Python / Numpy Tutorial
Python
这里介绍了python,并举了一个快排的例子,这个快排写的挺好看的。
def quicksort(arr):
if len(arr) <= 1:
return arr
pivot = arr[len(arr) / 2]
left = [x for x in arr if x < pivot]
middle = [x for x in arr if x == pivot]
right = [x for x in arr if x > pivot]
return quicksort(left) + middle + quicksort(right)
print quicksort([3,6,8,10,1,2,1])
# Prints "[1, 1, 2, 3, 6, 8, 10]"
Basic data types
介绍了python中的基本运算操作和变量。
有关int和浮点型的运算:
x = 3
print type(x) # Prints "<type 'int'>"
print x # Prints "3"
print x + 1 # Addition; prints "4"
print x - 1 # Subtraction; prints "2"
print x * 2 # Multiplication; prints "6"
print x ** 2 # Exponentiation; prints "9"
x += 1
print x # Prints "4"
x *= 2
print x # Prints "8"
y = 2.5
print type(y) # Prints "<type 'float'>"
print y, y + 1, y * 2, y ** 2 # Prints "2.5 3.5 5.0 6.25"
boolean型:
t = True
f = False
print type(t) # Prints "<type 'bool'>"
print t and f # Logical AND; prints "False"
print t or f # Logical OR; prints "True"
print not t # Logical NOT; prints "False"
print t != f # Logical XOR; prints "True"
string型:
hello = 'hello' # String literals can use single quotes
world = "world" # or double quotes; it does not matter.
print hello # Prints "hello"
print len(hello) # String length; prints "5"
hw = hello + ' ' + world # String concatenation
print hw # prints "hello world"
hw12 = '%s %s %d' % (hello, world, 12) # sprintf style string formatting
print hw12 # prints "hello world 12"
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"
容器(containers):
首先是Lists:
xs = [3, 1, 2] # Create a list
print xs, xs[2] # Prints "[3, 1, 2] 2"
print xs[-1] # Negative indices count from the end of the list; prints "2"
xs[2] = 'foo' # Lists can contain elements of different types
print xs # Prints "[3, 1, 'foo']"
xs.append('bar') # Add a new element to the end of the list
print xs # Prints "[3, 1, 'foo', 'bar']"
x = xs.pop() # Remove and return the last element of the list
print x, xs # Prints "bar [3, 1, 'foo']"
nums = range(5) # range is a built-in function that creates a list of integers
print nums # Prints "[0, 1, 2, 3, 4]"
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]"
animals = ['cat', 'dog', 'monkey']
for animal in animals:
print animal
# Prints "cat", "dog", "monkey", each on its own line.
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
nums = [0, 1, 2, 3, 4]
squares = []
for x in nums:
squares.append(x ** 2)
print squares # Prints [0, 1, 4, 9, 16]
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]"
其二是Dictionaries:
d = {'cat': 'cute', 'dog': 'furry'} # Create a new dictionary with some data
print d['cat'] # Get an entry from a dictionary; prints "cute"
print 'cat' in d # Check if a dictionary has a given key; prints "True"
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"
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 spider has 8 legs", "A cat has 4 legs"
d = {'person': 2, 'cat': 4, 'spider': 8}
for animal, legs in d.iteritems():
print 'A %s has %d legs' % (animal, legs)
# Prints "A person has 2 legs", "A spider has 8 legs", "A cat has 4 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}"
第三个是Sets:
animals = {'cat', 'dog'}
print 'cat' in animals # Check if an element is in a set; prints "True"
print 'fish' in animals # prints "False"
animals.add('fish') # Add an element to a set
print 'fish' in animals # Prints "True"
print len(animals) # Number of elements in a set; prints "3"
animals.add('cat') # Adding an element that is already in the set does nothing
print len(animals) # Prints "3"
animals.remove('cat') # Remove an element from a set
print len(animals) # Prints "2"
animals = {'cat', 'dog', 'fish'}
for idx, animal in enumerate(animals):
print '#%d: %s' % (idx + 1, animal)
# Prints "#1: fish", "#2: dog", "#3: cat"
from math import sqrt
nums = {int(sqrt(x)) for x in range(30)}
print nums # Prints "set([0, 1, 2, 3, 4, 5])"
最后是Tuples:
它与list很像,但他可以作为dictionaries的keys使用,可以作为sets的成员,而lists不能。
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 "<type 'tuple'>"
print d[t] # Prints "5"
print d[(1, 2)] # Prints "1"
Functions
def来定义函数。
def sign(x):
if x > 0:
return 'positive'
elif x < 0:
return 'negative'
else:
return 'zero'
for x in [-1, 0, 1]:
print sign(x)
# Prints "negative", "zero", "positive"
缺省的用法:
def hello(name, loud=False):
if loud:
print 'HELLO, %s!' % name.upper()
else:
print 'Hello, %s' % name
hello('Bob') # Prints "Hello, Bob"
hello('Fred', loud=True) # Prints "HELLO, FRED!"
