def calculate_popularity(file_path):
references_count = Counter()
for idx, ref in enumerate(ref_gen(file_path)):
if idx % 100 == 0:
print("cp %d" % idx)
references_count[ref.cited_id] += 1
return references_count
def calculate_popularity(file_path):
references_count = Counter()
for idx, ref in enumerate(ref_gen(file_path)):
if idx % 100 == 0:
print("cp %d" % idx)
references_count[ref.cited_id] += 1
return references_count
def count_paragraph_titles_for_citations(file_path):
id_titles_dict = defaultdict(Counter) #e.g. {"1233242":{"introduction":1234. "background":123}}
for idx, ref in enumerate(ref_gen(file_path)):
if idx % 100 == 0:
print(idx)
title = ref.title.lower()
id_titles_dict[ref.cited_id][title] += 1
return id_titles_dict
def find_cits_with_sentiment_words(file_path):
ret = set()
for idx, ref in enumerate(ref_gen(file_path)):
if idx % 100 == 0:
print(idx)
tokens = set(smart_tokenize(ref.get_sentence()))
intersect = tokens.intersection(sentiment_words)
if len(intersect) <> 0:
ret.add(ref, list(intersect))
return ret
def find_cits_with_sentiment_words(file_path):
ret = set()
for idx, ref in enumerate(ref_gen(file_path)):
if idx % 100 == 0:
print(idx)
tokens = set(smart_tokenize(ref.get_sentence()))
intersect = tokens.intersection(sentiment_words)
if len(intersect) <> 0:
ret.add(ref, list(intersect))
return ret
def count_words_in_context(file_path, popular_pmids):
word_count = defaultdict(Counter)
for idx, ref in enumerate(ref_gen(file_path)):
if idx % 100 == 0:
print(idx)
if ref.cited_id not in popular_pmids:
continue
citing_sentence = ref.get_sentence(0)
tokens = smart_tokenize(citing_sentence)
word_count[ref.cited_id] += Counter(tokens)
return word_count
def count_words_in_context(file_path, popular_pmids):
word_count = defaultdict(Counter)
for idx, ref in enumerate(ref_gen(file_path)):
if idx % 100 == 0:
print(idx)
if ref.cited_id not in popular_pmids:
continue
citing_sentence = ref.get_sentence(0)
tokens = smart_tokenize(citing_sentence)
word_count[ref.cited_id] += Counter(tokens)
return word_count