利用Python进行数据分析（2）—— Numpy Basic（2）

Boolean indexing

names = np.array(['Bob', 'Joe', 'Will', 'Bob', 'Will', 'Joe', 'Joe'])
data = np.random.randn(7, 4)
print(names)
print(data)

# 对 names 和 字符串 'Bob' 的比较运算符会产生一个布尔型数组
print(names == 'Bob')

# 这个布尔型数组可以用于索引
print(data[names == 'Bob'])

# data 数组的第一个下标对应 行数，第二个下标 对应 列数
print(data[names == 'Bob', 2:])
print(data[names == 'Bob', 3])

# 不等于
print(names != 'Bob')

# 非
print(data[~(names == 'Bob')])

# 或
mask = (names == 'Bob') | (names == 'Will')
print(mask)
print(data[mask])

# 令 data 数组中，小于 0 的数据，变为 0
data[data < 0] = 0
print(data)

#
data[names != 'Joe'] = 7
print(data)


names = np.array([0, 0, 0, 0, 1, 0, 1])
# 打印一个由 data 数组的 0,0,0,0,1,0,1 行 组成的数组
print(data[names])

# -----------------------------------------------------------

['Bob' 'Joe' 'Will' 'Bob' 'Will' 'Joe' 'Joe']
[[-0.2305  1.2412  0.2335 -0.8078]
 [-1.1944  0.5652 -1.1813 -0.223 ]
 [-1.2092  0.0819  0.0676 -1.2792]
 [ 1.3819  1.6011  1.5403 -0.3922]
 [ 1.5291 -1.2984 -0.8702 -0.4224]
 [-0.8074  1.5405 -0.2572  0.0881]
 [-0.3954 -0.9237 -0.7061 -0.0459]]
[ True False False  True False False False]
[[-0.2305  1.2412  0.2335 -0.8078]
 [ 1.3819  1.6011  1.5403 -0.3922]]
[[ 0.2335 -0.8078]
 [ 1.5403 -0.3922]]
[-0.8078 -0.3922]
[False  True  True False  True  True  True]
[[-1.1944  0.5652 -1.1813 -0.223 ]
 [-1.2092  0.0819  0.0676 -1.2792]
 [ 1.5291 -1.2984 -0.8702 -0.4224]
 [-0.8074  1.5405 -0.2572  0.0881]
 [-0.3954 -0.9237 -0.7061 -0.0459]]
[ True False  True  True  True False False]
[[-0.2305  1.2412  0.2335 -0.8078]
 [-1.2092  0.0819  0.0676 -1.2792]
 [ 1.3819  1.6011  1.5403 -0.3922]
 [ 1.5291 -1.2984 -0.8702 -0.4224]]
[[ 0.      1.2412  0.2335  0.    ]
 [ 0.      0.5652  0.      0.    ]
 [ 0.      0.0819  0.0676  0.    ]
 [ 1.3819  1.6011  1.5403  0.    ]
 [ 1.5291  0.      0.      0.    ]
 [ 0.      1.5405  0.      0.0881]
 [ 0.      0.      0.      0.    ]]
[[ 7.      7.      7.      7.    ]
 [ 0.      0.5652  0.      0.    ]
 [ 7.      7.      7.      7.    ]
 [ 7.      7.      7.      7.    ]
 [ 7.      7.      7.      7.    ]
 [ 0.      1.5405  0.      0.0881]
 [ 0.      0.      0.      0.    ]]
[[ 7.      7.      7.      7.    ]
 [ 7.      7.      7.      7.    ]
 [ 7.      7.      7.      7.    ]
 [ 7.      7.      7.      7.    ]
 [ 0.      0.5652  0.      0.    ]
 [ 7.      7.      7.      7.    ]
 [ 0.      0.5652  0.      0.    ]]

Process finished with exit code 0

---

Fancy indexing

# # fancy indexing 总是将数据复制到新数组中，与切片不同

arr = np.empty((8, 4))
for i in range(8):
    arr[i] = i
print(arr)

# fancy indexing ，利用整数数组进行索引
print(arr[[4, 3, 0, 6]])

print(arr[[-3, -5, -7]])

# more on reshape in Chapter 12
arr = np.arange(32).reshape((8, 4))

print(arr)

