def getClift(rule, s, c, decision_table, list_judgeNominal):
supp, conf = LERS.getSupportConfidence(rule, decision_table,list_judgeNominal)
rule_c = mlem2.delEfromRule(rule,s)
rule_c = rule_c.setValue(s,c)
supp_c, conf_c = LERS.getSupportConfidence(rule_c, decision_table, list_judgeNominal)
clift = conf / conf_c
return(clift)
def getElift(rule, attr, v, decision_table, list_judgeNominal):
supp, conf = LERS.getSupportConfidence(rule, decision_table, list_judgeNominal)
rule_s = delEFromRule(rule, attr, v)
supp_s, conf_s = LERS.getSupportConfidence(rule_s, decision_table, list_judgeNominal)
if conf_s == 0: elift = 999
else : elift = conf / conf_s
return(elift)
def MLEM2_LERS(FILENAME, iter1, iter2):
# rule induction and rule save
fullpath_filename = DIR_UCI + "/" + FILENAME + "/rules/" + "rules_" + str(iter1) + "-" + str(iter2) + ".pkl"
rules = (
mlem2.loadPickleRules(fullpath_filename)
if os.path.isfile(fullpath_filename)
else mlem2.getRulesByMLEM2(FILENAME, iter1, iter2)
)
if not os.path.isfile(fullpath_filename):
mlem2.savePickleRules(rules, fullpath_filename)
# test data setup
decision_table_test, decision_class = getData(FILENAME, iter1, iter2, T="test")
list_judgeNominal = getJudgeNominal(decision_table_test, FILENAME)
# predict by LERS
predictions = LERS.predictByLERS(rules, decision_table_test, list_judgeNominal)
# 正答率を求める
accuracy = accuracy_score(decision_class, predictions)
# rules の数を求める
num = len(rules)
# 各クラスのrulesの数を求める
num_class = strNumClassRules(rules)
# 平均の長さを求める
mean_length = mlem2.getMeanLength(rules)
# 平均支持度と平均確信度を求める
decision_table_train, decision_class = getData(FILENAME, iter1, iter2, T="train")
list_judgeNominal = getJudgeNominal(decision_table_train, FILENAME)
mean_support, mean_conf = LERS.getSupportConfidenceRules(rules, decision_table_train, list_judgeNominal)
# AccとRecallを求める
acc_recall = LERS.getAccurayRecall(rules, decision_table_train, list_judgeNominal)
# ファイルにsave
savepath = DIR_UCI + "/" + FILENAME + "/fairness/00_normal/MLEM2_LERS.csv"
with open(savepath, "a") as f:
f.writelines(
"MLEM2_LERS,{FILENAME},{iter1},{iter2},{acc},{num},{num_class},{mean_length},{mean_support},{mean_conf},{acc_recall}".format(
FILENAME=FILENAME,
iter1=iter1,
iter2=iter2,
acc=accuracy,
num=num,
num_class=num_class,
mean_length=mean_length,
mean_support=mean_support,
mean_conf=mean_conf,
acc_recall=strAccRecall(rules, acc_recall),
)
+ "\n"
)
return 0
def Apriori_LERS(FILENAME, iter1, iter2, minsup, minconf) :
# rule induction
fullpath_filename = '/data/uci/'+FILENAME+'/apriori/'+'rules_'+str(iter1)+'-'+str(iter2)+'-'+str(minsup)+'-'+str(minconf)+'.pkl'
rules = mlem2.loadPickleRules(fullpath_filename) if os.path.isfile(fullpath_filename) else apriori.getRulesByApriori(FILENAME, iter1, iter2, minsup, minconf)
# rule save
if not os.path.isfile(fullpath_filename): mlem2.savePickleRules(rules, fullpath_filename)
# test data setup
filepath = '/data/uci/'+FILENAME+'/'+FILENAME+'-test'+str(iter1)+'-'+str(iter2)+'.tsv'
decision_table_test = mlem2.getDecisionTable(filepath)
decision_table_test = decision_table_test.dropna()
decision_class = decision_table_test[decision_table_test.columns[-1]].values.tolist()
filepath = '/data/uci/'+FILENAME+'/'+FILENAME+'.nominal'
