def test_char_count():
textstat.set_lang("en_US")
count = textstat.char_count(long_test)
count_spaces = textstat.char_count(long_test, ignore_spaces=False)
assert count == 1750
assert count_spaces == 2123
def test_char_count():
count = textstat.char_count(long_test)
count_spaces = textstat.char_count(
long_test, ignore_spaces=False
)
assert count == 1750
assert count_spaces == 2123
def __init__(self, text):
self.__doc = self.preprocess(text)
self.__docWords = self.getTotalWords()
self.__totalWords = textstat.lexicon_count(self.__doc, removepunct=True)
self.__totalCharacters = textstat.char_count(self.__doc, ignore_spaces=True)
self.__totalSentences = self.getSentencesCount()
self.__totalSyllables = self.getSyllablesCount()
# self.__totalSyllables = textstat.syllable_count(self.__doc)
self.__polySyllableCount = self.getPolySyllableCount()
def test_char_count(self):
count = textstat.char_count(self.long_test)
count_spaces = textstat.char_count(self.long_test, ignore_spaces=False)
self.assertEqual(1750, count)
self.assertEqual(2123, count_spaces)
def get_redability_assessments(data_text: str) -> Optional[dict]:
divided_text = tokenize.sent_tokenize(data_text)
word_tokenizes = nltk.word_tokenize(data_text)
pos_tags = nltk.pos_tag(word_tokenizes)
pos_tags_tagger = TAGGER.tag(word_tokenizes)
f_dist = nltk.FreqDist(word_tokenizes)
uniqueWordCount = compute_unique_word_count(f_dist.most_common())
paragraphCount = max(len(data_text.split('\n')), len(data_text.split('\r\n')))
counts = Counter(tag for word, tag in pos_tags)
# Readability Grade Levels
readability_grade_levels = dict(fleschKincaid=0, gunningFog=0, colemanLiau=0, smog=0,
ari=0, forecastGradeLevel=0, powersSumnerKearlGrade=0, rix=0,
raygorReadability=0, fryReadability=0, flesch=0)
readability_grade_levels.update(fleschKincaid=textstat.flesch_kincaid_grade(data_text))
readability_grade_levels.update(gunningFog=textstat.gunning_fog(data_text))
readability_grade_levels.update(colemanLiau=textstat.coleman_liau_index(data_text))
readability_grade_levels.update(smog=textstat.smog_index(data_text))
readability_grade_levels.update(ari=textstat.automated_readability_index(data_text))
readability_grade_levels.update(rix=textstat.rix(data_text))
# need to check
readability_grade_levels.update(forcastGradeLevel=round(20 - (textstat.avg_syllables_per_word(data_text) / 10), 2))
readability_grade_levels.update(powersSumnerKearlGrade=round(textstat.avg_sentence_length(data_text) +
textstat.avg_syllables_per_word(data_text) +
2.7971, 2))
readability_grade_levels.update(raygorReadability=count_raygor_readability(divided_text))
readability_grade_levels.update(fryReadability=count_fry_readability(divided_text))
# need to check
readability_grade_levels.update(flesch=textstat.flesch_reading_ease(data_text))
# Readability Scores
readability_scores = dict(readableRating="", fleschReadingEase=0, cefrLevel='', ieltsLevel='', spacheScore=0,
newDaleChallScore=0, lixReadability=0, lensearWrite=0)
readability_scores.update(readableRating=count_average_grade_levels(readability_grade_levels))
readability_scores.update(fleschReadingEase=textstat.flesch_reading_ease(data_text))
readability_scores.update(cefrLevel=count_cefr_levels(readability_grade_levels))
readability_scores.update(ieltsLevel=count_ielts_levels(readability_grade_levels))
readability_scores.update(spacheScore=round(textstat.spache_readability(data_text), 2))
readability_scores.update(newDaleChallScore=textstat.dale_chall_readability_score_v2(data_text))
readability_scores.update(lixReadability=textstat.lix(data_text))
readability_scores.update(lensearWrite=textstat.linsear_write_formula(data_text))
# Text Statistics
text_statistics = dict(characterCount=0, syllableCount=0, wordCount=0, uniqueWordCount=0,
sentenceCount=0, paragraphCount=0)
