def download(resource, article):
article_text = download_article(article['url'])
if article['title'] != None and article_text != None:
print(article['url'])
print(textstat.automated_readability_index(article_text))
norm_score = int(
textstat.automated_readability_index(article_text) / 15 * 100)
vote = 0
req = requests.get('http://localhost:3000/posts?title=' +
article['title'])
if len(req.json()) is 0:
res = requests.post('http://localhost:3000/posts',
data={
'title': article['title'],
'vote': 0
})
else:
vote = req.json()[0]['vote']
if norm_score < 65:
easiness = "easy"
s = 1
elif norm_score < 75:
easiness = "easy_medium"
s = 2
elif norm_score < 85:
easiness = 'medium'
s = 3
elif norm_score < 95:
easiness = "medium_diff"
s = 4
else:
easiness = "difficult"
s = 5
date = article['publishedAt'].split('T')[0].replace(" ", "")
if article['urlToImage'] != '':
return {
'score': "X " + str(s),
'resource': resource.upper().replace("-",
" ").replace("THE", ""),
'title': article['title'],
'url': article['url'],
'img': article['urlToImage'],
'snippet': article['description'],
'easiness': easiness,
'date': date,
'vote': vote
}
def text_analytics(text):
if textstat.sentence_count(text) != 0:
lexicon = textstat.lexicon_count(text) #word count
sent = textstat.sentence_count(text) #sentence count
syll = textstat.syllable_count(text) #syllable count
flesch = textstat.flesch_reading_ease(text) #flesch score
smog = textstat.smog_index(text) #SMOG index
fog = textstat.gunning_fog(text) #FOG index
dale = textstat.dale_chall_readability_score(text) #grade level
ari = textstat.automated_readability_index(text) #grade level
cl = textstat.coleman_liau_index(text) #grade level
flesch1 = lexicon*flesch
flesch2 = sent*flesch
flesch3 = syll*flesch
smog1 = lexicon*smog
smog2 = sent*smog
smog3 = syll*smog
fog1 = lexicon*fog
fog2 = sent*fog
fog3 = syll*fog
dale1 = lexicon*dale
dale2 = sent*dale
dale3=syll*dale
ari1 = lexicon*ari
ari2 = sent*ari
ari3 = syll*ari
cl1 = lexicon*cl
cl2 = sent*cl
cl3 = syll*cl
x=[lexicon,sent,syll,flesch,smog,fog,dale,ari,cl,flesch1,flesch2,flesch3,smog1, smog2,smog3,fog1,fog2,fog3,dale1,dale2,dale3,ari1,ari2,ari3,cl1,cl2,cl3]
return(x)
def get_readability(df2):
df = df2.copy()
text_feats = df.select_dtypes(include=['object']).columns.values
for i, col in enumerate(text_feats):
df['flesch_reading_ease{}'.format(i)] = df[col].apply(
lambda x: textstat.flesch_reading_ease(x))
df['smog_index{}'.format(i)] = df[col].apply(
lambda x: textstat.smog_index(x))
df['flesch_kincaid_grade{}'.format(i)] = df[col].apply(
lambda x: textstat.flesch_kincaid_grade(x))
df['coleman_liau_index{}'.format(i)] = df[col].apply(
lambda x: textstat.coleman_liau_index(x))
df['automated_readability_index{}'.format(i)] = df[col].apply(
lambda x: textstat.automated_readability_index(x))
df['dale_chall_readability_score{}'.format(i)] = df[col].apply(
lambda x: textstat.dale_chall_readability_score(x))
df['difficult_words{}'.format(i)] = df[col].apply(
lambda x: textstat.difficult_words(x))
df['linsear_write_formula{}'.format(i)] = df[col].apply(
lambda x: textstat.linsear_write_formula(x))
df['gunning_fog{}'.format(i)] = df[col].apply(
lambda x: textstat.gunning_fog(x))
df['text_standard{}'.format(i)] = df[col].apply(
lambda x: textstat.text_standard(x))
return df
def readability(text):
print("Readability\n=================================\n\n")
print("Flesch Reading Ease\n________________________\n\n")
print str(textstat.flesch_reading_ease(text)) + "\n"
print("Smog Index\n________________________\n\n")
print str(textstat.smog_index(text)) + "\n"
print("Flesch Kincaid Grade\n________________________\n\n")
print str(textstat.flesch_kincaid_grade(text)) + "\n"
print("Coleman Liau Index\n________________________\n\n")
print str(textstat.coleman_liau_index(text)) + "\n"
print("ARI\n________________________\n\n")
print str(textstat.automated_readability_index(text)) + "\n"
print("Dale Chall\n________________________\n\n")
print str(textstat.dale_chall_readability_score(text)) + "\n"
print("Difficult Words\n________________________\n\n")
print str(textstat.difficult_words(text)) + "\n"
print("Linsear Write Formula\n________________________\n\n")
print str(textstat.linsear_write_formula(text)) + "\n"
print("Gunning Fog\n________________________\n\n")
print str(textstat.gunning_fog(text)) + "\n"
print "Compiled Score\n_____________________________\n\n"
print str(textstat.text_standard(text)) + "\n"
return len(adjectives)
def _get_reading_stats(no_code_text):
"""
Returns reading level information
:param no_code_text: String to analyse
:return: list of details
"""
group_by = 'Reading Level Analysis '
results = []
results.append(TextFeature('Flesch Reading Ease', textstat.flesch_reading_ease(no_code_text), group_by)) # higher is better, scale 0 to 100
results.append(TextFeature('Flesch-Kincaid Grade Level', textstat.flesch_kincaid_grade(no_code_text), group_by))
try:
results.append(TextFeature('The Fog Scale (Gunning FOG formula)', textstat.gunning_fog(no_code_text), group_by))
except IndexError: # Not sure why, but this test throws this error sometimes
results.append(TextFeature('The Fog Scale (Gunning FOG formula)', "Undetermined", group_by))
try:
results.append(TextFeature('The SMOG Index', textstat.smog_index(no_code_text), group_by))
except IndexError: # Not sure why, but this test throws this error sometimes
results.append(TextFeature('The SMOG Index', "Undetermined", group_by))
results.append(TextFeature('Automated Readability Index', textstat.automated_readability_index(no_code_text), group_by))
results.append(TextFeature('The Coleman-Liau Index', textstat.coleman_liau_index(no_code_text), group_by))
try:
results.append(TextFeature('Linsear Write Formula', textstat.linsear_write_formula(no_code_text), group_by))
except IndexError:
results.append(TextFeature('Linsear Write Formula', "Undetermined", group_by))
try:
results.append(TextFeature('Dale Chall Readability Score', textstat.dale_chall_readability_score(no_code_text), group_by))
except IndexError: # Not sure why, but this test throws this error sometimes
results.append(TextFeature('Dale Chall Readability Score', "Undetermined", group_by))
try:
results.append(TextFeature('Readability Consensus', textstat.readability_consensus(no_code_text), group_by))
except (TypeError, IndexError):
results.append(TextFeature('Readability Consensus', "Undetermined; One of the tests above failed.", group_by))
return results
def do_text_stats(self, text):
### Syllable Count
syllable_count = textstat.syllable_count(text)
### Lexicon Count
lexicon_count = textstat.lexicon_count(text, True)
### Sentence Count
sentence_count = textstat.sentence_count(text)
### The Flesch Reading Ease formula
try:
flesch_reading_ease = textstat.flesch_reading_ease(text)
except TypeError as e:
flesch_reading_ease = None
#* 90-100 : Very Easy
#* 80-89 : Easy
#* 70-79 : Fairly Easy
#* 60-69 : Standard
#* 50-59 : Fairly Difficult
#* 30-49 : Difficult
#* 0-29 : Very Confusing
### The The Flesch-Kincaid Grade Level
try:
flesch_kincaid_grade = textstat.flesch_kincaid_grade(text)
except TypeError as e:
flesch_kincaid_grade = None
## The Fog Scale (Gunning FOG Formula)
gunning_fog = textstat.gunning_fog(text)
### The SMOG Index
smog_index = textstat.smog_index(text)
### Automated Readability Index
automated_readability_index = textstat.automated_readability_index(
text)
### The Coleman-Liau Index
try:
coleman_liau_index = textstat.coleman_liau_index(text)
except TypeError as e:
coleman_liau_index = None
### Linsear Write Formula
linsear_write_formula = textstat.linsear_write_formula(text)
### Dale-Chall Readability Score
dale_chall_readability_score = textstat.dale_chall_readability_score(
text)
### Readability Consensus based upon all the above tests
try:
text_standard = textstat.text_standard(text)
except TypeError as e:
text_standard = None
return {
"syllable_count": syllable_count,
"lexicon_count": lexicon_count,
"sentence_count": sentence_count,
"flesch_reading_ease": flesch_reading_ease,
"flesch_kincaid_grade": flesch_kincaid_grade,
"gunning_fog": gunning_fog,
"smog_index": smog_index,
"automated_readability_index": automated_readability_index,
"coleman_liau_index": coleman_liau_index,
"linsear_write_formula": linsear_write_formula,
"dale_chall_readability_score": dale_chall_readability_score,
"text_standard": text_standard
}
def _calculate_scores(self, docs):
docs_scores = []
for doc in docs:
scores = {}
scores['chars'] = ts.char_count(doc)
scores['words'] = ts.lexicon_count(doc)
scores['sents'] = ts.sentence_count(doc)
#scores['syllables'] = ts.syllable_count(doc)
scores['avg_sent_length'] = ts.avg_sentence_length(doc)
scores['avg_syllables_per_word'] = ts.avg_syllables_per_word(doc)
scores['avg_letters_per_word'] = ts.avg_letter_per_word(doc)
scores['flesch'] = ts.flesch_reading_ease(doc)
#scores['smog'] = ts.smog_index(doc)
#scores['coleman_liau'] = ts.coleman_liau_index(doc)
scores['automated_readability'] = ts.automated_readability_index(
doc)
#scores['linsear'] = ts.linsear_write_formula(doc)
#scores['difficult_words'] = ts.difficult_words(doc)
scores['dale_chall'] = ts.dale_chall_readability_score(doc)
#scores['gunning_fog'] = ts.gunning_fog(doc)
scores['lix'] = ts.lix(doc)
docs_scores.append(scores)
return docs_scores
def automated_readability_index(text):
"""
:type text: Text
:param text: The text to be analysed
:rtype float
:returns Automated readability index
"""
return textstat.automated_readability_index(text.text)
def vecify(v):
return [ts.flesch_reading_ease(v),
# ts.smog_index(v),
ts.flesch_kincaid_grade(v),
ts.coleman_liau_index(v),
ts.automated_readability_index(v),
ts.dale_chall_readability_score(v),
ts.difficult_words(v),
ts.linsear_write_formula(v),
ts.gunning_fog(v)]
def all_trad_scores(text):
fre = textstat.flesch_reading_ease(text)
fkg = textstat.flesch_kincaid_grade(text)
smog = textstat.smog_index(text)
cole = textstat.coleman_liau_index(text)
ari = textstat.automated_readability_index(text)
dale = textstat.dale_chall_readability_score(text)
linsear = textstat.linsear_write_formula(text)
gunning = textstat.gunning_fog(text)
return [fre, fkg, smog, cole, ari, dale, linsear, gunning]
def reading_difficulty(self):
diff_words = textstat.difficult_words(self.text) / self.nword
flesch_kincaid = textstat.flesch_kincaid_grade(self.text)
coleman_liau = textstat.coleman_liau_index(self.text)
ari = textstat.automated_readability_index(self.text)
dale_chall = textstat.dale_chall_readability_score(self.text)
linsear = textstat.linsear_write_formula(self.text)
gunning_fog = textstat.gunning_fog(self.text) - 6
smog = textstat.smog_index(self.text)
avg_grade = max(
math.ceil((flesch_kincaid + coleman_liau + ari + dale_chall +
linsear + gunning_fog + smog) / 7), 12)
return avg_grade, diff_words
def textstat_analysis(profile_text):
fre = textstat.flesch_reading_ease(profile_text)
smog = textstat.smog_index(profile_text)
fkg = textstat.flesch_kincaid_grade(profile_text)
coleman = textstat.coleman_liau_index(profile_text)
ari = textstat.automated_readability_index(profile_text)
dale = textstat.dale_chall_readability_score(profile_text)
dw = textstat.difficult_words(profile_text)
lwf = textstat.linsear_write_formula(profile_text)
gf = textstat.gunning_fog(profile_text)
rc = textstat.readability_consensus(profile_text)
word_count = textstat.lexicon_count(profile_text)
return (fre, smog, fkg, coleman, ari, dale, dw, lwf, gf, rc, word_count)
def d():
resp = table.scan(FilterExpression=Attr("fips").exists())
sorted_by_fips = {}
sorted_by_fips['items'] = []
for item in resp['Items']:
concat = " ".join(item['tweet'])
polarity = textstat.automated_readability_index(concat)
sorted_by_fips['items'].append({
'id': str(item['fips']),
'rate': polarity
})
return json.dumps(sorted_by_fips)
def get_readability(contents):
readability = []
readability.append(textstat.flesch_reading_ease(contents))
readability.append(textstat.smog_index(contents))
readability.append(textstat.flesch_kincaid_grade(contents))
readability.append(textstat.automated_readability_index(contents))
readability.append(textstat.dale_chall_readability_score(contents))
readability.append(textstat.difficult_words(contents))
readability.append(textstat.linsear_write_formula(contents))
readability.append(textstat.gunning_fog(contents))
readability.append(textstat.coleman_liau_index(contents))
readability.append(textstat.text_standard(contents))
return readability
def analyze_one(self, email):
""" Analyzes a single email and stores results. """
sents = tstat.sentence_count(email)
self.sent_count.append(sents if sents > 0 else 1)
if email and len(email) > 0:
self.flesch_kincaid_grade.append(tstat.flesch_kincaid_grade(email))
self.automated_readability_index.append(
tstat.automated_readability_index(email))
self.coleman_liau_index.append(tstat.coleman_liau_index(email))
self.linsear_write_formula.append(
tstat.linsear_write_formula(email))
self.dale_chall_readability_score.append(
tstat.dale_chall_readability_score(email))
def main() :
for arg in sys.argv[1:]:
with open(arg) as f:
text = f.read()
with open(arg + '.readability.snip','w') as f:
f.write ("syllable_count : %s\n" % textstat.syllable_count(text))
f.write ("lexicon_count : %s\n" % textstat.lexicon_count(text))
f.write ("sentence_count : %s\n" % textstat.sentence_count(text))
f.write ("difficult_words : %s\n" % textstat.difficult_words(text))
f.write ("flesch_reading_ease : %s\n" % textstat.flesch_reading_ease(text))
f.write ("flesch_kincaid_grade : %s\n" % textstat.flesch_kincaid_grade(text))
f.write ("smog_index : %s\n" % textstat.smog_index(text))
f.write ("automated_readability_index : %s\n" % textstat.automated_readability_index(text))
f.write ("coleman_liau_index : %s\n" % textstat.coleman_liau_index(text))
f.write ("linsear_write_formula : %s\n" % textstat.linsear_write_formula(text))
f.write ("dale_chall_readability_score : %s\n" % textstat.dale_chall_readability_score(text))
def analyse_readbility(self, issue):
"""TODO: Docstring for analyse_readbility.