list_nominal = mlem2.getNominalList(filepath)
list_judgeNominal = mlem2.getJudgeNominal(decision_table_test, list_nominal)
# predict by LERS
predictions = LERS.predictByLERS(rules, decision_table_test, list_judgeNominal)
# 正答率を求める
accuracy = accuracy_score(list(map(str,decision_class)), predictions)
#print('{FILENAME} : {iter1} {iter2}'.format(FILENAME=FILENAME,iter1=iter1,iter2=iter2))
logging.basicConfig(filename=os.path.dirname(os.path.abspath("__file__"))+'/'+FILENAME+'.log',format='%(asctime)s,%(message)s',level=logging.DEBUG)
logging.info('Apriori_LERS,{FILENAME},{iter1},{iter2},{acc},{minsup},{minconf}'.format(FILENAME=FILENAME,iter1=iter1,iter2=iter2,acc=accuracy,minsup=minsup,minconf=minconf))
return(accuracy)
def MLEM2_LERS(FILENAME, iter1, iter2) :
# rule induction
fullpath_filename = DIR_UCI+'/'+FILENAME+'/rules/'+'rules_'+str(iter1)+'-'+str(iter2)+'.pkl'
rules = mlem2.loadPickleRules(fullpath_filename) if os.path.isfile(fullpath_filename) else mlem2.getRulesByMLEM2(FILENAME, iter1, iter2)
# rule save
if not os.path.isfile(fullpath_filename): mlem2.savePickleRules(rules, fullpath_filename)
# test data setup
filepath = DIR_UCI+'/'+FILENAME+'/'+FILENAME+'-test'+str(iter1)+'-'+str(iter2)+'.tsv'
decision_table_test = mlem2.getDecisionTable(filepath)
decision_table_test = decision_table_test.dropna()
decision_class = decision_table_test[decision_table_test.columns[-1]].values.tolist()
filepath = DIR_UCI+'/'+FILENAME+'/'+FILENAME+'.nominal'
list_nominal = mlem2.getNominalList(filepath)
list_judgeNominal = mlem2.getJudgeNominal(decision_table_test, list_nominal)
# predict by LERS
predictions = LERS.predictByLERS(rules, decision_table_test, list_judgeNominal)
# 正答率を求める
accuracy = accuracy_score(decision_class, predictions)
#print('{FILENAME} : {iter1} {iter2}'.format(FILENAME=FILENAME,iter1=iter1,iter2=iter2))
#logging.info('MLEM2_LERS,1,{FILENAME},{iter1},{iter2},{acc}'.format(FILENAME=FILENAME,iter1=iter1,iter2=iter2,acc=accuracy))
savepath = DIR_UCI+'/'+FILENAME+'/MLEM2_LERS.csv'
with open(savepath, "a") as f :
f.writelines('MLEM2_LERS,1,{FILENAME},{iter1},{iter2},{acc}'.format(FILENAME=FILENAME,iter1=iter1,iter2=iter2,acc=accuracy)+"\n")
return(accuracy)
def MLEM2_RuleClusteringByRandom_LERS(FILENAME, iter1, iter2, k):
# rule induction
fullpath_filename = DIR_UCI + '/' + FILENAME + '/rules/' + 'rules_' + str(
iter1) + '-' + str(iter2) + '.pkl'
rules = mlem2.loadPickleRules(fullpath_filename) if os.path.isfile(
fullpath_filename) else mlem2.getRulesByMLEM2(FILENAME, iter1, iter2)
# rule save
if not os.path.isfile(fullpath_filename):
mlem2.savePickleRules(rules, fullpath_filename)
# rule clustering
fullpath_filename = DIR_UCI + '/' + FILENAME + '/rules_cluster_random/' + 'rules-' + str(
k) + '_' + str(iter1) + '-' + str(iter2) + '.pkl'
rules = mlem2.loadPickleRules(fullpath_filename) if os.path.isfile(
fullpath_filename) else clustering.getRuleClusteringByRandom(rules,
k=k)
# rule save
if not os.path.isfile(fullpath_filename):
mlem2.savePickleRules(rules, fullpath_filename)
# test data setup
filepath = DIR_UCI + '/' + FILENAME + '/' + FILENAME + '-test' + str(
iter1) + '-' + str(iter2) + '.tsv'
decision_table_test = mlem2.getDecisionTable(filepath)
decision_table_test = decision_table_test.dropna()
