def main():
path='/home/shuo/Documents/AI_learning/LearningQ/data/teded/teded_crawled_data/'
analysis=text_analysis()
analysis.read_relation(path)
#analysis.get_mintues()
analysis.read_videoinfo(path)
questions=analysis.gather_question()
question=analysis.video_question
#for item in question:
# print(question[item]['quizzes'][0].keys())
"""
self.video_question[title]: video_link', 'video_title_length', 'video_description', 'quizzes', 'video_youtube_link
quizzes: quiz_description', 'question_type', 'quiz_options', 'hint', 'answer'
multiple-choices open-ended
"""
scripts=analysis.gather_transcripts(path)
stats_scripts(scripts)
temp_dic=analysis.build_question_transcripts(path)
# analysis.stats_scripts()
temp=[]
for item in temp_dic:
for quiz in temp_dic[item]['questions']:
if quiz['question_type']=='multiple-choices':
temp.append(temp_dic[item])
break
q=0
for d in temp:
for question in d['questions']:
xxx=len(question['quiz_description'].split('.'))
q+=xxx
nlp = en_core_web_sm.load()
#n_e=0
total_r=0
n=0
for title in scripts:
#sentences=scripts[title].split('\n')
#e=NER(sentences,nlp)
if len(scripts[title].split(' '))>=100:
n+=1
r = Readability(scripts[title])
total_r+=r.flesch().score
#n_e+=e
#print(n_e)
print(total_r)
print(n)
print(total_r/n)
def doc_to_readability(doc_str) -> ArrayField:
if len(doc_str) < 10:
return ArrayField(np.zeros(7))
str_to_read = doc_str
try:
while len(str_to_read.split()) < 150:
str_to_read += " " + doc_str
r = Readability(str_to_read)
r_scores = [
r.flesch_kincaid().score,
r.flesch().score,
r.gunning_fog().score,
r.coleman_liau().score,
r.dale_chall().score,
r.ari().score,
r.linsear_write().score
]
return ArrayField(np.array(r_scores))
except ReadabilityException:
return ArrayField(np.zeros(7))
#------------------
# Readability
#------------------
st.header('Readability')
# Context
passage = st.text_area("Candidate Bible Passage (English)", value='',
max_chars=None, key='readability_passage')
# Calculate readability
r = Readability(passage)
# Display readability
data = [
['Flesch-Kincaid Score', r.flesch_kincaid().score],
['Flesch Reading Ease', r.flesch().ease],
['Dale Chall Readability Score', r.dale_chall().score],
['Automated Readability Index Score', r.ari().score],
['Coleman Liau Index', r.coleman_liau().score],
['Gunning Fog', r.gunning_fog().score],
['Linsear Write', r.linsear_write().score],
['Spache Readability Formula', r.spache().score]
]
df = pd.DataFrame(data, columns=['Readability Metric', 'Value'])
if st.button('Assess Readability', key=None):
st.write(df)
class ReadabilityTest(unittest.TestCase):
def setUp(self):
text = """
In linguistics, the Gunning fog index is a readability test for English writing. The index estimates the years of formal education a person needs to understand the text on the first reading. For instance, a fog index of 12 requires the reading level of a United States high school senior (around 18 years old). The test was developed in 1952 by Robert Gunning, an American businessman who had been involved in newspaper and textbook publishing.
The fog index is commonly used to confirm that text can be read easily by the intended audience. Texts for a wide audience generally need a fog index less than 12. Texts requiring near-universal understanding generally need an index less than 8.