# 选出的元素为 (1,0) (5,3) (7,1) (2,2)
print(arr[[1, 5, 7, 2], [0, 3, 1, 2]])

# 选出的矩阵由 1,5,7,2 行构成，每行中，列的顺序为 0,3,1,2
print(arr[[1, 5, 7, 2]][:, [0, 3, 1, 2]])

# np.ix_ 函数可以将 两个一维数组转换 为 一个用于选择方形区域的 索引器
print(arr[np.ix_([1, 5, 7, 2], [0, 3, 1, 2])])

# -----------------------------------------------------

[[ 0.  0.  0.  0.]
 [ 1.  1.  1.  1.]
 [ 2.  2.  2.  2.]
 [ 3.  3.  3.  3.]
 [ 4.  4.  4.  4.]
 [ 5.  5.  5.  5.]
 [ 6.  6.  6.  6.]
 [ 7.  7.  7.  7.]]
[[ 4.  4.  4.  4.]
 [ 3.  3.  3.  3.]
 [ 0.  0.  0.  0.]
 [ 6.  6.  6.  6.]]
[[ 5.  5.  5.  5.]
 [ 3.  3.  3.  3.]
 [ 1.  1.  1.  1.]]
[[ 0  1  2  3]
 [ 4  5  6  7]
 [ 8  9 10 11]
 [12 13 14 15]
 [16 17 18 19]
 [20 21 22 23]
 [24 25 26 27]
 [28 29 30 31]]
[ 4 23 29 10]
[[ 4  7  5  6]
 [20 23 21 22]
 [28 31 29 30]
 [ 8 11  9 10]]
[[ 4  7  5  6]
 [20 23 21 22]
 [28 31 29 30]
 [ 8 11  9 10]]

Process finished with exit code 0

---

Transposing arrays and swapping axes

arr = np.arange(15).reshape((3, 5))
print(arr)
# 转置
print(arr.T)

arr = np.random.randn(6, 3)
# 点乘
print(np.dot(arr.T, arr))

# 高维数组需要一个 由轴编号 组成的元组才能对这些轴进行转置（费脑子）
arr = np.arange(16).reshape((2, 2, 4))
print(arr)
print(arr.transpose((1, 0, 2)))

# np.ndarray.swapaxes() 接受一对 轴编号
print(arr)
print(arr.swapaxes(1, 2))

# -----------------------------------------------------------

[[ 0  1  2  3  4]
 [ 5  6  7  8  9]
 [10 11 12 13 14]]
[[ 0  5 10]
 [ 1  6 11]
 [ 2  7 12]
 [ 3  8 13]
 [ 4  9 14]]
[[  3.9802  -0.2502   3.8607]
 [ -0.2502   7.7333   2.5982]
 [  3.8607   2.5982  10.7432]]
[[[ 0  1  2  3]
  [ 4  5  6  7]]

 [[ 8  9 10 11]
  [12 13 14 15]]]
[[[ 0  1  2  3]
  [ 8  9 10 11]]

 [[ 4  5  6  7]
  [12 13 14 15]]]
[[[ 0  1  2  3]
  [ 4  5  6  7]]

 [[ 8  9 10 11]
  [12 13 14 15]]]
[[[ 0  4]
  [ 1  5]
  [ 2  6]
  [ 3  7]]

 [[ 8 12]
  [ 9 13]
  [10 14]
  [11 15]]]

Process finished with exit code 0

---

Universal Functions: Fast element-wise array functions

快速的元素级数组函数

arr = np.arange(10)

# 开方
print(np.sqrt(arr))

# 自然对数的底数 e = 2.718..... 的 x 次幂
print(np.exp(arr))

x = np.random.randn(8)
y = np.random.randn(8)
print(x)
print(y)

# 接受两个数组
print(np.maximum(x, y)) # element-wise maximum

arr = np.random.randn(7) * 5
print(arr)

# 接受 一个数组，返回 两个数组，（将输入数组的 小数部分 与 整数部分 拆分）
print(np.modf(arr))
# -----------------------------------------------------------

[ 0.      1.      1.4142  1.7321  2.      2.2361  2.4495  2.6458  2.8284
  3.    ]
[    1.         2.7183     7.3891    20.0855    54.5982   148.4132
   403.4288  1096.6332  2980.958   8103.0839]
[-0.9039  0.6059  0.1219 -1.4536 -1.1021 -0.0681  0.2509  0.7939]
[ 0.9495 -1.8458  1.0095 -1.2951  0.3019 -1.5155 -0.1693 -0.4673]
[ 0.9495  0.6059  1.0095 -1.2951  0.3019 -0.0681  0.2509  0.7939]
[ 0.6628 -7.8998 -6.6542  3.9569 -1.4966  2.8784  3.5424]
(array([ 0.6628, -0.8998, -0.6542,  0.9569, -0.4966,  0.8784,  0.5424]), array([ 0., -7., -6.,  3., -1.,  2.,  3.]))

Process finished with exit code 0

---

Data processing using arrays

先不看了，累了…