def test_Add3(self):
counterHashMap1 = CounterHashMap()
for i in range(1000):
counterHashMap1.put(i)
counterHashMap2 = CounterHashMap()
for i in range(500, 1000):
counterHashMap2.putNTimes(1000 + i, i + 1)
counterHashMap1.add(counterHashMap2)
self.assertEquals(1500, len(counterHashMap1))
def test_Add2(self):
counterHashMap1 = CounterHashMap()
counterHashMap1.put("item1")
counterHashMap1.put("item2")
counterHashMap1.put("item1")
counterHashMap1.put("item2")
counterHashMap1.put("item1")
counterHashMap2 = CounterHashMap()
counterHashMap2.put("item4")
counterHashMap2.putNTimes("item5", 4)
counterHashMap2.put("item2")
counterHashMap1.add(counterHashMap2)
self.assertEquals(3, counterHashMap1.count("item1"))
self.assertEquals(3, counterHashMap1.count("item2"))
self.assertEquals(1, counterHashMap1.count("item4"))
self.assertEquals(4, counterHashMap1.count("item5"))
def countWords(self, wordCounter: CounterHashMap, height: int):
"""
Counts words recursively given height and wordCounter.
PARAMETERS
----------
wordCounter : CounterHashMap
word counter keeping symbols and their counts.
height : int
height for NGram. if height = 1, If height = 1, N-Gram is treated as UniGram, if height = 2, N-Gram is
treated as Bigram, etc.
"""
if height == 0:
wordCounter.putNTimes(self.__symbol, self.__count)
else:
for child in self.__children.values():
child.countWords(wordCounter, height - 1)
def __init__(self, fileName=None):
"""
Constructor of RootWordStatistics class that generates a new map for statistics.
"""
self.__statistics = {}
if fileName is not None:
inputFile = open(fileName, encoding="utf8")
size = int(inputFile.readline().strip())
for i in range(size):
line = inputFile.readline().strip()
items = line.split()
rootWord = items[0]
count = int(items[1])
wordMap = CounterHashMap()
for j in range(count):
line = inputFile.readline().strip()
items = line.split()
wordMap.putNTimes(items[0], int(items[1]))
self.__statistics[rootWord] = wordMap
inputFile.close()
def test_PutNTimes1(self):
counterHashMap = CounterHashMap()
counterHashMap.putNTimes("item1", 2)
counterHashMap.putNTimes("item2", 3)
counterHashMap.putNTimes("item3", 6)
counterHashMap.putNTimes("item1", 2)
counterHashMap.putNTimes("item2", 3)
counterHashMap.putNTimes("item1", 2)
self.assertEquals(6, counterHashMap.count("item1"))
self.assertEquals(6, counterHashMap.count("item2"))
self.assertEquals(6, counterHashMap.count("item3"))
def test_Add1(self):
counterHashMap1 = CounterHashMap()
counterHashMap1.put("item1")
counterHashMap1.put("item2")
counterHashMap1.put("item3")
counterHashMap1.put("item1")
counterHashMap1.put("item2")
counterHashMap1.put("item1")
counterHashMap2 = CounterHashMap()
counterHashMap2.putNTimes("item1", 2)
counterHashMap2.putNTimes("item2", 3)
counterHashMap2.putNTimes("item3", 6)
counterHashMap2.putNTimes("item1", 2)
counterHashMap2.putNTimes("item2", 3)
counterHashMap2.putNTimes("item1", 2)
counterHashMap1.add(counterHashMap2)
self.assertEquals(9, counterHashMap1.count("item1"))
self.assertEquals(8, counterHashMap1.count("item2"))
self.assertEquals(7, counterHashMap1.count("item3"))
def test_PutNTimes2(self):
counterHashMap = CounterHashMap()
for i in range(1000):
counterHashMap.putNTimes(randrange(1000), i + 1)
self.assertEquals(500500, counterHashMap.sumOfCounts())
def test_TopN2(self):
counterHashMap = CounterHashMap()
for i in range(1000):
counterHashMap.putNTimes(i, 2 * i + 2)
self.assertEquals(990, counterHashMap.topN(10)[9][1])
self.assertEquals(900, counterHashMap.topN(100)[99][1])