"""
self.readability = Readability(text)
def test_ari(self):
r = self.readability.ari()
print(r)
self.assertEqual(9.551245421245422, r.score)
self.assertEqual(['10'], r.grade_levels)
self.assertEqual([15, 16], r.ages)
def test_coleman_liau(self):
r = self.readability.coleman_liau()
print(r)
self.assertEqual(10.673162393162393, r.score)
self.assertEqual('11', r.grade_level)
def test_dale_chall(self):
r = self.readability.dale_chall()
print(r)
self.assertEqual(9.32399010989011, r.score)
self.assertEqual(['college'], r.grade_levels)
def test_flesch(self):
r = self.readability.flesch()
print(r)
self.assertEqual(51.039230769230784, r.score)
self.assertEqual(['10', '11', '12'], r.grade_levels)
self.assertEqual('fairly_difficult', r.ease)
def test_flesch_kincaid(self):
r = self.readability.flesch_kincaid()
print(r)
self.assertEqual(10.125531135531137, r.score)
self.assertEqual('10', r.grade_level)
def test_gunning_fog(self):
r = self.readability.gunning_fog()
print(r)
self.assertEqual(12.4976800976801, r.score)
self.assertEqual('12', r.grade_level)
def test_linsear_write(self):
r = self.readability.linsear_write()
print(r)
self.assertEqual(11.214285714285714, r.score)
self.assertEqual('11', r.grade_level)
def test_smog(self):
text = """
In linguistics, the Gunning fog index is a readability test for English writing. The index estimates the years of formal education a person needs to understand the text on the first reading. For instance, a fog index of 12 requires the reading level of a United States high school senior (around 18 years old). The test was developed in 1952 by Robert Gunning, an American businessman who had been involved in newspaper and textbook publishing.
The fog index is commonly used to confirm that text can be read easily by the intended audience. Texts for a wide audience generally need a fog index less than 12. Texts requiring near-universal understanding generally need an index less than 8.
"""
text = ' '.join(text for i in range(0, 5))
readability = Readability(text)
r = readability.smog()
print(r)
self.assertEqual(12.516099999999998, r.score)
self.assertEqual('13', r.grade_level)
def test_spache(self):
r = self.readability.spache()
print(r)
self.assertEqual(7.164945054945054, r.score)
self.assertEqual('7', r.grade_level)
def test_print_stats(self):
stats = self.readability.statistics()
self.assertEqual(562, stats['num_letters'])
self.assertEqual(117, stats['num_words'])
self.assertEqual(7, stats['num_sentences'])
self.assertEqual(20, stats['num_polysyllabic_words'])
def main():
# Read and normalise input text
content = sys.stdin.read()
tu = TextUtility(content)
cleanText = tu.normalizeText()
#removedInfrequent = tu.tokenizeAndRemoveCommonWords(4)
#print("Without frequent words: ", removedInfrequent)
#Readability measures
print("\n*** Readability ***")
readability = Readability(content)
Kincaid = readability.kincaid()
sys.stdout.write('Kincaid (school grade level): %f\n' % (Kincaid))
ARI_score = readability.ari()
sys.stdout.write('ARI (school grade level): %f\n' % (ARI_score))
ColemanLiau = readability.colemanLiau()
sys.stdout.write('ColemanLiau (school grade level): %f\n' % (ColemanLiau))
Flesch = readability.flesch()
sys.stdout.write('Flesch: 0=12th grade, 100=4th grade %f\n' % (Flesch))
Fog = readability.fog()
sys.stdout.write('Fog: grade level: %f\n' % (Fog))
SMOG = readability.smog()
sys.stdout.write('SMOG: years of education needed to comprehend: %f\n' %
(SMOG))
print("\n*** Lexical Diversity ***")
diversity = LexicalDiversity(content)
yulei = diversity.yulei()
sys.stdout.write('Yule I Lexical Diversity: %f\n' % yulei)
word_entropy = diversity.calcWordEntropy()
sys.stdout.write('Word entropy: %f \n' % (word_entropy))
synonym_suggestions = diversity.recommendSynonyms(90, 3)
sys.stdout.write(
'\nHere are some synonyms for frequently occuring words:\n')
for word in synonym_suggestions.keys():
