【Machine Learning】1.numpy及matplotlib.pyplot的使用入门（1）

首先，这只是介绍一些最常用最简单的用法，具体还得查文档

numpy文档
matplotlib文档

1.导入

import numpy as np
import matplotlib.pyplot as plt
# plt.style.use('./deeplearning.mplstyle')  这是一个关于matplotlib自定义风格的文件，具体可以查看https://matplotlib.org/stable/tutorials/introductory/customizing.html

matplotlib自定义风格网站

2.numpy向量操作

2.1 向量初始化

np.zeros() 全为0，但类型为float64
np.random.random_sample() 0-1间的随机数

# NumPy routines which allocate memory and fill arrays with value
a = np.zeros(4);                print(f"np.zeros(4) :   a = {a}, a shape = {a.shape}, a data type = {a.dtype}")
a = np.zeros((4,));             print(f"np.zeros(4,) :  a = {a}, a shape = {a.shape}, a data type = {a.dtype}")
a = np.random.random_sample(4); print(f"np.random.random_sample(4): a = {a}, a shape = {a.shape}, a data type = {a.dtype}")

返回结果：
np.zeros(4) :   a = [0. 0. 0. 0.], a shape = (4,), a data type = float64
np.zeros(4,) :  a = [0. 0. 0. 0.], a shape = (4,), a data type = float64
np.random.random_sample(4): a = [0.51463916 0.74891896 0.3779201  0.04746511], a shape = (4,), a data type = float64

np.arange() 从0开始到n-1，类型看arange参数类型
np.random.rand(4) 0-1的随机数

# NumPy routines which allocate memory and fill arrays with value but do not accept shape as input argument
a = np.arange(4.);              print(f"np.arange(4.):     a = {a}, a shape = {a.shape}, a data type = {a.dtype}")
a = np.random.rand(4);          print(f"np.random.rand(4): a = {a}, a shape = {a.shape}, a data type = {a.dtype}")

np.arange(4.):     a = [0. 1. 2. 3.], a shape = (4,), a data type = float64
np.random.rand(4): a = [0.1121962  0.79179091 0.42450942 0.0702467 ], a shape = (4,), a data type = float64

np.array() ，类型视数组的第一个类型而定

# NumPy routines which allocate memory and fill with user specified values
a = np.array([5,4,3,2]);  print(f"np.array([5,4,3,2]):  a = {a},     a shape = {a.shape}, a data type = {a.dtype}")
a = np.array([5.,4,3,2]); print(f"np.array([5.,4,3,2]): a = {a}, a shape = {a.shape}, a data type = {a.dtype}")

# x_train is the input variable (size in 1000 square feet)
# y_train is the target (price in 1000s of dollars)
x_train = np.array([1.0, 2.0])
y_train = np.array([300.0, 500.0]) 
print(f"x_train = {x_train}")
print(f"y_train = {y_train}")

2.2 np.shape()

# m is the number of training examples
print(f"x_train.shape: {x_train.shape}")
m = x_train.shape[0]   #效果同m = len(x_train)
print(f"Number of training examples is: {m}")

返回结果：
x_train.shape: (2,)
Number of training examples is: 2

2.3 slicing切片

#vector slicing operations
a = np.arange(10)
print(f"a         = {a}")

#access 5 consecutive elements (start:stop:step)
c = a[2:7:1];     print("a[2:7:1] = ", c)

# access 3 elements separated by two 
c = a[2:7:2];     print("a[2:7:2] = ", c)

# access all elements index 3 and above
c = a[3:];        print("a[3:]    = ", c)

# access all elements below index 3
c = a[:3];        print("a[:3]    = ", c)

# access all elements
c = a[:];         print("a[:]     = ", c)

结果：
a         = [0 1 2 3 4 5 6 7 8 9]
a[2:7:1] =  [2 3 4 5 6]
a[2:7:2] =  [2 4 6]
a[3:]    =  [3 4 5 6 7 8 9]
a[:3]    =  [0 1 2]
a[:]     =  [0 1 2 3 4 5 6 7 8 9]

2.4 Single vector operations

a = np.array([1,2,3,4])
print(f"a             : {a}")
# negate elements of a
b = -a 
print(f"b = -a        : {b}")

# sum all elements of a, returns a scalar
b = np.sum(a) 
print(f"b = np.sum(a) : {b}")

b = np.mean(a)
print(f"b = np.mean(a): {b}")

b = a**2
print(f"b = a**2      : {b}")

a             : [1 2 3 4]
b = -a        : [-1 -2 -3 -4]
b = np.sum(a) : 10
b = np.mean(a): 2.5
b = a**2      : [ 1  4  9 16]

2.5 向量间的运算

加减乘除即对应相加相减

np.dot()

# test 1-D
a = np.array([1, 2, 3, 4])
b = np.array([-1, 4, 3, 2])
c = np.dot(a, b)
print(f"NumPy 1-D np.dot(a, b) = {c}, np.dot(a, b).shape = {c.shape} ") 
c = np.dot(b, a)
print(f"NumPy 1-D np.dot(b, a) = {c}, np.dot(a, b).shape = {c.shape} ")

结果：
NumPy 1-D np.dot(a, b) = 24, np.dot(a, b).shape = () 
NumPy 1-D np.dot(b, a) = 24, np.dot(a, b).shape = () 

