def get_stats(text): fre = textstat.flesch_reading_ease(text) smog = textstat.smog_index(text) fkg = textstat.flesch_kincaid_grade(text) cli = textstat.coleman_liau_index(text) ari = textstat.automated_readability_index(text) dcr = textstat.dale_chall_readability_score(text) diff_words = textstat.difficult_words(text) lwf = textstat.linsear_write_formula(text) gunn_fog = textstat.gunning_fog(text) consolidated_score = textstat.text_standard(text) doc_length = len(text) # think about excluding spaces? quote_count = text.count('"') stats = { "flesch_reading_ease": fre, "smog_index": smog, "flesch_kincaid_grade": fkg, "coleman_liau_index": cli, "automated_readability_index": ari, "dale_chall_readability_score": dcr, "difficult_words": diff_words, "linsear_write_formula": lwf, "gunning_fog": gunn_fog, "consolidated_score": consolidated_score, "doc_length": doc_length, "quote_count": quote_count } return stats
def textstat_stats(text): doc_length = len(text.split()) flesch_ease = ts.flesch_reading_ease(text) #Flesch Reading Ease Score flesch_grade = ts.flesch_kincaid_grade(text) #Flesch-Kincaid Grade Level gfog = ts.gunning_fog(text) # FOG index, also indicates grade level # smog = ts.smog_index(text) # SMOG index, also indicates grade level, only useful on 30+ sentences auto_readability = ts.automated_readability_index(text) #approximates the grade level needed to comprehend the text. cl_index = ts.coleman_liau_index(text) #grade level of the text using the Coleman-Liau Formula. lw_formula = ts.linsear_write_formula(text) #grade level using the Linsear Write Formula. dcr_score = ts.dale_chall_readability_score(text) #uses a lookup table of the most commonly used 3000 English words # text_standard = ts.text_standard(text, float_output=False) # summary of all the grade level functions syll_count = ts.syllable_count(text, lang='en_US') syll_count_scaled = syll_count / doc_length lex_count = ts.lexicon_count(text, removepunct=True) lex_count_scaled = lex_count / doc_length idx = ['flesch_ease', 'flesch_grade','gfog', 'auto_readability','cl_index','lw_formula', 'dcr_score', # 'text_standard', 'syll_count', 'lex_count'] return pd.Series([flesch_ease, flesch_grade, gfog, auto_readability, cl_index, lw_formula, dcr_score, # text_standard, syll_count_scaled, lex_count_scaled], index = idx)
def test(text): #print (text) score = textstat.automated_readability_index((str(text))) if math.isnan(score) == True: return 0.0 else: return score
def getReadabilityMetrics(test_data): ''' for a given article IN TEXT FORMAT, returns its readability metrics Uses textstat library, please install it ''' metric = { "flesch_reading_ease": textstat.flesch_reading_ease(test_data), "smog_index": textstat.smog_index(test_data), "flesch_kincaid_grade": textstat.flesch_kincaid_grade(test_data), "coleman_liau_index": textstat.coleman_liau_index(test_data), "automated_readability_index": textstat.automated_readability_index(test_data), "dale_chall_readability_score": textstat.dale_chall_readability_score(test_data), "difficult_words": textstat.difficult_words(test_data), "linsear_write_formula": textstat.linsear_write_formula(test_data), "gunning_fog": textstat.gunning_fog(test_data), "text_standard": textstat.text_standard(test_data) } return metric
def fin(words): word_list = [] global wordle if 'wordle' not in globals(): wordle = {} #excepted = [] #definition = [] #example = [] from nltk.corpus import wordnet import textstat for word in words: syns = wordnet.synsets(word.lower()) if not syns: continue else: #li=[] #word_list.append(word) # #definition.append(syns[0].definition()) # #example.append(syns[0].examples()[0]) # li.append(syns[0].definition()) #li.append(textstat.automated_readability_index(word.lower())) # wordle[word]=textstat.flesch_reading_ease(word.lower()) wordle[word] = textstat.automated_readability_index(word.lower()) jso()
