def test2():
B = BST()
B.insert(4)
B.insert(3)
B.insert(6)
B.insert(5)
B.insert(7)
B.insert(8)
B.insert(1)
print B
def test_2(self):
A = BST()
A.insert(4)
A.insert(3)
A.insert(6)
A.insert(5)
A.insert(7)
A.insert(8)
A.insert(1)
def __init__(self, data_set):
"""Set the k attribute and fill the tree with the points in 'data_set'.
Raises:
TypeError: if 'data_set' is not a numpy array (of type np.ndarray)
"""
# Validate the input type.
if not isinstance(data_set, np.ndarray):
raise TypeError("data_set must be a numpy array.")
# Set the root and dimension attributes.
BST.__init__(self)
self.k = data_set.shape[1]
# Load the data into the tree one point at a time.
for point in data_set:
self.insert(point)
def test3():
B = BST()
B.insert(4)
B.insert(3)
B.insert(6)
B.insert(5)
B.insert(7)
B.insert(8)
B.insert(1)
print B
B.remove(6)
print B
C = BST()
C.insert(5)
C.insert(2)
C.insert(9)
C.insert(1)
C.insert(4)
C.insert(3)
print C
C.remove(2)
print C
D = BST()
D.insert(1)
D.insert(2)
D.insert(3)
D.insert(4)
D.insert(5)
D.insert(6)
print D
D.remove(1)
print D
def plot_times(filename="English.txt", start=500, stop=5500, step=500):
"""Vary n from 'start' to 'stop', incrementing by 'step'. At each
iteration, use the create_word_list() from the 'WordList' module to
generate a list of n randomized words from the specified file.
Time (separately) how long it takes to load a LinkedList, a BST, and
an AVL with the data set.
Choose 5 random words from the data set. Time how long it takes to
find each word in each object. Calculate the average search time for
each object.
Create one plot with two subplots. In the first subplot, plot the
number of words in each dataset against the build time for each object.
In the second subplot, plot the number of words against the search time
for each object.
Inputs:
filename (str): the file to use in creating the data sets.
start (int): the lower bound on the sample interval.
stop (int): the upper bound on the sample interval.
step (int): the space between points in the sample interval.
Returns:
Show the plot, but do not return any values.
"""
interval = (stop-start)/step
n_list = np.linspace(start,stop,interval+1)
n_list = np.int16(n_list)
word_list = create_word_list(filename)
load_list = []
load_BST = []
load_AVL = []
find_list = []
find_BST = []
find_AVL = []
for n in n_list:
temp_word_list = word_list[:n]
random_word_indices = np.random.randint(0,n,size=5)
words_to_find = []
for x in random_word_indices:
words_to_find.append(temp_word_list[x])
L = LinkedList()
B = BST()
A = AVL()
start = time()
for word in temp_word_list:
L.add(word)
end = time()
load_list.append(end-start)
start = time()
for word in temp_word_list:
B.insert(word)
end = time()
load_BST.append(end-start)
start = time()
for word in temp_word_list:
A.insert(word)
end = time()
load_AVL.append(end-start)
start = time()
for word in words_to_find:
iterative_search(L, word)
end = time()
find_list.append(end-start)
start = time()
for word in words_to_find:
B.find(word)
end = time()
find_BST.append(end-start)
start = time()
for word in words_to_find:
A.find(word)
end = time()
find_AVL.append(end-start)
avg_find_list = sum(find_list[:])/5.
avg_find_BST = sum(find_BST[:])/5.
avg_find_AVL = sum(find_AVL[:])/5.
plt.subplot(121)
list_plot1 = plt.plot(n_list, load_list,label='Singly-Linked List')
BST_plot1 = plt.plot(n_list, load_BST, label='Binary Search Tree')
AVL_plot1 = plt.plot(n_list, load_AVL, label='AVL Tree')
plt.legend()
plt.xlabel('Data Points')
plt.ylabel('Seconds')
plt.title('Build Times')
plt.subplot(122)
list_plot2 = plt.plot(n_list, find_list,label='Singly-Linked List')
BST_plot2 = plt.plot(n_list, find_BST, label='Binary Search Tree')
AVL_plot2 = plt.plot(n_list, find_AVL, label='AVL Tree')
plt.legend()
plt.xlabel('Data Points')
plt.ylabel('Seconds')
plt.title('Search Times')
plt.show()
def plot_times(filename="English.txt", start=500, stop=5500, step=500):
"""Vary n from 'start' to 'stop', incrementing by 'step'. At each
iteration, use the create_word_list() from the 'WordList' module to
generate a list of n randomized words from the specified file.
