def load_classifier(lang, tag):
classifier = {}
if lang == LANG_ID and tag == "nnp":
objects = serialization.read_all(ID_MODEL_NNP)
elif lang == LANG_ID and tag == "nn":
objects = serialization.read_all(ID_MODEL_NN)
elif lang == LANG_ID and tag == "cdp":
objects = serialization.read_all(ID_MODEL_CDP)
elif lang == LANG_EN and tag == "nnp":
objects = serialization.read_all(EN_MODEL_NNP)
elif lang == LANG_EN and tag == "jj":
objects = serialization.read_all(EN_MODEL_JJ)
elif lang == LANG_EN and tag == "nn":
objects = serialization.read_all(EN_MODEL_NN)
elif lang == LANG_EN and tag == "vbp":
objects = serialization.read_all(EN_MODEL_VBP)
elif lang == LANG_EN and tag == "cd":
objects = serialization.read_all(EN_MODEL_CD)
elif lang == LANG_EN and tag == "vb":
objects = serialization.read_all(EN_MODEL_VB)
classifier['classifier'] = Classifier(jobject=objects[0])
classifier['filter'] = Filter(jobject=objects[1])
return classifier
def PredecirUnaTemporada(path):
jvm.start()
insta = CrearInstanciaParaPredecir(path)
atributos = ""
file = open('ModelData/wekaHeader.arff', 'r')
atributos = file.readlines()
file.close()
file = open('ModelData/predictionFiles/inst.arff', 'w')
file.writelines(atributos)
file.write("\n" + insta + '\n')
file.close()
objects = serialization.read_all("ModelData/77PercentModelPaisajes.model")
classifier = Classifier(jobject=objects[0])
loader = Loader()
data = loader.load_file("ModelData/predictionFiles/inst.arff")
data.class_is_last()
clases = ["invierno", "verano", "otono", "primavera"]
prediccion = ""
for index, inst in enumerate(data):
pred = classifier.classify_instance(inst)
dist = classifier.distribution_for_instance(inst)
prediccion = clases[int(pred)]
jvm.stop()
return prediccion
def test_read_write_all(self):
"""
Tests methods read_all and write_all.
"""
fname = self.tempfile("readwrite.ser")
self.delfile(fname)
lin = []
for i in range(4):
lin.append(javabridge.make_instance("java/lang/Integer", "(I)V",
i))
serialization.write_all(fname, lin)
self.assertTrue(os.path.exists(fname),
msg="Failed to write to " + fname + "?")
lout = serialization.read_all(fname)
self.assertIsNotNone(lout, msg="Failed to read from " + fname + "?")
self.delfile(fname)
self.assertEqual(len(lin), len(lout), msg="Number of elements differ")
for i in range(len(lin)):
iin = javabridge.call(lin[i], "intValue", "()I")
iout = javabridge.call(lout[i], "intValue", "()I")
self.assertEqual(iin,
iout,
msg="Input/output differ at #" + str(i))
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 load_model(filename):
""" Load the model from cache.
Args:
filename(str): The target file name (without extension) to load. Example: LMT
Returns:
The classifier and data object if the target caching is saved, otherwise None.
"""
# Path to the cashed model (example: caches/model/LMT.cache)
path = os.path.join(os.path.join('caches', 'model'), filename + '.cache')
print("Path to the cashed model to load:", path)
if os.path.isfile(path):
cached_model, cached_data_used_for_training = serialization.read_all(
path)
print("Loading cached classifier")
trained_classifier = Classifier(jobject=cached_model)
print("Loading cached data")
training_data = Instances(jobject=cached_data_used_for_training)
localizer_log.msg("Loaded model: {filename}".format(filename=filename))
return [trained_classifier, training_data]
localizer_log.msg("Failed to load cache of 'model'.")
