cut(x, bins, right=True, labels=None, retbins=False, precision=3, include_lowest=False, duplicates='raise')
# x：被切分的数据，必须是一维的
# bins：①int型整数：将x按照数值大小平均分成分成bins份，x的范围在最左侧和最右侧分别扩展0.1%以包括最大值和最小值#②标量序列：自定义分组的每个区间，此时严格按照给定的区间分割，x最左和最右不扩展#③pandas.IntervalIndex
# right：布尔值，默认为True，表示分割后包含区间右侧值不包含左侧值，False表示分割后包含左侧值不包括右侧值
# labels：分组后bins的标签，默认为None显示分割后属于的区间
# retbins：返回结果中是否包括bins，一般bins参数使用整数时
# precision：保留的小数点位数，默认为3
# include_lowest：如果自定义标量序列分组，第一个区间是否包含左侧最小值
# duplicates：是否允许区间重复

arr = np.array([1,77,10,89,36,12,58,62,5,40,32,18,20,25,30,100])
c = pd.cut(arr,5,precision=1)
print(c)
# [(0.9, 20.8], (60.4, 80.2], (0.9, 20.8], (80.2, 100.0], (20.8, 40.6], ..., (0.9, 20.8], (0.9, 20.8], (20.8, 40.6], (20.8, 40.6], (80.2, 100.0]]
# Length: 16
# Categories (5, interval[float64]): [(0.9, 20.8] < (20.8, 40.6] < (40.6, 60.4] < (60.4, 80.2] < (80.2, 100.0]]

arr = np.array([1,5,10,40,36,12,58,62,77,89,100,18,20,25,30,32])
c = pd.cut(arr,5,precision=1,retbins = True)
print(c)
# ([(0.9, 20.8], (0.9, 20.8], (0.9, 20.8], (20.8, 40.6], (20.8, 40.6], ..., (0.9, 20.8], (0.9, 20.8], (20.8, 40.6], (20.8, 40.6], (20.8, 40.6]]
# Length: 16
# Categories (5, interval[float64]): [(0.9, 20.8] < (20.8, 40.6] < (40.6, 60.4] < (60.4, 80.2] < (80.2, 100.0]], \#             array([  0.901,  20.8  ,  40.6  ,  60.4  ,  80.2  , 100.   ]))

c = pd.cut(arr,bins = [1,5,18,35,50,100],labels = ['幼儿','少年','青年','中年','老年'],precision=1)
print(c)
# [NaN, 老年, 少年, 老年, 中年, ..., 少年, 青年, 青年, 青年, 老年]
# Length: 16
# Categories (5, object): [幼儿 < 少年 < 青年 < 中年 < 老年]

c = pd.cut(arr,bins = [1,5,18,35,50,100],labels = ['幼儿','少年','青年','中年','老年'],precision=1,include_lowest=True)
print(c)
# [幼儿, 老年, 少年, 老年, 中年, ..., 少年, 青年, 青年, 青年, 老年]
# Length: 16
# Categories (5, object): [幼儿 < 少年 < 青年 < 中年 < 老年]

c= pd.cut(arr,bins = [1,5,18,35,50,100],labels=False,include_lowest=True)
print(c)
# [0 0 1 3 3 1 4 4 4 4 4 1 2 2 2 2]