decision_class = decision_table_test[
decision_table_test.columns[-1]].values.tolist()
filepath = DIR_UCI + '/' + FILENAME + '/' + FILENAME + '.nominal'
list_nominal = mlem2.getNominalList(filepath)
list_judgeNominal = mlem2.getJudgeNominal(decision_table_test,
list_nominal)
# predict by LERS
predictions = LERS.predictByLERS(rules, decision_table_test,
list_judgeNominal)
# 正答率を求める
accuracy = accuracy_score(decision_class, predictions)
#logging.info('MLEM2_RuleClusteringByRandom_LERS,{k},{FILENAME},{iter1},{iter2},{acc}'.format(FILENAME=FILENAME,k=k,iter1=iter1,iter2=iter2,acc=accuracy))
savepath = DIR_UCI + '/' + FILENAME + '/MLEM2_RuleClusteringByRandom_LERS.csv'
with open(savepath, "a") as f:
f.writelines(
'MLEM2_RuleClusteringByRandom_LERS,{k},{FILENAME},{iter1},{iter2},{acc}'
.format(
FILENAME=FILENAME, k=k, iter1=iter1, iter2=iter2,
acc=accuracy) + "\n")
return (accuracy)
def Apriori_LERS(FILENAME, iter1, iter2, minsup, minconf):
# rule induction
fullpath_filename = '/data/uci/' + FILENAME + '/apriori/' + 'rules_' + str(
iter1) + '-' + str(iter2) + '-' + str(minsup) + '-' + str(
minconf) + '.pkl'
rules = mlem2.loadPickleRules(fullpath_filename) if os.path.isfile(
fullpath_filename) else apriori.getRulesByApriori(
FILENAME, iter1, iter2, minsup, minconf)
# rule save
if not os.path.isfile(fullpath_filename):
mlem2.savePickleRules(rules, fullpath_filename)
# test data setup
filepath = '/data/uci/' + FILENAME + '/' + FILENAME + '-test' + str(
iter1) + '-' + str(iter2) + '.tsv'
decision_table_test = mlem2.getDecisionTable(filepath)
decision_table_test = decision_table_test.dropna()
decision_class = decision_table_test[
decision_table_test.columns[-1]].values.tolist()
filepath = '/data/uci/' + FILENAME + '/' + FILENAME + '.nominal'
list_nominal = mlem2.getNominalList(filepath)
list_judgeNominal = mlem2.getJudgeNominal(decision_table_test,
list_nominal)
# predict by LERS
predictions = LERS.predictByLERS(rules, decision_table_test,
list_judgeNominal)
# 正答率を求める
accuracy = accuracy_score(list(map(str, decision_class)), predictions)
#print('{FILENAME} : {iter1} {iter2}'.format(FILENAME=FILENAME,iter1=iter1,iter2=iter2))
logging.basicConfig(filename=os.path.dirname(os.path.abspath("__file__")) +
'/' + FILENAME + '.log',
format='%(asctime)s,%(message)s',
level=logging.DEBUG)
logging.info(
'Apriori_LERS,{FILENAME},{iter1},{iter2},{acc},{minsup},{minconf}'.
format(FILENAME=FILENAME,
iter1=iter1,
iter2=iter2,
acc=accuracy,
minsup=minsup,
minconf=minconf))
return (accuracy)
def MLEM2_RuleClusteringByConsistentTimesSimExceptMRule_LERS(FILENAME, iter1, iter2, k, m) :
# rule induction
fullpath_filename = DIR_UCI+'/'+FILENAME+'/rules/'+'rules_'+str(iter1)+'-'+str(iter2)+'.pkl'
rules = mlem2.loadPickleRules(fullpath_filename) if os.path.isfile(fullpath_filename) else mlem2.getRulesByMLEM2(FILENAME, iter1, iter2)
# rule save
if not os.path.isfile(fullpath_filename): mlem2.savePickleRules(rules, fullpath_filename)
# rule clustering
filepath = DIR_UCI+'/'+FILENAME+'/'+FILENAME+'-train'+str(iter1)+'-'+str(iter2)+'.tsv'
decision_table = mlem2.getDecisionTable(filepath)
colnames = mlem2.getColNames(decision_table)
filepath = DIR_UCI+'/'+FILENAME+'/'+FILENAME+'.nominal'
list_nominal = mlem2.getNominalList(filepath)