:issue: TODO
:returns: TODO
"""
# Não realiza análise para uma issue sem 'body'
# if not issue.body:
# message = ' - [ ] To improve the readability of the text.\n'
# return (None, message)
gfm = GithubMarkdown(issue.body)
str_markdown = gfm.parse(issue.body)
str_text = self.markdown_to_text(str_markdown)
dic_test_readbility = dict()
if not issue.body:
message = (" - [ ] To improve the text in issue body.\n")
dic_test_readbility['flesch'] = -1
dic_test_readbility['ari'] = 100
dic_test_readbility['dale-chall'] = 100
return (dic_test_readbility, message)
# Analisando a métrica Flesch Reading Ease Score
score_flesch = textstat.flesch_reading_ease(str_text)
dic_test_readbility['flesch'] = score_flesch
# Analisando com o teste Automated Readability Index (ARI)
score_ari = textstat.automated_readability_index(str_text)
dic_test_readbility['ari'] = score_ari
# Analisando com o teste Dale-Chall Readbility Score
score_dale_chal = textstat.dale_chall_readability_score(str_text)
dic_test_readbility['dale-chall'] = score_dale_chal
if not issue.body:
message = (" - [ ] To improve the text in issue body.\n")
return (dic_test_readbility, message)
if self._has_low_readbility(dic_test_readbility):
message = ' - [ ] To improve the readability of the text.\n'
else:
message = None
return (dic_test_readbility, message)
def run_textstat(text):
#text = """Playing games has always been thought to be important to the development of well-balanced and creative children; however, what part, if any, they should play in the lives of adults has never been researched that deeply. I believe that playing games is every bit as important for adults as for children. Not only is taking time out to play games with our children and other adults valuable to building interpersonal relationships but is also a wonderful way to release built up tension."""
ts_flesch_reading_ease = textstat.flesch_reading_ease(text)
ts_smog_index = textstat.smog_index(text)
ts_flesch_kincaid_grade = textstat.flesch_kincaid_grade(text)
ts_coleman_liau_index = textstat.coleman_liau_index(text)
ts_automated_readability_index = textstat.automated_readability_index(text)
ts_dale_chall_readability_score = textstat.dale_chall_readability_score(
text)
ts_difficult_words = textstat.difficult_words(text)
ts_linsear_write_formula = textstat.linsear_write_formula(text)
ts_gunning_fog = textstat.gunning_fog(text)
ts_text_standard = textstat.text_standard(text)
return (ts_flesch_reading_ease, ts_smog_index, ts_flesch_kincaid_grade,
ts_coleman_liau_index, ts_automated_readability_index,
ts_dale_chall_readability_score, ts_difficult_words,
ts_linsear_write_formula, ts_gunning_fog, ts_text_standard)
def predict_readability_level(text):
#convert text from a list to data frame
data = pd.DataFrame([text])
#create an empty data frame for features
df = pd.DataFrame()
#get text features for all rows in data
df[['commas_number' , 'pronouns_number' , 'modal_verbs_number' , \
'personal_pronouns_number' , 'wh_pronouns_number' , 'function_words_number' , \
'VB_tags_number' , 'VBD_tags_number' , 'VBG_tags_number' , 'VBN_tags_number' , \
'VBP_tags_number' , 'nouns_number' , 'proper_nouns_number' , 'conjunctions_number' , \
'adjectives_number' , 'non_modal_verbs_number' , 'interjections_number' , \
'adverbs_number' , 'determiners_number' ]] \
= data[0].apply(lambda x:pd.Series(text_features(x)))
#calculate all readability equations for all rows in data
df["Flesch_Reading_Ease_score"] = data[0].apply(lambda x:flesch_reading_ease(x))
df["Flesch_Kincaid_Grade_Level"] = data[0].apply(lambda x:textstat.flesch_kincaid_grade(x))
df["Fog_Scale"] = data[0].apply(lambda x:gunning_fog(x))
df["SMOG_Index"] = data[0].apply(lambda x:smog_index(x))
df["Automated_Readability_Index"] = data[0].apply(lambda x:textstat.automated_readability_index(x))
df["Coleman_Liau_Index"] = data[0].apply(lambda x:textstat.coleman_liau_index(x))
df["Linsear_Write_Formula"] = data[0].apply(lambda x:textstat.linsear_write_formula(x))
df["Dale_Chall_Readability_Score"] = data[0].apply(lambda x:dale_chall_readability_score(x))
#get text parameters used in readability equations for all rows in data
df[['Word_count' , 'Sentence_count' , 'Average_Sentence_length' , \
'Syllable_Count' , 'Average_syllables_per_words' , 'poly_syllable_count' , \
'Lexical_Count' , 'average_poly_syllable' , 'long_word' , 'average_long_word' , \
'average_word_length']] = data[0].apply(lambda x:pd.Series(text_param(x)))
#Drop bad featurs
df = df.drop('long_word',axis=1)
df = df.drop('average_long_word',axis=1)
#Load readability model for predition
Readability_model=load_pkl("Readability_model.pkl")
#Use model to predict the right class based on features
result = Readability_model.predict(df)
#return the result
return str(result[0])
def automated_readability_index(text):
score = textstat.automated_readability_index(text)
level = 0
if 0 < score < 6:
level = 1
elif 6 <= score < 8:
level = 2
elif 8 <= score < 10:
level = 3
elif 10 <= score < 11:
level = 4
elif 11 <= score < 12:
level = 5
elif 12 <= score < 13:
level = 6
elif 13 <= score:
level = 7
return level
def analyze2(text):
# Automatically reject if no input
if text.isspace():
return -1.0
if text.startswith('http'):
return -1.0
# Analyze text
try:
x = textstat.automated_readability_index(text)
except:
return -1.0
# Keep outputs valid
if not isinstance(x, float):
return -1.0
if x < 0:
return -1.0
return x
def get_feat_readability_metrics(self):
# https://github.com/shivam5992/textstat
try:
test_data = self.webscrap.get_body()
out = []
out.append(textstat.flesch_reading_ease(test_data))
out.append(textstat.smog_index(test_data))
out.append(textstat.flesch_kincaid_grade(test_data))
out.append(textstat.coleman_liau_index(test_data))
out.append(textstat.automated_readability_index(test_data))
out.append(textstat.dale_chall_readability_score(test_data))
out.append(textstat.difficult_words(test_data))
out.append(textstat.linsear_write_formula(test_data))
out.append(textstat.gunning_fog(test_data))
#out.append(textstat.text_standard(test_data))
return out, False
except Exception as e:
config.logger.error(repr(e))
