def get_classifier(classifier, min_no):
"""
Return the classifier object given the options
:param classifier: string name of the classifier to use
:param min_no: Minimum number of instances correctly covered by the classifier
:return: classifier object
"""
if classifier.lower() == 'jrip':
cls = Classifier(classname="weka.classifiers.rules.JRip")
options = list()
options.append("-N")
options.append(str(min_no))
elif classifier.lower() in ['dec_tree', 'part']:
if classifier.lower() == 'dec_tree':
cls = Classifier(classname="weka.classifiers.trees.J48")
elif classifier.lower() == 'part':
cls = Classifier(classname="weka.classifiers.rules.PART")
options = list()
options.append("-M")
options.append(str(min_no))
else:
raise ValueError(
"Please enter the correct classifier name (jrip | dec_tree | part)"
)
cls.options = options
return cls
def get_classifier(min_no, seed):
cls = Classifier(classname="weka.classifiers.rules.JRip")
# options = ["-N", "25.0"] #-N: minNo, -F folds, -O num optimizations, -batch-size, -S: seed
options = list()
options.append("-N")
options.append(str(min_no))
options.append("-S")
options.append(str(seed))
cls.options = options
return cls
def get_classifier(min_no, seed):
"""
Return the classifier object given the options
:param min_no: Minimum number of instances correctly covered by JRIP
:param seed: Seed for randomizing instance order
:return: classifier object
"""
cls = Classifier(classname="weka.classifiers.rules.JRip")
options = list()
options.append("-N")
options.append(str(min_no))
options.append("-S")
options.append(str(seed))
cls.options = options
return cls
import weka.core.jvm as jvm jvm.start() jvm.start(system_cp=True, packages=True) jvm.start(packages="/usr/local/lib/python2.7/dist-packages/weka") jvm.start(max_heap_size="512m") data_dir="CSDMC2010_SPAM/CSDMC2010_SPAM/TRAINING" from weka.classifiers import Classifier cls = Classifier(classname="weka.classifiers.trees.J48") cls.options = ["-C", "0.3"] print(cls.options) jvm.stop()
Ypred = np.zeros(Y.shape, dtype='object')
print "Classification using K Nearest Neighbors"
for train_index, test_index in sss:
print "Iter", itr,
X_train, X_test = X[train_index], X[test_index]
X_test[:,-1] = classes[0] # make sure test classes is removed
y_test = Y[test_index]
write_to_weka('train.arff', 'training_data', data.columns, X_train, classes)
write_to_weka('test.arff', 'testing_data', data.columns, X_test, classes)
loader = Loader(classname="weka.core.converters.ArffLoader")
trdata = loader.load_file("train.arff")
trdata.class_is_last()
classifier = Classifier(classname="weka.classifiers.lazy.IBk")
classifier.options = ["-K", "10", "-W", "0", "-I", "-A",
"weka.core.neighboursearch.LinearNNSearch -A \"weka.core.ManhattanDistance -R first-last\""]
classifier.build_classifier(trdata)
tedata = loader.load_file("test.arff")
tedata.class_is_last()
for index, inst in enumerate(tedata):
result = classifier.classify_instance(inst)
Ypred[test_index[index]] = classes[int(result)]
accuracy = float(np.sum(y_test == Ypred[test_index])) / float(y_test.shape[0])
print " => Accuracy = ", accuracy
itr += 1
accuracy = float(np.sum(Y == Ypred)) / float(Y.shape[0])
print "Total accuracy = ", accuracy
def train(request):
jvm.start()
d_att1 = Attribute.create_numeric("bodydearword.feature")
d_att2 = Attribute.create_numeric("bodyform.feature")
d_att3 = Attribute.create_numeric("bodyhtml.feature")
d_att4 = Attribute.create_numeric("bodymultipart.feature")
d_att5 = Attribute.create_numeric("bodynumchars.feature")
d_att6 = Attribute.create_numeric("bodynumfunctionwords.feature")
d_att7 = Attribute.create_numeric("bodynumuniqwords.feature")
d_att8 = Attribute.create_numeric("bodynumwords.feature")
d_att9 = Attribute.create_numeric("bodyrichness.feature")
d_att10 = Attribute.create_numeric("bodysuspensionword.feature")
d_att11 = Attribute.create_numeric("bodyverifyyouraccountphrase.feature")
d_att12 = Attribute.create_numeric("externalsabinary.feature")
d_att13 = Attribute.create_numeric("externalsascore.feature")
d_att14 = Attribute.create_numeric("scriptjavascript.feature")
d_att15 = Attribute.create_numeric("scriptonclick.feature")
d_att16 = Attribute.create_numeric("scriptpopup.feature")
