R统计分析与资料探勘入门—以鸢尾花资料集为例

http://www.cc.ntu.edu.tw/chinese/epaper/0031/20141220_3105.html

 

 

http://www.36dsj.com/archives/39775

 

http://blog.csdn.net/zouxy09/article/details/9993371 

 

http://php-52cs.rhcloud.com/?cat=7

 

 

ndarray

a =array([[1,2,3],[4,5,6],[7,8,9],[10,11,12]])

min(axis=None)

max(axis=None)

axis 解释   0 矩阵列  1 矩阵行

a.min(0)array([1, 2, 3])a.min(1)array([ 1,  4,  7, 10])

 

def linspace(start, stop, num=50, endpoint=True, retstep=False, dtype=None)

N=3x1 = np.linspace(0, 10, N, endpoint=True)  0~10之间的数分成N等分array([  0.,   5.,  10.])

 

def logspace(start, stop, num=50, endpoint=True, base=10.0, dtype=None)  0~10之间的数分成N等分  然后10** 等分值

N=3x1 = np.logspace(0, 10, N, endpoint=True)array([  1.00000000e+00,   1.00000000e+05,   1.00000000e+10])  ＃10**0 ,10**5, 10**10

 

 

np.random.shuffle()  打乱顺序

y = np.dot(X, coef)  内积