list_judgeNominal = mlem2.getJudgeNominal(decision_table, list_nominal)
fullpath_filename = DIR_UCI+'/'+FILENAME+'/rules_cluster_consistent_times_sim_except_mrule/'+'rules-'+str(k)+'_'+str(iter1)+'-'+str(iter2)+'.pkl'
rules = mlem2.loadPickleRules(fullpath_filename) if os.path.isfile(fullpath_filename) else clustering.getRuleClusteringByConsistentTimesSimilarityExceptMRule(rules, colnames, list_judgeNominal, k=k, m=m)
# rule save
if not os.path.isfile(fullpath_filename): mlem2.savePickleRules(rules, fullpath_filename)
# test data setup
filepath = DIR_UCI+'/'+FILENAME+'/'+FILENAME+'-test'+str(iter1)+'-'+str(iter2)+'.tsv'
decision_table_test = mlem2.getDecisionTable(filepath)
decision_table_test = decision_table_test.dropna()
decision_class = decision_table_test[decision_table_test.columns[-1]].values.tolist()
filepath = DIR_UCI+'/'+FILENAME+'/'+FILENAME+'.nominal'
list_nominal = mlem2.getNominalList(filepath)
list_judgeNominal = mlem2.getJudgeNominal(decision_table_test, list_nominal)
# predict by LERS
predictions = LERS.predictByLERS(rules, decision_table_test, list_judgeNominal)
# 正答率を求める
accuracy = accuracy_score(decision_class, predictions)
#print('{FILENAME} : {iter1} {iter2}'.format(FILENAME=FILENAME,iter1=iter1,iter2=iter2))
#logging.info('MLEM2_RuleClusteringByConsistentSimExceptMRule_LERS,{k},{FILENAME},{iter1},{iter2},{acc}'.format(FILENAME=FILENAME,k=k,iter1=iter1,iter2=iter2,acc=accuracy))
savepath = DIR_UCI+'/'+FILENAME+'/MLEM2_RuleClusteringByConsistentTimesSimExceptMRule_LERS.csv'
with open(savepath, "a") as f :
f.writelines('MLEM2_RuleClusteringByConsistentTimesSimExceptMRule_LERS,{k},{FILENAME},{iter1},{iter2},{acc}'.format(FILENAME=FILENAME,k=k,iter1=iter1,iter2=iter2,acc=accuracy)+"\n")
return(accuracy)
#rules_new = getRuleClusteringBySimilarity(rules, colnames, list_judgeNominal, k=3)
#rules_new = getRuleClusteringByRandom(rules, k=3)
#rules_new = getRuleClusteringBySameCondition(rules, k=3)
#rules_new = getRuleClusteringByConsistentSimilarity(rules, colnames, list_judgeNominal, k=3)
#rules_new = getRuleClusteringByConsistentSimilarityExceptMRule(rules, colnames, list_judgeNominal, k=3, m=3)
#rules_new = getRuleClusteringByConsistentTimesSimilarityExceptMRule(rules, colnames, list_judgeNominal, k=3, m=3)
rules_new = getRuleClusteringBySimilarityExceptMRule(rules, colnames, list_judgeNominal, k=3, m=3)
rules_new = getRuleClusteringByConsistentExceptMRule(rules, colnames, list_judgeNominal, k=3, m=3)
# predict by LERS
filepath = '/mnt/data/uci/'+FILENAME+'/'+FILENAME+'-test'+str(iter1)+'-'+str(iter2)+'.tsv'
decision_table_test = mlem2.getDecisionTable(filepath)
decision_table_test = decision_table_test.dropna()
decision_class = decision_table_test[decision_table_test.columns[-1]].values.tolist()
predictions = LERS.predictByLERS(rules_new, decision_table_test, list_judgeNominal)
print(accuracy_score(decision_class, predictions))
# 全セットで確かめ
#for iter1 in range(1,11):