d_att17 = Attribute.create_numeric("scriptstatuschange.feature")
d_att18 = Attribute.create_numeric("scriptunmodalload.feature")
d_att19 = Attribute.create_numeric("senddiffreplyto.feature")
d_att20 = Attribute.create_numeric("sendnumwords.feature")
d_att21 = Attribute.create_numeric("sendunmodaldomain.feature")
d_att22 = Attribute.create_numeric("subjectbankword.feature")
d_att23 = Attribute.create_numeric("subjectdebitword.feature")
d_att24 = Attribute.create_numeric("subjectfwdword.feature")
d_att25 = Attribute.create_numeric("subjectnumchars.feature")
d_att26 = Attribute.create_numeric("subjectnumwords.feature")
d_att27 = Attribute.create_numeric("subjectreplyword.feature")
d_att28 = Attribute.create_numeric("subjectrichness.feature")
d_att29 = Attribute.create_numeric("subjectverifyword.feature")
d_att30 = Attribute.create_numeric("urlatchar.feature")
d_att31 = Attribute.create_numeric("urlbaglink.feature")
d_att32 = Attribute.create_numeric("urlip.feature")
d_att33 = Attribute.create_numeric("urlnumdomains.feature")
d_att34 = Attribute.create_numeric("urlnumexternallink.feature")
d_att35 = Attribute.create_numeric("urlnumimagelink.feature")
d_att36 = Attribute.create_numeric("urlnuminternallink.feature")
d_att37 = Attribute.create_numeric("urlnumip.feature")
d_att38 = Attribute.create_numeric("urlnumlink.feature")
d_att39 = Attribute.create_numeric("urlnumperiods.feature")
d_att40 = Attribute.create_numeric("urlnumport.feature")
d_att41 = Attribute.create_numeric("urlport.feature")
d_att42 = Attribute.create_numeric("urltwodoains.feature")
d_att43 = Attribute.create_numeric("urlunmodalbaglink.feature")
d_att44 = Attribute.create_numeric("urlwordclicklink.feature")
d_att45 = Attribute.create_numeric("urlwordherelink.feature")
d_att46 = Attribute.create_numeric("urlwordloginlink.feature")
d_att47 = Attribute.create_numeric("urlwordupdatelink.feature")
d_att48 = Attribute.create_nominal("class", {'phish', 'ham'})
#
data_dir = settings.BASE_DIR + "/phishing/public/datasets/"
#
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(data_dir + "dataset.arff")
data.class_is_last()
cls = Classifier(classname="weka.classifiers.trees.J48")
cls.options = ["-C", "0.3"]
cls.build_classifier(data)
serialization.write(data_dir + "out.model", cls)
classifier = Classifier(jobject=serialization.read(data_dir + "out.model"))
dataset = Instances.create_instances("test", [
d_att1, d_att2, d_att3, d_att4, d_att5, d_att6, d_att7, d_att8, d_att9,
d_att10, d_att11, d_att12, d_att13, d_att14, d_att15, d_att16, d_att17,
d_att18, d_att19, d_att20, d_att21, d_att22, d_att23, d_att24, d_att25,
d_att26, d_att27, d_att28, d_att29, d_att30, d_att31, d_att32, d_att33,
d_att34, d_att35, d_att36, d_att37, d_att38, d_att39, d_att40, d_att41,
d_att42, d_att43, d_att44, d_att45, d_att46, d_att47, d_att48
], 0)
values = [
0, 0, 0, 0, 890, 1, 124, 198, 0.22247191011236, 0, 0, 0, 0.0, 0, 0, 0,
0, 0, 1, 4, 0, 0, 0, 0, 21, 4, 1, 0.19047619047619, 0, 0, 0, 0, 2, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
Instance.missing_value()
]
inst = Instance.create_instance(values)
dataset.add_instance(inst)
dataset.class_is_last()
# print(str(dataset))
var = ''
for inst1 in dataset:
pred = classifier.classify_instance(inst1)
var = inst1.class_attribute.value(int(pred))
if var == 'ham':
print('No es pishing')
# do somthing
else:
print('Es pishing')
# do somthing
print(var)
jvm.stop()
return HttpResponse(str(var))
data = loader.load_file(arffFileName)
data.class_is_last()
data.delete_attribute(0) #delete source IP attribute
data.delete_attribute(1) #delete destination IP attribute
#nominalAttr = Attribute.create_nominal("class", "{yes, no}")
#data.delete_last_attribute()
#data.insert_attribute(nominalAttr, 0)
#data.class_is_first()
#print(data)
classifier = Classifier(classname="weka.classifiers.trees.RandomForest")
classifier.options = [
'-P', '100', '-I', '100', '-num-slots', '1', '-K', '0', '-M', '1.0', '-V',
'0.001', '-S', '1'
]
folds = 10
seed = 1
rnd = Random(seed)
rand_data = Instances.copy_instances(data)
rand_data.randomize(rnd)
if rand_data.class_attribute.is_nominal:
rand_data.stratify(folds)
progress = 0
predicted_data = None
evaluation = Evaluation(rand_data)
for i in range(folds):