return None
def TestClassification(arff, modelInput, results):
# 启动java虚拟机
jvm.start()
# 导入分析模型
objects = serialization.read_all(modelInput)
clsf = Classifier(jobject=objects[0])
print(clsf)
# 导入测试组
loader = Loader(classname="weka.core.converters.ArffLoader")
test = loader.load_file(arff)
test.class_is_first()
# 分析结果
resultsFile = open(results, "w")
resultsFile.write("序号\t原判断\t预测\t良性概率\t恶性概率\n")
print("序号\t原判断\t预测\t良性概率\t恶性概率")
for index, inst in enumerate(test):
pred = clsf.classify_instance(inst)
dist = clsf.distribution_for_instance(inst)
sampleID = index + 1
origin = inst.get_string_value(inst.class_index)
prediction = inst.class_attribute.value(int(pred))
sameAsOrigin = "yes" if pred != inst.get_value(
inst.class_index) else "no"
NRate = dist.tolist()[0]
PRate = dist.tolist()[1]
resultsFile.write(
"%d\t%s\t%s\t%s\t%s" %
(sampleID, origin, prediction, str(NRate), str(PRate)) + "\n")
print("%d\t%s\t%s\t%s\t%s" %
(sampleID, origin, prediction, str(NRate), str(PRate)))
resultsFile.close()
# 退出java虚拟机
jvm.stop()
print("检测完成")
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()
# train classifier
classifier = Classifier("weka.classifiers.trees.J48")
classifier.build_classifier(iris_data)
# save and read object
helper.print_title("I/O: single object")
outfile = tempfile.gettempdir() + os.sep + "j48.model"
serialization.write(outfile, classifier)
model = Classifier(jobject=serialization.read(outfile))
print(model)
# save classifier and dataset header (multiple objects)
helper.print_title("I/O: single object")
serialization.write_all(outfile, [classifier, Instances.template_instances(iris_data)])
objects = serialization.read_all(outfile)
for i, obj in enumerate(objects):
helper.print_info("Object #" + str(i+1) + ":")
if javabridge.get_env().is_instance_of(obj, javabridge.get_env().find_class("weka/core/Instances")):
obj = Instances(jobject=obj)
elif javabridge.get_env().is_instance_of(obj, javabridge.get_env().find_class("weka/classifiers/Classifier")):
obj = Classifier(jobject=obj)
print(obj)
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()
# train classifier
classifier = Classifier("weka.classifiers.trees.J48")
classifier.build_classifier(iris_data)
# save and read object
helper.print_title("I/O: model (using serialization module)")
outfile = tempfile.gettempdir() + os.sep + "j48.model"
serialization.write(outfile, classifier)
model = Classifier(jobject=serialization.read(outfile))
print(model)
# save classifier and dataset header (multiple objects)
helper.print_title("I/O: model and header (using serialization module)")
serialization.write_all(
outfile,
[classifier, Instances.template_instances(iris_data)])
objects = serialization.read_all(outfile)
for i, obj in enumerate(objects):
helper.print_info("Object #" + str(i + 1) + ":")
if javabridge.get_env().is_instance_of(
obj,
javabridge.get_env().find_class("weka/core/Instances")):
obj = Instances(jobject=obj)
elif javabridge.get_env().is_instance_of(
obj,
javabridge.get_env().find_class(
"weka/classifiers/Classifier")):
obj = Classifier(jobject=obj)
print(obj)
# save and read object
helper.print_title("I/O: just model (using Classifier class)")
outfile = tempfile.gettempdir() + os.sep + "j48.model"
classifier.serialize(outfile)
model, _ = Classifier.deserialize(outfile)
print(model)
# save classifier and dataset header (multiple objects)
helper.print_title("I/O: model and header (using Classifier class)")
classifier.serialize(outfile, header=iris_data)
model, header = Classifier.deserialize(outfile)
print(model)
if header is not None:
print(header)
def predicaoCluster(matricula, curso, tipo_predicao):
dados = retornarDadosCurso(curso)
# selecionando as caracteristicas do aluno
aluno = dados.loc[dados['MATRICULA'] == matricula][:]
aluno.drop('MATRICULA', axis=1, inplace=True)
aluno.drop('APROVADO', axis=1, inplace=True)
aluno.drop('COD_DISCIPLINA', axis=1, inplace=True)
aluno.drop('SIT_MATRICULA', axis=1, inplace=True)
aluno = aluno.head(1)
aluno.to_csv('aluno_temp.csv', index=False)
from weka.clusterers import Clusterer
import weka.core.jvm as jvm
from weka.core.converters import Loader
import weka.core.serialization as serialization
jvm.start()
if curso == 'si':
if tipo_predicao == 'reprovacao':
model = serialization.read_all("model/kmeans_si_reprovacao.model")
elif tipo_predicao == 'evasao':
