def test_all():
hash_map = HashMap()
el_count = EL_COUNT
for x in range(el_count):
hash_map.put(str(x), str(x))
for x in range(el_count):
assert hash_map.get(str(x)) == str(x)
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500,hash_function_2)
# This block of code will read a file one word as a time and
# put the word in `w`. It should be left as starter code.
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
if ht.contains_key(w.lower()):
ht.put(w.lower(), ht.get(w.lower()) + 1)
else:
ht.put(w.lower(), 1)
tup = ht.sorted_tup()
return tup[:number]
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set() # Variable representing empty set.
ht = HashMap(
2500, hash_function_2
) # Variable to represent hash map construct utilizing above function.
# This block of code will read a file one word as a time and
# put the word in `w`. It should be left as starter code.
with open(source
) as f: # Opens file to be used declaring it as variable 'f'.
for line in f: # Loops through each line within file (f).
words = rgx.findall(
line) # Variable utilized to represent words within each line.
for w in words: # Loops through each word within each line.
lw = w.lower(
) # Turns words lowercase to remove case sensitivity.
keys.add(
lw
) # Adds lowercase word to set represented by variable 'key'.
if ht.contains_key(
lw): # Checks if word is already present in hash map.
new_value = (
ht.get(lw) + 1
) # Variable represents word count increased by one.
ht.put(
lw, new_value
) # Inserts word into hash map to have word count be updated.
else:
ht.put(
lw, 1
) # Inserts word into hash map with initial count of one.
keys_list = [] # Variable represents an empty list.
for values in keys: # Loops through words present in set represented by variable 'keys'.
ind = ht._hash_function(values) % ht.capacity
# Variable to represent number established by chosen function and available capacity.
temp = ht._buckets[
ind] # Variable to represent position within hash map containing linked list.
node = temp.contains(
values
) # Variable to represent node containing key if already present.
keys_list.append(
(node.key,
node.value)) # Adds tuple to list containing word, word count.
keys_list.sort(
key=lambda tup: tup[1],
reverse=True) # Sorts list in descending order based on word count.
return keys_list[
0:
number] # Returns list of top words within given range provided by user.
def test_get(self):
"""Tests the HashMap get method"""
test_values = [("test_5", 5), ("test_-5", -5), ("test_5_", 5),
("diff_word", 15), ("another_word", 20), ("set", 10),
("anotha_one", -7), ("completely_different", 5),
("getting_there", -1)]
collision_values = [("completely_different", 5), ("anotha_one", -7),
("set", 10), ("another_word", 20)]
head_node = collision_values[0]
tail_node = collision_values[3]
student_map = HashMap(10, hash_function_1)
# add all key value pairs to the table
for key, val in test_values:
student_map.put(key, val)
# test get at linked_list head
self.assertEqual(student_map.get(head_node[0]), head_node[1])
# test get at linked_list tail
self.assertEqual(student_map.get(tail_node[0]), tail_node[1])
# test get at > 2 collision bucket
for node in collision_values:
self.assertEqual(student_map.get(node[0]), node[1])
# test get with no collision
self.assertEqual(student_map.get("getting_there"), -1)
# test that all values are in the list
for node in test_values:
self.assertEqual(student_map.get(node[0]), node[1])
def test_resize_table(self):
"""Tests the resize_table method: checks that links are not changed and properties are updated"""
test_values = [("test_5", 5), ("test_-5", -5), ("test_5_", 5),
("diff_word", 15), ("another_word", 20), ("set", 10),
("anotha_one", -7), ("completely_different", 5),
("getting_there", -1)]
student_map = HashMap(10, hash_function_1)
for key, value in test_values:
student_map.put(key, value)
self.assertEqual(10, student_map.capacity)
# get before resize state
keys_before_resize = get_keys_from_map(student_map)
size_before_resize = student_map.size
