cut 与qcut

cut qcut的区别

两者功能相似，都是将一个Series切割成若干个分组
首先创建数据

factors = np.random.randn(9)

[-0.01866508  0.72088087  0.67396285  0.50709849 -2.0963765   1.1875407
  0.56316144 -1.00214153  0.01905435]

pd.qcut()

qcut是根据这些值的频率来选择箱子的均匀间隔，即每个箱子中含有的数的数量是相同的。
传入q参数

pd.qcut(factors, 3)                   

>>>[(-2.097, 0.00648], (0.6, 1.188], (0.6, 1.188], (0.00648, 0.6], (-2.097, 0.00648], (0.6, 1.188], (0.00648, 0.6], (-2.097, 0.00648], (0.00648, 0.6]]
Categories (3, interval[float64]): [(-2.097, 0.00648] < (0.00648, 0.6] < (0.6, 1.188]]

pd.qcut(factors, 3).value_counts()    #计算每个分组中含有的数的数量

>>>
(-2.097, 0.00648]    3
(0.00648, 0.6]       3
(0.6, 1.188]         3
dtype: int64

传入label参数

pd.qcut(factors, 3, labels = ["a","b","c"])   #返回每个数对应的分组，但分组名称由label指示

[a, c, c, b, a, c, b, a, b]
Categories (3, object): [a < b < c]


pd.qcut(factors, 3, labels = False)           #返回每个数对应的分组，但仅显示分组下标

[0 2 2 1 0 2 1 0 1]

传入retbins参数

pd.qcut(factors, 3, retbins=True)             #返回每个数对应的分组，且额外返回bins，即每个边界值

([(-2.097, 0.00648], (0.6, 1.188], (0.6, 1.188], (0.00648, 0.6], (-2.097, 0.00648], (0.6, 1.188], (0.00648, 0.6], (-2.097, 0.00648], (0.00648, 0.6]]
Categories (3, interval[float64]): [(-2.097, 0.00648] < (0.00648, 0.6] < (0.6, 1.188]], array([-2.0963765 ,  0.00648121,  0.60009524,  1.1875407 ]))

pd.cut()

cut将根据值本身来选择箱子均匀间隔，即每个箱子的间距都是相同的

传入bins参数

pd.cut(factors, 3)        #返回每个数对应的数组

[(-1.002, 0.0929], (0.0929, 1.188], (0.0929, 1.188], (0.0929, 1.188], (-2.1, -1.002], (0.0929, 1.188], (0.0929, 1.188], (-2.1, -1.002], (-1.002, 0.0929]]
Categories (3, interval[float64]): [(-2.1, -1.002] < (-1.002, 0.0929] < (0.0929, 1.188]]

pd.cut(factors, bins=[-3, -2, -1, 0, 1, 2, 3])

>>> [(-1, 0], (0, 1], (0, 1], (0, 1], (-3, -2], (1, 2], (0, 1], (-2, -1], (0, 1]]
Categories (6, interval[int64]): [(-3, -2] < (-2, -1] < (-1, 0] < (0, 1] < (1, 2] < (2, 3]]


pd.cut(factors, 3).value_counts() #计算每个分组中含有的数的数量

>>>
(-2.1, -1.002]      2
(-1.002, 0.0929]    2
(0.0929, 1.188]     5
dtype: int64

传入label参数

pd.cut(factors, 3, labels=["a", "b", "c"])  #返回每个数对应的分组，但分组名称由label指示

>>> [b, c, c, c, a, c, c, a, b]
Categories (3, object): [a < b < c]

pd.cut(factors, 3, labels=False)            #返回每个数对应的分组，但仅显示分组下标

>>> [1 2 2 2 0 2 2 0 1]

传入retbins参数

pd.cut(factors, 3, retbins=True)            #返回每个数对应的分组，且额外返回bins，即每个边界值

>>> ([(-1.002, 0.0929], (0.0929, 1.188], (0.0929, 1.188], (0.0929, 1.188], (-2.1, -1.002], (0.0929, 1.188], (0.0929, 1.188], (-2.1, -1.002], (-1.002, 0.0929]]
Categories (3, interval[float64]): [(-2.1, -1.002] < (-1.002, 0.0929] < (0.0929, 1.188]], array([-2.09966042, -1.00173743,  0.09290163,  1.1875407 ]))