model = serialization.read_all("model/kmeans_si_evasao.model")
elif curso == 'eca':
if tipo_predicao == 'reprovacao':
model = serialization.read_all("model/kmeans_eca_reprovacao.model")
elif tipo_predicao == 'evasao':
model = serialization.read_all("model/kmeans_eca_evasao.model")
cluster = Clusterer(jobject=model[0])
loader = Loader(classname="weka.core.converters.CSVLoader")
dado_aluno = loader.load_file("aluno_temp.csv")
for aluno in dado_aluno:
cluster_aluno_pertence = cluster.cluster_instance(aluno)
#jvm.stop()
caracteristica = retornarCaracteristicaCluster(curso, tipo_predicao,
cluster_aluno_pertence)
return caracteristica
def load_trained_model(self, t_mod):
# using the serialization library for
# opening the model
objects = serialization.read_all(t_mod)
# and after the using the classifier
# for actually learn the classifier
classifier = Classifier(jobject=objects[0])
print "Model Classified"
print classifier
# returning both classifier and objects
return objects, classifier
def weka_predict(self):
# grab WEKA model
objects = serialization.read_all(self.weka_model)
classifier = Classifier(jobject=objects[0])
# load the dataset i.e. the .arff file generated for the supplied url
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(self.dataset)
data.class_is_last()
# for each url tested predict whether "Phishy" or not by using the Random Tree model
for item in data:
self.prediction = classifier.classify_instance(item)
def __init__(self, number, name=None):
"""
Minimax bot which uses a simple feed-forward neural net to score board states
:param number: Board.X for player1 or Board.O for player2
:param name: A descriptive name for the Bot
"""
if name is None:
name = "Continuous Neural Net Bot"
MinimaxBot.__init__(self, number, name=name)
self.player_type = 'continuous-nn minimax'
objects = serialization.read_all("models/game/bots/weka_models/mlp-tuned-continuous.model")
self.classifier = Classifier(jobject=objects[0])
def predict(attributes):
jvm.start()
file_path = print_to_file(attributes)
# load the saved model
objects = serialization.read_all("/Users/hosyvietanh/Desktop/data_mining/trained_model.model")
classifier = Classifier(jobject=objects[0])
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(file_path)
data.class_is_last()
for index, inst in enumerate(data):
pred = classifier.classify_instance(inst)
dist = classifier.distribution_for_instance(inst)
return int(pred)
jvm.stop()
def __init__(self, number, name=None):
"""
Minimax bot which uses a Model Tree to score board states
:param number: Board.X for player1 or Board.O for player2
:param name: A descriptive name for the Bot
"""
if name is None:
name = "Model Tree Bot"
MinimaxBot.__init__(self, number, name=name)
self.player_type = 'modeltree minimax'
objects = serialization.read_all(
"models/game/bots/weka_models/model-tree.model")
self.classifier = Classifier(jobject=objects[0])
def __init__(self, number, name=None):
"""
Minimax bot which uses a nominal neural network to score board states
The neural net outputs one of ten classes. The higher the class number, the better the board state for X
:param number: Board.X for player1 or Board.O for player2
:param name: A descriptive name for the Bot
"""
if name is None:
name = "Nominal NeuralNet Bot"
MinimaxBot.__init__(self, number, name=name)
self.player_type = 'nominal-neuralnet minimax'
objects = serialization.read_all("models/game/bots/weka_models/mlp-tuned-categorical.model")
self.classifier = Classifier(jobject=objects[0])
def deserialize(cls, ser_file):
"""
Deserializes a filter from a file.
:param ser_file: the file to deserialize from
:type ser_file: str
:return: model
:rtype: Filter
"""
objs = serialization.read_all(ser_file)
if len(objs) == 1:
return Filter(jobject=objs[0])
else:
raise Exception(
"Excepted one object in the model file (%s), but encountered: %d" % (ser_file, len(objs)))
def __init__(self, number, name=None):
"""
Minimax bot which uses a decision tree to score board states
The decision tree outputs one of ten classes. The higher the class number, the better the board state for X
:param number: Board.X for player1 or Board.O for player2
:param name: A descriptive name for the Bot
"""
if name is None:
name = "DTree Bot"
MinimaxBot.__init__(self, number, name=name)
self.player_type = 'dtree minimax'
objects = serialization.read_all(