Time (separately) how long it takes to load a LinkedList, a BST, and
an AVL with the data set.
Choose 5 random words from the data set. Time how long it takes to
find each word in each object. Calculate the average search time for
each object.
Create one plot with two subplots. In the first subplot, plot the
number of words in each dataset against the build time for each object.
In the second subplot, plot the number of words against the search time
for each object.
Inputs:
filename (str): the file to use in creating the data sets.
start (int): the lower bound on the sample interval.
stop (int): the upper bound on the sample interval.
step (int): the space between points in the sample interval.
Returns:
Show the plot, but do not return any values.
"""
def wrapper(func, *args, **kwargs):
def wrapped():
return func(*args, **kwargs)
return wrapped
def add_all(A, my_list):
for x in my_list:
A.add(x)
def add_all_tree(A, my_list):
for x in my_list:
A.insert(x)
def find_it(A, to_find):
A.find(to_find)
def find_average(A, my_list):
find_times = []
for x in range(5):
to_find = random.choice(my_list)
# to_find = my_list[x]
wrapped = wrapper(find_it, A, to_find)
find_times.append(timeit.timeit(wrapped, number=1))
return np.mean(find_times)
word_list = WordList.create_word_list()
word_list = np.random.permutation(word_list)
x_values = range(start, stop, step)
list_times = []
bst_times = []
avl_times = []
find_list= []
find_bst= []
find_avl= []
A = LinkedList()
B = BST()
C = AVL()
for x in x_values:
wrapped = wrapper(add_all, A, word_list[:int(x)])
list_times.append(timeit.timeit(wrapped, number=1))
find_list.append(find_average(A, word_list[:int(x)]))
A.clear()
for x in x_values:
wrapped = wrapper(add_all_tree, B, word_list[:int(x)])
bst_times.append(timeit.timeit(wrapped, number=1))
find_bst.append(find_average(B, word_list[:int(x)]))
B.clear()
for x in x_values:
wrapped = wrapper(add_all_tree, C, word_list[:int(x)])
avl_times.append(timeit.timeit(wrapped, number=1))
find_avl.append(find_average(C, word_list[:int(x)]))
C.clear()
plt.subplot(121)
plt.plot(x_values, list_times, label='Linked List')
plt.plot(x_values, bst_times, label='BST')
plt.plot(x_values, avl_times, label='AVL')
plt.legend(loc='upper left')
plt.xlabel('data points')
plt.ylabel('seconds')
plt.subplot(122)
plt.plot(x_values, find_list,label='Linked List')
plt.plot(x_values, find_bst, label='BST')
plt.plot(x_values, find_avl, label='AVL')
plt.legend(loc='upper left')
plt.xlabel('data points')
plt.ylabel('seconds')
plt.show()
plt.xlabel('data points')
plt.ylabel('seconds')
plt.subplot(122)
plt.plot(x_values, find_list,label='Linked List')
plt.plot(x_values, find_bst, label='BST')
plt.plot(x_values, find_avl, label='AVL')
plt.legend(loc='upper left')
plt.xlabel('data points')
plt.ylabel('seconds')
plt.show()
plt.xlabel('data points')
if __name__ == "__main__":
A = BST()
A.insert(2)
A.insert(1)
A.insert(7)
A.insert(6)
A.insert(5)
A.insert(4)
A.insert(3)
print A
A.remove(2)
print A
A.remove(3)
print A
# =============================== END OF FILE =============================== #
def plot_times(filename="English.txt", start=500, stop=5500, step=500):
"""Vary n from 'start' to 'stop', incrementing by 'step'. At each
iteration, use the create_word_list() from the 'WordList' module to
generate a list of n randomized words from the specified file.
Time (separately) how long it takes to load a LinkedList, a BST, and
an AVL with the data set.
Choose 5 random words from the data set. Time how long it takes to
find each word in each object. Calculate the average search time for
each object.
Create one plot with two subplots. In the first subplot, plot the
number of words in each dataset against the build time for each object.
In the second subplot, plot the number of words against the search time
for each object.
