def test_hasher():
ht = HashTable()
a = ht.hash("alice")
b = ht.hash("elica")
c = ht.hash("Alice")
assert a == b
assert a != c
def main():
testHashToIndex()
print("Starting with empty hash table")
hash = HashTable()
hash.put("A key", "a value")
assert hash.get("A key") == "a value"
assert hash.get("A key") != "another value"
def loadHash(lista):
if not lista is None:
MyHash = HashTable()
for item in lista:
MyHash.insert(item, item)
return MyHash
return None
def insertarTablaHash(arregloLleno: List, tablaHash : HashTable):
'''
Para insertar en la tabla hash los usuarios registrados
:param arregloLleno: arreglo de 2-tuplas compuesto por el nombre de usuario y el
arreglo de volumen
:param tablaHash: tabla hash donde se guardarn todos los nombres de los usuarios y el
arreglo de volumen
'''
for i in arregloLleno:
tablaHash.set(i[0],i[1])
def console():
hash_table = HashTable()
while True:
op = input(prompts['operations'])
if op == '1':
word = input(prompts['word'])
hash_table.add(word)
print(hash_table)
elif op == '4':
return
def _getLocations( self ):
table = HashTable(10)
# Add locations to hash table
with open( 'data/locations.csv' ) as file:
locationData = csv.reader( file, delimiter=',' )
# Iterate through locations
# Time Complexity: O(n)
for row in locationData:
location = Location( row[0], row[1], row[2] )
# Add location to hash table of locations
table.put( int( location.id ), location )
return table
def generation_mode(file_in, num, seed, file_del=None):
words = synthetic.words(file_in, num, seed)
size = input("How many lists should be in the hashmap?: ")
try:
size = int(size)
except ValueError as e:
print("ERROR: Invalid value was passed to the program.\n", e)
return -1
hash_table = HashTable(size)
begin = time.perf_counter()
hash_table.add_all(words)
end = time.perf_counter()
print("Adding time [s]: {:.6f}".format(end - begin))
begin = time.perf_counter()
for word in words:
hash_table.find(word)
end = time.perf_counter()
print("Enumerating time [s]: {:.6f}".format(end - begin))
if file_del is not None:
words = synthetic.read_file(file_del)
begin = time.perf_counter()
for word in words:
hash_table.delete_all(word)
end = time.perf_counter()
print("Deleting time [s]: {:.6f}".format(end - begin))
class Node(object):
def __init__(self, location):
self.edges = HashTable(10)
self.location = location
#Time Complexity: O(n) where n is the number of edges
def addEdge(self, edge):
self.edges.put(int(edge.id), edge)
#Time Complexity: O(n) where n is the number of edges
def findEdge(self, id):
return self.edges.get(id)
#Time Complexity: O(n) where n is the number of edges
def getDistance(self, location):
return self.edges.get(location.id).weight
def test_hash_table_constructor_creates_empty_hash_table():
"""Test that HashTable constructor creates an empty hash table."""
