def main():
t = Taxonomy()
product = "Nautilus"
signified = "Reliability"
# s = t.get_signifiers('Usability')
# alls = ''
# for word in s:
# alls += word
# alls += t.find_spelling(word)
# result = query_database('Evolution', [alls])
# for signified in t.get_signified(): # e.g. usability, performance, etc
# for product in t.get_products():
# result = query_database(product, t.get_signifiers(signified), t) #e.g. usability: usability, usable, etc.
# save_file(result, product, signified)
result = query_database(product, t.get_signifiers(signified), t) #e.g. usability: usability, usable, etc.
save_file(result, product, signified)
def main():
t = Taxonomy()
product = "Nautilus"
signified = "Reliability"
# s = t.get_signifiers('Usability')
# alls = ''
# for word in s:
# alls += word
# alls += t.find_spelling(word)
# result = query_database('Evolution', [alls])
# for signified in t.get_signified(): # e.g. usability, performance, etc
# for product in t.get_products():
# result = query_database(product, t.get_signifiers(signified), t) #e.g. usability: usability, usable, etc.
# save_file(result, product, signified)
result = query_database(product, t.get_signifiers(signified),
t) #e.g. usability: usability, usable, etc.
save_file(result, product, signified)
from names import Taxonomy
import subprocess
t = Taxonomy()
for sign in t.get_signified():
wordlist = t.get_signifiers(sign)
for word in wordlist:
p = subprocess.Popen(["perl", "typo.pl", word],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
stdin=subprocess.PIPE)
(out, err) = p.communicate()
print out
# print word
def get_counts(keyword):
""" store in the database"""
store_cursor = connect_corpus("data_objects")
t = Taxonomy()
prod = 'Nautilus'
total = 50
query_string = """ select event from data_objects.refsq_data
order by rand() limit %(total)d""" % {"prod":prod, "total":total} # msr_type = "Mail" where product = "%(prod)s"
# = """select event from data_objects.refsq_data where match(event)
# against (\'%(key)s\' in boolean mode)
# order by rand() limit %(total)d""" % {"key":keyword, "total":total}
try:
# print query_string
store_cursor.execute(query_string)
yes = 0.0
no = 0.0
i = 0
wn_fn_count = 0
ext_fn_count = 0
for result in store_cursor.fetchall():
event = result.values()[0]
#result = str(store_cursor.fetchall().values()[0]) #{'count(*)': 6L} dict
print event
i = i + 1
answer = raw_input("\n******\n"+ str(i) + "/" + str(total) + " Quality: [u/r/m/e/p/f/n]: ")
#wait for user input
if answer != 'n':
yes = yes + 1.0
#check against our algorithm
if answer == 'u':
signifiers_ext = t.get_signifiers('Usability')
signifiers_wn = t.get_signifiers_wn('Usability')
#print signifiers
elif answer == 'r':
signifiers_ext = t.get_signifiers('Reliability')
signifiers_wn = t.get_signifiers_wn('Reliability')
elif answer == 'm':
signifiers_ext = t.get_signifiers('Maintainability')
signifiers_wn = t.get_signifiers_wn('Maintainability')
elif answer == 'e':
signifiers_ext = t.get_signifiers('Efficiency')
signifiers_wn = t.get_signifiers_wn('Efficiency')
elif answer == 'p':
signifiers_ext = t.get_signifiers('Portability')
signifiers_wn = t.get_signifiers_wn('Portability')
elif answer == 'f':
signifiers_ext = t.get_signifiers('Functionality')
signifiers_wn = t.get_signifiers_wn('Functionality')
found_wn, found_ext = check_list(event, signifiers_wn, signifiers_ext)
if not found_wn:
# false negative
wn_fn_count += 1
print wn_fn_count
if not found_ext:
ext_fn_count += 1
print ext_fn_count
else:
no = no + 1.0 # TODO could extend this to see whether the standard query matches it even so
wn_rate = wn_fn_count/float(yes)
ext_rate = ext_fn_count/float(yes) #of the ones we marked, how many were not found?
print ext_fn_count
print "Number of matches was %s" % (yes)
print "False negative rate was wn: %s and ext: %s" % (str(wn_rate),str(ext_rate))
except (ValueError):
print 'Error in query syntax'
from names import Taxonomy
import subprocess
t = Taxonomy()
for sign in t.get_signified():
wordlist = t.get_signifiers(sign)
for word in wordlist:
p = subprocess.Popen(
["perl", "typo.pl", word], stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE
)
(out, err) = p.communicate()
print out
# print word
def get_counts(keyword):
""" store in the database"""
store_cursor = connect_corpus("data_objects")
t = Taxonomy()
prod = 'Nautilus'
total = 50
query_string = """ select event from data_objects.refsq_data
order by rand() limit %(total)d""" % {
"prod": prod,
"total": total
} # msr_type = "Mail" where product = "%(prod)s"
# = """select event from data_objects.refsq_data where match(event)
# against (\'%(key)s\' in boolean mode)
# order by rand() limit %(total)d""" % {"key":keyword, "total":total}
try:
# print query_string
store_cursor.execute(query_string)
yes = 0.0
no = 0.0
i = 0
wn_fn_count = 0
ext_fn_count = 0
for result in store_cursor.fetchall():
event = result.values()[0]
#result = str(store_cursor.fetchall().values()[0]) #{'count(*)': 6L} dict
print event
i = i + 1
answer = raw_input("\n******\n" + str(i) + "/" + str(total) +
" Quality: [u/r/m/e/p/f/n]: ")
#wait for user input
if answer != 'n':
yes = yes + 1.0
#check against our algorithm
if answer == 'u':
signifiers_ext = t.get_signifiers('Usability')
signifiers_wn = t.get_signifiers_wn('Usability')
#print signifiers
elif answer == 'r':
signifiers_ext = t.get_signifiers('Reliability')
signifiers_wn = t.get_signifiers_wn('Reliability')
elif answer == 'm':
signifiers_ext = t.get_signifiers('Maintainability')
signifiers_wn = t.get_signifiers_wn('Maintainability')
elif answer == 'e':
signifiers_ext = t.get_signifiers('Efficiency')
signifiers_wn = t.get_signifiers_wn('Efficiency')
elif answer == 'p':
signifiers_ext = t.get_signifiers('Portability')
signifiers_wn = t.get_signifiers_wn('Portability')
elif answer == 'f':
signifiers_ext = t.get_signifiers('Functionality')
signifiers_wn = t.get_signifiers_wn('Functionality')
found_wn, found_ext = check_list(event, signifiers_wn,
signifiers_ext)
if not found_wn:
# false negative
wn_fn_count += 1
print wn_fn_count
if not found_ext:
ext_fn_count += 1
print ext_fn_count
else:
no = no + 1.0 # TODO could extend this to see whether the standard query matches it even so
wn_rate = wn_fn_count / float(yes)
ext_rate = ext_fn_count / float(
yes) #of the ones we marked, how many were not found?
print ext_fn_count
print "Number of matches was %s" % (yes)
print "False negative rate was wn: %s and ext: %s" % (str(wn_rate),
str(ext_rate))
except (ValueError):
print 'Error in query syntax'