print(word, synonym_suggestions[word])
print("\n*** Description ***")
word_probability = WordProbability(content)
hashtags = word_probability.hashtagSuggestions(99)
sys.stdout.write('Hashtag suggestions %s\n' % hashtags)
tfidf = word_probability.tfidf(5)
print("tfidf: ", tfidf)
entrSyl = diversity.entropySyllable(5)
entrSylWords = [entry[0] for entry in entrSyl]
print("sylEntropy: ", entrSylWords)
summary = word_probability.summary(55)
sys.stdout.write('\nSummary %s\n' % summary)
print("\n*** Search/Plagarism ***")
plagarism = TextSearch()
txt = content
pat = "empowers consumers to take control"
setPat = {"empowers consumers", "a million bank acc", "Contact UsPrivacy "}
plg = plagarism.rabinKarp(setPat, txt)
sys.stdout.write('Rabin-Karp found pattern at %s \n' % str(plg))
#wildSearch = 'tsfd;lkasdi*ghasd'
wildSearch = 'the*est'
#empowers consumers to take control of their financial
#wildSearch = 'empowers c*to take*of their financial'
#wildSearch = 'consumers*take control of their'
wild = plagarism.wildCardSearch(wildSearch, txt)
sys.stdout.write('Wildcard search found %s \n' % str(wild))
print("\n*** Cliche Detection ***")
plagarism.findCliches(content)
class ReadabilityTest(unittest.TestCase):
def setUp(self):
text = """
“On a June day sometime in the early 1990s, encouraged by his friend and fellow economist Jörgen Weibull, Abhijit went swimming in the Baltic. He leaped in and instantly jumped out—he claims that his teeth continued to chatter for the next three days. In 2018, also in June, we went to the Baltic in Stockholm, several hundred miles farther north than the previous encounter. This time it was literally child’s play; our children frolicked in the water.
Wherever we went in Sweden, the unusually warm weather was a topic of conversation. It was probably a portent of something everyone felt, but for the moment it was hard not to be quite delighted with the new opportunities for outdoor life it offered.”.
"""
self.readability = Readability(text)
def test_ari(self):
r = self.readability.ari()
print(r)
self.assertEqual(9.551245421245422, r.score)
self.assertEqual(['10'], r.grade_levels)
self.assertEqual([15, 16], r.ages)
def test_coleman_liau(self):
r = self.readability.coleman_liau()
print(r)
self.assertEqual(10.673162393162393, r.score)
self.assertEqual('11', r.grade_level)
def test_dale_chall(self):
r = self.readability.dale_chall()
print(r)
self.assertEqual(9.32399010989011, r.score)
self.assertEqual(['college'], r.grade_levels)
def test_flesch(self):
r = self.readability.flesch()
print(r)
self.assertEqual(51.039230769230784, r.score)
self.assertEqual(['10', '11', '12'], r.grade_levels)
self.assertEqual('fairly_difficult', r.ease)
def test_flesch_kincaid(self):
r = self.readability.flesch_kincaid()
print(r)
self.assertEqual(10.125531135531137, r.score)
self.assertEqual('10', r.grade_level)
def test_gunning_fog(self):
r = self.readability.gunning_fog()
print(r)
self.assertEqual(12.4976800976801, r.score)
self.assertEqual('12', r.grade_level)
def test_linsear_write(self):
r = self.readability.linsear_write()
print(r)
self.assertEqual(11.214285714285714, r.score)
self.assertEqual('11', r.grade_level)
def test_smog(self):
text = """
“On a June day sometime in the early 1990s, encouraged by his friend and fellow economist Jörgen Weibull, Abhijit went swimming in the Baltic. He leaped in and instantly jumped out—he claims that his teeth continued to chatter for the next three days. In 2018, also in June, we went to the Baltic in Stockholm, several hundred miles farther north than the previous encounter. This time it was literally child’s play; our children frolicked in the water.
Wherever we went in Sweden, the unusually warm weather was a topic of conversation. It was probably a portent of something everyone felt, but for the moment it was hard not to be quite delighted with the new opportunities for outdoor life it offered.”.