Classes
类的定义也很简单:
class Greeter(object):
# Constructor
def __init__(self, name):
self.name = name # Create an instance variable
# Instance method
def greet(self, loud=False):
if loud:
print 'HELLO, %s!' % self.name.upper()
else:
print 'Hello, %s' % self.name
g = Greeter('Fred') # Construct an instance of the Greeter class
g.greet() # Call an instance method; prints "Hello, Fred"
g.greet(loud=True) # Call an instance method; prints "HELLO, FRED!"
Numpy
Numpy是Python中科学计算的核心库。
Arrays
看例子很好理解:
直接初始化:
import numpy as np
a = np.array([1, 2, 3]) # Create a rank 1 array
print type(a) # Prints "<type '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"
使用函数来初始化:
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]]"
slicing:
要注意的是,slicing完了之后的存储与原变量是同地址的,比如下面例子中的变量b:
import numpy as np
# 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]])
# Use slicing to pull out the subarray consisting of the first 2 rows
# and columns 1 and 2; b is the following array of shape (2, 2):
# [[2 3]
# [6 7]]
b = a[:2, 1:3]
# A slice of an array is a view into the same data, so modifying it
# will modify the original array.
print a[0, 1] # Prints "2"
b[0, 0] = 77 # b[0, 0] is the same piece of data as a[0, 1]
print a[0, 1] # Prints "77"
下面这个点十分值得注意,用slice和index访问会造成不同的后果,这点与matlab中并不一样,用index直接访问会降维,slice不会:
import numpy as np
# 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)"
# We can make the same distinction when accessing columns of an array:
col_r1 = a[:, 1]
col_r2 = a[:, 1:2]
print col_r1, col_r1.shape # Prints "[ 2 6 10] (3,)"
print col_r2, col_r2.shape # Prints "[[ 2]
# [ 6]
# [10]] (3, 1)"
int型的访问方法:
可以组成一对坐标来访问矩阵,比如下面例子中的a[[0, 1, 2], [0, 1, 0]],就表示访问坐标(0,0),(1,1),(2,0)元素:
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]"
# When using integer array indexing, you can reuse the same
# element from the source array:
print a[[0, 0], [1, 1]] # Prints "[2 2]"
# Equivalent to the previous integer array indexing example
print np.array([a[0, 1], a[0, 1]]) # Prints "[2 2]"
用array方法来访问:
import numpy as np
# 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]])
用bool型来访问满足特定条件的元素:
import numpy as np
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]"
np.array可以判断类型:
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"
array数学运算:
与matlab有区别的是,*在python中为elementwise的乘法,而在matlab中是矩阵乘法。
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)
dot为numpy中的矩阵乘法,若为两个向量相乘,则为求点积:
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)
转置:
import numpy as np
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]"
给每行加上一个向量:
import numpy as np
# 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 = np.empty_like(x) # Create an empty matrix with the same shape as x
# Add the vector v to each row of the matrix x with an explicit loop
for i in range(4):
y[i, :] = x[i, :] + v
# Now y is the following
# [[ 2 2 4]
# [ 5 5 7]
# [ 8 8 10]
# [11 11 13]]
print y
上面程序的代码在x非常大的时候跑循环很浪费时间,可以有如下优化:
import numpy as np
# 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])
vv = np.tile(v, (4, 1)) # Stack 4 copies of v on top of each other
print vv # Prints "[[1 0 1]
# [1 0 1]
# [1 0 1]
# [1 0 1]]"
y = x + vv # Add x and vv elementwise
print y # Prints "[[ 2 2 4
# [ 5 5 7]
# [ 8 8 10]
# [11 11 13]]"
由于broadcasting的特性,上述程序完全可以写为:
import numpy as np
# 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]]"
SciPy
SciPy提供了基本的图像操作,官方文档为:http://docs.scipy.org/doc/scipy/reference/index.html
Matplotlib
plot图像:
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.
#################
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()
#subplots
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)
# 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()
Ipython Notebook
这里介绍了Ipython Notebook,这个东西还挺好用的。能在网页上直接运行python。
Terminal.com
这个网页好像能在网页上直接打开一个终端来使用,但是好像被墙了。404。
AWS
简要介绍了一下AWS,听说目前大多数实验室都用这个来跑DL。不知道我将要去的实验室是怎么安排的,由此可以考虑新机器的配置。