def predBtn_clicked(self):
gender = self.gender_entry.get()
age = int(self.age_entry.get())
height = int(self.height_entry.get())
weight = int(self.weight_entry.get())
sociability = self.sociability_entry.get()
stability = self.stability_entry.get()
'''Create the model'''
objects = serialization.read_all("J48.model")
cls = Classifier(jobject=objects[0])
data = Instances(jobject=objects[1])
'''Create the test set to be classified'''
gender_values = ["Man", "Woman"]
sociability_values = ["Introvert", "Extrovert"]
stability_values = ["Stable", "Unstable"]
values = [
gender_values.index(gender), age, height, weight,
self.BMI(weight, height),
stability_values.index(stability),
sociability_values.index(sociability),
Instance.missing_value()
]
inst = Instance.create_instance(values)
inst.dataset = data
'''Classification'''
prediction = int(cls.classify_instance(inst))
self.controller.show_frame("Result").show(prediction)
self.clear()
def create_dataset(tweets):
text_att = Attribute.create_string('TEXT')
nom_att = Attribute.create_nominal('CLASS', class_values)
dataset = Instances.create_instances("tweets", [text_att, nom_att],
len(tweets))
for tweet in tweets:
values = []
values.append(dataset.attribute(0).add_string_value(tweet))
values.append(Instance.missing_value())
inst = Instance.create_instance(values)
dataset.add_instance(inst)
dataset.class_is_last()
return dataset
def transformUserInput(self,user_input):
'''
Transforma la entrada del usuario a una representación de 1s y 0s para poder realizar una predicción.
:param str entrada del usuario
:return str de 1s y 0s
:rtype str
'''
attributes = self.data.attribute_names()
data_size = len(attributes)
vector_input = ['0']*(data_size)
words = user_input.split()
attribute_map = { attributes[i] : i for i in range(len(attributes)) }
for word in words:
if word in attributes:
vector_input[attribute_map.get(word)] = '1'
vector_input[data_size-1] = Instance.missing_value()
return vector_input
def main():
"""
Just runs some example code.
"""
# load a dataset
iris_file = helper.get_data_dir() + os.sep + "iris.arff"
helper.print_info("Loading dataset: " + iris_file)
loader = Loader("weka.core.converters.ArffLoader")
iris_data = loader.load_file(iris_file)
iris_data.class_is_last()
helper.print_title("Iris dataset")
print(iris_data)
helper.print_title("Iris dataset (incrementally output)")
for i in iris_data:
print(i)
helper.print_title("Iris summary")
print(Instances.summary(iris_data))
helper.print_title("Iris attributes")
for a in iris_data.attributes():
print(a)
helper.print_title("Instance at #0")
print(iris_data.get_instance(0))
print(iris_data.get_instance(0).values)
print("Attribute stats (first):\n" + str(iris_data.attribute_stats(0)))
print("total count (first attribute):\n" + str(iris_data.attribute_stats(0).total_count))
print("numeric stats (first attribute):\n" + str(iris_data.attribute_stats(0).numeric_stats))
print("nominal counts (last attribute):\n"
+ str(iris_data.attribute_stats(iris_data.num_attributes - 1).nominal_counts))
helper.print_title("Instance values at #0")
for v in iris_data.get_instance(0):
print(v)
# append datasets
helper.print_title("append datasets")
data1 = Instances.copy_instances(iris_data, 0, 2)
data2 = Instances.copy_instances(iris_data, 2, 2)
print("Dataset #1:\n" + str(data1))
print("Dataset #2:\n" + str(data2))
msg = data1.equal_headers(data2)
print("#1 == #2 ? " + "yes" if msg is None else msg)
combined = Instances.append_instances(data1, data2)
print("Combined:\n" + str(combined))
# merge datasets
helper.print_title("merge datasets")
data1 = Instances.copy_instances(iris_data, 0, 2)
data1.class_index = -1
data1.delete_attribute(1)
data1.delete_first_attribute()
data2 = Instances.copy_instances(iris_data, 0, 2)
data2.class_index = -1
data2.delete_attribute(4)
data2.delete_attribute(3)
data2.delete_attribute(2)
print("Dataset #1:\n" + str(data1))
print("Dataset #2:\n" + str(data2))
msg = data1.equal_headers(data2)
print("#1 == #2 ? " + ("yes" if msg is None else msg))