"""
text = ' '.join(text for i in range(0, 5))
readability = Readability(text)
#Test SMOG with 30 sentences
r1 = readability.smog()
#Test SMOG with all sentences
r2 = readability.smog(all_sentences=True)
print("all_sentences=False: %s ; all_sentences=True: %s" % (r1, r2))
self.assertEqual(12.516099999999998, r1.score)
self.assertEqual('13', r1.grade_level)
self.assertEqual(12.785403640627713, r2.score)
self.assertEqual('13', r2.grade_level)
def test_spache(self):
r = self.readability.spache()
print(r)
self.assertEqual(7.164945054945054, r.score)
self.assertEqual('7', r.grade_level)
def test_print_stats(self):
stats = self.readability.statistics()
self.assertEqual(562, stats['num_letters'])
self.assertEqual(117, stats['num_words'])
self.assertEqual(7, stats['num_sentences'])
self.assertEqual(20, stats['num_polysyllabic_words'])
class ReadabilityAnalyser:
def __init__(self, text):
self.readability = Readability(text)
self.FLESCH_KINCAID = ['score', 'grade_level']
self.FLESCH_EASE = ['score', 'ease', 'grade_level']
self.DALE_CHALL = ['score', 'grade_level']
self.ARI = ['score', 'grade_level', 'ages']
self.CLI = ['score', 'grade_level']
self.GUNNING_FOG = ['score', 'grade_level']
self.SMOG = ['score', 'grade_level']
self.SPACHE = ['score', 'grade_level']
self.LINSEAR_WRITE = ['score', 'grade_level']
self.values_index = self.initialize_value_index_array()
def initialize_value_index_array(self):
values_index = dict()
values_index["flesch_kincaid"] = self.FLESCH_KINCAID
values_index["flesch_ease"] = self.FLESCH_EASE
values_index["dale_chall"] = self.DALE_CHALL
values_index["ari"] = self.ARI
values_index["cli"] = self.CLI
values_index["gunning_fog"] = self.GUNNING_FOG
values_index["smog_all"] = self.SMOG
values_index["smog"] = self.SMOG
values_index["spache"] = self.SPACHE
values_index["linsear_write"] = self.LINSEAR_WRITE
return values_index
def flesch_kincaid(self, content, error_ignore=True):
try:
record = dict()
fk = self.readability.flesch_kincaid()
record['score'] = fk.score
record['grade_level'] = fk.grade_level
content["flesch_kincaid"] = record
except ReadabilityException as e:
if not error_ignore:
content["flesch_kincaid"] = str(e)
print(e)
def flesch_ease(self, content, error_ignore=True):
try:
record = dict()
flesch_ease = self.readability.flesch()
record['score'] = flesch_ease.score
record['ease'] = flesch_ease.ease
record['grade_levels'] = flesch_ease.grade_levels
content['flesch_ease'] = record
except ReadabilityException as e:
if not error_ignore:
content['flesch_ease'] = str(e)
print(e)
def dale_chall(self, content, error_ignore=True):
try:
record = dict()
dale_chall = self.readability.dale_chall()
record['score'] = dale_chall.score
record['grade_level'] = dale_chall.grade_levels
content['dale_chall'] = record
except ReadabilityException as e:
if not error_ignore:
content['dale_chall'] = str(e)
print(e)
def automated_readability_index(self, content, error_ignore=True):
try:
record = dict()
ari = self.readability.ari()
record['score'] = ari.score
record['grade_level'] = ari.grade_levels
record['ages'] = ari.ages
content['ari'] = record
except ReadabilityException as e:
if not error_ignore:
content['ari'] = str(e)
print(e)
def coleman_liau_index(self, content, error_ignore=True):
try:
record = dict()
coleman_liau = self.readability.coleman_liau()
record['score'] = coleman_liau.score
record['grade_level'] = coleman_liau.grade_level
content['cli'] = record
print(record)
except ReadabilityException as e:
print(e)
if not error_ignore:
content['cli'] = str(e)
print(e)
def gunning_fog_index(self, content, error_ignore=True):
try:
record = dict()
gunning_fog = self.readability.gunning_fog()
record['score'] = gunning_fog.score
record['grade_level'] = gunning_fog.grade_level
content['gunning_fog'] = record
except ReadabilityException as e:
if not error_ignore:
content['gunning_fog'] = str(e)
