def inject_sva_error(example):
tok_sentence, features_seq = example[0].split(), example[1]
verb_indices = []
for i in range(len(features_seq)):
if features_seq[i]['universal_postag'] == 'VERB':
verb_indices.append(i)
if len(verb_indices) > 0:
j = random.choice(verb_indices)
lexeme = pattern.lexeme(tok_sentence[j])
if len(lexeme) > 0:
tok_sentence[j] = random.choice(lexeme)
return [' '.join(tok_sentence), features_seq]
def write_hypo(parent, count, list_of_neighbors):
return_dict = {}
for index in range(0, len(list_of_neighbors)):
s = wordnet.synsets(list_of_neighbors[index])
if len(s) > 0:
s = s[0]
synomyms = s.synonyms
hypernyms = s.hypernyms()
hyponyms = s.hyponyms()
holonyms = s.holonyms()
meronyms = s.meronyms()
singulars = [singularize(list_of_neighbors[index])]
plurals = [pluralize(list_of_neighbors[index])]
comparatives = [comparative(list_of_neighbors[index])]
superlatives = [superlative(list_of_neighbors[index])]
lemmas = [lemma(list_of_neighbors[index])]
lexemes = [lexeme(list_of_neighbors[index])]
tensess = [tenses(list_of_neighbors[index])]
suggests = [suggest(list_of_neighbors[index])]
neighbors_with_link_string = None
if parent in synomyms:
neighbors_with_link_string = str(
list_of_neighbors[index]) + "[SYNO]"
elif parent in hypernyms:
neighbors_with_link_string = str(
list_of_neighbors[index]) + "[HYPER]"
elif parent in hyponyms:
neighbors_with_link_string = str(
list_of_neighbors[index]) + "[HYPO]"
elif parent in holonyms:
neighbors_with_link_string = str(
list_of_neighbors[index]) + "[HOLO]"
elif parent in meronyms:
neighbors_with_link_string = str(
list_of_neighbors[index]) + "[MERO]"
elif parent in singulars:
neighbors_with_link_string = str(
list_of_neighbors[index]) + "[PLURAL]"
elif parent in plurals:
neighbors_with_link_string = str(
list_of_neighbors[index]) + "[SINGULAR]"
elif parent in comparatives:
neighbors_with_link_string = str(
list_of_neighbors[index]) + "[COMPA]"
elif parent in superlatives:
neighbors_with_link_string = str(
list_of_neighbors[index]) + "[SUPERLA]"
elif parent in lemmas:
neighbors_with_link_string = str(
list_of_neighbors[index]) + "[LEMMA]"
elif parent in lexemes:
neighbors_with_link_string = str(
list_of_neighbors[index]) + "[LEXEME]"
elif parent in tensess:
neighbors_with_link_string = str(
list_of_neighbors[index]) + "[TENSE]"
elif parent in suggests:
neighbors_with_link_string = str(
list_of_neighbors[index]) + "[MISPELL]"
if neighbors_with_link_string:
try:
return_dict[word][1].append(
neighbors_with_link_string)
except:
return_dict[word] = (count,
[neighbors_with_link_string])
return return_dict
def get_marks(data, image_file):
keywords_matched = 0
#maximum_marks = 5
maximum_marks = data[0]
keywords = []
keywords = data[3].copy()
# keywords=['data','mine','database','characterization','knowledge','background','task','classify','associate','visualize','predict','cluster']
expected_keywords = len(keywords)
#expected_no_of_words = 200
expected_no_of_words = data[1]
#expected_no_of_sentences = 15
expected_no_of_sentences = data[2]
print()
print("----------------------------------------------")
print()
spaced_keywords = []
for word in keywords:
if ' ' in word:
spaced_keywords.append(word)
for word in spaced_keywords:
keywords.remove(word)
print(spaced_keywords)
print(keywords)
# extended_keywords = []
# for word in keywords:
# for syn in wn.synsets(word):
# for l in syn.lemmas():
# extended_keywords.append(l.name())
forms = [
] #We'll store the derivational forms in a set to eliminate duplicates
for word in keywords:
for alemma in wn.lemmas(word): #for each "alemma" lemma in WordNet
forms.append(alemma.name()) #add the lemma itself
for related_lemma in alemma.derivationally_related_forms(
): #for each related lemma
forms.append(related_lemma.name()) #add the related lemma
verb = []
for word in keywords:
verb.extend(lexeme(word))
keywords.extend(forms)
keywords.extend(verb)
keywords = [x.lower() for x in keywords]
keywords = list(set(keywords))
print()
print("----------------------------------------------")
print()
print(keywords)
print()
with io.open(image_file, 'rb') as image_file:
content = image_file.read()
image_file.close()
image = vision.types.Image(content=content)
response = client.text_detection(image=image)
texts = response.text_annotations
string = texts[0].description.replace(
'\n', ' ').lower() #for converting to lower case
string = re.sub('[^A-Za-z0-9.]+', ' ',
string) #for eliminating special character
#here pyenchant is called
print("-----------------------------------------------")
print()
print(string)
print()
word_list = word_tokenize(string) #for word spliting
no_of_words = len(word_list)
word_list = word_enchant(word_list)
if no_of_words > expected_no_of_words:
no_of_words = expected_no_of_words
sent_list = sent_tokenize(string)
print(sent_list)
print()
print("------------------------------------------------")
print()
no_of_sentences = len(sent_list)
if no_of_sentences > expected_no_of_sentences:
no_of_sentences = expected_no_of_sentences
print('no_of_words:', no_of_words)
print('no_of_sentences:', no_of_sentences)
list_of_matched_keywords = []
for keyword in keywords:
if (keyword in word_list):
keywords_matched = keywords_matched + 1
list_of_matched_keywords.append(keyword)
for sent in spaced_keywords:
for sentence in sent_list:
if sent in sentence:
keywords_matched = keywords_matched + 1
list_of_matched_keywords.append(sent)
else:
match_ratio = similar(sentence, sent)
if match_ratio > 0.4:
keywords_matched = keywords_matched + 1
list_of_matched_keywords.append(sent)
if keywords_matched > expected_keywords:
keywords_matched = expected_keywords
print('no of keywords matched:', keywords_matched)
print('keywords matched: ', list_of_matched_keywords)
keywords_percentage = 0.60 * (keywords_matched / expected_keywords)
word_percentage = 0.30 * (no_of_words / expected_no_of_words)
sentence_percentage = 0.10 * (no_of_sentences / expected_no_of_sentences)
print('keywords_percentage:', keywords_percentage)
print('word_percentage:', word_percentage)
print('sentence_percentage:', sentence_percentage)
total_marks = maximum_marks * (keywords_percentage + word_percentage +
sentence_percentage)
total_marks = round(total_marks, 1)
digit = total_marks * 10
if (digit % 10 < 5):
total_marks = math.floor(total_marks)
if (digit % 10 > 5):
total_marks = math.ceil(total_marks)
print('total_marks:', total_marks)
print()
print("(^-^)(^-^)(^-^)(^-^)(^-^)(^-^)(^-^)(^-^)(^-^)(^-^)(^-^)")
print()
return total_marks
from pattern.text.en import conjugate, lemma, lexeme
print (lemma('gave'))
print (lexeme('gave'))