"models/game/bots/weka_models/j48_default.model")
self.classifier = Classifier(jobject=objects[0])
def functionProcessamento(self, ca1_r, ca1_l, ca2_ca3_r, ca2_ca3_l, sub_r,
sub_l, sexo, id):
jvm.start()
path = os.path.dirname(os.path.abspath(__file__))
# TODO: verificar qual o sexo do individuo para carregar o modelo corretamente
modelo = path + "\\naive_bayes_feminino_novo.model"
if (sexo == "Male"):
print("É masculino")
modelo = path + "\\naive_bayes_feminino_novo.model"
objects = serialization.read_all(modelo)
classifier = Classifier(jobject=objects[0])
loader = Loader(classname="weka.core.converters.ArffLoader")
arquivo = open(path + "\\novo_individuo.arff", "w")
conteudo = list()
conteudo.append("@relation alzheimer \n\n")
conteudo.append("@attribute doente {SIM, NAO} \n")
conteudo.append("@attribute ca1_right real \n")
conteudo.append("@attribute ca1_left real \n")
conteudo.append("@attribute ca2_ca3_right real\n")
conteudo.append("@attribute ca2_ca3_left real \n")
conteudo.append("@attribute subic_right real \n")
conteudo.append("@attribute subic_left real \n\n")
conteudo.append("@data \n")
#aqui passar as variáveis
conteudo.append("SIM," + str(ca1_r) + "," + str(ca1_l) + "," +
str(ca2_ca3_r) + "," + str(ca2_ca3_l) + "," +
str(sub_r) + "," + str(sub_l))
print(conteudo)
arquivo.writelines(conteudo)
arquivo.close()
data = loader.load_file(path + "\\novo_individuo.arff")
data.class_is_last()
for index, inst in enumerate(data):
pred = classifier.classify_instance(inst)
dist = classifier.distribution_for_instance(inst)
pc_doenca = round(((pred) * 100), 2)
pc_saudavel = round(((100 - pc_doenca)), 2)
print(" Porcentagem de alzheimer=" + str(pc_doenca) +
"%, porcentagem saudavel=" + str(pc_saudavel) + "%")
alzheimer = Alzheimer.objects.get(id=id)
alzheimer.resultado_ad = pc_doenca
alzheimer.resultado_cn = pc_saudavel
alzheimer.status_seg = 2
alzheimer.save()
jvm.stop()
def index():
if request.method == "GET":
return render_template('bot.html')
if request.method == "POST":
# jvm.stop()
jvm.start()
f = open("instances.arff", "a")
args = request.form.to_dict()
weight_lb = float(args['weight']) * 2.20462
bmi = (weight_lb / pow(float(args['height']), 2)) * 703
hypertensive_status = args['hypertensive_status']
heart_disease_status = args['heart_disease_status']
if heart_disease_status == "Yes":
heart_disease_status = '1'
else:
heart_disease_status = '0'
if hypertensive_status == "Yes":
hypertensive_status = '1'
else:
hypertensive_status = '0'
st = "\n"+args['gender']+","+args['age']+","+hypertensive_status+","+heart_disease_status+","+args['marrital_status'] + \
","+args['work_type']+","+args['residence']+"," + \
args['hypertension']+","+str(bmi)+",'"+args['smoking_status'].lower()+"',?"
print(st)
f.write(st)
f.close()
objects = serialization.read_all("J48.model")
loader = Loader(classname="weka.core.converters.ArffLoader")
csr = Classifier(jobject=objects[0])
output_results = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.CSV")
data1 = loader.load_file("instances.arff")
data1.class_is_last()
ev2 = Evaluation(data1)
ev2.test_model(csr, data1, output_results)
TESTDATA = StringIO("Instance,Actual,Predicted," +
output_results.buffer_content())
df = pd.read_csv(TESTDATA)
prediction = list(df.Predicted).pop().split(":")[1]
print(prediction)
# jvm.stop()
response = {"status": "200", "prediction": prediction}
return Response(json.dumps(response, indent=2),
mimetype="application/json")
def deserialize(cls, ser_file):
"""
Deserializes a clusterer from a file.
:param ser_file: the model file to deserialize
:type ser_file: str
:return: model and, if available, the dataset header
:rtype: tuple
"""
objs = serialization.read_all(ser_file)
if len(objs) == 1:
return Clusterer(jobject=objs[0]), None
elif len(objs) == 2:
return Clusterer(jobject=objs[0]), Instances(jobject=objs[1])
else:
raise Exception(
"Excepted one or two objects in the model file (%s), but encountered: %d"
% (ser_file, len(objs)))
def predict(self, modelName, x, arffName, debug=False):
# Carga el arrf para conocer la estructura de las instancias
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(arffName)
# Se asume que la clase es el ultimo atributo
data.class_is_last()
# Carga del modelo generado en Weka
objects = serialization.read_all(modelName)
cls = Classifier(jobject=objects[0])
if(debug):
print("Loaded model...")