print(e)
def smog(self, content, all_sentences=False, error_ignore=True):
record = dict()
try:
if all_sentences:
smog = self.readability.smog(all_sentences=all_sentences)
record['score'] = smog.score
record['grade_level'] = smog.grade_level
content['smog_all'] = record
else:
smog = self.readability.smog()
record['score'] = smog.score
record['grade_level'] = smog.grade_level
content['smog'] = record
except ReadabilityException as e:
print(e)
print(error_ignore)
if not error_ignore:
if all_sentences:
content['smog_all'] = str(e)
else:
content['smog'] = str(e)
print(e)
def spache_readability_formula(self, content, error_ignore=True):
try:
record = dict()
spache = self.readability.spache()
record['score'] = spache.score
record['grade_level'] = spache.grade_level
content['spache'] = record
except ReadabilityException as e:
if not error_ignore:
content['spache'] = str(e)
print(e)
def linsear_write(self, content, error_ignore=True):
try:
record = dict()
linsear_write = self.readability.linsear_write()
record['score'] = linsear_write.score
record['grade_level'] = linsear_write.grade_level
content['linsear_write'] = record
except ReadabilityException as e:
if not error_ignore:
content['linsear_write'] = str(e)
print(e)
@staticmethod
def check_readability_from_file(input_json_file, output_json_file):
result = []
json_file = load_as_json(input_json_file)
for record in json_file:
analyser = ReadabilityAnalyser(record['text'])
analysed_file_record = dict()
analysed_file_record['file'] = record['file']
analysed_file_record['category'] = record['category']
analyser.flesch_kincaid(analysed_file_record)
analyser.flesch_ease(analysed_file_record)
analyser.dale_chall(analysed_file_record)
analyser.automated_readability_index(analysed_file_record)
analyser.coleman_liau_index(analysed_file_record)
analyser.gunning_fog_index(analysed_file_record)
analyser.smog(analysed_file_record)
analyser.smog(analysed_file_record, True)
analyser.spache_readability_formula(analysed_file_record)
analyser.linsear_write(analysed_file_record)
result.append(analysed_file_record)
save_as_json(result, output_json_file)
def check_readability(self, use_methods=None, errors_included=True):
result_analysis = dict()
if use_methods is None or 'flesch_kincaid' in use_methods:
self.flesch_kincaid(result_analysis,
error_ignore=not errors_included)
if use_methods is None or 'flesch_ease' in use_methods:
self.flesch_ease(result_analysis, error_ignore=not errors_included)
if use_methods is None or 'dale_chall' in use_methods:
self.dale_chall(result_analysis, error_ignore=not errors_included)
if use_methods is None or 'ari' in use_methods:
self.automated_readability_index(result_analysis,
error_ignore=not errors_included)
if use_methods is None or 'cli' in use_methods:
self.coleman_liau_index(result_analysis,
error_ignore=not errors_included)
if use_methods is None or 'gunning_fog' in use_methods:
self.gunning_fog_index(result_analysis,
error_ignore=not errors_included)
if use_methods is None or 'smog' in use_methods:
self.smog(result_analysis, error_ignore=not errors_included)
if use_methods is None or 'smog_all' in use_methods:
self.smog(result_analysis, True, error_ignore=not errors_included)
if use_methods is None or 'spache' in use_methods:
self.spache_readability_formula(result_analysis,
error_ignore=not errors_included)
if use_methods is None or 'linsear_write' in use_methods:
self.linsear_write(result_analysis,
error_ignore=not errors_included)
return result_analysis
@staticmethod
def initialize_basic_dict(categories, values, process_category=True):
record = dict()
for value in values:
record = ReadabilityAnalyser.initialize_dict(record, value)
if process_category:
for category in categories:
record[category] = ReadabilityAnalyser.initialize_basic_dict(
categories, values, False)
return record
@staticmethod
def initialize_dict(record, value):
