def ex12_short(mdl_typ):
if mdl_typ == 'nml':
prms = ['TCchar', 'CountLineCode', 'CountLineComment' , 'N', 'NN', 'NF','SumCyclomatic']
elif mdl_typ == 'rfn':
prms = ['TCchar', 'CountLineCode', 'CountLineComment', 'N', 'NN', 'NF','SumCyclomatic','chum','relatedChum','delectChum','ncdChum']
elif mdl_typ == 'chrn':
prms = ['chum','relatedChum','delectChum','ncdChum']
THRESHOLD = 0.5
vers = version.get_version_short_list()
ev_values = []
prm_note = []
for curr_ver in vers :
next_ver = version.get_next_version(curr_ver)
print curr_ver
print next_ver
if curr_ver != '4.5.0':
curr_df = ex02.create_df_used_all_predate_nml(curr_ver)
# get paramaters that has lowest aic value
best_prms = ex11.get_best_paramaters(prms, curr_df, curr_ver, mdl_typ)
# dependent value
dv_data = curr_df['fault']
# explanatory value
ev_data = curr_df[list(best_prms)]
# create mdl
logit = sm.Logit(dv_data, ev_data)
result = logit.fit()
# get coefficients
params = result.params.values
coef = pd.Series(params, index=best_prms)
# create model used evaluatopn_ex
next_df = mmm.create_df(next_ver)
# explanatory value
ev_data = next_df[list(best_prms)]
# operate evaluation_ex
logit_odds = ev_data.dot(coef)
evals = logit.cdf(logit_odds)
ev_value = [curr_ver,]
ev_value.extend( ex01.evaluate_ex(next_df, evals) )
ev_values.append(ev_value)
prm_note.append(curr_ver)
prm_note.append(best_prms)
df = pd.DataFrame(ev_values)
df.columns = ['version','nm','np','nf','nc','f_value']
df = df.sort_index(ascending=False)
df.to_csv( './../result/ex12/record_ex12_' + mdl_typ + '_' + str(THRESHOLD) + '.csv', index=False, cols=None)
df = pd.DataFrame(prm_note)
df.to_csv( './../result/ex12/prm_note_'+mdl_typ+'.csv', index=False, cols=None)
def ex1_short(mdl_typ, threshold):
if mdl_typ == 'nml':
prms = ['TCchar', 'CountLineCode', 'CountLineComment' , 'N', 'NN', 'NF','SumCyclomatic']
elif mdl_typ == 'rfn':
prms = ['TCchar', 'CountLineCode', 'CountLineComment', 'N', 'NN', 'NF','SumCyclomatic','chum','relatedChum','delectChum','ncdChum']
elif mdl_typ == 'chrn':
prms = ['chum','relatedChum','delectChum','ncdChum']
THRESHOLD = threshold
vers = version.get_version_short_list()
ev_values = []
print 'operation starts'
for curr_ver in vers :
next_ver = version.get_next_version(curr_ver)
print curr_ver
print next_ver
if curr_ver != '4.5.0':
curr_df = mmm.create_df(curr_ver)
# dependent value
dv_data = curr_df['fault']
# explanatory value
ev_data = curr_df[prms]
# create mdl
logit = sm.Logit(dv_data, ev_data)
result = logit.fit()
# get coefficients
params = result.params.values
coef = pd.Series(params, index=prms)
print coef
# create model used evaluatopn_ex
next_df = mmm.create_df(next_ver)
ev_data = next_df[prms]
print ev_data
# operate evaluation_ex
logit_odds = ev_data.dot(coef)
# print logit_odds
evals = logit.cdf(logit_odds)
print evals
ev_value = [curr_ver,]
# ev_value.extend( evaluate_ex_report(next_df, evals, mdl_typ,curr_ver) )
ev_value.extend( evaluate_ex(next_df, evals) )
ev_values.append(ev_value)
df = pd.DataFrame(ev_values)
df.columns = ['version','nm','np','nf','nc','f_value']
