可以使用一个numpy数组作为索引数组去过滤原数组,索引数组里为true的值,保留,为false的值去掉

import numpy as np

使用索引数组

a = np.array([1, 2, 3, 4])
b = np.array([True, True, False, False])
print a[b]                                       #[1 2]
print a[np.array([True, False, True, False])]    #[1 3]

通过对原数组进行向量化运算得到索引数组

a = np.array([1, 2, 3, 2, 1])
b = (a >= 2)
print a[b]            #[2 3 2]
print a[a >= 2]       #[2 3 2]

通过对某一数组进行向量化运算得到索引数组

a = np.array([1, 2, 3, 4, 5])
b = np.array([1, 2, 3, 2, 1])
print b == 2      #[False True False True False]
print a[b == 2]   #[2 4] 

一个例子:

# 20个学生在课程上所花费的时间
time_spent = np.array([
       12.89697233,    0.        ,   64.55043217,    0.        ,
       24.2315615 ,   39.991625  ,    0.        ,    0.        ,
      147.20683783,    0.        ,    0.        ,    0.        ,
       45.18261617,  157.60454283,  133.2434615 ,   52.85000767,
        0.        ,   54.9204785 ,   26.78142417,    0.
])

# 20个学生参加学习的天数
days_to_cancel = np.array([
      4,   5,  37,   3,  12,   4,  35,  38,   5,  37,   3,   3,  68,
     38,  98,   2, 249,   2, 127,  35
])

def mean_time_for_paid_students(time_spent, days_to_cancel):
    '''
    计算参加课程大于等于7天的学生平均在课程上所花的时间
    '''
    index_array = days_to_cancel >= 7
    mean_time = time_spent[index_array].mean()
    return mean_time

print(mean_time_for_paid_students(time_spent, days_to_cancel))

# 结果: 41.0540034855