Inputs:
filename (str): the file to use in creating the data sets.
start (int): the lower bound on the sample interval.
stop (int): the upper bound on the sample interval.
step (int): the space between points in the sample interval.
Returns:
Show the plot, but do not return any values.
"""
def get_average_time_linked_list(to_search, linked_list, times_left, current_time = 0):
while times_left > 0:
start = time.time()
iterative_search(linked_list, to_search[times_left-1])
end =time.time()
current_time +=(end-start)
times_left -=1
return current_time/len(to_search)
def get_average_time_BST(to_search, BST_list, times_left, current_time =0):
while times_left >0:
start = time.time()
BST_list.find(to_search[times_left-1])
end = time.time()
current_time +=(end-start)
times_left -= 1
return current_time/len(to_search)
def get_average_time_AVL(to_search, AVL_list, times_left, current_time = 0):
while times_left > 0:
start = time.time()
AVL_list.find(to_search[times_left-1])
end = time.time()
current_time +=(end-start)
times_left -= 1
return current_time/len(to_search)
word_list = create_word_list(filename)
if (stop-start)%step!=0:
raise ValueError("Your steps won't get you from start to stop")
current = start
time_linked_list = []
time_BST_list = []
time_AVL_list = []
time_linked_list_search = []
time_BST_list_search = []
time_AVL_list_search = []
set_size = []
while current < stop:
current_linked_list = LinkedList()
current_BST = BST()
current_AVL = AVL()
current_list = word_list[:current]
to_search = np.random.permutation(current_list)
start_linked_time = time.time()
for x in current_list:
current_linked_list.add(x)
end_linked_time = time.time()
start_BST_time = time.time()
for y in current_list:
current_BST.insert(y)
end_BST_time = time.time()
start_AVL_time = time.time()
for z in current_list:
current_AVL.insert(z)
end_AVL_time = time.time()
time_linked_list.append(end_linked_time - start_linked_time)
time_BST_list.append(end_BST_time - start_BST_time)
time_AVL_list.append(end_AVL_time- start_AVL_time)
time_linked_list_search.append(get_average_time_linked_list(to_search,current_linked_list, len(to_search)))
time_BST_list_search.append(get_average_time_BST(to_search,current_BST, len(to_search)))
time_AVL_list_search.append(get_average_time_AVL(to_search,current_AVL, len(to_search)))
set_size.append(current)
current+=step
plt.subplot(2,1,1)
plt.title('Building Data Structures')
plt.plot(set_size,time_linked_list, label = 'Linked List', linewidth = 3)
plt.plot(set_size, time_BST_list, label = "BST", linewidth = 3)
plt.plot(set_size, time_AVL_list, label = "AVL", linewidth = 3)
plt.legend(loc = 2)
plt.subplot(2,1,2)
plt.title("Searching Data Structures")
plt.plot(set_size, time_linked_list_search, label = 'Linked list', linewidth = 3)
plt.plot(set_size, time_BST_list_search, label = 'BST', linewidth = 3)
plt.plot(set_size, time_AVL_list_search, label = 'AVL', linewidth = 3)
plt.legend(loc = 2)
plt.show()
def timings():
ll = LinkedList()
bst = BST()
avl = AVL()
ll_add = []
bst_add = []
avl_add = []
ll_search = []
bst_search = []
avl_search = []
for items in range(500,5500,500):
wordlist = create_word_list(items)
ll = LinkedList()
before = time.time()
for i in xrange(items):
ll.add_node(wordlist[i])
after = time.time()
ll_add.append(after - before)
random_indices = np.random.random_integers(0,items,5)
temp = []
for i in xrange(len(random_indices)):
before = time.time()
iterative_search(ll, wordlist[random_indices[i]])
after = time.time()
temp.append(after - before)
ll_search.append(sum(temp)/len(temp))
bst = BST()
before = time.time()
for i in xrange(items):
bst.insert(wordlist[i])
after = time.time()
bst_add.append(after - before)
temp = []
for i in xrange(len(random_indices)):
before = time.time()
bst.find(wordlist[random_indices[i]])
after = time.time()
temp.append(after - before)
bst_search.append(sum(temp)/len(temp))
avl = AVL()
before = time.time()
for i in xrange(items):
avl.insert(wordlist[i])
after = time.time()
avl_add.append(after - before)
temp = []
for i in xrange(len(random_indices)):
before = time.time()
avl.find(wordlist[random_indices[i]])
after = time.time()
temp.append(after - before)
avl_search.append(sum(temp)/len(temp))
plt.subplot(1,2,1)
plt.plot(ll_add, "r")
plt.plot(bst_add, "g")
plt.plot(avl_add, "b")
plt.subplot(1,2,2)
plt.plot(ll_search, "r")
plt.plot(bst_search, "g")
plt.plot(avl_search, "b")
plt.show()
plt.close()
return ll_add, ll_search, bst_add, bst_search, avl_add, avl_search
def test_3(self):
A = BST()
A.insert(3)
A.insert(2)
A.insert(1)
A.insert(8)
A.insert(9)
A.insert(5)
A.insert(6)
print A
A.remove(8)
print A
and find the sum pair.