return MISSING_FEATURE * 9, True
def lambda_handler(event, context):
text = event['text']
response = {}
response['flesch_reading_ease'] = textstat.flesch_reading_ease(text)
response['smog_index'] = textstat.smog_index(text)
response['flesch_kincaid_grade'] = textstat.flesch_kincaid_grade(text)
response['coleman_liau_index'] = textstat.coleman_liau_index(text)
response[
'automated_readability_index'] = textstat.automated_readability_index(
text)
response[
'dale_chall_readability_score'] = textstat.dale_chall_readability_score(
text)
response['difficult_words'] = textstat.difficult_words(text)
response['linsear_write_formula'] = textstat.linsear_write_formula(text)
response['gunning_fog'] = textstat.gunning_fog(text)
response['text_standard'] = textstat.text_standard(text)
return respond(None, response)
def getFeatures(files):
allStructuralLex = []
allFileData = []
allScores = []
allFres = []
allAri = []
df = files
rowNum = df.shape[0]
for i in range(rowNum):
structural_lex = []
review = (df.iloc[i].reviewText).strip().split()
summary = (df.iloc[i].summary).strip().split()
row_data = np.append(review, summary)
score = float(df.iloc[i].overall)
fres = textstat.flesch_reading_ease(str(row_data))
lor = lengthOfReview(str(row_data))
sc = sentenceCount(str(row_data))
cc = charCount(str(row_data))
acc = allCapCount(str(row_data))
qc = questionCount(str(row_data))
bg = bigramCount(str(row_data))
ari = textstat.automated_readability_index(str(row_data))
review = [element.lower() for element in review]
structural_lex.append(lor)
structural_lex.append(sc)
structural_lex.append(cc)
structural_lex.append(acc)
structural_lex.append(qc)
structural_lex.append(bg)
allFileData.append(review)
allScores.append(score)
allFres.append(fres)
allAri.append(ari)
allStructuralLex.append(structural_lex)
return allFileData, allStructuralLex, allScores, allFres, allAri
def feature_readability(essay):
syllable_count = textstat.syllable_count(essay)
#音节数统计
flesch_reading_ease = textstat.flesch_reading_ease(essay)
#文档的易读性0-100之间的分数
smog_index = textstat.smog_index(essay)
#烟雾指数，反映文档的易读程度，更精确，更容易计算
flesch_kincaid_index = textstat.flesch_kincaid_grade(essay)
#等级分数，年级等级
coleman_liau_index = textstat.coleman_liau_index(essay)
#返回文本的年级级别
automated_readability_index = textstat.automated_readability_index(essay)
#自动可读性指数，接近理解文本需要的年级
dale_chall_readability_score = textstat.dale_chall_readability_score(essay)
#返回年级级别，使用最常见的英文单词
difficult_words = textstat.difficult_words(essay)
linsear_write_formula = textstat.linsear_write_formula(essay)
#返回文本的年级级别
gunning_fog = textstat.gunning_fog(essay)
#迷雾指数， 反映文本的阅读难度
return syllable_count, flesch_reading_ease, smog_index, flesch_kincaid_index, coleman_liau_index, automated_readability_index, dale_chall_readability_score, difficult_words, linsear_write_formula, gunning_fog
def analyseText():
values = request.get_json()
required = [ 'inputText' ]
if not all(k in values for k in required):
return 'Missing values', 400
text = values['inputText']
result = {
'syllable_count': textstat.syllable_count(text),
'lexicon_count': textstat.lexicon_count(text),
'sentence_count': textstat.sentence_count(text),
'flesch_reading_ease': textstat.flesch_reading_ease(text),
'flesch_kincaid_grade': textstat.flesch_kincaid_grade(text),
'gunning_fog': textstat.gunning_fog(text),
'smog_index': textstat.smog_index(text),
'automated_readability_index': textstat.automated_readability_index(text),
'coleman_liau_index': textstat.coleman_liau_index(text),
'linsear_write_formula': textstat.linsear_write_formula(text),
'dale_chall_readability_score': textstat.dale_chall_readability_score(text)
};
return jsonify(result), 200
def calculate_readability_measures(id):
""" Count the words in doc and update the document. """
es = elasticsearch.Elasticsearch()
source = es.get_source(index='beek', doc_type='page', id=id)
# count = len(source['content'].split())
try:
measures = {
'flesch':
textstat.flesch_reading_ease(source['content']),
'smog':
textstat.smog_index(source['content']),
'flesch_kincaid':
textstat.flesch_kincaid_grade(source['content']),
'coleman_liau':
textstat.coleman_liau_index(source['content']),
'readability':
textstat.automated_readability_index(source['content']),
'dale_chall':
textstat.dale_chall_readability_score(source['content']),
'difficult_words':
textstat.difficult_words(source['content']),
'linsear_write_formula':
textstat.linsear_write_formula(source['content']),
'gunning_fog':
textstat.gunning_fog(source['content']),
'consensus':
textstat.readability_consensus(source['content']),
}
es.update(index='beek',
doc_type='page',
id=id,
body={'doc': {
'measures': measures
}},
refresh=True)
except Exception as err:
pass
def getContext(files):
allFileData = []
allScores = []
allFres = []
allAri = []
df = files
rowNum = df.shape[0]
for i in range(rowNum):
review = (df.iloc[i].reviewText).strip().split()
summary = (df.iloc[i].summary).strip().split()
row_data = np.append(review, summary)
score = float(df.iloc[i].overall)
fres = textstat.flesch_reading_ease(str(row_data))
ari = textstat.automated_readability_index(str(row_data))
review = [element.lower() for element in review]
allFileData.append(review)
allScores.append(score)
allFres.append(fres)
allAri.append(ari)
return allFileData, allScores, allFres, allAri
def calculate_readability_measures(id):
""" Count the words in doc and update the document. """
es = elasticsearch.Elasticsearch()
source = es.get_source(index='beek', doc_type='page', id=id)
# count = len(source['content'].split())
try:
measures = {
'flesch': textstat.flesch_reading_ease(source['content']),
'smog': textstat.smog_index(source['content']),
'flesch_kincaid': textstat.flesch_kincaid_grade(source['content']),
'coleman_liau': textstat.coleman_liau_index(source['content']),
'readability': textstat.automated_readability_index(source['content']),
'dale_chall': textstat.dale_chall_readability_score(source['content']),
'difficult_words': textstat.difficult_words(source['content']),
'linsear_write_formula': textstat.linsear_write_formula(source['content']),
'gunning_fog': textstat.gunning_fog(source['content']),