from hash import additive_hash, HashTable
t = HashTable(10, additive_hash)
assert len(t.buckets) == 10
assert t.hash_func is additive_hash
assert not all(t.buckets)
def __init__(self): #connect to permanent storage self.create_flag = False self.delimiter = '|' self.storage = "permanent_data.txt" self.database = HashTable(5479) #call function to read existing data into hash table self._import_data()
def _getPackages( self ):
packages = HashTable(10)
with open('data/packageFile.csv') as file:
packageData = csv.reader( file, delimiter = ',' )
for row in packageData:
package = Package(
row[0],
row[1],
row[2],
row[3],
row[4],
row[5],
row[6],
row[7]
)
package.setLocation( self.getLocationByAddress( row[1] ) )
packages.put( package.id, package )
return packages
def gen_step_mode(file_in, num, seed, file_del=None):
size = input("How many lists should be in the hashmap?: ")
step_val = input(
"Specify the step value (number of words generated additionally): ")
try:
size = int(size)
step_val = int(step_val)
except ValueError as e:
print("ERROR: Invalid value was passed to the program.\n", e)
return -1
words_num = 0
results = []
while True:
words_num += step_val
if words_num > num:
break
print(words_num, " words")
results.append(words_num)
words = synthetic.words(file_in, words_num, seed)
hash_table = HashTable(size)
begin = time.perf_counter()
hash_table.add_all(words)
end = time.perf_counter()
print("Adding time [s]: {:.6f}".format(end - begin))
results.append(end - begin)
begin = time.perf_counter()
for word in words:
hash_table.find(word)
end = time.perf_counter()
print("Enumerating time [s]: {:.6f}".format(end - begin))
results.append(end - begin)
if file_del is not None:
words = synthetic.read_file(file_del)
begin = time.perf_counter()
for word in words:
hash_table.delete_first(word)
end = time.perf_counter()
print("Deleting time [s]: {:.6f}".format(end - begin))
results.append(end - begin)
analyse_data(results, num, size)
class Graph(object):
def __init__(self):
self.nodes = HashTable(10)
# Add a vertex to the graph
# Time Complexity: O(n)
def addNode(self, location):
self.nodes.put(int(location.id), Node(location))
# Add edge between two nodes bidirectionally
# Time Complexity: O(n)
def addWeightedEdge(self, origin, terminus, weight):
originEdge = Edge(origin, weight)
terminusEdge = Edge(terminus, weight)
self.nodes.get(origin.id).addEdge(terminusEdge)
self.nodes.get(terminus.id).addEdge(originEdge)
# Get id of a vertex at a location
# Time Complexity: O(n)
def getNode(self, location):
return self.nodes.get(location.id)
# Get first node returned by location name: O(n)
def getNodeByAddress(self, address):
for node in self.nodes.getAll():
if (node.location.address == address):
return node
# Get distance between two lcoations
def getDistanceBetween(self, origin, terminus):
return self.nodes.get(origin.id).getDistance(terminus)
# Get nearest neighbor of a location
# Returns the closest location to the origin
# Time Complexity: O(n * m)
def getNearestNeighbor(self, origin, group):
resultEdges = []
originNode = self.getNodeByAddress(origin.address)
originEdges = originNode.edges.getAll()
for location in group:
for edge in originEdges:
if location == edge.location:
resultEdges.append(edge)
nearestNeighbor = min(resultEdges, key=lambda x: x.weight)
return nearestNeighbor.location
class test_hash(unittest.TestCase):
def setUp(self):
self.hash = HashTable(11)
def test_put(self):
self.hash.put("Lindsey Raymond", "9786217554")
self.assertEqual(self.hash.keys[3], "Lindsey Raymond")
self.assertEqual(self.hash.data[3], "9786217554")
def test_get(self):
self.assertEqual(self.hash.get("Lindsey Raymond"), "9786217554")
def test_size(self):
self.assertEqual(self.hash.length, 11)
def test_get(self):
self.hash["James Hayward"] = "123456789"
self.hash.put("Lindsey Raymond", "9786217554")
self.assertEqual(self.hash["Lindsey Raymond"], self.hash.get("Lindsey Raymond"))
self.assertEqual(self.hash["James Hayward"], "123456789")
def words_ready_mode(file_in, file_del=None):
words = synthetic.read_file(file_in)
print(words)
size = input("How many lists should be in the hashmap?: ")
try:
size = int(size)
except ValueError as e:
print("ERROR: Invalid value was passed to the program.\n", e)
return -1
hash_table = HashTable(size)
hash_table.add_all(words)
for arr in hash_table.array:
print(arr)