# Test 1
# resize the table smaller -> bigger
student_map.resize_table(50)
self.assertEqual(50, student_map.capacity)
# get after resize state
keys_after_resize = get_keys_from_map(student_map)
size_after_resize = student_map.size
# test that no nodes were lost in the resize
self.assertEqual(len(keys_before_resize), len(keys_after_resize))
self.assertEqual(size_before_resize, size_after_resize)
for key in keys_before_resize:
self.assertTrue(key in keys_after_resize)
for key in keys_after_resize:
self.assertTrue(key in keys_before_resize)
# Test 2
student_map = HashMap(10, hash_function_1)
for key, value in test_values:
student_map.put(key, value)
self.assertEqual(10, student_map.capacity)
# get before resize state
keys_before_resize = get_keys_from_map(student_map)
size_before_resize = student_map.size
# resize the table bigger -> smaller
student_map.resize_table(5)
self.assertEqual(5, student_map.capacity)
# get after resize state
keys_after_resize = get_keys_from_map(student_map)
size_after_resize = student_map.size
# test that no nodes were lost in the resize
self.assertEqual(len(keys_before_resize), len(keys_after_resize))
self.assertEqual(size_before_resize, size_after_resize)
for key in keys_before_resize:
self.assertTrue(key in keys_after_resize)
for key in keys_after_resize:
self.assertTrue(key in keys_before_resize)
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500, hash_function_2)
# Reads a file one word as a time and
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
w = w.lower(
) # covert word to lowercase for case-insensitive comparisons
if ht.contains_key(
w
): # if word already exists as key in ht, add 1 to value to track count
value = ht.get(w)
ht.put(w, value + 1)
else:
ht.put(
w, 1
) # if word does not exist in ht as key, add word as key and initialize value as 1
keys.add(w) # add word to set of keys
count_dict = {} # initialize empty dictionary
count_array = [] # initialize empty array
for key in keys: # for each key, get it's value from ht and then add key/value pair to count_dict
value = ht.get(key)
count_dict[key] = value
for key in keys: # for each key, add value/key pair to array for sorting
count_array.append((count_dict[key], key))
count_array = sorted(
count_array, reverse=True
) # reverse sort count_array from largest to smallest value
for i in range(
len(count_array)
): # reswap key/value pairs to get (word, count) for each tuple in count_array
count_array[i] = (count_array[i][1], count_array[i][0])
return count_array[:
number] # return only the requested number of top words
def test_put_4(self):
"""
Test put() with Example #1 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 1 ---")
m = HashMap(50, hash_function_1)
for i in range(150):
m.put('str' + str(i), i * 100)
if i % 25 == 24:
print(m.empty_buckets(), m.table_load(), m.size, m.capacity)
def test_empty_buckets_2(self):
"""
Test empty_buckets() with Example #2 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 2 ---")
m = HashMap(50, hash_function_1)
for i in range(150):
m.put('key' + str(i), i * 100)
if i % 30 == 0:
print(m.empty_buckets(), m.size, m.capacity)
def test_table_load_2(self):
"""
Test table_load() with Example #2 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 2 ---")
m = HashMap(50, hash_function_1)
for i in range(50):
m.put('key' + str(i), i * 100)
if i % 10 == 0:
print(m.table_load(), m.size, m.capacity)
def test_resize_table_1(self):
"""
Test resize_table() with Example #1 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 1 ---")
m = HashMap(20, hash_function_1)
m.put('key1', 10)
print(m.size, m.capacity, m.get('key1'), m.contains_key('key1'))
m.resize_table(30)
print(m.size, m.capacity, m.get('key1'), m.contains_key('key1'))
def test_put_5(self):
"""
Test put() with Example #2 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 2 ---")
m = HashMap(40, hash_function_2)
for i in range(50):
m.put('str' + str(i // 3), i * 100)
if i % 10 == 9:
print(m.empty_buckets(), m.table_load(), m.size, m.capacity)
def test_put_1(self):
"""
Test put() on a hash map of capacity 0.
