avg = np.mean([
metrics['FK'], metrics['CL'], metrics['DC'], metrics['SMOG'],
metrics['ARI']
])
if avg >= 6:
results.append('no')
else:
results.append('yes')
return results
path_for_pipeline = input(
'type in the path to a folder with texts to analyze: ')
suitability = classify_1_to_4(extracting_texts_paths(path_for_pipeline))
# declaration of all the vars for the output
file_names = []
texts = []
num_of_1st_class = []
str_of_1st_class = []
num_of_2nd_class_W = []
num_of_2nd_class_S = []
str_of_2nd_class_W = []
str_of_2nd_class_S = []
num_of_3rd_class_W = []
num_of_3rd_class_S = []
num_of_2nd_class_W = []
names_of_2nd_class_feats_W = []
num_of_2nd_class_S = []
names_of_2nd_class_feats_S = []
num_of_3rd_class_W = []
names_of_3rd_class_feats_W = []
num_of_3rd_class_S = []
names_of_3rd_class_feats_S = []
num_of_4th_class_W = []
names_of_4th_class_feats_W = []
num_of_4th_class_S = []
names_of_4th_class_feats_S = []
paths = extracting_texts_paths(path_for_pipeline)
# transform a word to a mask of type CVC... where C is a consonant and V is a vowel
def get_word_mask(word):
mask = []
for sym in word:
mask.append('V' if sym in text_accentAPI.VOWELS else 'C')
return mask
def get_accent_syl_id(accentuated_char_id, list_of_syls_lengths):
last = len(list_of_syls_lengths) - 1
writer.write(header_of_table + '\n')
for i in tqdm(range(len(list_of_paths))):
if list_of_paths[i][-3:] == 'csv':
pass
else:
length = len(list_of_paths)
with open(list_of_paths[i], 'r', encoding='utf-8') as opener:
readability_result = func(opener.read())
name = list_of_paths[i].split('\\')[-1]
if i == length-1:
writer.write(name + ', ' + ', '.join([str(round(value, 3))
for value in readability_result.values()]))
else:
writer.write(name + ', ' + ', '.join([str(round(value, 3))
for value in readability_result.values()]) + '\n')
if __name__ == '__main__':
header = 'filename, Flesch-Kincaid, Coleman-Liau index, Dale-Chale readability formula, readability level (SMOG), ' \
'Automated Readability Index, # of chars, # of spaces, # of letters, # of words, # of sentences, ' \
'# of complex words, # of simple words, average # of words per sentence, ' \
'average # of syllables per sentence, % of complex words'
path_for_offline_api = input("type in the path to a folder with texts to analyze: ")
create_an_output_table_offline(extracting_texts_paths(path_for_offline_api), IB_metrics_readability.calc_readability_metrics, header)