text_statistics.update(characterCount=textstat.char_count(data_text))
text_statistics.update(syllableCount=textstat.syllable_count(data_text))
text_statistics.update(wordCount=textstat.lexicon_count(data_text))
text_statistics.update(uniqueWordCount=uniqueWordCount)
text_statistics.update(sentenceCount=textstat.sentence_count(data_text))
text_statistics.update(paragraphCount=paragraphCount)
# Timings
timings_statistics = dict(readingTime=0, speakingTime=0)
timings_statistics.update(readingTime=reading_time(textstat.lexicon_count(data_text)))
timings_statistics.update(speakingTime=speaking_time(textstat.lexicon_count(data_text)))
# Text Composition
text_composition = dict(adjectives=0, adverbs=0, conjunctions=0, determiners=0, interjections=0, nouns=0, verbs=0,
properNouns=0, prepositions=0, pronouns=0, qualifiers=0, unrecognised=0, nonWords=0)
text_composition.update(adjectives=counts.get('JJ', 0) + counts.get('JJR', 0) + counts.get('JJS', 0))
text_composition.update(adverbs=counts.get('RB', 0) + counts.get('RBR', 0) + counts.get('RBS', 0))
text_composition.update(conjunctions=counts.get('CC', 0))
text_composition.update(determiners=counts.get('DT', 0) + counts.get('PDT', 0) + counts.get('WDT', 0))
text_composition.update(interjections=counts.get('UH', 0))
text_composition.update(nouns=counts.get('NN', 0) + counts.get('NNS', 0))
text_composition.update(
verbs=counts.get('VB', 0) + counts.get('VBD', 0) + counts.get('VBG', 0) + counts.get('VBN', 0) + counts.get(
'VBP', 0) + counts.get('VBZ', 0))
text_composition.update(properNouns=counts.get('NNP', 0) + counts.get('NNPS', 0))
text_composition.update(prepositions=counts.get('IN', 0))
text_composition.update(
pronouns=counts.get('PRP', 0) + counts.get('PRP$', 0) + counts.get('WP', 0) + counts.get('WP$', 0))
text_composition.update(qualifiers=counts.get('RB', 0))
text_composition.update(unrecognised=counts.get(None, 0))
text_composition.update(nonWords=counts.get('.', 0) + counts.get(',', 0) + counts.get(':', 0))
# Readability Issues
text_readability_issues = dict(sentences30SyllablesCount=0, sentences20SyllablesCount=0,
sentences30Syllables=[], sentences20Syllables=[],
words4SyllablesCount=0, words12LettersCount=0,
words4Syllables=[], words12Letters=[])
sentences_30_syllables, sentences_30_count, sentences_20_syllables, sentences_20_count = count_sentences_syllables(
divided_text)
sentences_30_syllables = find_limit_offcet(data_text, sentences_30_syllables,
"sentences_30_syllables",
"sentences_30_syllables",
"This sentence has more than 30 syllables. Consider rewriting it to be shorter or splitting it into smaller sentences.",
"Readability Issues")
sentences_20_syllables = find_limit_offcet(data_text, sentences_20_syllables,
"sentences_20_syllables",
"sentences_20_syllables",
"This sentence has more than 20 syllables. Consider rewriting it to be shorter or splitting it into smaller sentences.",
"Readability Issues")
text_readability_issues.update(sentences30SyllablesCount=sentences_30_count,
sentences20SyllablesCount=sentences_20_count)
words_12_letters, words_12_count, words_4_syllables, words_4_count = words_sentence_syllables(divided_text)
words_12_letters = find_limit_offcet(data_text, words_12_letters,
"words_12_letters",
"words_12_letters",
"This word is more than 12 letters",
"Readability Issues")
words_4_syllables = find_limit_offcet(data_text, words_4_syllables,
"words_4_syllables",
"words_4_syllables",
"This word is more than 4 syllables",
"Readability Issues")
text_readability_issues.update(words4SyllablesCount=words_4_count,
words12LettersCount=words_12_count)
# Writing Style Issues
text_style_issues = dict(passiveVoiceCount=0, passiveVoices=[],
adverbsCount=0, adverbs=[],
clicheCount=0, cliches=[])
passive_voises_return = find_passives(divided_text)
passive_voises_return = find_limit_offcet(data_text, passive_voises_return,