:passed: yes
"""
hash_m = HashMap(0, hash_function_1)
print("map before put():", hash_m)
hash_m.put("key1", 10)
print("put('key1', 10):", hash_m)
print(hash_m.put("key1", 10))
def test_remove_1(self):
"""
Test remove() with Example #1 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 1 ---")
m = HashMap(50, hash_function_1)
print(m.get('key1'))
m.put('key1', 10)
print(m.get('key1'))
m.remove('key1')
print(m.get('key1'))
m.remove('key4')
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500, hash_function_2)
# This block of code will read a file one word as a time and |
# put the word in `w`. It should be left as starter code. |
with open(source) as f: # |
for line in f: # |
words = rgx.findall(line) # |
for w in words: # |
# lower case all incoming words to make case insensitive
w = w.lower()
# Check if hashtable already contains word
if ht.contains_key(w):
# If so retrieve the count for the given word
count = ht.get(w)
# Update existing key with incremented count value
ht.put(w, count + 1)
else:
# Add new word to keys set collection
keys.add(w)
# put new word in hash table with a count of 1
ht.put(w, 1)
# Check if table load is over load limit before next word
if ht.table_load() > 8:
# if so, resize hash table to twice the capacity
ht.resize_table(2 * ht.capacity)
# initialize tuple word/count list
topWords = []
# for each key in the set of keys
for key in keys:
# append the key and value as a tuple in the topWords list
topWords.append((key, ht.get(key)))
# once all tuples are added to list, sort list by the count of each key in descending order
topWords.sort(key=lambda keyCountTup: keyCountTup[1], reverse=True)
# After sort, set top word list to only contain the given number of tuples requested
topWords = topWords[:number]
# return topWords list of tuples of length equal to number
return topWords
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500, hash_function_2)
# This block of code will read a file one word at a time and
# put the word in `w`. It should be left as starter code.
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
# Convert all words to lowercase prior to insertion
w = w.lower()
# If the word is already in the hash map, pass the value with a new updated count
if ht.contains_key(w):
count = ht.get(w) + 1
ht.put(w, count)
else:
# Otherwise, create a new entry in the hashmap
ht.put(w, 1)
# Add all of the words to the keys set
for bucket in ht.get_buckets():
# Iterate through each bucket/linked list
curr = bucket.head
while curr is not None:
# Add the keys as a tuple
keys.add((curr.key, curr.value))
curr = curr.next
# Cast the set as a list
all_words = list(keys)
# Sort the words according to their value in the tuple
all_words.sort(key=lambda word: word[1])
slice_val = (number * -1 - 1)
top_wds = all_words[:slice_val:-1]
return top_wds
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500, hash_function_2)
# This block of code will read a file one word as a time and
# put the word in `w`. It should be left as starter code.
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
#append the individual words to the list and convert letters
#to lowercase for case sensitivity
lower_case = w.lower()
keys.add(lower_case)
#check if word is alread in hashmap
if ht.contains_key(lower_case):
#increase word count and insert into hasmap and update count
val = (ht.get(lower_case) + 1)
ht.put(lower_case, val)
else:
#insert into hasmap with initial count being one 1 if not in hashmap already
ht.put(lower_case, 1)
#create a new list if words
word_list = []
#loop thru the list
for k in keys:
index = ht._hash_function(k) % ht.capacity
temp = ht._buckets[index]
#add tuples to list containing word and count
linked_node = temp.contains(k)
word_list.append((linked_node.key, linked_node.value))
#sort list in descending order
word_list.sort(key=lambda tup: tup[1], reverse=True)
#return list of top words
return word_list[0:number]
# print(top_words("alice.txt",10)) # COMMENT THIS OUT WHEN SUBMITTING TO GRADESCOPE
def test_table_load(self):
"""Tests HashMap table_load method"""
test_values = [("test_5", 5), ("test_-5", -5), ("test_5_", 5),
("diff_word", 15), ("another_word", 20)]
init_capacity = 10
student_map = HashMap(init_capacity, hash_function_1)
student_map_d = HashMap(init_capacity * 2, hash_function_1)
# 0 / 10 = 0, 0 / 20 = 0
self.assertEqual(student_map.table_load(), student_map_d.table_load())
for key, val in test_values:
student_map.put(key, val)
student_map_d.put(key, val)
# test known load ( 5 / 10 = 0.5 ), ( 5 / 20 = 0.25 )
self.assertEqual((len(test_values) / init_capacity),
student_map.table_load())
self.assertEqual((len(test_values) / (init_capacity * 2)),
student_map_d.table_load())
student_map = HashMap(init_capacity, hash_function_1)
student_map_d = HashMap(init_capacity * 2, hash_function_1)
# test high table load
random_cases = 1000
# add random key, value pairs to the table
for i in range(random_cases):
key, value = create_random_tuple()
student_map.put(key, value)
student_map_d.put(key, value)
self.assertAlmostEqual(student_map.table_load(),
student_map_d.table_load() * 2)
def test_clear_1(self):
"""
Test clear() with Example #1 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 1 ---")
m = HashMap(100, hash_function_1)
print(m.size, m.capacity)
m.put('key1', 10)
m.put('key2', 20)
m.put('key1', 30)
print(m.size, m.capacity)
m.clear()
print(m.size, m.capacity)
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500, hash_function_2)