def get_readibility(text, metric="flesch_kincaid_grade"): """ Return a score which reveals a piece of text's readability level. Reference: https://chartbeat-labs.github.io/textacy/getting_started/quickstart.html https://en.wikipedia.org/wiki/Flesch%E2%80%93Kincaid_readability_tests """ if metric == "flesch_kincaid_grade": result = textstat.flesch_kincaid_grade(text) elif metric == "flesch_reading_ease": result = textstat.flesch_reading_ease(text) elif metric == "smog_index": result = textstat.smog_index(text) elif metric == "coleman_liau_index": result = textstat.coleman_liau_index(text) elif metric == "automated_readability_index": result = textstat.automated_readability_index(text) elif metric == "dale_chall_readability_score": result = textstat.dale_chall_readability_score(text) elif metric == "difficult_words": result = textstat.difficult_words(text) elif metric == "linsear_write_formula": result = textstat.linsear_write_formula(text) elif metric == "gunning_fog": result = textstat.gunning_fog(text) elif metric == "text_standard": result = textstat.text_standard(text) else: print("ERROR: Please select correct metric!") result = None return result
def read_metrics(text_clean): table = {} #table['flesch'] = textstat.flesch_reading_ease(text_clean) #table['flesch_kincaid'] = textstat.flesch_kincaid_grade(text_clean) table['fog'] = textstat.gunning_fog(text_clean) table['smog'] = textstat.smog_index(text_clean) table['ari'] = textstat.automated_readability_index(text_clean) table['coleman_liau'] = textstat.coleman_liau_index(text_clean) r_read_mets = quanteda.textstat_readability(text_clean, measure='all') table['ari_r'] = float(r_read_mets[1].r_repr()) table['rix_r'] = float(r_read_mets[35].r_repr()) table['Coleman_Liau_Grade_R'] = float(r_read_mets[9].r_repr()) table['Coleman_Liau_Short_R'] = float(r_read_mets[10].r_repr()) table['Danielson_Bryan_R'] = float(r_read_mets[14].r_repr()) table['Dickes_Steiwer_R'] = float(r_read_mets[16].r_repr()) table['ELF_R'] = float(r_read_mets[18].r_repr()) table['Farr_Jenkins_Paterson_R'] = float(r_read_mets[19].r_repr()) table['flesch_R'] = float(r_read_mets[20].r_repr()) table['flesh_kincaid_R'] = float(r_read_mets[22].r_repr()) table['FORCAST_R'] = float(r_read_mets[26].r_repr()) table['Fucks_R'] = float(r_read_mets[28].r_repr()) table['FOG_R'] = float(r_read_mets[23].r_repr()) table['Linsear_Write_R'] = float(r_read_mets[29].r_repr()) table['nWS_R'] = float(r_read_mets[31].r_repr()) table['SMOG_R'] = float(r_read_mets[37].r_repr()) table['Strain_R'] = float(r_read_mets[43].r_repr()) table['Wheeler_Smith_R'] = float(r_read_mets[46].r_repr()) return table
def seven_test(processed_essay): """ score which is assigned to every script in on the basis of some predifened fomulas These scores are known as readability score. flesch_score,gunning_index,kincaid_grade,liau_index,automated_readability_index,dale_readability_score,difficult_word,linsear_write :param processed_essay: :return:flesch_score,gunning_index,kincaid_grade,liau_index,automated_readability_index,dale_readability_score,difficult_word,linsear_write """ flesch_score = ["FS"] gunning_index = ["GI"] kincaid_grade = ["KG"] liau_index = ["LI"] automated_readability_index = ["ARI"] dale_readability_score = ["DLS"] difficult_word = ["DW"] linsear_write = ["LW"] for v in processed_essay: flesch_score.append(textstat.flesch_reading_ease(str(v))) gunning_index.append(textstat.gunning_fog(str(v))) kincaid_grade.append(textstat.flesch_kincaid_grade(str(v))) liau_index.append(textstat.coleman_liau_index(str(v))) automated_readability_index.append(textstat.automated_readability_index(str(v))) dale_readability_score.append(textstat.dale_chall_readability_score(str(v))) difficult_word.append(textstat.difficult_words(str(v))) linsear_write.append(textstat.linsear_write_formula(str(v))) return flesch_score,gunning_index,kincaid_grade,liau_index,automated_readability_index,dale_readability_score,difficult_word,linsear_write
