class WordCountTest(unittest.TestCase):
'''
generate test input files and use them for invoking the tests
'''
def setUp(self):
self.wc = WordCount()
self.word_dict_counts = {"this":1,"is":2,"a":2,"test":1,"file":2,"contents":1,"are":1,"written":1,"to":1,"used":1,"it":1,"for":2,"the":1,"purpose":1,"testing":2}
self.word_dict_counts_total = {"this":5,"is":10,"a":10,"test":5,"file":10,"contents":5,"are":5,"written":5,"to":5,"used":5,"it":5,"for":10,"the":5,"purpose":5,"testing":10}
self.file_list = []
fp2 =open("test_path.txt","w")
for i in range(1,6):
file_name = str(i)+".txt"
fp =open(file_name,"w")
fp.write("This is a test file. Contents are written to the file for testing!\n")
fp.write("It is used for a testing purpose!\n")
fp2.write(os.path.abspath(file_name))
fp2.write("\n")
fp.close()
self.file_list.append(os.path.abspath(file_name))
fp2.close()
def test_count_totoal_words(self):
countedWords = self.wc.process_input_file("test_path.txt")
#print (countedWords)
self.assertEqual(len(countedWords), len(self.word_dict_counts_total), FAILURE)
def test_count_words_single_file_2(self):
countedWords = self.wc.count_words("2.txt")
self.assertEqual(len(countedWords), 15, FAILURE)
def test_search_word_totoal_count(self):
countedWords = self.wc.process_input_file("test_path.txt")
table = self.wc.search_word("file")
self.assertEqual(countedWords['file']['total_count'], self.word_dict_counts_total["file"], FAILURE)
def test_search_word_totoal_count_individual_file(self):
countedWords = self.wc.count_words("2.txt")
self.assertEqual(countedWords['file']['total_count'], self.word_dict_counts["file"], FAILURE)
def test_invalid_search_word(self):
countedWords = self.wc.process_input_file("test_path.txt")
table = self.wc.search_word("invalid_word")
self.assertFalse("invalid_word" in countedWords)
def test_list_words(self):
countedWords = self.wc.process_input_file("test_path.txt")
for k,v in self.word_dict_counts_total.items():
self.assertEqual(countedWords[k]['total_count'],v,FAILURE)
def test_search_words_count_across_files(self):
countedWords = self.wc.process_input_file("test_path.txt")
word_info = countedWords["for"]
for i in range(len(self.file_list)):
self.assertEqual(word_info[self.file_list[i]],self.word_dict_counts["for"],FAILURE)
def tearDown(self):
for i in range(len(self.file_list)):
os.remove(self.file_list[i])
os.remove("test_path.txt")
def __init__(self):
self.files = FileUtils().get_files_from_path(sys.argv[1])
self.file_count = len(self.files)
self.k1 = 1.2
self.b = 0.75
self.max_score = 0
self.min_score = 100
self.avg_doc_length = 0
self.idf = {}
self.word_count_calculator = WordCount()
self.bm_25_scores = {}
def test_word_occurance8(self):
self.assertDictEqual({
'hello': 1,
'world': 1
},
WordCount.words('hello\nworld'),
msg='should not count multilines')
def test_word_occurance9(self):
self.assertDictEqual({
'hello': 1,
'world': 1
},
WordCount.words('hello\tworld'),
msg='should not count tabs')
def test_word_occurance0(self):
self.assertDictEqual({
'hello': 1,
'world': 1
},
WordCount.words('hello world'),
msg='should count multiple spaces as one')
def setUp(self):
self.wc = WordCount()
self.word_dict_counts = {"this":1,"is":2,"a":2,"test":1,"file":2,"contents":1,"are":1,"written":1,"to":1,"used":1,"it":1,"for":2,"the":1,"purpose":1,"testing":2}
self.word_dict_counts_total = {"this":5,"is":10,"a":10,"test":5,"file":10,"contents":5,"are":5,"written":5,"to":5,"used":5,"it":5,"for":10,"the":5,"purpose":5,"testing":10}
self.file_list = []
fp2 =open("test_path.txt","w")
for i in range(1,6):
file_name = str(i)+".txt"
fp =open(file_name,"w")
fp.write("This is a test file. Contents are written to the file for testing!\n")
fp.write("It is used for a testing purpose!\n")
fp2.write(os.path.abspath(file_name))
fp2.write("\n")
fp.close()
self.file_list.append(os.path.abspath(file_name))
fp2.close()
def test_word_occurance2(self):
self.assertDictEqual({
'one': 1,
'of': 1,
'each': 1
},
WordCount.words("one of each"),
msg='should count one of each')
def test_word_occurance5(self):
self.assertDictEqual({
'testing': 2,
1: 1,
2: 1
},
WordCount.words('testing 1 2 testing'),
msg='should include numbers')
def test_word_occurance6(self):
self.assertDictEqual({
'go': 1,
'Go': 1,
'GO': 1
},
WordCount.words('go Go GO'),
msg='should respect case')
def main():
# NOTE: Change this to name of .txt file you are using within /data/.
file_path = 'data/book.txt'
start = time.time()
print("Starting up.")
