def __init__(self, table_name_key):
DataProcessInterface.__init__(self, table_name_key)
#self.output_filename = parameters.get('output_filename')
#self.output_folder = parameters.get('output_folder')
util = Util()
self.input_folder = util.getInputFolder(table_name_key)
self.doc_no = 1 # assumeing all docs are read form the begining to the end
self.para_no = 1
self.sentance_no = 1
self.word_no = 1
self.wordCounter = WordCounter()
#self.bufferedWriter = BufferedWriter(self.output_folder,
# self.output_filename)
self.bufferedWriter = BufferedWriter(
util.getOutputFolder(table_name_key),
'{}.json'.format(table_name_key))
self.dict_ = {
'documents': {},
'paragraphs': {},
'words': {},
'word-documents': {}
}
self.current_doc_name = None
def testAppostrophesHandledOk(self):
wc = WordCounter()
basicString = "I'm a Quick brown fox jumped over 9 the lazy dog"
wc.processString(basicString)
self.assertEqual(11, wc.getWordCount())
wl = wc.getWordList()
self.assertTrue("I\'m" in wl.keys())
def testCountWords(self):
"""
Function that tests the countWords function within the
Word Counter class.
"""
# Number of words in text4.txt
num = 200
tester = WordCounter("tests/text4.txt")
self.assertEqual(tester.countWords(), num)
def testWordTally(self):
wc = WordCounter()
basicString = "I am bad bad bad at python, its amazing how quickly you can forget python"
wc.processString(basicString)
wordList = wc.getWordList()
self.assertEqual(3, wordList['bad'])
self.assertEqual(2, wordList['python'])
def testGetTopOccurences(self):
"""
Function that tests the getTopOccurrences method
from WordCounter class. Takes a test .txt file and
checks it against pre-checked dict
"""
object = WordCounter("tests/testFile.txt")
trueValue = {
"quick": 7,
"jumps": 7,
"brown": 5,
"zebra": 3,
"table": 3,
"over": 4,
"dog": 4,
"layer": 5,
"crazy": 3,
"productive": 4
}
self.assertDictEqual(object.getTopOccurrences(), trueValue)
def test_get_total_words(self):
obj = WordCounter()
obj.text_content = self.content
self.assertEqual(obj.get_total_words(), 10)
def test_initialize_word_count_has_default_content(self):
obj = WordCounter()
self.assertIn('Lady Gaga', obj.text_content)
def testNumbersCounted(self):
wc = WordCounter()
basicString = "Quick brown fox jumped over 9 the lazy dog"
wc.processString(basicString)
self.assertEqual(9, wc.getWordCount())
def test_count_word_simple():
"""Count word in a short text"""
text = TextBody("the white white whale")
counter = WordCounter(text)
assert_equal(counter.count_word("white"), 2)
def setUp(self):
"""Prepare before each test"""
MOBYDICK_SUMMARY = open('mobydick_summary.txt').read()
self.text = TextBody(MOBYDICK_SUMMARY)
self.counter = WordCounter(self.text)
def run():
word_counter = WordCounter('kennedy.txt')
word_counter.display()
def set_up(self, filename):
self.f = open(filename)
self.fr = self.f.read()
self.wc = WordCounter(self.fr)
def testBasicSentence(self):
wc = WordCounter()
basicString = "Quick brown fox jumped over the lazy dog."
wc.processString(basicString)
self.assertEqual(8, wc.getWordCount())
def testHandlesTemperature(self):
wc = WordCounter()
basicString = "The temperature outside, is -9C"
wc.processString(basicString)
self.assertEqual(5, wc.getWordCount())
def testHandlesCommasOk(self):
wc = WordCounter()
basicString = "I'm a Quick brown, fox jumped over 9 the lazy dog"
wc.processString(basicString)
self.assertEqual(11, wc.getWordCount())
def test_get_most_common_words(self):
obj = WordCounter()
obj.text_content = self.content
self.assertEqual(obj.get_most_common_words(2), [('Four', 4),
('Three', 3)])
import re
from word_counter import WordCounter
# pattern for splitting words
PATTERN = "[\d\W\s_]+"
wc = WordCounter()
with open('README.md', 'r') as file:
for line in file:
for word in re.split(PATTERN, line.strip()):
if word:
wc.add_word(word)
# display the word counts
for word in sorted(wc):
print(f"{wc[word]:3} {word}")
if __name__ == '__main__':
started = datetime.now()
keywords = ["Familie"] # erstelle eine liste mit keywords
analyzer = Analyzer(keywords).start() # erstelle eine Analyzer-Instanz und starte diese
ended = datetime.now()
elapsed = ended - started
print("Analyzer time: {}".format(elapsed))
if input("WordCount errechnen? (y/n) - ").lower() == "y":
# wenn vom User gewollt, wird die Wortanzahl berechnet
ended = None
# erstlle WordCounter-Instanz und starte diese
counter = WordCounter()
counter.start()
# erstlle WeeklyCounter-Instanz
weekly = WeeklyCounter(counter)
weekly.start()
if not ended: ended = datetime.now()
elapsed = ended - started
print("Time started: {}".format(started))
print("Time ended: {}".format(ended))
print("Total time running: {}".format(elapsed))
def setUp(self):
conf = SparkConf().setAppName("appTest").setMaster("local[*]")
self.sc = SparkContext(conf=conf)
self.counter = WordCounter()
def test_count_word_simple(self):
"""Count a single word"""
counter = WordCounter(MockText)
self.assertEqual(counter.count_word("white"), 2)
from word_counter import WordCounter
from ui import ui
if __name__ == "__main__":
_ui = ui()
_ui.handle_input()
counter = WordCounter(_ui.file_name)
success = counter.run()
if success:
_ui.display_word_count(counter)
_ui.display_exit_message()
else:
_ui.display_error_message()
exit()
#!/usr/bin/env python
#
# example of a test generator
#
from nose.tools import assert_equal
from word_counter import TextBody, WordCounter
MOBYDICK_SUMMARY = open('mobydick_summary.txt').read()
TEXT = TextBody(MOBYDICK_SUMMARY)
COUNTER = WordCounter(TEXT)
WORD_PAIRS = [('months', 1), ('whale', 5), ('captain', 4), ('white', 2),
('harpoon', 1), ('Ahab', 1)]
def check_word(word, number):
assert_equal(COUNTER.count_word(word), number)
def test_word_pairs():
# Tests a series of example words
# creates one test for each word
# --- no docstring so that parameters are visible ---
for word, number in WORD_PAIRS:
yield check_word, word, number
# nose does
for x, y, z in test_word_pairs:
if x(y, z):
def main():
logging.info("Starting...")