def feature_getter(text): try: text=text.decode('utf-8') except: pass text1=re.sub(r'[^\x00-\x7F]+',' ', text) ##text1=re.sub('\n','. ', text) text=text1 features=[] tokens=[] sentences = nltk.sent_tokenize(text) [tokens.extend(nltk.word_tokenize(sentence)) for sentence in sentences] syllable_count = textstat.syllable_count(text, lang='en_US') word_count = textstat.lexicon_count(text, removepunct=True) flesch = textstat.flesch_reading_ease(text) readability = textstat.automated_readability_index(text) features.append(len(sentences)) #num_sentences features.append(syllable_count) #num_sentences features.append(word_count) #num_sentences features.append(flesch) #num_sentences features.append(readability) #num_sentences return features
def create_csv(config): csv_path = config.get('Paths','CsvPath') result_path = config.get('Paths','ResultPath') csv_name = config.get('Paths', 'CsvName') result_list = [] # タプル: (読み込んだcsvの行番号, 生成された文のARI, 生成された文, 生成された文の日本語訳) csv_title = ("読み込んだcsvの行番号", "word1", "word2", "FN", "word1 FE","word2 FE","生成された文のARI", "生成された文", "生成された文の日本語訳") words = csv_name.split("_") # ['water','pen.csv'] word1 = words[0] # 'water' word2 = words[1].split(".")[0] # 'pen' with open(csv_path, 'r') as f: for i, row in enumerate(csv.reader(f)): current_row_generated_sentences = row[2].split('\n') fn = row[3] word1_fe = row[4] word2_fe = row[5] for sentence in current_row_generated_sentences: if len(sentence) != 0: result_list.append( #(i,textstat.automated_readability_index(sentence),sentence, Translator().translate(sentence, dest = 'ja').text) (i, word1, word2, fn, word1_fe, word2_fe, textstat.automated_readability_index(sentence),sentence, "リクエスト制限") ) print(i) del result_list[0] result_list.sort(key=lambda tup: tup[6]) # ARIでソート with open(result_path, 'w') as f: writer = csv.writer(f) writer.writerow(csv_title) for row in result_list: writer.writerow(row)
def readability(queries): scores = pd.DataFrame(columns=[ 'Flesch', 'Smog', 'Flesch grade', 'Coleman', 'Automated', 'Dale', 'Difficult', 'Linsear', 'Gunning', 'Text Standard' ]) scores = { 'Flesch': [], 'Smog': [], 'Flesch grade': [], 'Coleman': [], 'Automated': [], 'Dale': [], 'Difficult': [], 'Linsear': [], 'Gunning': [], 'Text Standard': [] } for line in queries: # results = readability.getmeasures(line, lang='en') # frescores.append(results['readability grades']['FleschReadingEase']) # line = 'yao family wines . yao family wines is a napa valley producer founded in 2011 by yao ming , the chinese-born , five-time nba all star . now retired from the houston rockets , yao ming is the majority owner in yao family wines , which has entered the wine market with a luxury cabernet sauvignon sourced from napa valley vineyards .' scores['Flesch'].append(textstat.flesch_reading_ease(line)) scores['Smog'].append(textstat.smog_index(line)) scores['Flesch grade'].append(textstat.flesch_kincaid_grade(line)) scores['Coleman'].append(textstat.coleman_liau_index(line)) scores['Automated'].append(textstat.automated_readability_index(line)) scores['Dale'].append(textstat.dale_chall_readability_score(line)) scores['Difficult'].append(textstat.difficult_words(line)) scores['Linsear'].append(textstat.linsear_write_formula(line)) scores['Gunning'].append(textstat.gunning_fog(line)) scores['Text Standard'].append( textstat.text_standard(line, float_output=True)) return scores
def analyze(): print(request) str_to_read = request.data.decode("utf-8").strip() report = { "flesch-reading-ease": textstat.flesch_reading_ease(str_to_read), "smog-index": textstat.smog_index(str_to_read), "flesch-kincaid-grade": textstat.flesch_kincaid_grade(str_to_read), "coleman-liau-index": textstat.coleman_liau_index(str_to_read), "automated-readability-index": textstat.automated_readability_index(str_to_read), "dale-chall-readability-score": textstat.dale_chall_readability_score(str_to_read), "difficult-words": textstat.difficult_words(str_to_read), "linsear-write-formula": textstat.linsear_write_formula(str_to_read), "gunning-fog": textstat.gunning_fog(str_to_read), "text-standard": textstat.text_standard(str_to_read) } return decorate_response(jsonify(report))
