def main():
filename = './origin_data/bugreports.xml'
path = './bug_reports'
bugslist = utils.read_xml(filename)
# print(bugslist)
label = utils.read_label('./origin_data/goldset.txt')
# print(label)
samples, ids = utils.get_content(bugslist)
# print(samples)
num_word_list, numword = utils.count_word(samples)
# print(len(num_word_list))
# for i in num_word_list:
# num_sentence.append(len(i))
utils.savefile(samples)
# print(num_sentence)
results = textrank.bugsum(path, numword, num_word_list)
print(len(i) for i in results)
# extra_ids = index2id(results,ids)
# print(len(extra_ids))
pred = eval.index2pred(results, ids)
y = eval.label2y(label, ids)
mean_acc, mean_pr, mean_re, mean_f1 = eval.evaluate(y, pred)
print('mean_acc, mean_pr, mean_re, mean_f1', mean_acc, mean_pr, mean_re,
mean_f1)
def on_modified(self, event):
modified_content = file_reader(event.src_path)
count = count_word(modified_content, KEYWORD_TO_COUNT)
log_writer = Logger()
log_writer.write_logs(
f'In file: {event.src_path} Keyword count of {KEYWORD_TO_COUNT} is {count}'
)
print('%s File modified CDS count: %s' % (event.src_path, count))
def clean_data():
start_time = time.time()
processer = dataProcessor.DataProcessor()
data = pd.read_csv(data_path, header=0)
if mode.lower() == 'clean':
data['word_count'] = utils.count_word(data.text)
data['count_number'] = utils.count_numbers(data.text)
data['emojies'] = utils.view_emojie(data.text)
data['emoticons'] = utils.view_emoticon(data.text)
data['len_tweet'] = utils.len_tweet(data.text)
data['avg_words_len'] = utils.avg_word_len(data.text)
data['count_stopwords'] = utils.count_stopwords(data.text)
data['count_tagging'] = utils.count_tagging(data.text)
data['flagged'] = utils.repeated_char(data.text)
# data_copy.append([word_count, count_number, emojies, len_tweet, avg_words_len, count_stopwords, count_tagging], ignore_index=True)
data.to_csv(filename + '.csv', index=False)
tf = utils.term_freq(data.text)
tf.to_csv('term_frequency.csv', index=False)
data_pro, _ = processer.proccess_data(data.text,
handle_emojies=handle_emojies)
data_pro = pd.DataFrame(data_pro, columns=['text'])
data_pro.append(data['label'])
data_pro.to_csv('cleaned.csv', index=False)
elapsed_time = time.time() - start_time
print(f'Finished in {elapsed_time}')
return None
def text_summary(self):
"""Composes a textual summary of the event."""
msg = "The build event was started on %s." % self.text_timestamp()
msg += ' It'
pkgCount = len(self.list_package_files())
changesName = self.file_path('changes.html')
commitCount = 0
if os.path.exists(changesName):
commitCount = utils.count_word('<li>', file(changesName).read())
if commitCount:
moreThan = ''
if commitCount == 100: moreThan = 'more than '
msg += " contains %s%i commits and" % (moreThan, commitCount)
msg += " produced %i installable binary package%s." % \
(pkgCount, 's' if (pkgCount != 1) else '')
return msg
def text_summary(self):
"""Composes a textual summary of the event."""
msg = "The build event was started on %s." % self.text_timestamp()
msg += ' It'
pkgCount = len(self.list_package_files())
changesName = self.file_path('changes.html')
commitCount = 0
if os.path.exists(changesName):
commitCount = utils.count_word('<li>', file(changesName).read())
if commitCount:
moreThan = ''
if commitCount == 100: moreThan = 'more than '
msg += " contains %s%i commits and" % (moreThan, commitCount)
msg += " produced %i package%s." % \
(pkgCount, 's' if (pkgCount != 1) else '')
return msg
def html_description(self, encoded=True):
"""Composes an HTML build report."""