# This block of code will read a file one word as a time and
# put the word in `w`. It should be left as starter code.
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words: # Iterate through all the words in the line.
# Place lowercased version of words.
if ht.contains_key(
w.lower()): # If the word is in the hashmap.
ht.put(w.lower(),
ht.get(w.lower()) +
1) # Update the word count by 1.
else: # If the word does not exist in the hashmap.
ht.put(w.lower(),
1) # Place the key in the map with the value of 1.
keys.add(w.lower()) # Add the new keys into the keys set.
list_of_occurences = [
] # Create an empty list to hold the tuples of keys and values.
for key in keys: # Iterate through all the keys.
list_of_occurences.append(
(key, ht.get(key))) # Add the key and value tuple into the list.
# Source to help me find a way to implement this:
# stackoverflow.com/questions/10695139/sort-a-list-of-tuples-by-2nd-item-integer-value
# We use lambda here to sort the list of tuples by its second value.
# The sorting is also reversed to make it in descending order.
sorted_list = sorted(list_of_occurences, key=lambda x: x[1], reverse=True)
return sorted_list[:
number] # Using list slice, return the top numbers of the list depending on what the user inputs
# print(top_words("alice.txt",10)) # COMMENT THIS OUT WHEN SUBMITTING TO GRADESCOPE
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500, hash_function_2)
# This block of code will read a file one word as a time and
# put the word in `w`. It should be left as starter code.
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
if (ht.get(w) is None):
ht.put(w, 1)
else:
#Buffer into hash map
ht.put(w, ht.get(w) + 1)
#Handle sorting
tuples = []
for i in range(ht.capacity):
cur = ht._buckets[i]
if cur.head is not None:
cur = cur.head
while (cur != None):
#Buffer key pair into tuples
tuples.append((cur.key, cur.value))
#Go to next
cur = cur.next
tuples = sorted(tuples, key=lambda x: x[1], reverse=True)
newTuples = []
for j in range(number):
newTuples.append(tuples[j])
return newTuples
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500,hash_function_2)
# This block of code will read a file one word as a time and
# put the word in `w`. It should be left as starter code.
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
w = w.lower() # make everything lower case
# if the word is already in keys, get and increase the count.
if w in keys:
count = ht.get(w)
count += 1
ht.put(w, count) # update the count
# otherwise add the new word to the hashmap with count of 1
else:
ht.put(w, 1)
keys.add(w)
count_list = [] # list of tuples of keys and counts
# for each key, get the value, and add these pairs as tuples to count_list
for k in keys:
val = ht.get(k)
pair = (k, val)
count_list.append(pair)
# sort count_list with a lambda function using sorted(). Reverse the list for descending order
count_list = sorted(count_list, key=lambda x: x[1], reverse=True) # where x is a tuple and x[1] is the word count
# return the appropriate number of top words
return count_list[:number]
def test_clear_2(self):
"""
Test clear() with Example #2 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 2 ---")
m = HashMap(50, hash_function_1)
print(m.size, m.capacity)
m.put('key1', 10)
print(m.size, m.capacity)
m.put('key2', 20)
print(m.size, m.capacity)
m.resize_table(100)
print(m.size, m.capacity)
m.clear()
print(m.size, m.capacity)
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500, hash_function_2)