record['min_' + value] = 999999999
record['max_' + value] = -999999999
record['sum_' + value] = 0
record['avg_' + value] = 0
record['freq_' + value] = 0
record['skipped_' + value] = 0
return record
def initialize_values(self, statistic, categories):
statistic["flesch_kincaid"] = self.initialize_basic_dict(
categories, self.FLESCH_KINCAID)
statistic["flesch_ease"] = self.initialize_basic_dict(
categories, self.FLESCH_EASE)
statistic["dale_chall"] = self.initialize_basic_dict(
categories, self.DALE_CHALL)
statistic["ari"] = self.initialize_basic_dict(categories, self.ARI)
statistic["cli"] = self.initialize_basic_dict(categories, self.CLI)
statistic["gunning_fog"] = self.initialize_basic_dict(
categories, self.GUNNING_FOG)
statistic["smog_all"] = self.initialize_basic_dict(
categories, self.SMOG)
statistic["smog"] = self.initialize_basic_dict(categories, self.SMOG)
statistic["spache"] = self.initialize_basic_dict(
categories, self.SPACHE)
statistic["linsear_write"] = self.initialize_basic_dict(
categories, self.LINSEAR_WRITE)
statistic['indexes'] = [
"flesch_kincaid", "flesch_ease", "dale_chall", "ari", "cli",
"gunning_fog", "smog_all", "smog", "spache", "linsear_write"
]
statistic['categories'] = categories
@staticmethod
def fill_min_max_sum_category(index, value_index, statistics,
readability_index, category):
if index[value_index] < statistics[readability_index][category][
'min_' + value_index]:
statistics[readability_index][category][
'min_' + value_index] = index[value_index]
if index[value_index] > statistics[readability_index][category][
'max_' + value_index]:
statistics[readability_index][category][
'max_' + value_index] = index[value_index]
statistics[readability_index][category]['sum_' + value_index] = \
statistics[readability_index][category]['sum_' + value_index] + index[value_index]
@staticmethod
def fill_min_max_sum_category_value(value, value_index, statistics,
readability_index, category):
if value < statistics[readability_index][category]['min_' +
value_index]:
statistics[readability_index][category]['min_' +
value_index] = value
if value > statistics[readability_index][category]['max_' +
value_index]:
statistics[readability_index][category]['max_' +
value_index] = value
statistics[readability_index][category]['sum_' + value_index] = \
statistics[readability_index][category]['sum_' + value_index] + value
@staticmethod
def fill_min_max_sum(index, value_index, statistics, readability_index):
if index[value_index] < statistics[readability_index]['min_' +
value_index]:
statistics[readability_index]['min_' +
value_index] = index[value_index]
if index[value_index] > statistics[readability_index]['max_' +
value_index]:
statistics[readability_index]['max_' +
value_index] = index[value_index]
statistics[readability_index]['sum_' + value_index] = \
statistics[readability_index]['sum_' + value_index] + index[value_index]
@staticmethod
def fill_min_max_sum_value(value, value_index, statistics,
readability_index):
if value < statistics[readability_index]['min_' + value_index]:
statistics[readability_index]['min_' + value_index] = value
if value > statistics[readability_index]['max_' + value_index]:
statistics[readability_index]['max_' + value_index] = value
statistics[readability_index]['sum_' + value_index] = \
statistics[readability_index]['sum_' + value_index] + value
@staticmethod
def cast_to_float(value):
try:
return float(value)
except ValueError:
return None
except TypeError:
return None
def record_analysis(self, record, statistics):
for readability_index in statistics['indexes']:
if 'category' in record:
category = record['category']
if readability_index in record:
index = record[readability_index]
for value_index in self.values_index[readability_index]:
if value_index in index:
obtained_value = ReadabilityAnalyser.cast_to_float(
index[value_index])
if obtained_value is not None:
index[value_index] = obtained_value
ReadabilityAnalyser.fill_min_max_sum_category(
index, value_index, statistics,
readability_index, category)
if 'freq_' + value_index not in statistics[
readability_index][category]:
statistics[readability_index][category][
'freq_' + value_index] = 0
statistics[readability_index][category]['freq_' + value_index] = \
statistics[readability_index][category]['freq_' + value_index] + 1
elif isinstance(index[value_index], list):
for rec in index[value_index]:
if value_index not in statistics[
readability_index][category]:
statistics[readability_index][
category][value_index] = dict()
if isinstance(rec, str):
if 'freq_' + rec not in statistics[
readability_index][category][
value_index]:
statistics[readability_index][
category][value_index]['freq_'
+
rec] = 0
statistics[readability_index][category][value_index]['freq_' + rec] = \
statistics[readability_index][category][value_index]['freq_' + rec] + 1
else:
ReadabilityAnalyser.fill_min_max_sum_category_value(
rec, value_index, statistics,
readability_index, category)
if 'freq_' + value_index not in \
statistics[readability_index][category][value_index]:
statistics[readability_index][
category]['freq_' +
value_index] = 0
statistics[readability_index][category]['freq_' + value_index] = \
statistics[readability_index][category]['freq_' + value_index] + 1
elif isinstance(index[value_index], str):
rec = index[value_index]
if value_index not in statistics[
readability_index][category]:
statistics[readability_index][category][
value_index] = dict()
if 'freq_' + rec not in statistics[
readability_index][category][
value_index]:
statistics[readability_index][category][
value_index]['freq_' + rec] = 0
statistics[readability_index][category][value_index]['freq_' + rec] = \
statistics[readability_index][category][value_index]['freq_' + rec] + 1
else:
print("Uncategorized: " +
str(index[value_index]))
statistics[readability_index][category]['freq_' + value_index] = \
statistics[readability_index][category]['freq_' + value_index] + 1
else:
statistics[readability_index][category]['skipped_' + value_index] = \
statistics[readability_index][category]['skipped_' + value_index] + 1
else:
for value_index in self.values_index[readability_index]:
statistics[readability_index][category]['skipped_' + value_index] = \
statistics[readability_index][category]['skipped_' + value_index] + 1
else:
print("THIS: " + record)
if readability_index in record:
index = record[readability_index]
for value_index in self.values_index[readability_index]:
if value_index in index:
obtained_value = ReadabilityAnalyser.cast_to_float(
index[value_index])
if obtained_value is not None:
index[value_index] = float(index[value_index])
ReadabilityAnalyser.fill_min_max_sum(
index, value_index, statistics,
readability_index)
if 'freq_' + value_index not in statistics[
readability_index]:
statistics[readability_index]['freq_' +
value_index] = 0
statistics[readability_index]['freq_' + value_index] = \
statistics[readability_index]['freq_' + value_index] + 1
elif isinstance(index[value_index], list):
for rec in index[value_index]:
if value_index not in statistics[
readability_index]:
statistics[readability_index][
value_index] = dict()
if isinstance(rec, str):
# print(value_index + " " + str(index[value_index]))
if 'freq_' + rec not in statistics[
readability_index][value_index]:
statistics[readability_index][
value_index]['freq_' + rec] = 0
statistics[readability_index][value_index]['freq_' + rec] = \
statistics[readability_index][value_index]['freq_' + rec] + 1
else:
ReadabilityAnalyser.fill_min_max_sum_value(
rec, value_index, statistics,
readability_index)
if 'freq_' + value_index not in statistics[
readability_index][value_index]:
statistics[readability_index][
'freq_' + value_index] = 0
statistics[readability_index]['freq_' + value_index] = \