df = df.sort_index(ascending=False)
df.to_csv( './../result/ex1/record_ex1_' + mdl_typ + '_' + str(THRESHOLD) + '.csv', index=False, cols=None)
def evaluate_merged(exNum):
THRESHOLD = 0.5
vers = version.get_version_short_list()
ev_values = []
print 'operation starts'
for curr_ver in vers :
next_ver = version.get_next_version(curr_ver)
print curr_ver
print next_ver
if curr_ver != '4.5.0':
ev_value = [curr_ver,]
ev_value.extend( evaluate_ex_merge(exNum,curr_ver) )
ev_values.append(ev_value)
df = pd.DataFrame(ev_values)
df.columns = ['version','nm','np','nf','nc','f_value']
df = df.sort_index(ascending=False)
df.to_csv( './../result/ex'+str(exNum)+'/Mrecord_ex'+str(exNum)+'_' + str(THRESHOLD) + '.csv', index=False, cols=None)
def ex12_short(mdl_typ):
if mdl_typ == 'nml':
prms = [
'TCchar', 'CountLineCode', 'CountLineComment', 'N', 'NN', 'NF',
'SumCyclomatic'
]
elif mdl_typ == 'rfn':
prms = [
'TCchar', 'CountLineCode', 'CountLineComment', 'N', 'NN', 'NF',
'SumCyclomatic', 'chum', 'relatedChum', 'delectChum', 'ncdChum'
]
elif mdl_typ == 'chrn':
prms = ['chum', 'relatedChum', 'delectChum', 'ncdChum']
THRESHOLD = 0.5
vers = version.get_version_short_list()
ev_values = []
prm_note = []
for curr_ver in vers:
next_ver = version.get_next_version(curr_ver)
print curr_ver
print next_ver
if curr_ver != '4.5.0':
curr_df = ex02.create_df_used_all_predate_nml(curr_ver)
# get paramaters that has lowest aic value
best_prms = ex11.get_best_paramaters(prms, curr_df, curr_ver,
mdl_typ)
# dependent value
dv_data = curr_df['fault']
# explanatory value
ev_data = curr_df[list(best_prms)]
# create mdl
logit = sm.Logit(dv_data, ev_data)
result = logit.fit()
# get coefficients
params = result.params.values
coef = pd.Series(params, index=best_prms)
# create model used evaluatopn_ex
next_df = mmm.create_df(next_ver)
# explanatory value
ev_data = next_df[list(best_prms)]
# operate evaluation_ex
logit_odds = ev_data.dot(coef)
evals = logit.cdf(logit_odds)
ev_value = [
curr_ver,
]
ev_value.extend(ex01.evaluate_ex(next_df, evals))
ev_values.append(ev_value)
prm_note.append(curr_ver)
prm_note.append(best_prms)
df = pd.DataFrame(ev_values)
df.columns = ['version', 'nm', 'np', 'nf', 'nc', 'f_value']
df = df.sort_index(ascending=False)
df.to_csv('./../result/ex12/record_ex12_' + mdl_typ + '_' +
str(THRESHOLD) + '.csv',
index=False,
cols=None)
df = pd.DataFrame(prm_note)
df.to_csv('./../result/ex12/prm_note_' + mdl_typ + '.csv',
index=False,
cols=None)
def ex4():
global record
global THRESHOLD
list = version.get_version_list()
records = []
for curr_ver in list:
if curr_ver != '10.10.2.0':
next_version = version.get_next_version(curr_ver)
print curr_ver
# print next_version
record = []
record.append(curr_ver)
df = create_df_ref('./../data/metrics/METRICS_V' + curr_ver +
'.csv')
# normalize
df = nrmlize(df)
# dependent value
dv_data = df['fault']
# explanatory value
ev_data = df[[
'TCchar', 'LOC', 'N', 'NN', 'NF', 'chum', 'relatedChum',
'delectChum', 'ncdChum', 'intercept'
]]
# create mdl
logit = sm.Logit(dv_data, ev_data)
try:
result = logit.fit()
except:
print curr_ver + 'is singular.'