k = int(input("Enter a value for k:\n"))
# Parse and sort data using collections.
data = WordCount(file_path)
data.sort_and_pop_word_dict(k)
# Parse and sort data using dictionary and max heap.
# data = WordCountDict('data/book.txt')
# heap = MaxHeap()
# heap.insert_dict(data.get_word_dict())
# heap.pop_top_k_words(k)
print(time.time()-start)
def test_word_occurance7(self):
self.assertDictEqual(
{
"¡Hola!": 1,
"¿Qué": 1,
"tal?": 1,
"Привет!": 1
},
WordCount.words('¡Hola! ¿Qué tal? Привет!'),
msg='should count international characters properly')
def generate_counts():
res = request.get_json()
urls = res['urls']
print(urls)
for url in urls:
if cache.get(url) is None:
cache.set(url, '')
job = q.enqueue_call(func=WordCount().run, args=(url, ))
return ('Accepted', 202)
def test_word_occurance3(self):
self.assertDictEqual(
{
'one': 1,
'fish': 4,
'two': 1,
'red': 1,
'blue': 1
},
WordCount.words("one fish two fish red fish blue fish"),
msg='should count multiple occurrences')
def test_word_occurance4(self):
self.assertDictEqual(
{
'car': 1,
":": 2,
'carpet': 1,
'as': 1,
'java': 1,
'javascript!!&@$%^&': 1
},
WordCount.words('car : carpet as java : javascript!!&@$%^&'),
msg='should include punctuation')
def generate_dict(reviewList):
dictionary = wc.count_words(wc, reviewList)
dictionary = wc.sort_freq_dict(wc, dictionary)
return dictionary
# coding=utf-8
from word_count import WordCount
from lookup import lookup
FLAG_LAST_WORD = 1
FLAG_MIDDLE_WORD = 2
wc = WordCount()
def word_topk(k, flag):
if flag == FLAG_LAST_WORD:
return wc.last_word_topk(k)
if flag == FLAG_MIDDLE_WORD:
return wc.middle_word_topk(k)
return []
def word_freq(word, flag):
"""返回常见系数、级别"""
if flag == FLAG_LAST_WORD:
ret = wc.last_word_freq(word)
else:
ret = wc.middle_word_freq(word)
freq, rank, total = ret
# 1/4 -- 2/4 -- 3/4 -- 1
if rank <= total / 4:
comment = u'大众名'
def test_word_occurance1(self):
self.assertDictEqual({'word': 1},
WordCount.words('word'),
msg='should count one word')
class TermWeights:
def __init__(self):
self.files = FileUtils().get_files_from_path(sys.argv[1])
self.file_count = len(self.files)
self.k1 = 1.2
self.b = 0.75
self.max_score = 0
self.min_score = 100
self.avg_doc_length = 0
self.idf = {}
self.word_count_calculator = WordCount()
self.bm_25_scores = {}
# Calculates the IDF value for a word
def calculate_idf(self):
for word, count in self.word_count_calculator.document_count.items():
self.idf[word] = math.log10(
(self.file_count - count + 0.5) / (count + 0.5))
self.avg_doc_length = sum(self.word_count_calculator.document_length.
values()) / self.file_count
# normalizes the BM25 scores to values between 0 and 1
def normalize_score(self, score):
if (self.max_score - self.min_score) == 0:
return 0
else:
return ((score - self.min_score) /
(self.max_score - self.min_score))
# Primary method that calculates the BM25 score using the word count
# Also keeps track of the max and min BM25 scores to be used for normalization
def calculate(self):
self.word_count_calculator.calculate()
self.calculate_idf()
for file_name, word_count_dict in self.word_count_calculator.word_counts.items(
):
bm_25 = {}
for word, count in word_count_dict.items():
try:
if self.word_count_calculator.global_count[
word] != 1 and len(word) != 1:
count = int(count)
numerator = (count *
(self.k1 + 1)) * float(self.idf[word])
denominator = (
count + self.k1 *
(1 - self.b +
(self.b *
(int(self.word_count_calculator.document_length[
file_name]) / self.avg_doc_length))))
bm_25_score = (numerator / denominator)
bm_25[word] = bm_25_score
if bm_25_score > self.max_score:
self.max_score = bm_25_score
if bm_25_score < self.min_score:
self.min_score = bm_25_score
except KeyError:
continue
self.bm_25_scores[file_name] = bm_25
self.normalize()
def normalize(self):
for file_name, bm_25 in self.bm_25_scores.items():
for word, score in bm_25.items():
bm_25[word] = self.normalize_score(score)