def get_readability_score(text, metric="flesch"): global tknzr, DIFFICULT text = text.replace("’", "'") # https://pypi.org/project/textstat/ if metric == "flesch": return textstat.flesch_reading_ease(text) elif metric == "smog": return textstat.smog_index(text) elif metric == "coleman_liau_index": return textstat.coleman_liau_index(text) elif metric == "automated_readability_index": return textstat.automated_readability_index(text) elif metric == "dale_chall_readability_score": return textstat.dale_chall_readability_score(text) elif metric == "difficult_words": nb_difficult = 0 nb_easy = 0 for w in set(tknzr.tokenize(text.lower())): if w not in EASY_WORDS and len(w) >= 6: nb_difficult += 1 else: nb_easy += 1 return 100 * nb_difficult / (nb_difficult + nb_easy) #return textstat.difficult_words(text)#/len(text.split()) elif metric == "linsear_write_formula": return textstat.linsear_write_formula(text) elif metric == "gunning_fog": return textstat.gunning_fog(text) elif metric == "avg_word_length": words = tknzr.tokenize(text) words = [w for w in words if w not in misc_utils.PUNCT] if len(words) == 0: return 0 return np.average([len(w) for w in words])
def score(text): a = textstat.flesch_reading_ease(text) b = textstat.flesch_kincaid_grade(text) c = textstat.gunning_fog(text) d = textstat.smog_index(text) e = textstat.coleman_liau_index(text) f = textstat.automated_readability_index(text) return a, b, c, d, e, f
def getReadability(df): import textstat df['ARI'] = df.headline_text.apply( lambda x: textstat.automated_readability_index(x)) df['DCR'] = df.headline_text.apply( lambda x: textstat.dale_chall_readability_score(x)) df['TS'] = df.headline_text.apply( lambda x: textstat.text_standard(x, float_output=True)) return df
def do_datas(): # logging.info('do_datas') ########### Save text statistics ##### 1. nw 2. nvocab 3. nsyllable 4.nsentence 5. tone 6. readability ## 1. nw nw.append(len(words)) ## 2. nvocab nvocab.append(len(vocab)) ## 3. syllable n = textstat.syllable_count(contents) nsyllable.append(n) ## 4. sentence n = textstat.sentence_count(contents) nsentence.append(n) ## 5. tone ### LM dictionary n_neg_lm.append(count_occurrence(words, lm_neg)) n_pos_lm.append(count_occurrence(words, lm_pos)) n_uctt_lm.append(count_occurrence(words, lm_uctt)) n_lit_lm.append(count_occurrence(words, lm_lit)) n_cstr_lm.append(count_occurrence(words, lm_cstr)) n_modal1_lm.append(count_occurrence(words, lm_modal1)) n_modal2_lm.append(count_occurrence(words, lm_modal2)) n_modal3_lm.append(count_occurrence(words, lm_modal3)) n_negation_lm.append(count_negation(words, lm_pos, gt_negation)) ### General Inquirer dictionary n_neg_gi.append(count_occurrence(words, gi_neg)) n_pos_gi.append(count_occurrence(words, gi_pos)) n_negation_gi.append(count_negation(words, gi_pos, gt_negation)) ### Henry dictionary n_neg_hr.append(count_occurrence(words, hr_neg)) n_pos_hr.append(count_occurrence(words, hr_pos)) n_negation_hr.append(count_negation(words, gi_pos, gt_negation)) ## 4. readability fre_i = textstat.flesch_reading_ease(contents) if fre_i > 100: fre_i = 100 if fre_i < 0: fre_i = float('NaN') fre.append(fre_i) fkg_i = textstat.flesch_kincaid_grade(contents) if fkg_i < 0: fkg_i = float('NaN') fkg.append(fkg_i) # RIX cl_i = textstat.coleman_liau_index(contents) if cl_i < 0: cl_i = float('NaN') cl.append(cl_i) f = textstat.gunning_fog(contents) fog.append(f) f = textstat.automated_readability_index(contents) ari.append(f) f = textstat.smog_index(contents) smog.append(f)
def ari_for_col(a_data, a_col): ari_col = [] for review in a_data[a_col]: ari = -1 try: ari = textstat.automated_readability_index(review) except: pass #print("unable to find ARI for", review) ari_col.append(ari) a_data["ari"] = ari_col return a_data
