Python容器和 Numpy库基础

Python容器和 Numpy库基础

这是CS223图像识别的补充的python和Numpy库的基础课程，我稍微做了整理，原文链接：http://cs231n.github.io/python-numpy-tutorial/#python

1.     运算符//，

" // "来表示整数除法，返回不大于结果的一个最大的整数，而" / "则单纯的表示浮点数除法

例如： 5//2 = 2

2.     字符串的运用

s = "hello"

print(s.capitalize())  # Capitalize a string; prints "Hello"

print(s.upper())       # Convert a string to uppercase;prints "HELLO"

print(s.rjust(7))     #Right-justify a string, padding with spaces; prints "  hello"

print(s.center(7))    #Center a string, padding with spaces; prints " hello "

print(s.replace('l','(ell)')) #Replace all instances of one substring with another;

                                # prints"he(ell)(ell)o"

print('  world '.strip()) # Strip leading and trailing whitespace; prints "world"

3.     容器-Lists

an contain elements of different types:如：[1,2,”jk”,]

切割：

print(nums[2:4])          # Get a slice from index 2 to 4 (exclusive); prints "[2, 3]"

print(nums[2:])           # Get a slice from index 2 to the end; prints "[2, 3, 4]"

print(nums[:2])           # Get a slice from the start to index 2 (exclusive); prints "[0, 1]"

print(nums[:])            # Get a slice of the whole list; prints "[0, 1, 2, 3, 4]"

print(nums[:-1])          # Slice indices can be negative; prints "[0, 1, 2, 3]"

nums[2:4] = [8, 9]        # Assign a new sublist to a slice

print(nums)               # Prints "[0, 1, 8, 9, 4]"

循环：

animals = ['cat', 'dog', 'monkey']

for idx, animal in enumerate(animals):

    print('#%d: %s' % (idx + 1, animal))

# Prints "#1: cat", "#2: dog", "#3: monkey", each on its own line

可以对列表进行各元素统一处理不需要循环

nums = [0, 1, 2, 3, 4]

squares = [x ** 2 for x in nums]

print(squares)   # Prints [0, 1, 4, 9, 16]

nums = [0, 1, 2, 3, 4]

even_squares = [x ** 2 for x in nums if x % 2 == 0]

print(even_squares)  # Prints "[0, 4, 16]"

4.     容器-Dictionaries（字典）

A dictionary stores (key, value) pairs,注意Get的用法

d = {'cat': 'cute', 'dog': 'furry'}  # Create a new dictionary with some data

d['fish'] = 'wet'     # Set an entry in a dictionary

print(d['fish'])      # Prints "wet"

# print(d['monkey'])  # KeyError: 'monkey' not a key of d

print(d.get('monkey', 'N/A'))  # Get an element with a default; prints "N/A"

print(d.get('fish', 'N/A'))    # Get an element with a default; prints "wet"

del d['fish']         # Remove an element from a dictionary

print(d.get('fish', 'N/A')) # "fish" is no longer a key; prints "N/A"

循环：（默认是索引，d.iteme对应索引和内容）

d = {'person': 2, 'cat': 4, 'spider': 8}

for animal in d:

    legs = d[animal]

    print('A %s has %d legs' % (animal, legs))

# Prints "A person has 2 legs", "A cat has 4 legs", "A spider has 8 legs"

d = {'person': 2, 'cat': 4, 'spider': 8}

for animal, legs in d.items():

    print('A %s has %d legs' % (animal, legs))

# Prints "A person has 2 legs", "A cat has 4 legs", "A spider has 8 legs"

nums = [0, 1, 2, 3, 4]

even_num_to_square = {x: x ** 2 for x in nums if x % 2 == 0}

print(even_num_to_square)  # Prints "{0: 0, 2: 4, 4: 16}"

5.     容器-Set（不同元素的无序集合）

如：animals = {'cat', 'dog'}

from math import sqrt

nums = {int(sqrt(x)) for x in range(30)}

print(nums)  # Prints "{0, 1, 2, 3, 4, 5}"

注意set不能像Lists那样数字索引获得内容

6.     容器-Tuples元组

A tuple is an (immutable) ordered list of values.

与Lists不同的地方是：可以作为字典的索引  和 set的元素

d = {(x, x + 1): x for x in range(10)}  # Create a dictionary with tuple keys

t = (5, 6)        # Create a tuple

print(type(t))    # Prints "<class 'tuple'>"

print(d[t])       # Prints "5"

print(d[(1, 2)])  # Prints "1"

 

Numpy库

1.     Arrays（注意要使用Array, import numpy）

注意.shape() 获得

import numpy as np

a = np.array([1, 2, 3])   # Create a rank 1 array

print(type(a))            # Prints "<class 'numpy.ndarray'>"

print(a.shape)            # Prints "(3,)"

print(a[0], a[1], a[2])   # Prints "1 2 3"

a[0] = 5                  # Change an element of the array

print(a)                  # Prints "[5, 2, 3]"

b = np.array([[1,2,3],[4,5,6]])    # Create a rank 2 array

print(b.shape)                     # Prints "(2, 3)"

print(b[0, 0], b[0, 1], b[1, 0])   # Prints "1 2 4"

常用的Array

import numpy as np

a = np.zeros((2,2))   # Create an array of all zeros

print(a)              # Prints "[[ 0.  0.]