'''
# Import BST defined in Trees.py
from Trees import BST
def findPairSum(target):
inorder = tree.inOrderTraversal()
i, j = 0, len(inorder) - 1
while i < j:
left, right = inorder[i].data, inorder[j].data
if left + right == target:
print(left, right)
return
if left + right > target:
j -= 1
else:
i += 1
print("No such pair found")
inp = [12, 3, 31, -1, 11, -1, 41, -1, -1, -1, -1]
target = 15
# Creating a new BST
tree = BST()
tree.constructBST(inp)
findPairSum(target)
def plot_times(filename="English.txt", start=500, stop=5500, step=500):
"""Vary n from 'start' to 'stop', incrementing by 'step'. At each
iteration, use the create_word_list() from the 'WordList' module to
generate a list of n randomized words from the specified file.
Time (separately) how long it takes to load a LinkedList, a BST, and
an AVL with the data set.
Choose 5 random words from the data set. Time how long it takes to
find each word in each object. Calculate the average search time for
each object.
Create one plot with two subplots. In the first subplot, plot the
number of words in each dataset against the build time for each object.
In the second subplot, plot the number of words against the search time
for each object.
Inputs:
filename (str): the file to use in creating the data sets.
start (int): the lower bound on the sample interval.
stop (int): the upper bound on the sample interval.
step (int): the space between points in the sample interval.
Returns:
Show the plot, but do not return any values.
"""
ll = LinkedList()
bst = BST()
avl = AVL()
ll_add = []
bst_add = []
avl_add = []
ll_search = []
bst_search = []
avl_search = []
for items in range(start,stop,step):
wordlist = create_word_list()[:items]
ll = LinkedList()
before = time.time()
for i in xrange(items):
ll.add(wordlist[i])
after = time.time()
ll_add.append(after - before)
random_indices = np.random.random_integers(0,items,5)
temp = []
for i in xrange(len(random_indices)):
before = time.time()
iterative_search(ll, wordlist[random_indices[i]])
after = time.time()
temp.append(after - before)
ll_search.append(sum(temp)/len(temp))
bst = BST()
before = time.time()
for i in xrange(items):
bst.insert(wordlist[i])
after = time.time()
bst_add.append(after - before)
temp = []
for i in xrange(len(random_indices)):
before = time.time()
bst.find(wordlist[random_indices[i]])
after = time.time()
temp.append(after - before)
bst_search.append(sum(temp)/len(temp))
avl = AVL()
before = time.time()
for i in xrange(items):
avl.insert(wordlist[i])
after = time.time()
avl_add.append(after - before)
temp = []
for i in xrange(len(random_indices)):
before = time.time()
avl.find(wordlist[random_indices[i]])
after = time.time()
temp.append(after - before)
avl_search.append(sum(temp)/len(temp))
plt.subplot(1,2,1)
plt.title("Build Times")
plt.plot(ll_add, "b", label="Single-Linked List")
plt.plot(bst_add, "g", label="Binary Search Tree")
plt.plot(avl_add, "r", label ="AVL Tree")
plt.legend(loc="upper left")
plt.subplot(1,2,2)
plt.title("Search Times")
plt.plot(ll_search, "b", label="Single-Linked List")
plt.plot(bst_search, "g", label="Binary Search Tree")
plt.plot(avl_search, "r", label="AVL Tree")
plt.legend(loc="upper left")
plt.show()
plt.close()
return ll_add, ll_search, bst_add, bst_search, avl_add, avl_search