combined = Instances.merge_instances(data2, data1)
print("Combined:\n" + str(combined))
# load dataset incrementally
iris_file = helper.get_data_dir() + os.sep + "iris.arff"
helper.print_info("Loading dataset incrementally: " + iris_file)
loader = Loader("weka.core.converters.ArffLoader")
iris_data = loader.load_file(iris_file, incremental=True)
iris_data.class_is_last()
helper.print_title("Iris dataset")
print(iris_data)
for inst in loader:
print(inst)
# create attributes
helper.print_title("Creating attributes")
num_att = Attribute.create_numeric("num")
print("numeric: " + str(num_att))
date_att = Attribute.create_date("dat", "yyyy-MM-dd")
print("date: " + str(date_att))
nom_att = Attribute.create_nominal("nom", ["label1", "label2"])
print("nominal: " + str(nom_att))
# create dataset
helper.print_title("Create dataset")
dataset = Instances.create_instances("helloworld", [num_att, date_att, nom_att], 0)
print(str(dataset))
# create an instance
helper.print_title("Create and add instance")
values = [3.1415926, date_att.parse_date("2014-04-10"), 1.0]
inst = Instance.create_instance(values)
print("Instance #1:\n" + str(inst))
dataset.add_instance(inst)
values = [2.71828, date_att.parse_date("2014-08-09"), Instance.missing_value()]
inst = Instance.create_instance(values)
dataset.add_instance(inst)
print("Instance #2:\n" + str(inst))
inst.set_value(0, 4.0)
print("Instance #2 (updated):\n" + str(inst))
print("Dataset:\n" + str(dataset))
dataset.delete_with_missing(2)
print("Dataset (after delete of missing):\n" + str(dataset))
values = [(1, date_att.parse_date("2014-07-11"))]
inst = Instance.create_sparse_instance(values, 3, classname="weka.core.SparseInstance")
print("sparse Instance:\n" + str(inst))
dataset.add_instance(inst)
print("dataset with mixed dense/sparse instance objects:\n" + str(dataset))
# create dataset (lists)
helper.print_title("Create dataset from lists")
x = [[randint(1, 10) for _ in range(5)] for _ in range(10)]
y = [randint(0, 1) for _ in range(10)]
dataset2 = ds.create_instances_from_lists(x, y, "generated from lists")
print(dataset2)
x = [[randint(1, 10) for _ in range(5)] for _ in range(10)]
dataset2 = ds.create_instances_from_lists(x, name="generated from lists (no y)")
print(dataset2)
# create dataset (matrices)
helper.print_title("Create dataset from matrices")
x = np.random.randn(10, 5)
y = np.random.randn(10)
dataset3 = ds.create_instances_from_matrices(x, y, "generated from matrices")
print(dataset3)
x = np.random.randn(10, 5)
dataset3 = ds.create_instances_from_matrices(x, name="generated from matrices (no y)")
print(dataset3)
# create more sparse instances
diabetes_file = helper.get_data_dir() + os.sep + "diabetes.arff"
helper.print_info("Loading dataset: " + diabetes_file)
loader = Loader("weka.core.converters.ArffLoader")
diabetes_data = loader.load_file(diabetes_file)
diabetes_data.class_is_last()
helper.print_title("Create sparse instances using template dataset")
sparse_data = Instances.template_instances(diabetes_data)
for i in range(diabetes_data.num_attributes - 1):
inst = Instance.create_sparse_instance(
[(i, float(i+1) / 10.0)], sparse_data.num_attributes, classname="weka.core.SparseInstance")
sparse_data.add_instance(inst)
print("sparse dataset:\n" + str(sparse_data))
# simple scatterplot of iris dataset: petalwidth x petallength
iris_data = loader.load_file(iris_file)
iris_data.class_is_last()
pld.scatter_plot(
iris_data, iris_data.attribute_by_name("petalwidth").index,
iris_data.attribute_by_name("petallength").index,
percent=50,
wait=False)
# line plot of iris dataset (without class attribute)
iris_data = loader.load_file(iris_file)
iris_data.class_is_last()
pld.line_plot(iris_data, atts=range(iris_data.num_attributes - 1), percent=50, title="Line plot iris", wait=False)
# matrix plot of iris dataset
iris_data = loader.load_file(iris_file)
iris_data.class_is_last()
pld.matrix_plot(iris_data, percent=50, title="Matrix plot iris", wait=True)
def main():
"""
Just runs some example code.