'consensus': textstat.readability_consensus(source['content']),
}
es.update(index='beek', doc_type='page', id=id,
body={'doc': {'measures': measures}}, refresh=True)
except Exception as err:
pass
def text_stats(corpus):
tk = TweetTokenizer(preserve_case=False, reduce_len=True, strip_handles=True).tokenize
toks = [tk(entry) for entry in corpus]
# get function words
with open('function_words.txt') as file:
funcs = file.read().split(',')
funcs = [f.strip() for f in funcs]
amb = ambiguity(toks) # calculate ambiguity
matrix = [["Chars/Word", "Lexical Diversity", "Lexical Density", "Function Words", "Syllables", "ARI"]]
for tokens, sentence in zip(toks, corpus):
unique = set(tokens)
avchar = 0
lexdiv = 0
lexden = 0
nfunc = 0
numsyl = 0
ari = 0
if len(sentence) > 1:
lexdiv = len(unique) / len(tokens) # Lexical Diversity
lexden = len([x for x in tokens if x not in funcs]) / len(tokens) # Lexical Density
numsyl = textstat.syllable_count(sentence) / len(tokens) / 10 # Number of syllables in text
# may be a bit dodgy without punctuation
ari = abs(textstat.automated_readability_index(sentence)) / 14 # Automated Readability index
for t in tokens:
avchar += len(t) / len(tokens) / len(sentence) # Average num chars
if t in funcs:
nfunc += 1 / len(tokens) # Number of function words
matrix.append([avchar, lexdiv, lexden, nfunc, numsyl, ari])
matrix = [m + [a] for m, a in zip(matrix, amb)]
return np.array(matrix)
def stats(self, text):
test_data = text
stats = {}
stats['flesch_reading_ease'] = textstat.flesch_reading_ease(test_data)
stats['smog'] = textstat.smog_index(test_data)
stats['flesch kincaid'] = textstat.flesch_kincaid_grade(test_data)
stats['coleman Liau'] = textstat.coleman_liau_index(test_data)
stats['automated'] = textstat.automated_readability_index(test_data)
stats['dale chall'] = textstat.dale_chall_readability_score(test_data)
stats['difficult'] = textstat.difficult_words(test_data)
stats['linsear'] = textstat.linsear_write_formula(test_data)
stats['gunning_fog'] = textstat.gunning_fog(test_data)
stats['standard'] = textstat.text_standard(test_data)
stats['charcount'] = textstat.char_count(test_data)
stats['lexicon count'] = textstat.lexicon_count(test_data)
stats['syllable count'] = textstat.syllable_count(test_data)
stats['sentence count'] = textstat.sentence_count(test_data)
stats['avg sentence length'] = textstat.avg_sentence_length(test_data)
stats['avg_syllables_per_word'] = textstat.avg_syllables_per_word(
test_data)
stats['avg_letter_per_word'] = textstat.avg_letter_per_word(test_data)
stats['avg_sentence_per_word'] = textstat.avg_sentence_per_word(
test_data)
return stats
def process(data):
res = np.array([])
cleaned = data.lower().strip()
original = data.strip()
fea1 = numOfWords(cleaned)
# fea1 = fea1 / 10
fea2 = numOfChar(cleaned)
# fea2 = fea2 / 100
fea3 = count(cleaned, string.punctuation)
fea5 = numOfContUpperCase(original)
fea4 = textstat.gunning_fog(data)
fea6 = textstat.automated_readability_index(data)
fea7 = textstat.linsear_write_formula(data)
fea8 = textstat.difficult_words(data)
fea9 = textstat.dale_chall_readability_score(data)
fea10 = data.count("\'") + data.count(".") + data.count("\"") + data.count(",") + data.count(
"’") + data.count("‘") + data.count("”") + data.count("“")
fea10 = (fea10 / len(data)) * 1000
fea11 = data.count("1") + data.count("2") + data.count("3") + data.count("4") + data.count(
"5") + data.count("6") + data.count("7") + data.count("8") + data.count("9") + data.count("0")
fea12 = data.count("?") + data.count("!") + data.count("@") + data.count("#") + data.count(
"$") + data.count("%") + data.count("&")
fea13 = data.count(":") + data.count(";")
fea14 = data.count("—") + data.count("-") + data.count("_")
fea15 = (fea10 / len(data)) * 100
fea16 = data.count("(") + data.count(")") + data.count("[") + data.count("]") + data.count(
"{") + data.count("}")
fea17 = data.count("*") + data.count("/")
fea18 = data.count("?")
fea19 = fea10 + fea11 + fea12 + fea13 + fea14 + fea15 + fea16 + fea17 + fea18
res = np.array([[fea1, fea2, fea3, fea5, fea4, fea6, fea7, fea8, fea9, fea10, fea11, fea12, fea13, fea14,
fea15, fea16, fea17, fea18, fea19]])
return res
def get_readability(self, corpus, type='ari'):
readability = None
if type == 'ari':
readability = textstat.automated_readability_index(corpus)
elif type == 'flesch':
readability = textstat.flesch_reading_ease(corpus)
elif type == 'smog':
readability = textstat.smog_index(corpus)
elif type == 'flesch_kinciad':
readability = textstat.flesch_kincaid_grade(corpus)
elif type == 'coleman':
readability = textstat.coleman_liau_index(corpus)
elif type == 'dale_chall':
readability = textstat.dale_chall_readability_score(corpus)
elif type == 'difficult_words':
readability = textstat.difficult_words(corpus)
elif type == 'linsear':
readability = textstat.linsear_write_formula(corpus)
elif type == 'gunning_fog':
readability = textstat.gunning_fog(corpus)
elif type == 'readability_conensus':
readability = textstat.readability_consensus(corpus)
return readability
def __init__(self, path):
"""
Create document instance for analysis.
Opens and reads document to string raw_text.
Textract interprets the document format and
opens to plain text string (docx, pdf, odt, txt)
Args:
path (str): path to file to open, anaylze, close
Public attributes:
-user: (str) optional string to set username.
-path: (str) relative path to document.
-abs_path: (str) the absolute path to the document.
-file_name: (str) the file name with extension of document (base
name).
-mime: tbd
-guessed_type: makes best guess of mimetype of document.
-file_type: returns index[0] from guessed_type.
-raw_text: (str) plain text extracted from .txt, .odt, .pdf, .docx,
and .doc.
-ptext: (str) raw text after a series of regex expressions to
eliminate special characters.
-text_no_feed: (str) ptext with most new line characters eliminated
/n/n stays intact.
-sentence_tokens: list of all sentences in a comma separated list
derived by nltk.
-sentence_count: (int) count of sentences found in list.
-passive_sentences: list of passive sentences identified by the
passive module.