# This block of code will read a file one word as a time and
# put the word in `w`. It should be left as starter code.
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
# Place word in hash map or update value by one
w = w.lower()
if not ht.contains_key(w):
keys.add(w)
ht.put(w, 1)
else:
ht.put(w, ht.get(w) + 1)
# Sort the words by mentions
sorted_words = []
for word in keys:
next_word = (word, ht.get(word))
if sorted_words == []:
sorted_words.append(next_word)
else:
for index, value in enumerate(sorted_words):
if next_word[1] >= value[1]:
sorted_words.insert(index, next_word)
break
return sorted_words[:number]
# print(top_words("alice.txt",10)) # COMMENT THIS OUT WHEN SUBMITTING TO GRADESCOPE
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500, hash_function_2)
# This block of code will read a file one word as a time and
# put the word in `w`. It should be left as starter code.
# build hash table
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
# convert to lowercase so words are counted properly
lowercase_w = w.lower()
keys.add(lowercase_w)
word_count = ht.get(lowercase_w)
# have value of node track number of times word has appeared
if word_count is None:
ht.put(lowercase_w, 1)
else:
ht.put(lowercase_w, word_count + 1)
# for the amount of top words requested, find the word with maximum count
max_list = []
for count in range(number):
max_w = ""
max_value = 0
# iterate over all words to find max key, value
for w in keys:
value = ht.get(w)
if value > max_value:
max_key = w
max_value = value
max_list.append((max_key, max_value))
# remove max word from set for next iteration to get next top word
keys.remove(max_key)
return max_list
def test_contains_key(self):
"""Tests the HashMap contains_key method"""
test_values = [("test_5", 5), ("test_-5", -5), ("test_5_", 5),
("diff_word", 15), ("another_word", 20), ("set", 10),
("anotha_one", -7), ("completely_different", 5),
("getting_there", -1)]
student_map = HashMap(10, hash_function_1)
# simple check to test that all values are in the list
for key, val in test_values:
student_map.put(key, val)
found = False
for bucket in student_map._buckets:
if bucket.contains(key):
found = True
self.assertEqual(found, student_map.contains_key(key))
def test_contains_key_5(self):
"""
Test contains_key with Example #1 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 1 ---")
m = HashMap(50, hash_function_1)
print(m.contains_key('key1'))
m.put('key1', 10)
m.put('key2', 20)
m.put('key3', 30)
print(m.contains_key('key1'))
print(m.contains_key('key4'))
print(m.contains_key('key2'))
print(m.contains_key('key3'))
m.remove('key3')
print(m.contains_key('key3'))
def top_words(source, number):
"""
Takes a plain text file and counts the number of occurrences of case insensitive words.
Returns the top `number` of words in a list of tuples of the form (word, count).
Args:
source: the file name containing the text
number: the number of top results to return (e.g. 5 would return the 5 most common words)
Returns:
A list of tuples of the form (word, count), sorted by most common word. (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500, hash_function_2)
# This block of code will read a file one word as a time and
# put the word in `w`. It should be left as starter code.
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
w = w.lower()
count = ht.get(w)
if count is None:
ht.put(w, 1) # Word is not in the hash map; add it
else:
ht.put(w, count +
1) # Word is in the hash map; increment the count
heap = Heap() # Create a heap to do the sorting
for i in range(ht.capacity):
node = ht._buckets[i].head
while node is not None:
t = (node.key, node.value)
heap.insert(t) # Add each tuple to the heap
node = node.next
heap.sort() # Sort by word count, descending
if number <= len(heap.heap):
return heap.heap[0:number]
else:
return heap.heap # Handles the case where the user requests too many words
def test_contains_key_6(self):
"""
Test contains_key with Example #2 from the guidelines.