def score(self, strText): self.automated_readability_index = textstat.automated_readability_index( strText) self.str_automated_readability_index = self.grade( self.automated_readability_index) self.coleman_liau_index = textstat.coleman_liau_index(strText) self.str_coleman_liau_index = self.grade(self.coleman_liau_index) self.dale_chall_readability_score = textstat.dale_chall_readability_score( strText) if self.dale_chall_readability_score >= 9.0: self.str_dale_chall_readability_score = ' | ' + '13th to 15th grade (college)' elif self.dale_chall_readability_score >= 8.0: self.str_dale_chall_readability_score = ' | ' + '11th to 12th grade' elif self.dale_chall_readability_score >= 7.0: self.str_dale_chall_readability_score = ' | ' + '9th to 10th grade' elif self.dale_chall_readability_score >= 6.0: self.str_dale_chall_readability_score = ' | ' + '7th to 8th grade' elif self.dale_chall_readability_score >= 5.0: self.str_dale_chall_readability_score = ' | ' + '5th to 6th grade' else: self.str_dale_chall_readability_score = ' | ' + '4th grade or lower' self.difficult_words = textstat.difficult_words(strText) self.flesch_kincaid_grade = textstat.flesch_kincaid_grade(strText) self.str_flesch_kincaid_grade = self.grade(self.flesch_kincaid_grade) self.flesch_reading_ease = textstat.flesch_reading_ease(strText) if self.flesch_reading_ease >= 90: self.str_flesch_reading_ease = ' | ' + 'Very Easy' elif self.flesch_reading_ease >= 80: self.str_flesch_reading_ease = ' | ' + 'Easy' elif self.flesch_reading_ease >= 70: self.str_flesch_reading_ease = ' | ' + 'Fairly Easy' elif self.flesch_reading_ease >= 60: self.str_flesch_reading_ease = ' | ' + 'Standard' elif self.flesch_reading_ease >= 50: self.str_flesch_reading_ease = ' | ' + 'Fairly Difficult' elif self.flesch_reading_ease >= 30: self.str_flesch_reading_ease = ' | ' + 'Difficult' else: self.str_flesch_reading_ease = ' | ' + 'Very Confusing' self.gunning_fog = textstat.gunning_fog(strText) self.str_gunning_fog = self.grade(self.gunning_fog) self.linsear_write_formula = textstat.linsear_write_formula(strText) self.str_linsear_write_formula = self.grade(self.linsear_write_formula) self.smog_index = textstat.smog_index(strText) self.str_smog_index = self.grade(self.smog_index) self.text_standard = textstat.text_standard(strText)
def compute_readability_stats(text): """ Compute reading statistics of the given text Reference: https://github.com/shivam5992/textstat Parameters ========== text: str, input section or abstract text """ try: readability_dict = { 'flesch_reading_ease': textstat.flesch_reading_ease(text), 'smog': textstat.smog_index(text), 'flesch_kincaid_grade': textstat.flesch_kincaid_grade(text), 'coleman_liau_index': textstat.coleman_liau_index(text), 'automated_readability_index': textstat.automated_readability_index(text), 'dale_chall': textstat.dale_chall_readability_score(text), 'difficult_words': textstat.difficult_words(text), 'linsear_write': textstat.linsear_write_formula(text), 'gunning_fog': textstat.gunning_fog(text), 'text_standard': textstat.text_standard(text), 'n_syllable': textstat.syllable_count(text), 'avg_letter_per_word': textstat.avg_letter_per_word(text), 'avg_sentence_length': textstat.avg_sentence_length(text) } except: readability_dict = { 'flesch_reading_ease': None, 'smog': None, 'flesch_kincaid_grade': None, 'coleman_liau_index': None, 'automated_readability_index': None, 'dale_chall': None, 'difficult_words': None, 'linsear_write': None, 'gunning_fog': None, 'text_standard': None, 'n_syllable': None, 'avg_letter_per_word': None, 'avg_sentence_length': None } return readability_dict
def create_readability_features(self): """ Adds readability features using textstat library. Numbers represent grade level needed to understand the text. ari: Automated Readability Index """ for df in [self.X_train, self.X_test]: df["review_text_readability_flesch_kincaid"] = df[ "review_text"].apply( lambda x: textstat.flesch_kincaid_grade(x)) df["review_text_ari"] = df["review_text"].apply( lambda x: textstat.automated_readability_index(x))