"""
# load a dataset
iris_file = helper.get_data_dir() + os.sep + "iris.arff"
helper.print_info("Loading dataset: " + iris_file)
loader = Loader("weka.core.converters.ArffLoader")
iris_data = loader.load_file(iris_file)
iris_data.class_is_last()
helper.print_title("Iris dataset")
print(iris_data)
helper.print_title("Iris dataset (incrementally output)")
for i in iris_data:
print(i)
helper.print_title("Iris summary")
print(Instances.summary(iris_data))
helper.print_title("Iris attributes")
for a in iris_data.attributes():
print(a)
helper.print_title("Instance at #0")
print(iris_data.get_instance(0))
print(iris_data.get_instance(0).values)
print("Attribute stats (first):\n" + str(iris_data.attribute_stats(0)))
print("total count (first attribute):\n" +
str(iris_data.attribute_stats(0).total_count))
print("numeric stats (first attribute):\n" +
str(iris_data.attribute_stats(0).numeric_stats))
print("nominal counts (last attribute):\n" + str(
iris_data.attribute_stats(iris_data.num_attributes -
1).nominal_counts))
helper.print_title("Instance values at #0")
for v in iris_data.get_instance(0):
print(v)
# append datasets
helper.print_title("append datasets")
data1 = Instances.copy_instances(iris_data, 0, 2)
data2 = Instances.copy_instances(iris_data, 2, 2)
print("Dataset #1:\n" + str(data1))
print("Dataset #2:\n" + str(data2))
msg = data1.equal_headers(data2)
print("#1 == #2 ? " + "yes" if msg is None else msg)
combined = Instances.append_instances(data1, data2)
print("Combined:\n" + str(combined))
# merge datasets
helper.print_title("merge datasets")
data1 = Instances.copy_instances(iris_data, 0, 2)
data1.class_index = -1
data1.delete_attribute(1)
data1.delete_first_attribute()
data2 = Instances.copy_instances(iris_data, 0, 2)
data2.class_index = -1
data2.delete_attribute(4)
data2.delete_attribute(3)
data2.delete_attribute(2)
print("Dataset #1:\n" + str(data1))
print("Dataset #2:\n" + str(data2))
msg = data1.equal_headers(data2)
print("#1 == #2 ? " + ("yes" if msg is None else msg))
combined = Instances.merge_instances(data2, data1)
print("Combined:\n" + str(combined))
# load dataset incrementally
iris_file = helper.get_data_dir() + os.sep + "iris.arff"
helper.print_info("Loading dataset incrementally: " + iris_file)
loader = Loader("weka.core.converters.ArffLoader")
iris_data = loader.load_file(iris_file, incremental=True)
iris_data.class_is_last()
helper.print_title("Iris dataset")
print(iris_data)
for inst in loader:
print(inst)
# create attributes
helper.print_title("Creating attributes")
num_att = Attribute.create_numeric("num")
print("numeric: " + str(num_att))
date_att = Attribute.create_date("dat", "yyyy-MM-dd")
print("date: " + str(date_att))
nom_att = Attribute.create_nominal("nom", ["label1", "label2"])
print("nominal: " + str(nom_att))
# create dataset
helper.print_title("Create dataset")
dataset = Instances.create_instances("helloworld",
[num_att, date_att, nom_att], 0)
print(str(dataset))
# create an instance
helper.print_title("Create and add instance")
values = [3.1415926, date_att.parse_date("2014-04-10"), 1.0]
inst = Instance.create_instance(values)
print("Instance #1:\n" + str(inst))
dataset.add_instance(inst)
values = [
2.71828,
date_att.parse_date("2014-08-09"),
Instance.missing_value()
]
inst = Instance.create_instance(values)
dataset.add_instance(inst)
print("Instance #2:\n" + str(inst))
inst.set_value(0, 4.0)
print("Instance #2 (updated):\n" + str(inst))
print("Dataset:\n" + str(dataset))
dataset.delete_with_missing(2)
print("Dataset (after delete of missing):\n" + str(dataset))
values = [(1, date_att.parse_date("2014-07-11"))]
inst = Instance.create_sparse_instance(
values, 3, classname="weka.core.SparseInstance")
print("sparse Instance:\n" + str(inst))