if file_del is not None:
words = synthetic.read_file(file_del)
for word in words:
hash_table.delete_all(word)
for arr in hash_table.array:
print(arr)
class Phonebook:
def __init__(self):
#connect to permanent storage
self.create_flag = False
self.delimiter = '|'
self.storage = "permanent_data.txt"
self.database = HashTable(5479)
#call function to read existing data into hash table
self._import_data()
def _read_lines(self):
with open(self.storage, 'r') as old_data:
for row in old_data:
if not row.startswith("#"):
yield row
def _import_data(self):
for row in self._read_lines():
if row.startswith("~"):
self.create()
else:
name = row.split(self.delimiter)[0]
number = row.split(self.delimiter)[-1]
self.database[name] = number
def add(self, name, number):
#print(self.database.hashkeys)
if name not in set(self.database.hashkeys):
self.database[name] = number
else:
raise KeyError("Value already exists")
def remove(self, name):
self.database.put(name, None)
self.database.hashkeys[self.database.hashkeys.index(name)] = None
def change(self, name, number):
if name in set(self.database.hashkeys):
self.database[name] = number
else:
raise KeyError("Value does not exist")
def lookup(self, name):
try:
return self.database[name]
except:
raise KeyError("Value does not exist")
def reverse_lookup(self, number):
#Note that this will be slow
try:
location = self.database.data.index(number)
return self.database.hashkeys[location]
except:
raise LookupError("Value does not exist")
def create(self):
self.create_flag = True
def save(self):
with open(self.storage, 'w') as txt_file:
txt_file.write("#permanent storage file\n")
if self.create_flag:
txt_file.write("~CREATED\n")
for name in self.database.keys:
if name != None:
txt_file.write(name+"|"+self.database[name]+"\n")
def check_input_errors(self, args):
if len(args) == 1:
raise RuntimeError("Need more input")
def parse_arguments(self, args):
self.check_input_errors(args)
if self.create_flag:
if args[1] == "add":
self.add(*args[2:4])
else:
result = getattr(self, args[1])(args[2])
else:
if args[1] == 'create':
self.create()
else:
raise RuntimeError("Phonebook does not exist")
self.save()
return result
def setUp(self): self.hash = HashTable(11)
def dict_hash():
dict_hash = HashTable(1024)
dictionary = open("/usr/share/dict/words", 'r')
for word in dictionary:
dict_hash.set(word.rstrip(), 1)
return dict_hash
def test_hash_fill_table(read_test_lexicon):
ht = HashTable()
for i in read_test_lexicon:
ht.set(i)
for i in read_test_lexicon:
assert ht.get(i) == i
class TestHashTable(unittest.TestCase):
def setUp(self):
self.ht = HashTable()
def test_hash(self):
self.assertEqual(self.ht.hash("Maximus"), self.ht.hash("Maximus"))
self.assertTrue(self.ht.hash("Maximus") < self.ht.capacity)
def test_insert(self):
self.ht.insert("key", "value")
self.assertEqual(self.ht.size, 1)
self.assertEqual(self.ht.buckets[self.ht.hash("key")].value, "value")
def test_find(self):
obj = "Maximus"
self.ht.insert("Intel", obj)
self.assertEqual(obj, self.ht.find("Intel"))
obj = ["Hello", "world"]
self.ht.insert("hobby", obj)
self.assertEqual(obj, self.ht.find("hobby"))
def test_remove(self):
obj = "19"
self.ht.insert("age", obj)
self.assertEqual(1, self.ht.size)
self.assertEqual(obj, self.ht.remove("age"))
self.assertEqual(0, self.ht.size)
def test_get_returns_value_of_key_provided():
"""Test that get function returns the value of key provided."""
from hash import HashTable, additive_hash
t = HashTable(10, additive_hash)
t.set('word', 444)
assert t.get('word')
def test_get_raises_error_if_key_not_not_in_table():
"""Test that keyerror raised if key not in table."""
from hash import HashTable, additive_hash
t = HashTable(10, additive_hash)
with pytest.raises(KeyError):
t.get('key')
def test_set_raises_error_if_key_not_string():
"""Test that type error raised if key not string in set."""
from hash import HashTable, additive_hash
t = HashTable(10, additive_hash)
with pytest.raises(TypeError):
t.set(12, 44)
def test_set_places_key_value_pairs_in_hash_table():
"""Test that set function places key value pairs in hash table correctly."""
from hash import HashTable, additive_hash
t = HashTable(10, additive_hash)
t.set('word', 444)
assert t.buckets[4][0] == ['word', 444]
def test_hash_initialized_with_oat():
"""Test if hash table can be initialized using oat hashing function."""