name = self.name
buildDir = self.buildDir
oses = self.oses
msg = '<p>' + self.text_summary() + '</p>'
# What do we have here?
files = self.list_package_files()
# Print out the matrix.
msg += '<p><table cellspacing="4" border="0">'
msg += '<tr style="text-align:left;"><th>OS<th>Binary<th>Logs<th>Issues</tr>'
for osName, osExt, osIdent in oses:
isFirst = True
# Find the binaries for this OS.
binaries = []
for f in files:
if self.os_from_filename(f)[2] == osIdent:
binaries.append(f)
if not binaries:
# Nothing available for this OS.
msg += '<tr><td>' + osName + '<td>n/a'
# Do we have a log?
logName = log_filename(self.packages[0], osIdent)
if os.path.exists(self.file_path(logName)):
msg += self.html_table_log_issues(logName)
msg += '</tr>'
continue
# List all the binaries. One row per binary.
for binary in self.sort_by_package(binaries):
msg += '<tr><td>'
if isFirst:
msg += osName
isFirst = False
msg += '<td>'
msg += '<a href="%s">%s</a>' % (self.download_uri(binary), binary)
# Status of the log.
logName = self.compressed_log_filename(binary)
if not os.path.exists(self.file_path(logName)):
msg += '</tr>'
continue
# Link to the compressed log.
msg += self.html_table_log_issues(logName)
msg += '</tr>'
msg += '</table></p>'
# Changes.
chgFn = self.file_path('changes.html')
if os.path.exists(chgFn):
if utils.count_word('<li>', file(chgFn).read()):
msg += '<h2>Commits</h2>' + file(chgFn, 'rt').read()
# Enclose it in a CDATA block if needed.
if encoded: return '<![CDATA[' + msg + ']]>'
return msg
def html_description(self, encoded=True):
"""Composes an HTML build report."""
name = self.name
buildDir = self.buildDir
oses = self.oses
msg = '<p>' + self.text_summary() + '</p>'
# What do we have here?
files = self.list_package_files()
# Print out the matrix.
msg += '<p><table cellspacing="4" border="0">'
msg += '<tr style="text-align:left;"><th>OS<th>Binary<th>Logs<th>Issues</tr>'
for osName, osExt, osIdent in oses:
isFirst = True
# Find the binaries for this OS.
binaries = []
for f in files:
if self.os_from_filename(f)[2] == osIdent:
binaries.append(f)
if not binaries:
# Nothing available for this OS.
msg += '<tr><td>' + osName + '<td>n/a'
# Do we have a log?
logName = log_filename(self.packages[0], osIdent)
if os.path.exists(self.file_path(logName)):
msg += self.html_table_log_issues(logName)
msg += '</tr>'
continue
# List all the binaries. One row per binary.
for binary in self.sort_by_package(binaries):
msg += '<tr><td>'
if isFirst:
msg += osName
isFirst = False
msg += '<td>'
msg += '<a href="%s">%s</a>' % (self.download_uri(binary),
binary)
# Status of the log.
logName = self.compressed_log_filename(binary)
if not os.path.exists(self.file_path(logName)):
msg += '</tr>'
continue
# Link to the compressed log.
msg += self.html_table_log_issues(logName)
msg += '</tr>'
msg += '</table></p>'
# Changes.
chgFn = self.file_path('changes.html')
if os.path.exists(chgFn):
if utils.count_word('<li>', file(chgFn).read()):
msg += '<h2>Commits</h2>' + file(chgFn, 'rt').read()
# Enclose it in a CDATA block if needed.
if encoded: return '<![CDATA[' + msg + ']]>'
return msg
test = collection.find().next()
articles_wordcount = {}
i = 0
for article in collection.find({
'type': 'article',
'creationDate': {
'$gte': datetime(2019, 1, 1)
}
}):
i += 1
print(i)
wordcount = 0
title_wordcount = 0
for chapter in article['title'].values():
title_wordcount += count_word(chapter)
for chapter in article['chapters']:
if chapter['type'] == 'paragraph':
text = [text for text in chapter['text'].values()]
for t in text:
wordcount += count_word(t)
articles_wordcount[article['id']] = wordcount
with open("Articles_wordcount.json", 'w') as f:
json.dump(articles_wordcount, f)
f.close()
with open("title_wordcount.json", 'w') as f:
json.dump(articles_wordcount, f)
f.close()
