def getDescriptors(decision_table) :
list_descriptors = defaultdict(list)
columns = mlem2.getColNames(decision_table)
for i in range(len(columns)) :
tmp = list(pd.Series(decision_table.ix[:,i]).unique())
list_descriptors[columns[i]] = tmp
return(list_descriptors)
def MLEM2_RuleClusteringByConsistentExceptMRule_STAT(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_except_mrule/' + 'rules-' + str(
k) + '_' + str(iter1) + '-' + str(iter2) + '.pkl'
rules = mlem2.loadPickleRules(fullpath_filename) if os.path.isfile(
fullpath_filename
) else clustering.getRuleClusteringByConsistentExceptMRule(
rules, colnames, list_judgeNominal, k=k, m=m)
# rule save
if not os.path.isfile(fullpath_filename):
mlem2.savePickleRules(rules, fullpath_filename)
# rules の数を求める
num = len(rules)
# 平均の長さを求める
leng = mlem2.getMeanLength(rules)
# 平均支持度を求める
support = mlem2.getMeanSupport(rules)
# ファイルにsave
savepath = DIR_UCI + '/' + FILENAME + '/MLEM2_RuleClusteringByConsistentExceptMRule_STAT.csv'
with open(savepath, "a") as f:
f.writelines(
'MLEM2_RuleClusteringByConsistentExceptMRule_STAT,{k},{FILENAME},{iter1},{iter2},{num},{leng},{support}'
.format(FILENAME=FILENAME,
k=k,
iter1=iter1,
iter2=iter2,
num=num,
leng=leng,
support=support) + "\n")
return (0)
def MLEM2_RuleClusteringByConsistentSim_Identified(FILENAME, iter1, iter2, k,
p):
# 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_sim/' + 'rules-' + str(
k) + '_' + str(iter1) + '-' + str(iter2) + '.pkl'
rules = mlem2.loadPickleRules(fullpath_filename) if os.path.isfile(
fullpath_filename
) else clustering.getRuleClusteringByConsistentSimilarity(
rules, colnames, list_judgeNominal, k=k)
# rule save
if not os.path.isfile(fullpath_filename):
mlem2.savePickleRules(rules, fullpath_filename)
# PerIdentifiedClass を求める
ans = mlem2.getPerIdentifiedClass(rules, p)
# save
savepath = DIR_UCI + '/' + FILENAME + '/Identify_MLEM2_RuleClusteringByConsistentSim.csv'
with open(savepath, "a") as f:
f.writelines(
'Identify_MLEM2_RuleClusteringByConsistentSim,{k},{p},{FILENAME},{iter1},{iter2},{ans}'
.format(
FILENAME=FILENAME, k=k, p=p, iter1=iter1, iter2=iter2,
ans=ans) + "\n")
return (ans)
def MLEM2_RuleClusteringBySim_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
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_sim/'+'rules-'+str(k)+'_'+str(iter1)+'-'+str(iter2)+'.pkl'
rules = mlem2.loadPickleRules(fullpath_filename) if os.path.isfile(fullpath_filename) else clustering.getRuleClusteringBySimilarity(rules, colnames, list_judgeNominal, 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)
#print('{FILENAME} : {iter1} {iter2}'.format(FILENAME=FILENAME,iter1=iter1,iter2=iter2))
#logging.info('MLEM2_RuleClusteringBySim_LERS,{k},{FILENAME},{iter1},{iter2},{acc}'.format(FILENAME=FILENAME,k=k,iter1=iter1,iter2=iter2,acc=accuracy))
savepath = DIR_UCI+'/'+FILENAME+'/MLEM2_RuleClusteringBySim_LERS.csv'
with open(savepath, "a") as f :
f.writelines('MLEM2_RuleClusteringBySim_LERS,{k},{FILENAME},{iter1},{iter2},{acc}'.format(FILENAME=FILENAME,k=k,iter1=iter1,iter2=iter2,acc=accuracy)+"\n")
return(accuracy)
# ========================================
# main
# ========================================
if __name__ == "__main__":
FILENAME = 'hayes-roth'
iter1 = 5
iter2 = 4
rules = mlem2.getRulesByMLEM2(FILENAME, iter1, iter2)
filepath = '/mnt/data/uci/'+FILENAME+'/'+FILENAME+'-train'+str(iter1)+'-'+str(iter2)+'.tsv'
decision_table = mlem2.getDecisionTable(filepath)
colnames = mlem2.getColNames(decision_table)
filepath = '/mnt/data/uci/'+FILENAME+'/'+FILENAME+'.nominal'
list_nominal = mlem2.getNominalList(filepath)
list_judgeNominal = mlem2.getJudgeNominal(decision_table, list_nominal)
# ルールクラスタリング
#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)
def MLEM2_RuleClusteringBySim_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
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_sim/' + 'rules-' + str(
k) + '_' + str(iter1) + '-' + str(iter2) + '.pkl'
rules = mlem2.loadPickleRules(fullpath_filename) if os.path.isfile(
fullpath_filename) else clustering.getRuleClusteringBySimilarity(
rules, colnames, list_judgeNominal, 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)
#print('{FILENAME} : {iter1} {iter2}'.format(FILENAME=FILENAME,iter1=iter1,iter2=iter2))
#logging.info('MLEM2_RuleClusteringBySim_LERS,{k},{FILENAME},{iter1},{iter2},{acc}'.format(FILENAME=FILENAME,k=k,iter1=iter1,iter2=iter2,acc=accuracy))
savepath = DIR_UCI + '/' + FILENAME + '/MLEM2_RuleClusteringBySim_LERS.csv'
with open(savepath, "a") as f:
f.writelines(
'MLEM2_RuleClusteringBySim_LERS,{k},{FILENAME},{iter1},{iter2},{acc}'
.format(
FILENAME=FILENAME, k=k, iter1=iter1, iter2=iter2,
acc=accuracy) + "\n")
return (accuracy)
# ========================================
# main
# ========================================
if __name__ == "__main__":
FILENAME = 'hayes-roth'
iter1 = 5
iter2 = 4
rules = mlem2.getRulesByMLEM2(FILENAME, iter1, iter2)
filepath = '/mnt/data/uci/' + FILENAME + '/' + FILENAME + '-train' + str(
iter1) + '-' + str(iter2) + '.tsv'
decision_table = mlem2.getDecisionTable(filepath)
colnames = mlem2.getColNames(decision_table)
filepath = '/mnt/data/uci/' + FILENAME + '/' + FILENAME + '.nominal'
list_nominal = mlem2.getNominalList(filepath)
list_judgeNominal = mlem2.getJudgeNominal(decision_table, list_nominal)
# ルールクラスタリング
#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,