training_parser = InputParser(
'/Users/skobovm/repos/csep517/hmm/data/twt.train.json')
dev_parser = InputParser(
'/Users/skobovm/repos/csep517/hmm/data/twt.dev.json')
test_parser = InputParser(
'/Users/skobovm/repos/csep517/hmm/data/twt.test.json')
# First, count the words!
counter = WordCounter()
for parsed_sentence in training_parser.get_tokenized_sentences():
if parsed_sentence:
for i in range(1, len(parsed_sentence) - 1):
counter.add_word(parsed_sentence[i][0])
# Finalize counter and separate high frequency from low frequency
counter.finalize()
# Initialize the models
bigram = BigramHMM()
trigram = TrigramHMM()
for parsed_sentence in training_parser.get_tokenized_sentences():
if parsed_sentence:
# Convert the low frequency words to classes
counter.classify_sentence(parsed_sentence)
bigram.add_sentence(parsed_sentence)
trigram.add_sentence(parsed_sentence)
# Models have been initialized at this point, finalize the distributions
#bigram.finalize()
trigram.finalize()
# PICK THE PARSER HERE
parser = dev_parser
# Iterate over data and try to predict
num_correct_bigram = 0
num_correct_trigram = 0
total_words = 0
for parsed_sentence in parser.get_tokenized_sentences():
if parsed_sentence:
original_sentence = copy.deepcopy(parsed_sentence)
# Convert the low frequency words to classes
counter.classify_sentence(parsed_sentence)
# Bigram lattice
#lattice = Lattice(bigram, parsed_sentence)
# Trigram lattice
tri_lattice = TrigramLattice(trigram, parsed_sentence)
# Calculate best POS using viterbi
#pos_list_bigram = lattice.get_pos()
pos_list_trigram = tri_lattice.get_pos()
# Determine how many were correct
#num_correct_bigram += get_num_correct(parsed_sentence, pos_list_bigram, lattice)
num_correct_trigram += get_num_correct(parsed_sentence,
pos_list_trigram,
tri_lattice,
original_sentence, counter)
# Remove the START and STOP chars
total_words += (len(parsed_sentence) - 2)
print("Accuracy: %s" % (num_correct_trigram / total_words))
else:
print('ERROR! Couldnt parse sentence')
print("Bigram HMM Accuracy: %s/%s - %s" %
(num_correct_bigram, total_words,
(num_correct_bigram / total_words)))
print("Trigram HMM Accuracy: %s/%s - %s" %
(num_correct_trigram, total_words,
(num_correct_trigram / total_words)))
print("\nPuede escoger una de las siguientes opciones:")
print("(1) Relación de las palabras utilizadas en el texto, así como las veces que aparecen.")
print(f"(2) Las {words_most_used} palabras más utilizadas en el texto, asi como las veces que aparecen.")
try:
option = int(input("Escribe el número de una de la opción seleccionada: "))
except ValueError:
print(f"\nLo sentimos, la opción seleccionada no es válida.")
another_try = input("¿Gusta volver a seleccionar una opción? S=si / N=no: ")
another_try = another_try.lower()
if another_try == "s":
continue
else:
print("\nMuchas gracias por haber usado esta aplicación, esperamos que vuelva pronto.")
exit()
if option == 1:
word_counter = WordCounter(words_in_text)
counted_words = word_counter.count_words()
print(f"\nLa relación de palabras que aprecen {text.file_name}, con la cantidad de veces que aparece cada una de ellas, es la siguiente:")
for key, value in counted_words.items():
if value == 1:
print(f"{key} aparece {value} vez.")
else:
print(f"{key} aparece {value} veces.")
is_done = True
elif option == 2:
word_counter_sorter = CountedWordsSorter(words_in_text, words_to_ignore)
counted_words = word_counter_sorter.count_words()
sorted_counted_words = word_counter_sorter.sort_counted_words(counted_words)
counter = 0
if words_most_used == 1:
print(f"\nLa palabra más utilizada en {text.file_name} es la siguiente:")
def test_count_word_complex():
"""Count word in a longer text"""
text = TextBody(MOBYDICK_SUMMARY)
counter = WordCounter(text)
assert_equal(counter.count_word("white"), 2)
def read(self, filePlace, type):
movies = self._sc.textFile(filePlace)
counter = WordCounter()
if type is 'Years':
counter = YearsCounter()
return counter.getMaxValues(movies)