])
 >>> s2
 0    5.0
 1    2.0
 2    NaN
 3    7.0
 4    NaN
 dtype: float64
 >>> s2.isnull()
 0    False
 1    False
 2     True
 3    False
 4     True
 dtype: bool
 >>> s2.notnull()
 0     True
 1     True
 2    False
 3     True
 4    False
 dtype: bool

>>> s2[s2.isnull()]
2   NaN
4   NaN
dtype: float64

Frame的使用

 frame2=pd.DataFrame(fram,columns=['name','age'])
 >>> frame2
         name  age
 red        1    2
 yellow     5    6
 blue       9   10
 black     13   14
 >>> frame2.values
 array([[ 1,  2],
        [ 5,  6],
        [ 9, 10],
        [13, 14]])
 >>> frame2.index
 Index([u'red', u'yellow', u'blue', u'black'], dtype='object')
 >>> frame2.columns
 Index([u'name', u'age'], dtype='object')
 >>> frame2['name']
 red        1
 yellow     5
 blue       9
 black     13
 Name: name, dtype: int32
 >>> frame2.name
 red        1
 yellow     5
 blue       9
 black     13
 Name: name, dtype: int32
 >>> frame2.age
 red        2
 yellow     6
 blue      10
 black     14
 Name: age, dtype: int32
 >>> frame2[index=['red']]

>>> frame2[0:2]
        name  age
red        1    2
yellow     5    6
>>> frame2['name'][2]
9

 >>> s.idxmin()
 'a'
 >>> s.idxmax9)
 SyntaxError: invalid syntax
 >>> s.idxmax()
 'c'
 >>> s.index.is_unique
 True

>>> fram
        id  name  age  home
red      0     1    2     3
yellow   4     5    6     7
blue     8     9   10    11
black   12    13   14    15
>>> frame4=fram.drop(['name','age'],axis=1)   删除列
>>> frame4
        id  home
red      0     3
yellow   4     7
blue     8    11
black   12    15

 >>> f=lambda x:x.max()-x.min()   对frame运用自定义函数
 >>> fram.apply(f)
 id      12
 name    12
 age     12
 home    12
 dtype: int64
 >>> fram.apply(f,axis=1)
 red       3
 yellow    3
 blue      3
 black     3
 dtype: int64
 >>> fram.apply(f,axis=0)
 id      12
 name    12
 age     12
 home    12
 dtype: int64
 >>> def f(x):
     return pd.Series([x.min(),x.max()],index=['min','max'])

 >>> fram.apply(f)
      id  name  age  home
 min   0     1    2     3
 max  12    13   14    15

　　frame的一些数学统计值

 >>> fram.describe()
               id       name        age       home
 count   4.000000   4.000000   4.000000   4.000000
 mean    6.000000   7.000000   8.000000   9.000000
 std     5.163978   5.163978   5.163978   5.163978
 min     0.000000   1.000000   2.000000   3.000000
 25%     3.000000   4.000000   5.000000   6.000000
 50%     6.000000   7.000000   8.000000   9.000000
 75%     9.000000  10.000000  11.000000  12.000000
 max    12.000000  13.000000  14.000000  15.000000
 >>> fram.sum()
 id      24
 name    28
 age     32
 home    36
 dtype: int64
 >>> fram.mean()
 id      6.0
 name    7.0
 age     8.0
 home    9.0
 dtype: float64
 >>> fram.min()
 id      0
 name    1
 age     2
 home    3
 dtype: int32