def run_cba(Xtr,
Ytr,
Xt,
Yt,
lb,
support=0.20,
confidence=0.5,
k=None,
log=None):
txns_train = TransactionDB.from_DataFrame(pd.concat([Xtr, Ytr], axis=1))
txns_test = TransactionDB.from_DataFrame(pd.concat([Xt, Yt], axis=1))
cba = CBA(support=support, confidence=confidence, algorithm="m1")
cba.fit(txns_train)
if k is not None:
cba.clf.rules = cba.clf.rules[:k]
Y_pred = [int(i) for i in cba.predict(txns_test)]
for r in cba.clf.rules:
r.covered = set(
[i for i, rd in enumerate(txns_train) if r.antecedent <= rd])
if log is None:
from logger import log
log('cba-k', len(cba.clf.rules))
log('cba-rules', str(cba.clf.rules))
[log('cba-nconds', len(r), i) for i, r in enumerate(cba.clf.rules)]
log('cba-auc', roc_auc_score(lb.transform(Yt.values),
lb.transform(Y_pred)))
log('cba-bacc', balanced_accuracy_score(Yt, Y_pred))
log('cba-disp', dispersion_(cba.clf.rules, average=True))
log('cba-overlap', overlap(cba.clf.rules))
print(confusion_matrix(Yt, Y_pred))
def misuse(train_df, test_df):
print("\nMisuse Data")
train = train_df.copy()
test = test_df.copy()
train = train[(train['Label'] != 'Benign') == True]
txns_train = TransactionDB.from_DataFrame(train, target="Label")
txns_test = TransactionDB.from_DataFrame(test)
print("Association Rule Generation")
cba = CBA(support=0.01, confidence=0.01)
cba.fit(txns_train)
predict = cba.predict(txns_test)
test['predict'] = predict
return test