# for iter2 in range(1,11):
# print('i1:{iter1} i2:{iter2}'.format(iter1=iter1,iter2=iter2))
# rules = mlem2.getRulesByMLEM2(FILENAME, iter1, iter2)
# filepath = '/data/uci/'+FILENAME+'/'+FILENAME+'-train'+str(iter1)+'-'+str(iter2)+'.tsv'
# decision_table = mlem2.getDecisionTable(filepath)
# colnames = mlem2.getColNames(decision_table)
# filepath = '/data/uci/'+FILENAME+'/'+FILENAME+'.nominal'
# list_nominal = mlem2.getNominalList(filepath)
# list_judgeNominal = mlem2.getJudgeNominal(decision_table, list_nominal)
# ========================================
# main
# ========================================
if __name__ == "__main__":
FILENAME = 'hayes-roth'
iter1 = 4
iter2 = 5
minsup = 10
minconf = 1.0
rules = getRulesByApriori(FILENAME, iter1, iter2, minsup, minconf)
# test data setup
filepath = '/data/uci/'+FILENAME+'/'+FILENAME+'-test'+str(iter1)+'-'+str(iter2)+'.tsv'
decision_table_test = mlem2.getDecisionTable(filepath)
decision_table_test = decision_table_test.dropna()
decision_class = decision_table_test[decision_table_test.columns[-1]].values.tolist()
filepath = '/data/uci/'+FILENAME+'/'+FILENAME+'.nominal'
list_nominal = mlem2.getNominalList(filepath)
list_judgeNominal = mlem2.getJudgeNominal(decision_table_test, list_nominal)
# predict by LERS
predictions = LERS.predictByLERS(rules, decision_table_test, list_judgeNominal)
# 正答率を求める
accuracy = accuracy_score(list(map(str,decision_class)), predictions)
print(accuracy)
def MLEM2_delEAlphaRule_LERS(FILENAME, iter1, iter2, DELFUN, CLASS,
ATTRIBUTE_VALUE, alpha):
print(datetime.now().strftime('%Y/%m/%d %H:%M:%S') + ' ' + FILENAME + ' ' +
str(iter1) + ' ' + str(iter2) + ' ' + DELFUN.__name__ + ' ' +
strAttributeValue(ATTRIBUTE_VALUE) + ' ' + str(alpha) + ' ' +
"START")
# rule induction and rule save
fullpath_filename = DIR_UCI + '/' + FILENAME + '/rules/' + 'rules_' + str(
iter1) + '-' + str(iter2) + '.pkl'
rules = mlem2.loadPickleRules(fullpath_filename) if os.path.isfile(
fullpath_filename) else mlem2.getRulesByMLEM2(FILENAME, iter1, iter2)
if not os.path.isfile(fullpath_filename):
mlem2.savePickleRules(rules, fullpath_filename)
# train data setup
decision_table_train, decision_class = getData(FILENAME,
iter1,
iter2,
T="train")
list_judgeNominal = getJudgeNominal(decision_table_train, FILENAME)
# alpha差別的なルールの基本条件削除 or ルールを削除
if CLASS != "ALL":
rules_target = mlem2.getRulesClass(rules, CLASS)
rules_nontarget = mlem2.getRulesClass(rules, CLASS, judge=False)
for attr in ATTRIBUTE_VALUE:
for e in ATTRIBUTE_VALUE[attr]:
rules_target = DELFUN(rules_target, attr, e,
decision_table_train, list_judgeNominal,
alpha)
rules_target.extend(rules_nontarget)
rules = rules_target
else:
for attr in ATTRIBUTE_VALUE:
for e in ATTRIBUTE_VALUE[attr]:
rules = DELFUN(rules, attr, e, decision_table_train,
list_judgeNominal, alpha)
print(datetime.now().strftime('%Y/%m/%d %H:%M:%S') + ' ' + FILENAME + ' ' +
str(iter1) + ' ' + str(iter2) + ' ' + DELFUN.__name__ + ' ' +
strAttributeValue(ATTRIBUTE_VALUE) + ' ' + str(alpha) + ' ' +
"RULES")
# test data setup
decision_table_test, decision_class = getData(FILENAME,
iter1,
iter2,
T="test")
list_judgeNominal = getJudgeNominal(decision_table_test, FILENAME)
# predict by LERS
predictions = LERS.predictByLERS(rules, decision_table_test,
list_judgeNominal)
# 正答率を求める
accuracy = accuracy_score(decision_class, predictions)
# rules の数を求める
num = len(rules)
# 各クラスのrulesの数を求める
num_class = strNumClassRules(rules)
# 平均の長さを求める
mean_length = mlem2.getMeanLength(rules)
# 平均支持度と平均確信度を求める
list_judgeNominal = getJudgeNominal(decision_table_train, FILENAME)