def generate_score(self, text): self.flesch_reading_grade = ts.flesch_reading_ease(text) self.flesch_reading_grade_consensus = readability_test_consensus(self.flesch_reading_grade, flesch_ease_grading_system) self.flesch_kincaid_grade = ts.flesch_kincaid_grade(text) self.flesch_kincaid_grade_consensus = readability_test_consensus(self.flesch_kincaid_grade, us_grade_level_system_age) self.dale_chall_grade = ts.dale_chall_readability_score(text) self.dale_chall_grade_consensus = readability_test_consensus(self.dale_chall_grade, dale_chall_system) self.smog_grade = ts.smog_index(text) self.ari_grade = ts.automated_readability_index(text) """ self.ari_grade_consensus = readability_test_consensus(self.ari_grade, us_grade_level_system_level) """ self.coleman_liau_grade = ts.coleman_liau_index(text) pass
def process(self, df): t0 = time() print("\n---Generating Readability Features:---\n") def lexical_diversity(text): words = nltk.tokenize.word_tokenize(text.lower()) word_count = len(words) vocab_size = len(set(words)) diversity_score = vocab_size / word_count return diversity_score def get_counts(text, word_list): words = nltk.tokenize.word_tokenize(text.lower()) count = 0 for word in words: if word in word_list: count += 1 return count df['flesch_reading_ease'] = df['articleBody'].map(lambda x: textstat.flesch_reading_ease(x)) df['smog_index'] = df['articleBody'].map(lambda x: textstat.smog_index(x)) df['flesch_kincaid_grade'] = df['articleBody'].map(lambda x: textstat.flesch_kincaid_grade(x)) df['coleman_liau_index'] = df['articleBody'].map(lambda x: textstat.coleman_liau_index(x)) df['automated_readability_index'] = df['articleBody'].map(lambda x: textstat.automated_readability_index(x)) df['dale_chall_readability_score'] = df['articleBody'].map(lambda x: textstat.dale_chall_readability_score(x)) df['difficult_words'] = df['articleBody'].map(lambda x: textstat.difficult_words(x)) df['linsear_write_formula'] = df['articleBody'].map(lambda x: textstat.linsear_write_formula(x)) df['gunning_fog'] = df['articleBody'].map(lambda x: textstat.gunning_fog(x)) df['i_me_myself'] = df['articleBody'].apply(get_counts,args = (['i', 'me', 'myself'],)) df['punct'] = df['articleBody'].apply(get_counts,args = ([',','.', '!', '?'],)) df['lexical_diversity'] = df['articleBody'].apply(lexical_diversity) feats = ['flesch_reading_ease', 'smog_index', 'flesch_kincaid_grade', 'coleman_liau_index', 'automated_readability_index', 'dale_chall_readability_score', 'difficult_words', 'linsear_write_formula', 'gunning_fog', 'i_me_myself', 'punct', 'lexical_diversity' ] outfilename_xReadable = df[feats].values with open('../saved_data/read.pkl', 'wb') as outfile: pickle.dump(feats, outfile, -1) pickle.dump(outfilename_xReadable, outfile, -1) print ('readable features saved in read.pkl') print('\n---Readability Features is complete---') print("Time taken {} seconds\n".format(time() - t0)) return 1
def readability_scores(self, text): self.ari = textstat.automated_readability_index(text) self.flesch_kincaid_grade = textstat.flesch_kincaid_grade(text) self.coleman_liau_index = textstat.coleman_liau_index(text) self.dale_chall_readability_score = textstat.dale_chall_readability_score( text) self.flesch_reading_ease = textstat.flesch_reading_ease(text) self.gunning_fog = textstat.gunning_fog(text) self.linsear_write_formula = textstat.linsear_write_formula(text) self.lix = textstat.lix(text) self.rix = textstat.rix(text) self.smog_index = textstat.smog_index(text) self.text_standard = textstat.text_standard(text)