from hash import HashTable
cust_hash = HashTable(hash_type='oat')
cust_hash.hash_type == 'oat'
def table1key():
"""Table with just 1 key/pair."""
t = HashTable()
t.set_key('apple', 'chapel')
return t
def table6_add():
"""Initialize table with 6 buckets."""
t = HashTable()
return t
class TestHashTable(unittest.TestCase):
def setUp(self):
self.ht = HashTable()
def test_hash(self):
self.assertEqual(self.ht.hash("hello"), self.ht.hash("hello"))
self.assertTrue(self.ht.hash("hello") < self.ht.capacity)
def test_insert(self):
self.assertEqual(self.ht.size, 0)
self.ht.insert("test_key", "test_value")
self.assertEqual(self.ht.size, 1)
self.assertEqual(
self.ht.buckets[self.ht.hash("test_key")].value, "test_value")
def test_find(self):
self.assertEqual(self.ht.size, 0)
obj = "hello"
self.ht.insert("key1", obj)
self.assertEqual(obj, self.ht.find("key1"))
obj = ["this", "is", "a", "list"]
self.ht.insert("key2", obj)
self.assertEqual(obj, self.ht.find("key2"))
def test_remove(self):
self.assertEqual(self.ht.size, 0)
obj = "test object"
self.ht.insert("key1", obj)
self.assertEqual(1, self.ht.size)
self.assertEqual(obj, self.ht.remove("key1"))
self.assertEqual(0, self.ht.size)
self.assertEqual(None, self.ht.remove("some random key"))
def test_capacity(self):
# Test all public methods in one run at a large capacity
for i in range(0, 1000):
self.assertEqual(i, self.ht.size)
self.ht.insert("key" + str(i), "value")
self.assertEqual(self.ht.size, 1000)
for i in range(0, 1000):
self.assertEqual(1000-i, self.ht.size)
self.assertEqual(self.ht.find("key" + str(i)),
self.ht.remove("key" + str(i)))
def test_issue2(self):
self.assertEqual(self.ht.size, 0)
self.ht.insert('A', 5)
self.assertEqual(self.ht.size, 1)
self.ht.insert('B', 10)
self.assertEqual(self.ht.size, 2)
self.ht.insert('Ball', 'hello')
self.assertEqual(self.ht.size, 3)
self.assertEqual(5, self.ht.remove('A'))
self.assertEqual(self.ht.size, 2)
self.assertEqual(None, self.ht.remove('A'))
self.assertEqual(self.ht.size, 2)
self.assertEqual(None, self.ht.remove('A'))
self.assertEqual(self.ht.size, 2)
def test_get_non_string_key_raises_error():
"""Test taht get with a non string key raises error."""
from hash import HashTable, additive_hash
t = HashTable(10, additive_hash)
with pytest.raises(TypeError):
t.get(22)
def setUp(self):
self.ht = HashTable()
def test_bad_hash_type_raises_error():
"""Test if ValueError raised if function other than additive or oat is passed."""
from hash import HashTable
with pytest.raises(NameError):
HashTable(hash_type='something')
def table6_elf():
"""Initialize table with 6 buckets."""
t = HashTable(hash_type='elf')
return t
def test_hash_table_uses_additive_hash_function():
"""Test that hash table hashes keys with function provided."""
from hash import additive_hash, HashTable
t = HashTable(10, additive_hash)
assert t._hash('one') == additive_hash('one')
def adt6_no_dups():
"""Full hash table with only one item in each bucket."""
t = HashTable()
t.set_key('aaaaaa', 'bettie')
t.set_key('a', 'bettie')
t.set_key('apple', 'bob')
t.set_key('potato', 'fred')
t.set_key('spinach', 'james')
t.set_key('sweet potato', 'jenny')
return t
def test_hash_table_uses_horner_hash_function():
"""Test that hash table hashes keys with function provided."""
from hash import horner_hash, HashTable
t = HashTable(10, horner_hash)
assert t._hash('two') == horner_hash('two')