-passive_sentence_count: count of the passive_sentences list.
-percent_passive: (float) ratio of passive sentences to all sentences
in percent form.
-be_verb_analysis: (int) sum number of occurrences of each to be verb
(am, is, are, was, were, be, being been).
-be_verb_count: tbd
-be_verb_analysis: tbd
-weak_sentences_all: (int) sum of be verb analysis.
-weak_sentences_set: (set) set of all sentences identified as
having to be verbs.
-weak_sentences_count: (int) count of items in weak_sentences_set.
-weak_verbs_to_sentences: (float) proportion of sentences with to
be to all sentences in percent (this might not be sound).
-word_tokens: list of discreet words in text that breaks
contractions up (default nltk tokenizer).
-word_tokens_no_punct: list of all words in text including
contractions but otherwise no punctuation.
-no_punct: (str) full text string without sentence punctuation.
-word_tokens_no_punct: uses white-space tokenizer to create a list
of all words.
-readability_flesch_re: (int) Flesch Reading Ease Score (numeric
score) made by textstat module.
-readability_smog_index: (int) grade level as determined by the
SMOG algorithum made by textstat module.
-readability_flesch_kincaid_grade: (int) Flesch-Kincaid grade level
of reader made by textstat module.
-readability_coleman_liau_index: (int) grade level of reader as made by
textstat module.
-readability_ari: (int) grade leader of reader determined by
automated readability index algorithum implemented by textstat.
-readability_linser_write: FIX SPELLING grade level as determined
by Linsear Write algorithum implemented by textstat.
-readability_dale_chall: (int) grade level based on Dale-Chall
readability as determined by textstat.
-readability_standard: composite grade level based on readability
algorithums.
-flesch_re_key: list for interpreting Flesch RE Score.
-word_count: word count of document based on white space tokener,
this word count should be used.
-page_length: (float) page length in decimal format given 250
words per page.
-paper_count: (int) number of printed pages given 250 words per
page.
-parts_of_speech: words with parts of speech tags.
-pos_counts: values in word, tag couple grouped in a list (Counter).
-pos_total: (int) sum of pos_counts values
-pos_freq: (dict) word, ratio of whole
-doc_pages: (float) page length based on 250 words per page
(warning, this is the second time this attribute is defined).
-freq_words: word frequency count not standardized based on the
correct word tokener (not ratio, just count).
modal_dist: count of auxillary verbs based on word_tokens_no_punct.
sentence_count (int): Count the sentence tokens
passive_sentences (list): List of all sentences identified as passive
passive_sentence_count (int): count of items in passive_sentences
be_verb_count (int): count "to be" verbs in text
word_tokens_no_punct (list): words separated, stripped of punctuation,
made lower case
flesch_re_key (str): reading ease score to description
freq_words (list or dict): frequency distribution of all words
modal_dist (list): frequency distribution of aux verbs
"""
self.user = ""
self.path = path
self.abs_path = os.path.abspath(self.path)
if os.path.isfile(self.path):
self.time_stamp = self.timestamp()
self.file_name = os.path.basename(path)
self.mime = MimeTypes()
self.guessed_type = self.mime.guess_type(self.path)
self.file_type = self.guessed_type[0]
self.raw_text = textract.process(self.path, encoding="ascii")
self.ptext = re.sub(u'[\u201c\u201d]', '"', self.raw_text)
self.ptext = re.sub(u"\u2014", "--", self.ptext)
self.ptext = re.sub(",", ",", self.ptext)
self.ptext = re.sub("—", "--", self.ptext)
self.ptext = re.sub("…", "...", self.ptext)
self.text_no_feed = self.clean_new_lines(self.ptext)
self.sentence_tokens = self.sentence_tokenize(self.text_no_feed)
self.sentence_count = len(self.sentence_tokens)
self.passive_sentences = passive(self.text_no_feed)
self.passive_sentence_count = len(self.passive_sentences)
self.percent_passive = (100 * (float(self.passive_sentence_count) /
float(self.sentence_count)))
self.percent_passive_round = round(self.percent_passive, 2)
self.be_verb_analysis = self.count_be_verbs(self.sentence_tokens)
self.be_verb_count = self.be_verb_analysis[0]
self.weak_sentences_all = self.be_verb_analysis[1]
self.weak_sentences_set = set(self.weak_sentences_all)
self.weak_sentences_count = len(self.weak_sentences_set)
self.weak_verbs_to_sentences = 100 * float(
self.weak_sentences_count) / float(self.sentence_count)
self.weak_verbs_to_sentences_round = round(
self.weak_verbs_to_sentences, 2)
self.word_tokens = self.word_tokenize(self.text_no_feed)
self.word_tokens_no_punct = \
self.word_tokenize_no_punct(self.text_no_feed)
self.no_punct = self.strip_punctuation(self.text_no_feed)
# use this! It make lower and strips symbols
self.word_tokens_no_punct = self.ws_tokenize(self.no_punct)
self.readability_flesch_re = \
textstat.flesch_reading_ease(self.text_no_feed)
self.readability_smog_index = \
textstat.smog_index(self.text_no_feed)
self.readability_flesch_kincaid_grade = \
textstat.flesch_kincaid_grade(self.text_no_feed)
self.readability_coleman_liau_index = \
textstat.coleman_liau_index(self.text_no_feed)
self.readability_ari = \
textstat.automated_readability_index(self.text_no_feed)
self.readability_linser_write = \
textstat.linsear_write_formula(self.text_no_feed)
self.readability_dale_chall = \
textstat.dale_chall_readability_score(self.text_no_feed)
self.readability_standard = \
textstat.text_standard(self.text_no_feed)
self.flesch_re_desc_str = self.flesch_re_desc(
int(textstat.flesch_reading_ease(self.text_no_feed)))
self.polysyllabcount = textstat.polysyllabcount(self.text_no_feed)
self.lexicon_count = textstat.lexicon_count(self.text_no_feed)
self.avg_syllables_per_word = textstat.avg_syllables_per_word(
self.text_no_feed)
self.avg_sentence_per_word = textstat.avg_sentence_per_word(
self.text_no_feed)
self.avg_sentence_length = textstat.avg_sentence_length(
self.text_no_feed)
self.avg_letter_per_word = textstat.avg_letter_per_word(
self.text_no_feed)
self.difficult_words = textstat.difficult_words(self.text_no_feed)
self.rand_passive = self.select_random(self.passive_sentence_count,
self.passive_sentences)
self.rand_weak_sentence = self.select_random(
len(self.weak_sentences), self.weak_sentences)
if self.word_tokens_no_punct:
self.word_count = len(self.word_tokens_no_punct)