                      #          [ 0.  0.]]"

b = np.ones((1,2))    # Create an array of all ones

print(b)              # Prints "[[ 1.  1.]]"

c = np.full((2,2), 7)  # Create a constant array

print(c)               # Prints "[[ 7.  7.]

                       #          [ 7.  7.]]"

d = np.eye(2)         # Create a 2x2 identity matrix

print(d)              # Prints "[[ 1.  0.]

                      #          [ 0.  1.]]"

e = np.random.random((2,2))  # Create an array filled with random values

print(e)    # Might print "[[ 0.91940167  0.08143941]

            #               [ 0.68744134  0.87236687]]"

与Lists类似，Arrays也可以切割检索

# Create the following rank 2 array with shape (3, 4)

# [[ 1  2  3  4]

#  [ 5  6  7  8]

#  [ 9 10 11 12]]

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

# Two ways of accessing the data in the middle row of the array.

# Mixing integer indexing with slices yields an array of lower rank,

# while using only slices yields an array of the same rank as the

# original array:

row_r1 = a[1, :]    # Rank 1 view of the second row of a

row_r2 = a[1:2, :]  # Rank 2 view of the second row of a

print(row_r1, row_r1.shape)  # Prints "[5 6 7 8] (4,)"

print(row_r2, row_r2.shape)  # Prints "[[5 6 7 8]] (1, 4)"

 

整合Array： allows youto construct arbitrary arrays using the data from another array.

import numpy as np

a = np.array([[1,2], [3, 4], [5, 6]])

# An example of integer array indexing.

# The returned array will have shape (3,) and

print(a[[0, 1, 2], [0, 1, 0]])  # Prints "[1 4 5]"

# The above example of integer array indexing is equivalent to this:

print(np.array([a[0, 0], a[1, 1], a[2, 0]]))  # Prints "[1 4 5]"

为了便于理解可以把array写成矩阵样式

# Create a new array from which we will select elements

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

print(a)  # prints "array([[ 1,  2,  3],

          #                [ 4,  5,  6],

          #                [ 7,  8,  9],

          #                [10, 11, 12]])"

# Create an array of indices

b = np.array([0, 2, 0, 1])

# Select one element from each row of a using the indices in b

print(a[np.arange(4), b])  # Prints "[ 1  6  7 11]"

# Mutate one element from each row of a using the indices in b

a[np.arange(4), b] += 10

print(a)  # prints "array([[11,  2,  3],

          #                [ 4,  5, 16],

          #                [17,  8,  9],

          #                [10, 21, 12]])

注：numpy中的arange() 和 python自带的range()相似，不过一个返回array，一个返回list

同时也可以用 布尔bool 进行整合

a=np.array([[1,2], [3, 4], [5, 6]])

bool_idx = (a > 2)   # Find the elements of a that are bigger than 2;

                     # this returns a numpy array of Booleans of the same

                     # shape as a, where each slot of bool_idx tells

                     # whether that element of a is > 2.

print(bool_idx)      # Prints "[[False False]

                     #          [ True  True]

                     #          [ True  True]]"

# We use boolean array indexing to construct a rank 1 array

# consisting of the elements of a corresponding to the True values

# of bool_idx

print(a[bool_idx])  # Prints "[3 4 5 6]"

# We can do all of the above in a single concise statement:

print(a[a > 2])     # Prints "[3 4 5 6]"

2.Datatypes

import numpy as np

x = np.array([1, 2])   # Let numpy choose the datatype

print(x.dtype)         # Prints "int64"

x = np.array([1.0, 2.0])   # Let numpy choose the datatype

print(x.dtype)             # Prints "float64"

x = np.array([1, 2], dtype=np.int64)   # Force a particular datatype

print(x.dtype)                         # Prints "int64"

3.Array的数学运算

数学运算符同样可以运用到Array中,将对应元素进行运算即可

import numpy as np

 

x = np.array([[1,2],[3,4]], dtype=np.float64)

y = np.array([[5,6],[7,8]], dtype=np.float64)

 

# Elementwise sum; both produce the array

# [[ 6.0  8.0]

#  [10.0 12.0]]

print(x +y)

print(np.add(x,y))

 

# Elementwise difference; both produce the array

# [[-4.0 -4.0]

#  [-4.0 -4.0]]

print(x -y)

print(np.subtract(x,y))

 

# Elementwise product; both produce the array

# [[ 5.0 12.0]

#  [21.0 32.0]]

print(x *y)

print(np.multiply(x,y))

 

# Elementwise division; both produce the array

# [[ 0.2         0.33333333]

#  [ 0.42857143  0.5      ]]

print(x /y)

print(np.divide(x,y))

 

# Elementwise square root; produces the array

# [[ 1.          1.41421356]

#  [ 1.73205081  2.       ]]

print(np.sqrt(x))

注意：*与MATLAB中不同，向量矩阵乘在numpy中用dot()

import numpy as np

 

x = np.array([[1,2],[3,4]])

y = np.array([[5,6],[7,8]])