statistics[readability_index]['freq_' + value_index] + 1
elif isinstance(index[value_index], str):
rec = index[value_index]
if value_index not in statistics[
readability_index]:
statistics[readability_index][
value_index] = dict()
if 'freq_' + rec not in statistics[
readability_index][value_index]:
statistics[readability_index][value_index][
'freq_' + rec] = 0
statistics[readability_index][value_index]['freq_' + rec] = \
statistics[readability_index][value_index]['freq_' + rec] + 1
else:
print("Uncategorized: " + str(index[value_index]))
statistics[readability_index]['freq_' + value_index] = \
statistics[readability_index]['freq_' + value_index] + 1
else:
statistics[readability_index]['skipped_' + value_index] = \
statistics[readability_index]['skipped_' + value_index] + 1
else:
for value_index in self.values_index[readability_index]:
statistics[readability_index]['skipped_' + value_index] = \
statistics[readability_index]['skipped_' + value_index] + 1
def count_average(self, statistics):
for readability_index in statistics['indexes']:
for value_index in self.values_index[readability_index]:
if statistics[readability_index]['sum_' + value_index] != 0:
statistics[readability_index]['avg_' + value_index] = \
statistics[readability_index]['sum_' + value_index] / statistics[readability_index][
'freq_' + value_index]
else:
statistics[readability_index]['sum_' + value_index] = 0
for category in statistics['categories']:
if statistics[readability_index][category][
'sum_' + value_index] != 0:
statistics[readability_index][category]['avg_' + value_index] = \
statistics[readability_index][category]['sum_' + value_index] / \
statistics[readability_index][category]['freq_' + value_index]
else:
statistics[readability_index][category][
'sum_' + value_index] = 0
def analyse_readability_file(self, readability_file, categories):
statistic = dict()
self.initialize_values(statistic, categories)
file = load_as_json(readability_file)
for record in file:
self.record_analysis(record, statistic)
self.count_average(statistic)
return statistic
def analyse_readability_file_save_results(self, readability_file,
output_statistics_file,
categories):
statistics = self.analyse_readability_file(readability_file,
categories)
save_as_json(statistics, output_statistics_file)
to lay thee out upon the couch , and make
the wonder plain , and i blang and rear
and strange the love of all the war the stream
when the goddest from the shill belied
for heart of starchous and his warrall
and lack the must of the strange of love
the shall pare , the far should was every
where the world spoke the storn she parts
who faither paunts parture let the last of streams
and art his was a wings of love and dead
for strength and men world of the pressing
love god the scorn , and will with the store
and sleep , while chose with stare while our change
and the long which strand , for the glorious bear.'''
r = Readability(text)
fk = r.flesch_kincaid()
fkk = r.flesch()
print("Score: "fk.score)
print("Grade Level: "fk.grade_level)
#30-50 score ensures :
#difficult to read, best understood by college graduates
#so this ensures sonnet readebality.
#(source: https://yoast.com/flesch-reading-ease-score/ )
l_gunning_fog = []
l_coleman_liau = []
l_dale_chall = []
l_ari = []
l_linsear_write = []
l_spache = []
l_flesch_ease = []
for i in os.listdir(PATH):
if not i.startswith('.'):
if i not in l_not_use:
with open(PATH + i, 'r') as f:
text = f.read()
r = Readability(clean(text))
s1 = r.flesch_kincaid()
s2 = r.flesch()
s3 = r.gunning_fog()
s4 = r.coleman_liau()
s5 = r.dale_chall()
s6 = r.ari()
s7 = r.linsear_write()
# r.smog()
s8 = r.spache()
l_flesch_kincaid.append(s1.score)
l_flesch.append(s2.score)
l_flesch_ease.append(s2.ease)
l_gunning_fog.append(s3.score)
l_coleman_liau.append(s4.score)
l_dale_chall.append(s5.score)
l_ari.append(s6.score)
l_linsear_write.append(s7.score)