"passive_voises",
"passive_voises",
"Too much of using passive voises",
"Writing Style Issues")
adverbs_return = find_adverbs(pos_tags_tagger)
adverbs_return = find_limit_offcet(data_text, adverbs_return,
"adverbs", # writing_style_issues
"adverbs",
"Too much of using adverbs",
"Writing Style Issues")
text_style_issues.update(passiveVoiceCount=len(passive_voises_return),
adverbsCount=len(adverbs_return))
# Text Density Issues
text_density_issues = dict(charactersPerWord=0, syllablesPerWord=0, wordsPerSentence=0,
wordsPerParagraph=0, sentencesPerParagraph=0)
text_density_issues.update(charactersPerWord=textstat.avg_character_per_word(data_text),
syllablesPerWord=textstat.avg_syllables_per_word(data_text),
wordsPerSentence=round(textstat.lexicon_count(data_text) / len(divided_text), 2),
wordsPerParagraph=round(textstat.lexicon_count(data_text) / paragraphCount, 2),
sentencesPerParagraph=round(len(divided_text) / paragraphCount, 2))
# Language Issues
text_language_issues = dict(spellingIssuesCount=0, grammarIssueCount=0)
matches_limit_offcet = sentences_20_syllables + sentences_30_syllables + words_4_syllables + words_12_letters + \
passive_voises_return + adverbs_return
return dict(readabilityGradeLevels=readability_grade_levels,
readabilityScores=readability_scores,
textStatistics=text_statistics,
timings=timings_statistics,
textComposition=text_composition,
textReadabilityIssues=text_readability_issues,
textStyleIssues=text_style_issues,
textDensityIssues=text_density_issues,
textLanguageIssues=text_language_issues,
matches=matches_limit_offcet)
#Read in data
data = pd.read_csv("INPUT_2.txt",
sep='\t',
header=None,
names=['id', 'target', 'tweet'],
encoding='utf-8')
data.drop(['id', 'target'], axis=1, inplace=True)
#Total number of tweets
print("Total number of tweets is ", len(data))
#Total number of characters
char = 0
i = 0
while i < len(data):
char = char + textstat.char_count(data['tweet'][i])
i += 1
print("Total number of characters is ", char)
#Total number of distinct words
twt = TweetTokenizer(strip_handles=True, reduce_len=True)
words = []
i = 0
while i < len(data):
for word in twt.tokenize(data['tweet'][i]):
words.append(word)
i += 1
print("Total number of distinct words is ", len(set(words)))
#Avg number of of characters in each tweet
def test_char_count():
count = textstat.char_count(long_test)
count_spaces = textstat.char_count(long_test, ignore_spaces=False)
assert count == 1750
assert count_spaces == 2123
characters_based_features['number_of_close_paranthesis'] += 1
if k == '()':
characters_based_features['number_of_pair_paranthesis'] += 1
if k == '[':
characters_based_features['number_of_open_squareBracket'] += 1
if k == ']':
characters_based_features['number_of_close_squareBracket'] += 1
if k == '[]':
characters_based_features['number_of_pair_squareBracket'] += 1
if k == '{':
characters_based_features['number_of_open_curlyBracket'] += 1
if k == '}':
characters_based_features['number_of_close_curlyBracket'] += 1
if k == '{}':
characters_based_features['number_of_pair_curlyBracket'] += 1
characters_based_features['number_of_characters'] = textstat.char_count(
i, ignore_spaces=False)
characters_based_features['number_of_quotation'] = len(
re.compile(r"\"").findall(i))
characters_based_features['number_of_numbersigns'] = len(
re.compile(r"\#").findall(i))
characters_based_features['number_of_dollar'] = len(
re.compile(r"\$").findall(i))
characters_based_features['number_of_percent'] = len(
re.compile(r"\%").findall(i))
characters_based_features['number_of_ampersand'] = len(
re.compile(r"\&").findall(i))
characters_based_features['number_of_asterisk'] = len(
re.compile(r"\*").findall(i))
characters_based_features['number_of_plus'] = len(
re.compile(r"\+").findall(i))
characters_based_features['number_of_minus'] = len(