dataset.add_instance(inst)
print("dataset with mixed dense/sparse instance objects:\n" + str(dataset))
# create dataset (lists)
helper.print_title("Create dataset from lists")
x = [[randint(1, 10) for _ in range(5)] for _ in range(10)]
y = [randint(0, 1) for _ in range(10)]
dataset2 = ds.create_instances_from_lists(x, y, "generated from lists")
print(dataset2)
x = [[randint(1, 10) for _ in range(5)] for _ in range(10)]
dataset2 = ds.create_instances_from_lists(
x, name="generated from lists (no y)")
print(dataset2)
# create dataset (matrices)
helper.print_title("Create dataset from matrices")
x = np.random.randn(10, 5)
y = np.random.randn(10)
dataset3 = ds.create_instances_from_matrices(x, y,
"generated from matrices")
print(dataset3)
x = np.random.randn(10, 5)
dataset3 = ds.create_instances_from_matrices(
x, name="generated from matrices (no y)")
print(dataset3)
# create more sparse instances
diabetes_file = helper.get_data_dir() + os.sep + "diabetes.arff"
helper.print_info("Loading dataset: " + diabetes_file)
loader = Loader("weka.core.converters.ArffLoader")
diabetes_data = loader.load_file(diabetes_file)
diabetes_data.class_is_last()
helper.print_title("Create sparse instances using template dataset")
sparse_data = Instances.template_instances(diabetes_data)
for i in xrange(diabetes_data.num_attributes - 1):
inst = Instance.create_sparse_instance(
[(i, float(i + 1) / 10.0)],
sparse_data.num_attributes,
classname="weka.core.SparseInstance")
sparse_data.add_instance(inst)
print("sparse dataset:\n" + str(sparse_data))
# simple scatterplot of iris dataset: petalwidth x petallength
iris_data = loader.load_file(iris_file)
iris_data.class_is_last()
pld.scatter_plot(iris_data,
iris_data.attribute_by_name("petalwidth").index,
iris_data.attribute_by_name("petallength").index,
percent=50,
wait=False)
# line plot of iris dataset (without class attribute)
iris_data = loader.load_file(iris_file)
iris_data.class_is_last()
pld.line_plot(iris_data,
atts=xrange(iris_data.num_attributes - 1),
percent=50,
title="Line plot iris",
wait=False)
# matrix plot of iris dataset
iris_data = loader.load_file(iris_file)
iris_data.class_is_last()
pld.matrix_plot(iris_data, percent=50, title="Matrix plot iris", wait=True)
#classifier.classify_instance(inst=data.get_instance(index=4))
# In[4]:
from weka.core import dataset
from weka.core.dataset import Instance
# In[5]:
age, gender, mar_stat, ocd_hist, q2, q5, q10, q12, q13, q15, q17 = input(
"Input list here : ").split(" ")
# In[6]:
x = [age, gender, mar_stat, ocd_hist, q2, q5, q10, q12, q13, q15, q17]
x.append(Instance.missing_value())
data.add_instance(inst=Instance.create_instance(x))
classify = classifier.classify_instance(inst=data.get_instance(
index=data.num_instances - 1))
if (classify == 0.0):
print("No OCD")
else:
print("OCD")
# In[7]:
#print(data)
# In[8]:
jvm.stop()
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))
fc.classifier = cls
fc.build_classifier(train_data)
# Create test data
class_att = Attribute.create_nominal("class", ["good", "neutral", "bad"])
str_att = Attribute.create_string("title")
test_dataset = Instances.create_instances(
name="test_news_set",
atts=[str_att, class_att],
capacity=1
)
inst = Instance.create_instance([Instance.missing_value(), Instance.missing_value()])
test_dataset.add_instance(inst)
test_dataset.get_instance(0).set_string_value(0, article['processed']['title'])
test_dataset.class_is_last()
# Run classifier
article_instance = test_dataset.get_instance(0)
prediction = fc.classify_instance(article_instance)
article_type = article_instance.class_attribute.value(int(prediction))
if article_type is 'good' or 'neutral' or 'bad':
articles_collection.update_one({
"_id": article_id},
{
"$set": {