print(cls)
# Se crea la instancia correspondiente a la entrada y se clasifica
if(debug): print("Input", x)
# Anyade un valor tonto para la clase de la instancia
if data.class_attribute.is_nominal:
x.append('a')
else:
x.append(0)
# Convierte los valores nominales a la posicion entera que ocupa dentro de sus lista
#print data.num_attributes
for i in range(0, data.num_attributes):
attribute = data.attribute(i)
if attribute.is_nominal:
x[i] = attribute.index_of(x[i])
'''print x[i]
print '''''
# Realiza la prediccion
inst = Instance.create_instance(x)
inst.dataset = data
pred = cls.classify_instance(inst)
if data.class_attribute.is_nominal:
pred = data.class_attribute.value(pred)
if(debug): print("Prediction", pred)
return pred
def test_read_write_all(self):
"""
Tests methods read_all and write_all.
"""
fname = self.tempfile("readwrite.ser")
self.delfile(fname)
lin = []
for i in range(4):
lin.append(javabridge.make_instance("java/lang/Integer", "(I)V", i))
serialization.write_all(fname, lin)
self.assertTrue(os.path.exists(fname), msg="Failed to write to " + fname + "?")
lout = serialization.read_all(fname)
self.assertIsNotNone(lout, msg="Failed to read from " + fname + "?")
self.delfile(fname)
self.assertEqual(len(lin), len(lout), msg="Number of elements differ")
for i in range(len(lin)):
iin = javabridge.call(lin[i], "intValue", "()I")
iout = javabridge.call(lout[i], "intValue", "()I")
self.assertEqual(iin, iout, msg="Input/output differ at #" + str(i))
from iotdata import IOTData
from ShimmerBluetooth import ShimmerBluetooth
import weka.core.serialization as serialization
from weka.classifiers import Classifier
import weka.core.jvm as jvm
from weka.core.converters import Loader
from weka.classifiers import Evaluation
from weka.core.classes import Random
# devices = ["Ground_Truth_Treadmill1", "Ground_Truth_Treadmill2", "Ground_Truth_Treadmill3", "Ground_Truth_Treadmill5"]
# device = IOTData(devices, 'Ground_Truth_data\\03_27_16\\')
# devices = IOTData(None, comport = "COM5")
jvm.start()
objects = serialization.read_all("test.model")
classifier = Classifier(jobject=objects[0])
# sensors = [ShimmerBluetooth("COM9", 256)]
dataManager = IOTData(None, comport = 'COM30')
predictions = [0]*len(sensors)
stepCount = 0
try:
while True:
for i in range(len(sensors)):
# aquire data
# df = sensors[i].getFrame()
df = dataManager.getNextWindow()
def main():
workbook = xlsxwriter.Workbook('../data/demo.xlsx')
worksheet = workbook.add_worksheet()
# Widen the first column to make the text clearer.
worksheet.set_column('A:A', 20)
worksheet.set_column('B:B', 20)
worksheet.set_column('C:C', 20)
worksheet.set_column('D:D', 20)
worksheet.set_column('E:E', 20)
worksheet.set_column('F:F', 20)
bold = workbook.add_format({'bold': True})
worksheet.write('A1', 'Source IP', bold)
worksheet.write('B1', 'TCP/UDP', bold)
worksheet.write('C1', 'Service Port', bold)
worksheet.write('D1', 'Description of Service', bold)
worksheet.write('E1', 'Destination IP', bold)
worksheet.write('F1', 'Action', bold)
# load a dataset
loader = Loader(classname="weka.core.converters.ArffLoader")
test_data = loader.load_file("../Logs/arff/logs_training_test.arff")
test_data.class_is_last() # set class attribute
#
# classifier2 = Classifier(classname="weka.classifiers.trees.J48", options=["-C", "0.3"])
# classifier2.build_classifier(test_data)
# # evaluate model on train/test split
objects = serialization.read_all("out.model")
classifier2 = Classifier(jobject=objects[0])
evaluation = Evaluation(test_data)
evl = evaluation.test_model(classifier2, test_data)
# print(evl)
# evaluation.evaluate_train_test_split(classifier2, test_data, 66.0, Random(1))
# print(evaluation.predictions)
# evaluation.evaluate_train_test_split(classifier2, test_data, 66.0, Random(1))
#
# print(list(enumerate(test_data)))
i = 0
for index, inst in enumerate(test_data):
pred = classifier2.classify_instance(inst)
dist = classifier2.distribution_for_instance(inst)
data_line = str(inst).split(",")
src_host = data_line[0]
dst_host = data_line[1]
dst_port = data_line[3]