self.page_length = float(self.word_count) / float(250)
self.paper_count = int(math.ceil(self.page_length))
self.parts_of_speech = pos_tag(self.word_tokens_no_punct)
self.pos_counts = Counter(
tag for word, tag in self.parts_of_speech)
self.pos_total = sum(self.pos_counts.values())
self.pos_freq = dict(
(word, float(count) / self.pos_total)
for word, count in self.pos_counts.items())
self.doc_pages = float(float(self.word_count) / float(250))
self.freq_words = \
self.word_frequency(self.word_tokens_no_punct)
self.modal_dist = self.modal_count(self.word_tokens_no_punct)
# self.ws_tokens = self.ws_tokenize(self.text_no_cr)
self.pos_count_dict = self.pos_counts.items()
# Model - use for any pos
self.modals = self.pos_isolate('MD', self.pos_count_dict)
self.preposition_count = self.pos_isolate('IN',
self.pos_count_dict)
self.adjective_count = self.pos_isolate_fuzzy(
'JJ', self.pos_count_dict)
self.adverb_count = self.pos_isolate_fuzzy('RB',
self.pos_count_dict)
self.proper_nouns = self.pos_isolate_fuzzy('NNP',
self.pos_count_dict)
self.cc_count = self.pos_isolate('CC', self.pos_count_dict)
self.commas = self.char_count(",")
self.comma_sentences = self.list_sentences(",")
self.comma_example = self.select_random(len(self.comma_sentences),
self.comma_sentences)
self.semicolons = self.char_count(";")
self.semicolon_sentences = self.list_sentences(";")
self.semicolon_example = self.select_random(
len(self.semicolon_sentences), self.semicolon_sentences)
self.lint_suggestions = lint(self.raw_text)
def updateData(self):
# Full list of polarity scores
self.polscore = self.sid.polarity_scores(self.text)
##### INDEX 0 IN DATA: Text Sentiment #####
# [INDEX 0] Compounded score (0.0 - 1.0) [INDEX 1] Negative connotation rating (0.0 - 1.0),
# [INDEX 2] Positive connotation rating (0.0 - 1.0) [INDEX 3] Neutral connotation rating (0.0 - 1.0)
self.data.append([
self.polscore['compound'], self.polscore['neg'],
self.polscore['pos'], self.polscore['neu']
])
##### INDEX 1 IN DATA: Sentence Info #####
# [INDEX 0] Sentence count [INDEX 1] Average sentence length
# [INDEX 2] Syllable count [INDEX 3] Overall word count
# [INDEX 4] Character count [INDEX 5] Character count without spaces
# [INDEX 6] Avg letters per word [INDEX 7] Avg syllables per word
self.data.append([
textstat.sentence_count(self.text),
textstat.avg_sentence_length(self.text),
textstat.syllable_count(self.text),
len(self.splList),
textstat.char_count(self.text, False),
textstat.char_count(self.text, True),
textstat.avg_letter_per_word(self.text),
textstat.avg_syllables_per_word(self.text)
])
##### INDEX 2 IN DATA: Flesch Reading Ease #####
# [INDEX 0] Pure score [INDEX 1] Approximate grade [INDEX 2] Normalized (ratio) score
# SCORE SCALE: 0 - 100
self.freRaw = textstat.flesch_reading_ease(self.text)
self.freStat = min(max(self.freRaw, 0), 100)
self.data.append([
round(self.freStat, 3),
self.freGrade(self.freStat),
round(abs(self.freStat - 100), 2)
])
##### INDEX 3 IN DATA: Flesch-Kincaid Grade #####
# [INDEX 0] Pure score [INDEX 1] Approximate grade [INDEX 2] Normalized (ratio) score
# SCORE SCALE: 0 - 18
self.fkgRaw = textstat.flesch_kincaid_grade(self.text)
self.fkgStat = self.adjustScore(self.fkgRaw)
self.data.append([
round(self.fkgStat, 3),
self.grade(self.fkgStat),
round(self.fkgStat / 0.18, 2)
])
##### INDEX 4 IN DATA: Gunning FOG Index #####
# [INDEX 0] Pure Score [INDEX 1] Approximate grade [INDEX 2] Normalized (ratio) score
# SCORE SCALE: 0 - 18
self.fogRaw = textstat.gunning_fog(self.text)
self.fogStat = self.adjustScore(self.fogRaw)
self.data.append([
round(self.fogStat, 3),
self.grade(self.fogStat),
round(self.fogStat / 0.18, 2)
])
##### INDEX 5 IN DATA: SMOG Index #####
# [INDEX 0] Pure Score [INDEX 1] Approximate grade [INDEX 2] Normalized (ratio) score
# SCORE SCALE: 0 - 18
self.smogRaw = textstat.smog_index(self.text)
self.smogStat = self.adjustScore(self.smogRaw)
self.data.append([
round(self.smogStat, 3),
self.grade(self.smogStat),
round(self.smogStat / 0.18, 2)
])
##### INDEX 6 IN DATA: Automated Readability Index #####
# [INDEX 0] Pure Score [INDEX 1] Approximate grade [INDEX 2] Normalized (ratio) score
# SCORE SCALE: 0 - 14
self.ariRaw = textstat.automated_readability_index(self.text)
self.ariStat = min(max(self.ariRaw, 0), 14)
self.data.append([
round(self.ariStat, 3),
self.ariGrade(ceil(self.ariStat)),
round(self.ariStat / 0.14, 2)
]) #13
##### INDEX 7 IN DATA: Coleman-Liau Index #####
# [INDEX 0] Pure Score [INDEX 1] Approximate grade [INDEX 2] Normalized (ratio) score
# SCORE SCALE: 0 - 18
self.cliRaw = textstat.coleman_liau_index(self.text)
self.cliStat = self.adjustScore(self.cliRaw)
self.data.append([
round(self.cliStat, 3),
self.grade(self.cliStat),
round(self.cliStat / 0.18, 2)
])
##### INDEX 8 IN DATA: Linsear Write Index #####
# [INDEX 0] Pure Score [INDEX 1] Approximate grade [INDEX 2] Normalized (ratio) score
# SCORE SCALE: 0 - 18
self.lwiRaw = textstat.linsear_write_formula(self.text)
self.lwiStat = self.adjustScore(self.lwiRaw)
self.data.append([
round(self.lwiStat, 3),
self.grade(self.lwiStat),
round(self.lwiStat / 0.18, 2)
])
##### INDEX 9 IN DATA: Dale-Chall Readability Score #####
# [INDEX 0] Pure Score [INDEX 1] Approximate grade [INDEX 2] Normalized (ratio) score
# SCORE SCALE: 0 - 10
self.dcrRaw = textstat.dale_chall_readability_score(self.text)
self.dcrStat = min(max(self.dcrRaw, 0), 10)
self.data.append([
round(self.dcrStat, 3),
self.daleChallGrade(self.dcrStat),
round(self.dcrStat / 0.1, 2)
])
##### INDEX 10 IN DATA: Overall Score #####
# [INDEX 0] Pure Score [INDEX 1] Approximate grade [INDEX 2] Normalized (ratio) score
# SCORE SCALE: 0 - 20
self.txtRaw = textstat.text_standard(self.text, True)
self.txtStd = min(max(self.txtRaw, 0), 20)
self.txtInfo = textstat.text_standard(self.text)
self.data.append([
round(self.txtStd, 3),
self.txtGrade(self.txtStd, self.txtInfo),
round(self.txtStd / 0.2, 2)
])
return self.data
def get_textstats(text): return textstat.sentence_count(text), textstat.automated_readability_index(text), textstat.flesch_reading_ease(text)
#main script
if __name__ == '__main__':
print "TextStat Comparison Script"
print "--------------------------"
#read in text from the command line
#This needs to be fixed to deal/escape special characters
textToCheck = raw_input("Please enter the text you would like to analyse: ")
#read in text from a file- but what format?
