def exp(v1, v2):
version1 = Metrics_Origin(v1, METRICS_DIR)
version2 = Metrics_Origin(v2, METRICS_DIR)
print(v1 + '-' + v2)
alike_metrics = st.compare_two_versions(version1, version2)
print(alike_metrics)
predict(v1, v2, alike_metrics)
def exp(model, metrics_dir):
metrics_dir = '/Users/{}/Dropbox/STUDY/{}/Derby/all'\
.format(ENV, model.dir_name)
ex01 = Ex01(model, metrics_dir)
ex01.METRICS_DIR = metrics_dir
v1 = model.curr_version
v2 = model.pre_version
version1 = Metrics_Origin(v1, metrics_dir)
version2 = Metrics_Origin(v2, metrics_dir)
print(v1 + '-' + v2)
alike_metrics = st.compare_two_versions(version1, version2)
print(alike_metrics)
ex01.predict(v1, v2, alike_metrics)
def predict(ver, predict_ver, alike_metrics):
predictor_rep = PredictorRepository(predict_ver, ver)
training_m = Metrics_Origin(ver, METRICS_DIR)
evaluate_m = Metrics_Origin(predict_ver, METRICS_DIR)
ens_analyzer = AUCAnalyzer(predict_ver, 'ENS', TARGET)
for i in tqdm(range(ITER)):
# NML MODEL
predictor = predictor_rep.get_predictor('ENS', PRED_TYPE)
if predictor is None:
print(' predictor has not found, type: ' + PRED_TYPE)
return
# sm = RandomOverSampler(ratio='auto', random_state=random.randint(1,100))
# X_resampled, y_resampled = sm.fit_sample(training_m.product_df, training_m.fault)
X_resampled, y_resampled = training_m.product_df.as_matrix(
), training_m.fault.as_matrix()
nml_model = predictor.train_model(X_resampled, y_resampled)
ev_data, dv_data = evaluate_m.get_not_modified_df()
nml_value, _ = predictor.predict_ensemble_test_data(
nml_model, ev_data, dv_data, None)
# RFN MODEL
sm = RandomOverSampler(ratio='auto',
random_state=random.randint(1, 100))
X_resampled, y_resampled = sm.fit_sample(training_m.mrg_df,
training_m.fault)
rfn_model = predictor.train_model(X_resampled, y_resampled)
ev_data, dv_data = evaluate_m.get_modified_df()
mrg_value, _ = predictor.predict_ensemble_test_data(
rfn_model, ev_data, dv_data, None)
predictor.set_is_new_df(evaluate_m.isNew)
predictor.set_is_modified_df(evaluate_m.isModified)
report_df = predictor.export_report(predict_ver)
report_df[REPORT_COLUMNS].to_csv('df.csv')
if report_df is not None:
ens_analyzer.set_report_df(report_df[REPORT_COLUMNS])
ens_analyzer.calculate()
ens_analyzer.analyze_predict_result()
# export report
ens_df = ens_analyzer.calculate_average(ITER)
ens_analyzer.export(target_sw=TARGET, df=ens_df, predictor_type=PRED_TYPE)
ens_df = ens_analyzer.calculate_num_report_averge(ITER)
ens_analyzer.export_count_report(target_sw=TARGET,
df=ens_df,
predictor_type=PRED_TYPE)
def predict(ver, predict_ver, alike_metrics):
training_m = Metrics_Origin(ver, METRICS_DIR)
evaluate_m = Metrics_Origin(predict_ver, METRICS_DIR)
ens_analyzer = Analyzer(predict_ver, 'ENS')
predictor_rep = PredictorRepository(predict_ver, ver)
for i in tqdm(range(ITER)):
# NML MODEL
predictor = predictor_rep.get_predictor('ENS', PRED_TYPE)
if predictor is None:
print(' predictor has not found, type: ' + PRED_TYPE)
return
sm = RandomOverSampler(ratio='auto',
random_state=random.randint(1, 100))
X_resampled, y_resampled = sm.fit_sample(training_m.product_df,
training_m.fault)
model = predictor.train_model(X_resampled, y_resampled)
ev_data, dv_data = evaluate_m.get_not_modified_df()