def get_readability_stats(text): return { 'flesch_reading_ease': textstat.flesch_reading_ease(text), 'smog_index': textstat.smog_index(text), 'flesch_kincaid_grade': textstat.flesch_kincaid_grade(text), 'coleman_liau_index': textstat.coleman_liau_index(text), 'automated_readability_index': textstat.automated_readability_index(text), 'dale_chall_readability_score': textstat.dale_chall_readability_score(text), 'linsear_write_formula': textstat.linsear_write_formula(text), 'gunning_fog': textstat.gunning_fog(text), 'text_standard': textstat.text_standard(text, float_output=True), }
def simple_example_ari(): test_data = ( "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." ) print("Calculating automated readability index (ARI)") readability_index = textstat.automated_readability_index(test_data) print("ARI:", readability_index)
def vocab_check(text): #Construct dictionary vocab_results = {'dale_chall_readability_score': dale_chall_readability_score(text), 'smog_index': smog_index(text), 'gunning_fog': gunning_fog(text), 'flesch_reading_ease': flesch_reading_ease(text), 'flesch_kincaid_grade': flesch_kincaid_grade(text), 'linsear_write_formula': linsear_write_formula(text), 'coleman_liau_index': coleman_liau_index(text), 'automated_readability_index': automated_readability_index(text), 'yule_vocab_richness': yule(text), 'total_score': text_standard(text, float_output=True)} diff_words, easy_word_dict = difficult_words(text) return(vocab_results, diff_words, easy_word_dict)
def lisibilty(text): f_lis = ([ textstat.syllable_count(str(text), lang='en_arabic'), textstat.lexicon_count(str(text), removepunct=True), textstat.sentence_count(str(text)), textstat.flesch_reading_ease(str(text)), textstat.flesch_kincaid_grade(str(text)), textstat.gunning_fog(str(text)), textstat.smog_index(str(text)), textstat.automated_readability_index(str(text)), textstat.coleman_liau_index(str(text)), textstat.linsear_write_formula(str(text)), textstat.dale_chall_readability_score(str(text)) ]) return f_lis
def calculate_ari(dataframe): df = dataframe ari_values = [] for name in df['name']: df_count = pd.read_sql(""" SELECT body FROM May2015 WHERE name == '{}' """.format(name),sql_conn) tmp_str = ''.join(df_count['body']) ari_value = textstat.automated_readability_index(tmp_str) ari_values.append(ari_value) df['ARI_value'] = ari_values df.to_csv('test.csv', encoding='utf-8')
def analyze_vocab(text): return { 'num_words': textstat.lexicon_count(text), 'flesch_reading_ease': textstat.flesch_reading_ease(text), 'smog_index': textstat.smog_index(text), 'flesch_kincaid_grade': textstat.flesch_kincaid_grade(text), 'coleman_liau_index': textstat.coleman_liau_index(text), 'automated_readability_index': textstat.automated_readability_index(text), 'dale_chall_readability_score': textstat.dale_chall_readability_score(text), 'difficult_words': textstat.difficult_words(text), 'linsear_write_formula': textstat.linsear_write_formula(text), 'gunning_fog': textstat.gunning_fog(text), 'text_standard': textstat.text_standard(text, float_output=True) }
def calcReadabilityScores(content, basename, stats=[], outFile=""): scores = { "flesch_reading_ease": textstat.flesch_reading_ease(content), "gunning_fog": textstat.gunning_fog(content), "automated_readability_index": textstat.automated_readability_index(content), "coleman_liau_index": textstat.coleman_liau_index(content) } for metric in scores: if scores[ metric] > 0.0: #Ignore scores that are 0, as this is an error. stats.append([basename, metric, scores[metric]])
def textstat_stats(text): difficulty = textstat.flesch_reading_ease(text) grade_difficulty = textstat.flesch_kincaid_grade(text) gfog = textstat.gunning_fog(text) smog = textstat.smog_index(text) ari = textstat.automated_readability_index(text) cli = textstat.coleman_liau_index(text) lwf = textstat.linsear_write_formula(text) dcrs = textstat.dale_chall_readability_score(text) idx = [ 'difficulty', 'grade_difficulty', 'gfog', 'smog', 'ari', 'cli', 'lwf', 'dcrs' ] return pd.Series( [difficulty, grade_difficulty, gfog, smog, ari, cli, lwf, dcrs], index=idx)
def test_automated_readability_index(): index = textstat.automated_readability_index(long_test) assert index == 12.3