 

v = np.array([9,10])

w = np.array([11,12])

 

# Inner product of vectors; both produce 219

print(v.dot(w))

print(np.dot(v,w))

 

# Matrix / vector product; both produce the rank 1 array [29 67]

print(x.dot(v))

print(np.dot(x,v))

 

# Matrix / matrix product; both produce the rank 2 array

# [[19 22]

#  [43 50]]

print(x.dot(y))

print(np.dot(x,y))

一些常用函数：sum()，.T()

x = np.array([[1,2],[3,4]])

 

print(np.sum(x)) # Compute sum of all elements; prints "10"

print(np.sum(x, axis=0)) #Compute sum of each column; prints "[4 6]"

print(np.sum(x, axis=1)) #Compute sum of each row; prints "[3 7]"

 

x = np.array([[1,2], [3,4]])

print(x)    # Prints "[[1 2]

            #          [3 4]]"

print(x.T)  # Prints "[[1 3]

            #          [2 4]]"

 

# Note that taking the transpose of a rank 1 array does nothing:

v = np.array([1,2,3])

print(v)    # Prints "[1 2 3]"

print(v.T)  # Prints "[1 2 3]"

4.Broadcasting广播机制

一定要注意，执行 broadcast的前提在于，两个 ndarray执行的是 element-wise（按位加，按位减）的运算

注意的几条规则：

（1）如果数组不具有相同的秩，则先将低层数组的形状用1表示，直到两个形状都有相同的长度。

# We will add the vector v to each row of the matrix x,

# storing the result in the matrix y

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

v = np.array([1, 0, 1])

y = x + v  # Add v to each row of x using broadcasting

print(y)  # Prints "[[ 2  2  4]

          #          [ 5  5  7]

          #          [ 8  8 10]

          #          [11 11 13]]"

（2）两个数组要是相容的（即shape相同）或其中数组有维度为1

维度有1的Array操作时对应另一数组的该维度的每一行（ were copiedalong that dimension）

注意reshape()的运用

# Compute outer product of vectors

v = np.array([1,2,3])  # v has shape (3,)

w = np.array([4,5])    # w has shape (2,)

# To compute an outer product, we first reshape v to be a column

# vector of shape (3, 1); we can then broadcast it against w to yield

# an output of shape (3, 2), which is the outer product of v and w:

# [[ 4  5]

#  [ 8 10]

#  [12 15]]

print(np.reshape(v, (3, 1)) * w)

# Add a vector to each row of a matrix

x = np.array([[1,2,3], [4,5,6]])

# x has shape (2, 3) and v has shape (3,) so they broadcast to (2, 3),

# giving the following matrix:

# [[2 4 6]

#  [5 7 9]]

print(x + v)

# Add a vector to each column of a matrix

# x has shape (2, 3) and w has shape (2,).

# If we transpose x then it has shape (3, 2) and can be broadcast

# against w to yield a result of shape (3, 2); transposing this result

# yields the final result of shape (2, 3) which is the matrix x with

# the vector w added to each column. Gives the following matrix:

# [[ 5  6  7]

#  [ 9 10 11]]

print((x.T + w).T)

# Another solution is to reshape w to be a column vector of shape (2, 1);

# we can then broadcast it directly against x to produce the same

# output.

print(x + np.reshape(w, (2, 1)))

# Multiply a matrix by a constant:

# x has shape (2, 3). Numpy treats scalars as arrays of shape ();

# these can be broadcast together to shape (2, 3), producing the

# following array:

# [[ 2  4  6]

#  [ 8 10 12]]

print(x * 2)

5. Matplotlib

主要用于画图

import numpy as np

import matplotlib.pyplot as plt

# Compute the x and y coordinates for points on a sine curve

x = np.arange(0, 3 * np.pi, 0.1)

y = np.sin(x)

# Plot the points using matplotlib

plt.plot(x, y)

plt.show()  # You must call plt.show() to make graphics appear.

 

 

添加标签，题目，抬头

import numpy as np

import matplotlib.pyplot as plt

# Compute the x and y coordinates for points on sine and cosine curves

x = np.arange(0, 3 * np.pi, 0.1)

y_sin = np.sin(x)

y_cos = np.cos(x)

# Plot the points using matplotlib

plt.plot(x, y_sin)

plt.plot(x, y_cos)

plt.xlabel('x axis label')

plt.ylabel('y axis label')

plt.title('Sine and Cosine')

plt.legend(['Sine', 'Cosine'])

plt.show()

subplot（）将多幅图放置一起

# Compute the x and y coordinates for points on sine and cosine curves

x = np.arange(0, 3 * np.pi, 0.1)

y_sin = np.sin(x)

y_cos = np.cos(x)

# Set up a subplot grid that has height 2 and width 1,

# and set the first such subplot as active.

plt.subplot(2, 1, 1)

# Make the first plot

plt.plot(x, y_sin)

plt.title('Sine')

# Set the second subplot as active, and make the second plot.

plt.subplot(2, 1, 2)

plt.plot(x, y_cos)

plt.title('Cosine')

# Show the figure.

plt.show()