nml_value, _ = predictor.predict_ensemble_proba(
model, ev_data, dv_data, None)
# DST MODEL
predictor2 = predictor_rep.get_predictor('ENS', PRED_TYPE2)
if predictor2 is None:
print(' predictor has not found, type: ' + PRED_TYPE2)
return
sm = RandomOverSampler(ratio='auto',
random_state=random.randint(1, 100))
X_resampled, y_resampled = sm.fit_sample(training_m.mrg_df,
training_m.fault)
model = predictor2.train_model(X_resampled, y_resampled)
ev_data, dv_data = evaluate_m.get_modified_df()
mrg_value, _ = predictor2.predict_ensemble_proba(
model, ev_data, dv_data, None)
predictor2.set_is_new_df(evaluate_m.isNew)
predictor2.set_is_modified_df(evaluate_m.isModified)
report_df = predictor2.export_report(predict_ver)
if report_df is not None:
ens_analyzer.set_report_df(report_df[REPORT_COLUMNS])
ens_analyzer.calculate()
# export report
ens_df = ens_analyzer.calculate_average(ITER)
predictor_type_name = "{0}{1}".format(PRED_TYPE, PRED_TYPE2)
ens_analyzer.export(target_sw=TARGET, df=ens_df, predictor_type=PRED_TYPE)
ens_analyzer.export_accum_df(target_sw=TARGET)
def main():
import csv
f = open('sw_indecies.csv', 'w')
writer = csv.writer(f, lineterminator='\n')
model_dict = model_creator.get_model_dictionary()
indecies_list = []
col_list = ['total modules', 'modified modules', 'bug modules',
'modified bug modules']
writer.writerow(col_list)
for sw_name, models in model_dict.items():
for model in models:
print(sw_name, model.final_version)
metrics_dir = "/Users/{}/Dropbox/STUDY/Metrics/".format(ENV)
version = model.final_version
metrics = Metrics_Origin(version, metrics_dir, model)
modified_df, modified_fault = metrics.get_modified_df()
df = pd.concat([modified_df, modified_fault], axis=1)
modified_df = df.rename(columns = {df.columns[-1]:'fault'})
mrg_df, fault = metrics.mrg_df, metrics.fault
df = pd.concat([mrg_df, fault], axis=1)
df = df.rename(columns = {df.columns[-1]:'fault'})
# print(df)
li = ['{} {}'.format(sw_name, model.final_version)]
# 総モジュール数
print('total modules, {}'.format(len(df)))
li.append(len(df))
# 変更モジュール数
print('modified modules, {}'.format(len(modified_df)))
li.append(len(modified_df))
# 総欠陥数
d = df[fault.apply(lambda x: x==1)]
print('bug modules, {}'.format(len(d)))
li.append(len(d))
# 変更が合ったうちの総欠陥数
d = modified_df[fault.apply(lambda x: x==1)]
print('modified bug modules, {}'.format(len(d)))
li.append(len(d))
writer.writerow(li)
def __create_boxplot_seaborn(g1, g2, save_name, title=None):
# create graph just one version
import seaborn as sns
g1.columns = [['pre']]
g2.columns = [['cre']]
hige = pd.concat([g1, g2], axis=1)
# print(hige)
sns.stripplot(data=hige)
# ax.set_xticklabels(['pre', 'cre'])
plt.grid()
plt.xlabel('VERSION')
plt.ylabel('METRICS VALUE')
plt.savefig(save_name)
if __name__ == '__main__':
"""
メトリクスの分布を箱ひげ図で表すスクリプト
"""
v1 = '4.1.0'
v2 = '4.2.0'
METRICS_DIR = '/Users/' + ENV + '/Dropbox/STUDY/Metrics/Solr/all'
version1 = Metrics_Origin(v1, METRICS_DIR)
version2 = Metrics_Origin(v2, METRICS_DIR)
metrics = 'pd2'
_v1 = version1.mrg_df[[metrics]]
_v2 = version2.mrg_df[[metrics]]
save_name = 'compare-wisky-' + metrics + '.png'
# _create_boxplot_diagram(_v1, _v2, save_name)
__create_boxplot_seaborn(_v1, _v2, save_name)
def predict(ver, predict_ver, alike_metrics):