向量的点积与循环之间的速度比较：

np.random.seed(1)
a = np.random.rand(10000000)  # very large arrays
b = np.random.rand(10000000)

tic = time.time()  # capture start time
c = np.dot(a, b)
toc = time.time()  # capture end time

print(f"np.dot(a, b) =  {c:.4f}")
print(f"Vectorized version duration: {1000*(toc-tic):.4f} ms ")

tic = time.time()  # capture start time
c = my_dot(a,b)
toc = time.time()  # capture end time

print(f"my_dot(a, b) =  {c:.4f}")
print(f"loop version duration: {1000*(toc-tic):.4f} ms ")

del(a);del(b)  #remove these big arrays from memory


np.dot(a, b) =  2501072.5817
Vectorized version duration: 6.9878 ms 
my_dot(a, b) =  2501072.5817
loop version duration: 3275.7676 ms 

3.numpy矩阵操作

3.1 矩阵初始化

a = np.zeros((1, 5))                                       
print(f"a shape = {a.shape}, a = {a}")                     

a = np.zeros((2, 1))                                                                   
print(f"a shape = {a.shape}, a = {a}") 

a = np.random.random_sample((1, 1))  
print(f"a shape = {a.shape}, a = {a}") 

# NumPy routines which allocate memory and fill with user specified values
a = np.array([[5], [4], [3]]);   print(f" a shape = {a.shape}, np.array: a = {a}")
a = np.array([[5],   # One can also
              [4],   # separate values
              [3]]); #into separate rows
print(f" a shape = {a.shape}, np.array: a = {a}")

结果：
a shape = (1, 5), a = [[0. 0. 0. 0. 0.]]
a shape = (2, 1), a = [[0.]
 [0.]]
a shape = (1, 1), a = [[0.5792328]]
 a shape = (3, 1), np.array: a = [[5]
 [4]
 [3]]
 a shape = (3, 1), np.array: a = [[5]
 [4]
 [3]]

#vector indexing operations on matrices
a = np.arange(6).reshape(-1, 2)   #-1参数代表这个值自动计算，reshape方便用来创建矩阵（数量确定，规定行列）
print(f"a.shape: {a.shape}, \na= {a}")

#access an element
print(f"\na[2,0].shape:   {a[2, 0].shape}, a[2,0] = {a[2, 0]},     type(a[2,0]) = {type(a[2, 0])} Accessing an element returns a scalar\n")

#access a row
print(f"a[2].shape:   {a[2].shape}, a[2]   = {a[2]}, type(a[2])   = {type(a[2])}")


结果：
a.shape: (3, 2), 
a= [[0 1]
 [2 3]
 [4 5]]

a[2,0].shape:   (), a[2,0] = 4,     type(a[2,0]) = <class 'numpy.int32'> Accessing an element returns a scalar

a[2].shape:   (2,), a[2]   = [4 5], type(a[2])   = <class 'numpy.ndarray'>

3.2 切片

#vector 2-D slicing operations
a = np.arange(20).reshape(-1, 10)
print(f"a = \n{a}")

#access 5 consecutive elements (start:stop:step)
print("a[0, 2:7:1] = ", a[0, 2:7:1], ",  a[0, 2:7:1].shape =", a[0, 2:7:1].shape, "a 1-D array")

#access 5 consecutive elements (start:stop:step) in two rows
print("a[:, 2:7:1] = \n", a[:, 2:7:1], ",  a[:, 2:7:1].shape =", a[:, 2:7:1].shape, "a 2-D array")

# access all elements
print("a[:,:] = \n", a[:,:], ",  a[:,:].shape =", a[:,:].shape)

# access all elements in one row (very common usage)
print("a[1,:] = ", a[1,:], ",  a[1,:].shape =", a[1,:].shape, "a 1-D array")
# same as
print("a[1]   = ", a[1],   ",  a[1].shape   =", a[1].shape, "a 1-D array")

结果：
a = 
[[ 0  1  2  3  4  5  6  7  8  9]
 [10 11 12 13 14 15 16 17 18 19]]
a[0, 2:7:1] =  [2 3 4 5 6] ,  a[0, 2:7:1].shape = (5,) a 1-D array
a[:, 2:7:1] = 
 [[ 2  3  4  5  6]
 [12 13 14 15 16]] ,  a[:, 2:7:1].shape = (2, 5) a 2-D array
a[:,:] = 
 [[ 0  1  2  3  4  5  6  7  8  9]
 [10 11 12 13 14 15 16 17 18 19]] ,  a[:,:].shape = (2, 10)
a[1,:] =  [10 11 12 13 14 15 16 17 18 19] ,  a[1,:].shape = (10,) a 1-D array
a[1]   =  [10 11 12 13 14 15 16 17 18 19] ,  a[1].shape   = (10,) a 1-D array

4.matplotlib.pyplot

scatter是画点的函数，plot是画线的

def compute_model_output(x, w, b):# 定义模型函数
    """
    Computes the prediction of a linear model
    Args:
      x (ndarray (m,)): Data, m examples 
      w,b (scalar)    : model parameters  
    Returns
      y (ndarray (m,)): target values
    """
    m = x.shape[0]
    f_wb = np.zeros(m) //大小为m的0数组
    for i in range(m):
        f_wb[i] = w * x[i] + b
        
    return f_wb

tmp_f_wb = compute_model_output(x_train, w, b,) #这是自定义的函数，不用管

#从这里开始才是重点

# Plot our model prediction
plt.plot(x_train, tmp_f_wb, c='b',label='Our Prediction')  #画线

# Plot the data points
plt.scatter(x_train, y_train, marker='x', c='r',label='Actual Values')  #画点，marker代表点类型，c代表颜色

# Set the title
plt.title("Housing Prices")
# Set the y-axis label
plt.ylabel('Price (in 1000s of dollars)')
# Set the x-axis label
plt.xlabel('Size (1000 sqft)')
plt.legend()  #代表左上角的图例
plt.show()

绘图效果：