print "\n\n"
print "Results"
print "=============================================="
print "==============================================\n"
print "Syllable Count: " + str(textstat.syllable_count(textToCheck))
print "Lexicon Count: " + str(textstat.lexicon_count(textToCheck)) #TRUE is default and removes punctuation before counting
print "Sentence Count: " + str(textstat.sentence_count(textToCheck))
print "Flesch Reading Ease formula: " + str(textstat.flesch_reading_ease(textToCheck))
print "Flesch-Kincaid Grade Level: " + str(textstat.flesch_kincaid_grade(textToCheck))
print "Fog Scale (Gunning FOG Formula): " + str(textstat.gunning_fog(textToCheck))
print "SMOG Index: " + str(textstat.smog_index(textToCheck))
print "Automated Readability Index: " + str(textstat.automated_readability_index(textToCheck))
print "Coleman-Liau Index: " + str(textstat.coleman_liau_index(textToCheck))
print "Linsear Write Formula: " + str(textstat.linsear_write_formula(textToCheck))
print "Dale-Chall Readability Score: " + str(textstat.dale_chall_readability_score(textToCheck))
print "--------------------------------------------------------------"
print "Readability Consensus based upon all the above tests: " + str(textstat.text_standard(textToCheck))
print "\n\n"
# skipping tweets which are not just contextbased text. if textstat.sentence_count(tweet) < 1: continue flesch_kincaid_grade = textstat.flesch_kincaid_grade(tweet) flesch_kincaid_grades.append(flesch_kincaid_grade) flesch_kincaid_total_grade += flesch_kincaid_grade gunning_fog_grade = textstat.gunning_fog(tweet) gunning_fog_grades.append(gunning_fog_grade) gunning_fog_total_grade += gunning_fog_grade smog_index_grade = textstat.smog_index(tweet) smog_index_grades.append(smog_index_grade) smog_index_total_grade += smog_index_grade ar_index_grade = textstat.automated_readability_index(tweet) ar_index_grades.append(ar_index_grade) ar_index_total_grade += ar_index_grade cl_index_grade = textstat.coleman_liau_index(tweet) cl_index_grades.append(cl_index_grade) cl_index_total_grade += cl_index_grade lwf_grade = textstat.linsear_write_formula(tweet) lwf_grades.append(lwf_grade) lwf_total_grade += lwf_grade dcr_grade = textstat.dale_chall_readability_score(tweet) dcr_grades.append(dcr_grade) dcr_total_grade += dcr_grade
# print("The SMOG Index")
# print("Texts of fewer than 30 sentences are statistically invalid, "
# "because the SMOG formula was normed on 30-sentence samples.")
# print("textstat requires atleast 3 sentences for a result.")
# print(textstat.smog_index(test_data))
print("The Flesch-Kincaid Grade")
# print(textstat.flesch_kincaid_grade(test_data))
flesch_kincaid_grade = textstat.flesch_kincaid_grade(test_data)
print(flesch_kincaid_grade)
print("The Coleman-Liau Index")
# print(textstat.coleman_liau_index(test_data))
coleman_liau_index = textstat.coleman_liau_index(test_data)
print(coleman_liau_index)
print("Automated Readability Index (ARI)")
# print(textstat.automated_readability_index(test_data))
automated_readability_index = textstat.automated_readability_index(
test_data)
print(automated_readability_index)
# print("Dale-Chall Readability Score")
# print(textstat.dale_chall_readability_score(test_data))
print("Linsear Write Formula")
# print(textstat.linsear_write_formula(test_data))
linsear_write_formula = textstat.linsear_write_formula(test_data)
print(linsear_write_formula)
print("The Fog Scale (Gunning FOG Formula)")
# print(textstat.gunning_fog(test_data))
gunning_fog = textstat.gunning_fog(test_data)
print(gunning_fog)
print(
"---------------------------------Summary----------------------------------"
)
#!/bin/python import sys, string, os from textstat.textstat import textstat inputfile = '' test_data = "" script_name = sys.argv[0] inputfile = sys.argv[1] with open(inputfile) as myfile: test_data="".join(line.rstrip() for line in myfile) var1 = str(textstat.flesch_reading_ease(test_data)) var2 = str(textstat.smog_index(test_data)) var3 = str(textstat.flesch_kincaid_grade(test_data)) var4 = str(textstat.coleman_liau_index(test_data)) var5 = str(textstat.automated_readability_index(test_data)) var6 = str(textstat.dale_chall_readability_score(test_data)) var7 = str(textstat.difficult_words(test_data)) var8 = str(textstat.linsear_write_formula(test_data)) var9 = str(textstat.gunning_fog(test_data)) var10 = str(textstat.readability_consensus(test_data)) var11 = str(textstat.syllable_count(test_data)) var12 = str(textstat.lexicon_count(test_data, 1)) var13 = str(textstat.sentence_count(test_data)) print(var1 + ',' + var2 + ',' + var3 + ',' + var4 + ',' + var5 + ',' + var6 + ',' + var7 + ',' + var8 + ',' + var9 + ',' + var10 + ',' + var11 + ',' + var12 + ',' + var13)
def extract_features_sub(text, dialogue = True):
## aggregate all dialogue, action
#scenes = format_script(file_name)
if len(text) > 0:
try:
language_complexity = {'flesch_reading_ease': textstat.flesch_reading_ease(text), 'flesch_kincaid_grade': textstat.flesch_kincaid_grade(text), 'automated_readability_index': textstat.automated_readability_index(text)}
except:
language_complexity = {'flesch_reading_ease': None, 'flesch_kincaid_grade': None, 'automated_readability_index': None}
else:
#badD.write(movie_name + "\n")
language_complexity = {'flesch_reading_ease': 0, 'flesch_kincaid_grade': 0, 'automated_readability_index': 0}
lexical_diversity = find_lex_d(text)
sentiment = extract_senti_wordnet(text)
#print sentiment
inquirer_features = general_inquirer_features(text)
final_features = {}
final_features.update(language_complexity)
final_features.update(lexical_diversity)
final_features.update(sentiment)
final_features.update(inquirer_features)
curr_keys = [feature for feature in final_features]
if dialogue:
new_keys = [feature + "_" + "dialogue" for feature in final_features]
else:
new_keys = [feature + "_" + "action" for feature in final_features]
#print final_features
"""
if dialogue:
for feature in final_features:
final_features[feature + "_dialogue"] = final_features.pop(feature)
else:
for feature in final_features:
final_features[feature + "_action"] = final_features.pop(feature)
#final_features = language_complexity + lexical_diversity + sentiment + inquirer_features
"""
return convert(final_features, dict(zip(curr_keys, new_keys)))