:passed: yes
"""
print("--- EXAMPLE 2 ---")
m = HashMap(75, hash_function_2)
keys = [i for i in range(1, 1000, 20)]
for key in keys:
m.put(str(key), key * 42)
print(m.size, m.capacity)
result = True
for key in keys:
# all inserted keys must be present
result = result and m.contains_key(str(key))
# all NOT inserted keys must be absent
result = result and not m.contains_key(str(key + 1))
print(result)
def test_hash_map(self):
test_map = HashMap()
for i in range(0,1000):
if i%2 is 0:
test_map.put((i,), i)
else: # i%2 is 1
test_map.put(str(i), [i])
# initialize the map with 1001 kv pairs
self.assertEquals(test_map.size(), 1000)
for i in range(0,1000):
if i%2 is 0:
self.assertEquals(test_map.get((i,)), i)
else: # i%2 is 1
self.assertEquals(test_map.get(str(i)), [i])
with self.assertRaises(KeyNotFound):
test_map.get("8")
with self.assertRaises(KeyNotFound):
test_map.get((991,))
with self.assertRaises(KeyNotFound):
test_map.get("test_key")
with self.assertRaises(KeyNotFound):
test_map.get((1002,))
# remove 700 elements
for i in range(100,800):
if i%2 is 0:
test_map.remove((i,))
else: # i%2 is 1
test_map.remove(str(i))
self.assertEquals(test_map.size(), 300)
self.assertTrue(test_map.contains((80,)))
self.assertFalse(test_map.contains((120,)))
# insert 9000 more values
for i in range(1000,10000):
if i%2 is 1:
test_map.put((i,), i)
else: # i%2 is 0
test_map.put(str(i), [i])
self.assertEquals(test_map.size(), 9300)
for i in range(1000,10000):
if i%2 is 1:
self.assertEquals(test_map.get((i,)), i)
else: # i%2 is 0
self.assertEquals(test_map.get(str(i)), [i])
def top_words(source, number):
"""
Take a plain text file and count the number of occurrences of case insensitive words.
Return the top `number` of words in a list of tuples of the form (word, count).
:param source: the file name containing the text
:param number: the number of top results to return (e.g. 5 would return the 5 most common words)
:return: a list of tuples of the form (word, count), sorted by most common word (e.g. [("a", 23), ("the", 20), ("it", 10)])
"""
keys = set()
ht = HashMap(2500, hash_function_2)
# Read the file one word at a time and put the word in `w`
with open(source) as f:
for line in f:
words = rgx.findall(line)
for w in words:
# Convert the word to lowercase to enforce case insensitivity
word_lower = w.lower()
# If the word already exists in the table, get and update its
# current count
if ht.contains_key(word_lower):
cur_count = ht.get(word_lower) # Get current count
ht.put(word_lower, cur_count + 1) # Update current count
# If the word does not exist in the table, add it and set its
# count to 1
else:
ht.put(word_lower, 1)
# Get a list of tuples consisting of all the key-value pairs in the table
tuple_list = ht.get_tuples()
# Sort the list of tuples in descending order by word count
tuple_list.sort(key=get_count, reverse=True)
# print("sorted tuple_list:", tuple_list)
# Slice the list of tuples to contain `number` amount of tuples
sliced_list = tuple_list[0:number]
# Return the sliced list of tuples
return sliced_list
def test_hash_map(self):
test_map = HashMap()
for i in range(0, 1000):
if i % 2 is 0:
test_map.put((i, ), i)
else: # i%2 is 1
test_map.put(str(i), [i])
# initialize the map with 1001 kv pairs
self.assertEquals(test_map.size(), 1000)
for i in range(0, 1000):
if i % 2 is 0:
self.assertEquals(test_map.get((i, )), i)
else: # i%2 is 1
self.assertEquals(test_map.get(str(i)), [i])
with self.assertRaises(KeyNotFound):
test_map.get("8")
with self.assertRaises(KeyNotFound):
test_map.get((991, ))
with self.assertRaises(KeyNotFound):
test_map.get("test_key")
with self.assertRaises(KeyNotFound):
test_map.get((1002, ))
# remove 700 elements
for i in range(100, 800):
if i % 2 is 0:
test_map.remove((i, ))
else: # i%2 is 1
test_map.remove(str(i))
self.assertEquals(test_map.size(), 300)
self.assertTrue(test_map.contains((80, )))
self.assertFalse(test_map.contains((120, )))
# insert 9000 more values
for i in range(1000, 10000):
if i % 2 is 1:
test_map.put((i, ), i)
else: # i%2 is 0
test_map.put(str(i), [i])
self.assertEquals(test_map.size(), 9300)
for i in range(1000, 10000):
if i % 2 is 1:
self.assertEquals(test_map.get((i, )), i)
else: # i%2 is 0
self.assertEquals(test_map.get(str(i)), [i])