# result = logit.fit(method='bfgs')
# print result.summary()
# get coefficients
params = result.params.values
coef = pd.Series(params,
index=[
'TCchar', 'LOC', 'N', 'NN', 'NF', 'chum',
'relatedChum', 'delectChum', 'ncdChum',
'intercept'
])
# create model used evaluatopn_ex
df = create_df_ref('./../data/metrics/METRICS_V' + next_version +
'.csv')
# normalize
df = nrmlize(df)
ev_data = df[[
'TCchar', 'LOC', 'N', 'NN', 'NF', 'chum', 'relatedChum',
'delectChum', 'ncdChum', 'intercept'
]]
# operate evaluation_ex
logit_odds = ev_data.dot(coef)
print '---logit_odds---'
print logit_odds
evals = logit.cdf(logit_odds)
print '---evals---'
print evals
# operate evaluation_ex
df = evaluate_ex(df, evals)
pd.DataFrame(df).to_csv('./../data/result/ex4_ref/result_' +
curr_ver + 'ex4_ref.csv',
index=False)
records.append(record)
pd.DataFrame(records).to_csv('./../data/result/record_ex4_ref_' +
str(THRESHOLD) + '.csv',
index=False,
cols=None)
def ex3(threshold):
# global record
global THRESHOLD
global nrm_prms
global ref_prms
THRESHOLD = threshold
vers = version.get_version_short_list()
ev_values_nml = []
ev_values_ref = []
print 'operation starts'
for curr_ver in vers:
next_ver = version.get_next_version(curr_ver)
print curr_ver
print next_ver
if curr_ver != '4.5.0':
curr_df = mm.create_df(curr_ver)
# dependent value
dv_data = curr_df['fault']
# explanatory value
ev_data = curr_df[nrm_prms]
# normalize
ev_data = ev_data.div(ev_data.sum(1), axis=0)
# create mdl
logit = sm.Logit(dv_data, ev_data)
result = logit.fit()
# get coefficients
params = result.params.values
coef = pd.Series(params, index=nrm_prms)
print coef
# create model used evaluatopn_ex
next_df = mm.create_df(next_ver)
# explanatory value
ev_data = next_df[nrm_prms]
# normalize
ev_data = ev_data.div(ev_data.sum(1), axis=0)
# operate evaluation_ex
logit_odds = ev_data.dot(coef)
evals = logit.cdf(logit_odds)
ev_value = [
curr_ver,
]
ev_value.extend(ex01.evaluate_ex(next_df, evals))
ev_values_nml.append(ev_value)
# explanatory value
ev_data = curr_df[ref_prms]
# normalize
ev_data = ev_data.div(ev_data.sum(1), axis=0)
# create mdl
logit = sm.Logit(dv_data, ev_data)
try:
result = logit.fit()
except:
print 'Singular matrix occured'
# get coefficients
params = result.params.values
coef = pd.Series(params, index=ref_prms)
# create model used evaluatopn_ex
ev_data = next_df[ref_prms]
# normalize
ev_data = ev_data.div(ev_data.sum(1), axis=0)
# operate evaluation_ex
logit_odds = ev_data.dot(coef)
evals = logit.cdf(logit_odds)
ev_value = [
curr_ver,
]
ev_value.extend(ex01.evaluate_ex(next_df, evals))
ev_values_ref.append(ev_value)
df = pd.DataFrame(ev_values_nml)
df.columns = ['version', 'nm', 'np', 'nf', 'nc', 'f_value']
df.to_csv('./../result/ex3/record_ex3_nml_' + str(THRESHOLD) + '.csv',
index=False,
cols=None)
df = pd.DataFrame(ev_values_ref)
df.columns = ['version', 'nm', 'np', 'nf', 'nc', 'f_value']
df.to_csv('./../result/ex3/record_ex3_rfn_' + str(THRESHOLD) + '.csv',
index=False,
cols=None)
def ex3(threshold):
# global record
global THRESHOLD
global nrm_prms
global ref_prms
THRESHOLD = threshold
vers = version.get_version_short_list()
ev_values_nml = []
ev_values_ref = []
print 'operation starts'
for curr_ver in vers :
next_ver = version.get_next_version(curr_ver)
print curr_ver
print next_ver
if curr_ver != '4.5.0':
curr_df = mm.create_df(curr_ver)
# dependent value
dv_data = curr_df['fault']
# explanatory value
ev_data = curr_df[nrm_prms]
# normalize
ev_data = ev_data.div(ev_data.sum(1),axis=0)
# create mdl
logit = sm.Logit(dv_data, ev_data)
