注：这是我参加招行Fintech精英训练营金融工程课程跟着做的笔记，代码是在Pycharm上写的。
里面用到的股票数据均来自雅虎财经（https://finance.yahoo.com/），数据下载方法我在（一）中有介绍。
量化交易基础：使用python处理金融数据
01-03:NumPy的强大优势
import numpyas np
#6/7/8.creating NumPy arrays
def test_run():
print(np.array([(2,3,4),(5,6,7)]))
#empty array
print(np.empty((5.4)))
print(np.ones((5,4)),dtype=np.int_)
if __name__=="__main__":
test_run()
#9. generating random numbers
def test_run():
#产生[0，1）之间的随机数
print(np.random.random((5,4)))
print(np.random.rand(5, 4))#function argumemts(not a tuple)
#sample numbers from a Gaussion (normal) distribution
print(np.random.normal(50,10,size=(2,3)))#mean=50,std=10,row=2,column=3
#random integers
print(np.random.randint(10))#a single integer in [0,10)
print(np.random.randint(0,10))# a single integer in [0,10),same as above, specifying [low,high) explicit
print(np.random.randint(0,10,size=5))# 5 random integers as a 1D array
print(np.random.randint(0, 10, size=(2,3)))# 2x3 array of random integers
if __name__=="__main__"
test_run()
#10. arrasy attributes
def test_run():
a=np.random.random((5,4))
print(a.shape)
print(a.shape[0])#number of rows
print(a.shape(1))#number of columns
print(len(a.shape))
print(a.size)#array 中值的个数
print(a.dtype)#data type of the values present in array
# 11.ndarray 操作
def test_run():
np.random.seed(693)#seed the random number generator,为了每次得到相同的序列数字
a = np.random.randint(0,10,size=(5,4))
print("Array:\n",a)
#sum of all elements
print("Sum of all elements:",a.sum())
#iterate over rows, to compute sum of each column
print("Sum of each column:\n",a.sum(axis=0))
# iterate over columns, to compute sum of each row
print("Sum of each column:\n", a.sum(axis=1))
#statistics:min,max,mean(across rows,cols, and overall)
print("Minimum of each column:\n",a.min(axis=0))
print("Maximum of each row:\n", a.max(axis=1))
print("Mean of all elements:\n", a.mean())#leave out axis arg
#12. exercise: locate maximum value
def get_max_index(a):
"""Return the index of the maximum value in given 1D array."""
return np.argmax(a)
# 或 return a.argmax()
def test_run():
a = np.array([9, 6, 2, 3, 12, 14, 7, 10], dtype=np.int32)# 32-bit integer array
"Array:", a
# Find the maximum and its index in array
"Maximum value:", a.max()
"Index of max.:", get_max_index(a)
if __name__ =="__main__":
test_run()
13. 记录python操作花费的时间
"""using time function """
import time
def test_run():
t1 = time.time()
print("ML4T")
t2 = time.time()
print("The time taken by print statement is", t2-t1, "seconds")
if __name__=="__main__":
test_run()
14. NumPy的运行速度有多快？
def manual_mean(arr):
sum=0
for iin xrange(0,arr.shape[0]):
for jin arange(0,arr.shape[1]):
sum=sum+arr[i,j]
return sum/arr.size
def numpy_mean(arr):
return arr.mean()
def how_long(func,*args):
t0=time()
result=func(*args)
ti =time()
return result,t1-t0
def test_run():
nd1=np.random.random((1000,10000))
res_manual,t_manual=how_long(manual_mean,nd1)
res_numpy, t_numpy = how_long(numpy_mean, nd1)
#15. accessing array elements
#slicing
def test_run():
a = np.random.rand(5,4)
print(a[:,0:3:2])#1star,3-1end,2step
#16. modifying array elements
#assigning a list to a column in and array
a[:,3]=[1,2,3,4,5]
#17. indexing an array with another array
def test_run():
a=np.random.rand(5)
indices=np.array([1,1,2,3])
print(a[indices])
if __name__=="__main__":
test_run()
#18. Bboolean or _mask_index arrays
mean=a.mean()
#masking
a[a
print(a)
#18. arithmetic operation:all element wise(+,-,*,/)