mean_support, mean_conf = LERS.getSupportConfidenceRules(
rules, decision_table_train, list_judgeNominal)
# AccとRecallを求める
acc_recall = LERS.getAccurayRecall(rules, decision_table_train,
list_judgeNominal)
# ファイルにsave
savepath = DIR_UCI + '/' + FILENAME + '/fairness/02_alpha_preserve/MLEM2_delEAlphaRule_LERS.csv'
with open(savepath, "a") as f:
f.writelines(
'MLEM2_delEAlphaRule_LERS,{DELFUN},{CLASS},{FILENAME},{ATTRIBUTE_VALUE},{alpha},{iter1},{iter2},{acc},{num},{num_class},{mean_length},{mean_support},{mean_conf},{acc_recall}'
.format(DELFUN=DELFUN.__name__,
CLASS=CLASS,
FILENAME=FILENAME,
ATTRIBUTE_VALUE=strAttributeValue(ATTRIBUTE_VALUE),
alpha=alpha,
iter1=iter1,
iter2=iter2,
acc=accuracy,
num=num,
num_class=num_class,
mean_length=mean_length,
mean_support=mean_support,
mean_conf=mean_conf,
acc_recall=strAccRecall(rules, acc_recall)) + "\n")
print(datetime.now().strftime('%Y/%m/%d %H:%M:%S') + ' ' + FILENAME + ' ' +
str(iter1) + ' ' + str(iter2) + ' ' + DELFUN.__name__ + ' ' +
strAttributeValue(ATTRIBUTE_VALUE) + ' ' + str(alpha) + ' ' + "END")
return (0)
# rule induction
rules = mlem2.getRulesByMLEM2(FILENAME, iter1, iter2)
# test data
filepath = DIR_UCI+FILENAME+'/'+FILENAME+'-test'+str(iter1)+'-'+str(iter2)+'.tsv'
decision_table_test = mlem2.getDecisionTable(filepath)
decision_table_test = decision_table_test.dropna()
decision_class = decision_table_test[decision_table_test.columns[-1]].values.tolist()
# nominal data
filepath = DIR_UCI+FILENAME+'/'+FILENAME+'.nominal'
list_nominal = mlem2.getNominalList(filepath)
list_judgeNominal = mlem2.getJudgeNominal(decision_table_test, list_nominal)
# predict by LERS
predictions = LERS.predictByLERS(rules, decision_table_test, list_judgeNominal)
# 正答率を求める
accuracy_score(decision_class, predictions)
# rules の数を求める
num = len(rules)
# 平均の長さを求める
mean_length = mlem2.getMeanLength(rules)
# train data setup
decision_table_train, decision_class = getData(FILENAME, iter1, iter2, T = "train")
list_judgeNominal = getJudgeNominal(decision_table_train, FILENAME)
# 平均支持度と平均確信度を求める
mean_support, mean_conf = LERS.getSupportConfidenceRules(rules, decision_table_train, list_judgeNominal)
def MLEM2_delEAlphaRule_LERS(FILENAME, iter1, iter2, DELFUN, CLASS, ATTRIBUTE_VALUE, alpha):
print(
datetime.now().strftime("%Y/%m/%d %H:%M:%S")
+ " "
+ FILENAME
+ " "
+ str(iter1)
+ " "
+ str(iter2)
+ " "
+ DELFUN.__name__
+ " "
+ strAttributeValue(ATTRIBUTE_VALUE)
+ " "
+ str(alpha)
+ " "
+ "START"
)
# rule induction and rule save
fullpath_filename = DIR_UCI + "/" + FILENAME + "/rules/" + "rules_" + str(iter1) + "-" + str(iter2) + ".pkl"
rules = (
mlem2.loadPickleRules(fullpath_filename)
if os.path.isfile(fullpath_filename)
else mlem2.getRulesByMLEM2(FILENAME, iter1, iter2)
)
if not os.path.isfile(fullpath_filename):
mlem2.savePickleRules(rules, fullpath_filename)
# train data setup
decision_table_train, decision_class = getData(FILENAME, iter1, iter2, T="train")
list_judgeNominal = getJudgeNominal(decision_table_train, FILENAME)
# alpha差別的なルールの基本条件削除 or ルールを削除
if CLASS != "ALL":
rules_target = mlem2.getRulesClass(rules, CLASS)
rules_nontarget = mlem2.getRulesClass(rules, CLASS, judge=False)
for attr in ATTRIBUTE_VALUE:
for e in ATTRIBUTE_VALUE[attr]:
rules_target = DELFUN(rules_target, attr, e, decision_table_train, list_judgeNominal, alpha)
rules_target.extend(rules_nontarget)
rules = rules_target
else:
for attr in ATTRIBUTE_VALUE:
for e in ATTRIBUTE_VALUE[attr]:
rules = DELFUN(rules, attr, e, decision_table_train, list_judgeNominal, alpha)
print(
datetime.now().strftime("%Y/%m/%d %H:%M:%S")
+ " "
+ FILENAME
+ " "
+ str(iter1)
+ " "
+ str(iter2)
+ " "
+ DELFUN.__name__
+ " "
+ strAttributeValue(ATTRIBUTE_VALUE)
+ " "
+ str(alpha)
+ " "
+ "RULES"
)
# test data setup
decision_table_test, decision_class = getData(FILENAME, iter1, iter2, T="test")
list_judgeNominal = getJudgeNominal(decision_table_test, FILENAME)
# predict by LERS
predictions = LERS.predictByLERS(rules, decision_table_test, list_judgeNominal)
# 正答率を求める
accuracy = accuracy_score(decision_class, predictions)
# rules の数を求める
num = len(rules)
# 各クラスのrulesの数を求める
num_class = strNumClassRules(rules)
# 平均の長さを求める
mean_length = mlem2.getMeanLength(rules)
# 平均支持度と平均確信度を求める
list_judgeNominal = getJudgeNominal(decision_table_train, FILENAME)
mean_support, mean_conf = LERS.getSupportConfidenceRules(rules, decision_table_train, list_judgeNominal)
# AccとRecallを求める
acc_recall = LERS.getAccurayRecall(rules, decision_table_train, list_judgeNominal)
# ファイルにsave
savepath = DIR_UCI + "/" + FILENAME + "/fairness/02_alpha_preserve/MLEM2_delEAlphaRule_LERS.csv"
with open(savepath, "a") as f:
f.writelines(
"MLEM2_delEAlphaRule_LERS,{DELFUN},{CLASS},{FILENAME},{ATTRIBUTE_VALUE},{alpha},{iter1},{iter2},{acc},{num},{num_class},{mean_length},{mean_support},{mean_conf},{acc_recall}".format(
DELFUN=DELFUN.__name__,
CLASS=CLASS,
FILENAME=FILENAME,
ATTRIBUTE_VALUE=strAttributeValue(ATTRIBUTE_VALUE),
alpha=alpha,
iter1=iter1,
iter2=iter2,
acc=accuracy,
num=num,
num_class=num_class,
mean_length=mean_length,
mean_support=mean_support,
mean_conf=mean_conf,
acc_recall=strAccRecall(rules, acc_recall),
)
+ "\n"
)
print(
datetime.now().strftime("%Y/%m/%d %H:%M:%S")
+ " "
+ FILENAME
+ " "
+ str(iter1)
+ " "
+ str(iter2)
+ " "
+ DELFUN.__name__
+ " "
+ strAttributeValue(ATTRIBUTE_VALUE)
+ " "
+ str(alpha)
+ " "
+ "END"
)
return 0
# rule induction
rules = mlem2.getRulesByMLEM2(FILENAME, iter1, iter2)
# test data
filepath = DIR_UCI+FILENAME+'/'+FILENAME+'-test'+str(iter1)+'-'+str(iter2)+'.tsv'
decision_table_test = mlem2.getDecisionTable(filepath)
decision_table_test = decision_table_test.dropna()
decision_class = decision_table_test[decision_table_test.columns[-1]].values.tolist()
# nominal data
filepath = DIR_UCI+FILENAME+'/'+FILENAME+'.nominal'
list_nominal = mlem2.getNominalList(filepath)
list_judgeNominal = mlem2.getJudgeNominal(decision_table_test, list_nominal)
# predict by LERS
predictions = LERS.predictByLERS(rules, decision_table_test, list_judgeNominal)
# 正答率を求める
accuracy_score(decision_class, predictions)
# rules の数を求める
num = len(rules)
# 平均の長さを求める
mean_length = mlem2.getMeanLength(rules)
# train data setup
decision_table_train, decision_class = getData(FILENAME, iter1, iter2, T = "train")
list_judgeNominal = getJudgeNominal(decision_table_train, FILENAME)
# 平均支持度と平均確信度を求める
mean_support, mean_conf = LERS.getSupportConfidenceRules(rules, decision_table_train, list_judgeNominal)