result = logit.fit()
# get coefficients
params = result.params.values
coef = pd.Series(params, index=nrm_prms)
print coef
# create model used evaluatopn_ex
next_df = mm.create_df(next_ver)
# explanatory value
ev_data = next_df[nrm_prms]
# normalize
ev_data = ev_data.div(ev_data.sum(1),axis=0)
# operate evaluation_ex
logit_odds = ev_data.dot(coef)
evals = logit.cdf(logit_odds)
ev_value = [curr_ver,]
ev_value.extend( ex01.evaluate_ex(next_df, evals) )
ev_values_nml.append(ev_value)
# explanatory value
ev_data = curr_df[ref_prms]
# normalize
ev_data = ev_data.div(ev_data.sum(1),axis=0)
# create mdl
logit = sm.Logit(dv_data, ev_data)
try :
result = logit.fit()
except:
print 'Singular matrix occured'
# get coefficients
params = result.params.values
coef = pd.Series(params, index=ref_prms)
# create model used evaluatopn_ex
ev_data = next_df[ref_prms]
# normalize
ev_data = ev_data.div(ev_data.sum(1),axis=0)
# operate evaluation_ex
logit_odds = ev_data.dot(coef)
evals = logit.cdf(logit_odds)
ev_value = [curr_ver,]
ev_value.extend( ex01.evaluate_ex(next_df, evals) )
ev_values_ref.append(ev_value)
df = pd.DataFrame(ev_values_nml)
df.columns = ['version','nm','np','nf','nc','f_value']
df.to_csv( './../result/ex3/record_ex3_nml_' + str(THRESHOLD) +'.csv', index=False, cols=None)
df = pd.DataFrame(ev_values_ref)
df.columns = ['version','nm','np','nf','nc','f_value']
df.to_csv( './../result/ex3/record_ex3_rfn_' + str(THRESHOLD) +'.csv', index=False, cols=None)
def ex4_short(mdl_typ):
if mdl_typ == 'nml':
prms = ['TCchar', 'CountLineCode', 'N', 'NN', 'NF', 'SumCyclomatic']
elif mdl_typ == 'rfn':
prms = [
'TCchar', 'CountLineCode', 'N', 'NN', 'NF', 'SumCyclomatic',
'chum', 'relatedChum', 'delectChum', 'ncdChum'
]
elif mdl_typ == 'chrn':
prms = ['chum', 'relatedChum', 'delectChum', 'ncdChum']
THRESHOLD = 0.5
vers = version.get_version_short_list()
ev_values = []
print 'operation starts'
for curr_ver in vers:
next_ver = version.get_next_version(curr_ver)
print curr_ver
print next_ver
if curr_ver != '4.5.0':
curr_df = mm.create_df(curr_ver)
prm_dit = {}
hash_dict = {}
key = 0
# dependent value
dv_data = curr_df['fault']
# explanatory value
ev_data = curr_df[prms]
# get aic
aic = get_aic(dv_data, ev_data)
# prm_dit.update(nrm_prms:aic)
prm_dit[key] = aic
hash_dict[key] = prms
key += 1
length = len(prms)
for variables in itertools.combinations(prms, length - 1):
# dependent value
dv_data = curr_df['fault']
# explanatory value
ev_data = curr_df[list(variables)]
# get aic
aic = get_aic(dv_data, ev_data)
# prm_dit.update(variables:aic)
prm_dit[key] = aic
hash_dict[key] = variables
key += 1
print prm_dit
best_hash = max((v, k) for (k, v) in prm_dit.items())[1]
best_prms = hash_dict[best_hash]
# print best_prms
# dependent value
dv_data = curr_df['fault']
# explanatory value
ev_data = curr_df[list(best_prms)]
# create mdl
logit = sm.Logit(dv_data, ev_data)
result = logit.fit()
# get coefficients
params = result.params.values
coef = pd.Series(params, index=best_prms)
# print coef
# create model used evaluatopn_ex
next_df = mm.create_df(next_ver)
# explanatory value
ev_data = next_df[list(best_prms)]
# operate evaluation_ex
logit_odds = ev_data.dot(coef)
evals = logit.cdf(logit_odds)
ev_value = [
curr_ver,
]
ev_value.extend(ex01.evaluate_ex(next_df, evals))
ev_values.append(ev_value)
df = pd.DataFrame(ev_values)
df.columns = ['version', 'nm', 'np', 'nf', 'nc', 'f_value']
df = df.sort_index(ascending=False)
df.to_csv('./../result/ex4/record_ex4_' + mdl_typ + '_' + str(THRESHOLD) +
'.csv',
index=False,
cols=None)
def ex1_short(mdl_typ, threshold):