predictor_rep = PredictorRepository(predict_ver, ver)
# if TARGET == 'Derby':
# # Apache-Derby
# training_m = Metrics_Origin(ver, METRICS_DIR)
# evaluate_m = Metrics_Origin(predict_ver, METRICS_DIR)
# else:
# # NO SERVUCE
# return
training_m = Metrics_Origin(ver, METRICS_DIR)
evaluate_m = Metrics_Origin(predict_ver, METRICS_DIR)
# nml_analyzer = AUCAnalyzer(predict_ver, 'NML', TARGET)
# rfn_analyzer = AUCAnalyzer(predict_ver, 'RFN', TARGET)
# itg_analyzer = AUCAnalyzer(predict_ver, 'ITG', TARGET)
nml_analyzer = Analyzer(predict_ver, 'NML')
rfn_analyzer = Analyzer(predict_ver, 'RFN')
itg_analyzer = Analyzer(predict_ver, 'ITG')
for i in tqdm(range(ITER)):
# NML MODEL
predictor = predictor_rep.get_predictor('NML', PRED_TYPE)
if predictor is None:
print(' predictor has not found, type: ' + PRED_TYPE)
return
sm = RandomOverSampler(ratio='auto',
random_state=random.randint(1, 100))
X_resampled, y_resampled = sm.fit_sample(training_m.product_df,
training_m.fault)
model = predictor.train_model(X_resampled, y_resampled)
nml_value, importance = predictor.predict_proba(
model, evaluate_m.product_df, evaluate_m.fault,
TARGET + "-ex1nml.csv")
predictor.set_is_new_df(evaluate_m.isNew)
predictor.set_is_modified_df(evaluate_m.isModified)
report_df = predictor.export_report(predict_ver)
if report_df is not None:
nml_analyzer.set_report_df(report_df[REPORT_COLUMNS])
nml_analyzer.calculate()
# RFN MODEL
predictor = predictor_rep.get_predictor('RFN', PRED_TYPE)
sm = RandomOverSampler(ratio='auto',
random_state=random.randint(1, 100))
X_resampled, y_resampled = sm.fit_sample(training_m.mrg_df,
training_m.fault)
model = predictor.train_model(X_resampled, y_resampled)
rfn_value, importance = predictor.predict_proba(
model, evaluate_m.mrg_df, evaluate_m.fault, TARGET + "-ex1rfn.csv")
predictor.set_is_new_df(evaluate_m.isNew)
predictor.set_is_modified_df(evaluate_m.isModified)
report_df = predictor.export_report(predict_ver)
if report_df is not None:
rfn_analyzer.set_report_df(report_df[REPORT_COLUMNS])
rfn_analyzer.calculate()
# INTELLIGENCE MODEL
predictor = predictor_rep.get_predictor('ITG', PRED_TYPE)
sm = RandomOverSampler(ratio='auto',
random_state=random.randint(1, 100))
alike_df = training_m.get_specific_df(alike_metrics)
X_resampled, y_resampled = sm.fit_sample(alike_df, training_m.fault)
model = predictor.train_model(X_resampled, y_resampled)
alike_df = evaluate_m.get_specific_df(alike_metrics)
rfn_value, importance = predictor.predict_proba(
model, alike_df, evaluate_m.fault, TARGET + "-ex1itg.csv")
predictor.set_is_new_df(evaluate_m.isNew)
predictor.set_is_modified_df(evaluate_m.isModified)
report_df = predictor.export_report(predict_ver)
if report_df is not None:
itg_analyzer.set_report_df(report_df[REPORT_COLUMNS])
itg_analyzer.calculate()
# export report
nml_df = nml_analyzer.calculate_average(ITER)
rfn_df = rfn_analyzer.calculate_average(ITER)
itg_df = itg_analyzer.calculate_average(ITER)
df = pd.concat([nml_df, rfn_df, itg_df], ignore_index=True)
nml_analyzer.export_accum_df(target_sw=TARGET)
rfn_analyzer.export_accum_df(target_sw=TARGET)
itg_analyzer.export_accum_df(target_sw=TARGET)
nml_analyzer.export(target_sw=TARGET, df=df,
predictor_type=PRED_TYPE) # どのanalyzerクラスでも良い