if mdl_typ == 'nml':
prms = [
'TCchar', 'CountLineCode', 'CountLineComment', 'N', 'NN', 'NF',
'SumCyclomatic'
]
elif mdl_typ == 'rfn':
prms = [
'TCchar', 'CountLineCode', 'CountLineComment', 'N', 'NN', 'NF',
'SumCyclomatic', 'chum', 'relatedChum', 'delectChum', 'ncdChum'
]
elif mdl_typ == 'chrn':
prms = ['chum', 'relatedChum', 'delectChum', 'ncdChum']
THRESHOLD = threshold
vers = version.get_version_short_list()
ev_values = []
print 'operation starts'
for curr_ver in vers:
next_ver = version.get_next_version(curr_ver)
print curr_ver
print next_ver
if curr_ver != '4.5.0':
curr_df = mmm.create_df(curr_ver)
# dependent value
dv_data = curr_df['fault']
# explanatory value
ev_data = curr_df[prms]
# create mdl
logit = sm.Logit(dv_data, ev_data)
result = logit.fit()
# get coefficients
params = result.params.values
coef = pd.Series(params, index=prms)
print coef
# create model used evaluatopn_ex
next_df = mmm.create_df(next_ver)
ev_data = next_df[prms]
print ev_data
# operate evaluation_ex
logit_odds = ev_data.dot(coef)
# print logit_odds
evals = logit.cdf(logit_odds)
print evals
ev_value = [
curr_ver,
]
# ev_value.extend( evaluate_ex_report(next_df, evals, mdl_typ,curr_ver) )
ev_value.extend(evaluate_ex(next_df, evals))
ev_values.append(ev_value)
df = pd.DataFrame(ev_values)
df.columns = ['version', 'nm', 'np', 'nf', 'nc', 'f_value']
df = df.sort_index(ascending=False)
df.to_csv('./../result/ex1/record_ex1_' + mdl_typ + '_' + str(THRESHOLD) +
'.csv',
index=False,
cols=None)
def ex4_short(mdl_typ):
if mdl_typ == 'nml':
prms = ['TCchar', 'CountLineCode', 'N', 'NN', 'NF','SumCyclomatic']
elif mdl_typ == 'rfn':
prms = ['TCchar', 'CountLineCode', 'N', 'NN', 'NF','SumCyclomatic','chum','relatedChum','delectChum','ncdChum']
elif mdl_typ == 'chrn':
prms = ['chum','relatedChum','delectChum','ncdChum']
THRESHOLD = 0.5
vers = version.get_version_short_list()
ev_values = []
print 'operation starts'
for curr_ver in vers :
next_ver = version.get_next_version(curr_ver)
print curr_ver
print next_ver
if curr_ver != '4.5.0':
curr_df = mm.create_df(curr_ver)
prm_dit = {}
hash_dict = {}
key = 0
# dependent value
dv_data = curr_df['fault']
# explanatory value
ev_data = curr_df[prms]
# get aic
aic = get_aic(dv_data, ev_data)
# prm_dit.update(nrm_prms:aic)
prm_dit[key]=aic
hash_dict[key]=prms
key += 1
length = len(prms)
for variables in itertools.combinations(prms, length-1):
# dependent value
dv_data = curr_df['fault']
# explanatory value
ev_data = curr_df[list(variables)]
# get aic
aic = get_aic(dv_data, ev_data)
# prm_dit.update(variables:aic)
prm_dit[key]=aic
hash_dict[key]=variables
key += 1
print prm_dit
best_hash = max((v,k) for (k,v) in prm_dit.items())[1]
best_prms = hash_dict[best_hash]
# print best_prms
# dependent value
dv_data = curr_df['fault']
# explanatory value
ev_data = curr_df[list(best_prms)]
# create mdl
logit = sm.Logit(dv_data, ev_data)
result = logit.fit()
# get coefficients
params = result.params.values
coef = pd.Series(params, index=best_prms)
# print coef
# create model used evaluatopn_ex
next_df = mm.create_df(next_ver)
# explanatory value
ev_data = next_df[list(best_prms)]
# operate evaluation_ex
logit_odds = ev_data.dot(coef)
evals = logit.cdf(logit_odds)
ev_value = [curr_ver,]
ev_value.extend( ex01.evaluate_ex(next_df, evals) )
ev_values.append(ev_value)
df = pd.DataFrame(ev_values)
df.columns = ['version','nm','np','nf','nc','f_value']
df = df.sort_index(ascending=False)
df.to_csv( './../result/ex4/record_ex4_' + mdl_typ + '_' + str(THRESHOLD) + '.csv', index=False, cols=None)