protocol = data_line[4]
# print(int(pred))
if int(pred) == 1:
action = "permitted"
# print(action)
# print(src_host)
worksheet.write(i + 1, 0, src_host)
worksheet.write(i + 1, 1, protocol)
worksheet.write(i + 1, 2, dst_port)
worksheet.write(i + 1, 4, dst_host)
worksheet.write(i + 1, 5, action)
i = i + 1
# print(str(inst).split(","))
# print(len(inst))
# print(str(pred))
# print(str(index+1) + ": label index=" + str(pred) + ", class distribution=" + str(dist))
print(evaluation.summary())
workbook.close()
__author__ = 'umanoidTyphoon'
from build_weka_database import build
from classifier_model_analyzer import classify_dump
from weka.classifiers import Classifier
import util
import weka.core.jvm as jvm
import weka.core.serialization as serialization
# WINDOW_WIDTH = 10000
WINDOW_WIDTH = 25
jvm.start()
deserialized_objects = serialization.read_all("default.model")
classifier = Classifier(jobject=deserialized_objects[0])
print classifier
jvm.stop()
# build(WINDOW_WIDTH)
#
# conn = util.connect_to_db()
#
# cursor = conn.cursor()
#
# cursor.execute("""SELECT max(dump_id) from pe_dumps""")
# lastID = cursor.fetchone()[0]
#
# currID = lastID - WINDOW_WIDTH
def loadClassifier(self, filename, path='/home/sbiastoch/Schreibtisch/classifiers/'): objects = serialization.read_all(path+filename) self.classifier = Classifier(jobject=objects[0])
warnings.simplefilter(action='ignore', category=FutureWarning)
from weka.core.converters import Loader
l = Loader("weka.core.converters.ArffLoader")
# d = l.load_file("C:\Users\Paolo\Documents\school stuff\4th Year\for Implementation\dataset_Updated.arff")
d = l.load_file("C:\Program Files\Weka-3-8\data\dataset_new.arff")
#print(d)
# In[2]:
import weka.core.jvm as jvm
import weka.core.serialization as serialization
from weka.classifiers import Classifier
data = d
data.class_is_last()
objects = serialization.read_all("NBTree_trained.model")
classifier = Classifier(jobject=objects[0])
# In[3]:
#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(" ")
def getInstance(self, gameState):
headers = ""
headers = headers + "@relation prueba\n\n"
headers = headers + "@attribute score5 NUMERIC\n"
headers = headers + "@attribute score2 NUMERIC\n"
headers = headers + "@attribute score NUMERIC\n"
headers = headers + "@attribute ghost1-living {True, False}\n"
headers = headers + "@attribute ghost2-living {True, False}\n"
headers = headers + "@attribute ghost3-living {True, False}\n"
headers = headers + "@attribute ghost4-living {True, False}\n"
headers = headers + "@attribute distance-ghost1 NUMERIC \n"
headers = headers + "@attribute distance-ghost2 NUMERIC \n"
headers = headers + "@attribute distance-ghost3 NUMERIC \n"
headers = headers + "@attribute distance-ghost4 NUMERIC \n"
headers = headers + "@attribute posX NUMERIC\n"
headers = headers + "@attribute posY NUMERIC\n"
headers = headers + "@attribute direction {North, South, East, West, Stop}\n"
headers = headers + "@attribute wall-east {True, False}\n"
headers = headers + "@attribute wall-south {True, False}\n"
headers = headers + "@attribute wall-west {True, False}\n"
headers = headers + "@attribute wall-north {True, False}\n"
headers = headers + "@attribute move {North, South, East, West, Stop}\n\n"
headers = headers + "@data\n\n\n"
objects = serialization.read_all("data/out.model")
cls = [
classifiers.Classifier("weka.classifiers.trees.REPTree"),
classifiers.Classifier(
"weka.classifiers.functions.LinearRegression"),
classifiers.Classifier("weka.classifiers.functions.SMOreg"),
]
cls = Classifier()
file = open('data/instances.arff', 'w+')
file.write(headers)
line = ""
for i in gameState.livingGhosts[
1:]: #discard the first value, as it is PacMan
line = line + str(i) + ","
for i in gameState.data.ghostDistances:
if i is None:
line = line + "0" + ","
else:
line = line + str(i) + ","
line = line + str(gameState.data.agentStates[0].getPosition()[0]) + "," +\
str(gameState.data.agentStates[0].getPosition()[1])+ "," +\
str(gameState.data.agentStates[0].getDirection()) + "," +\
str(gameState.hasWall(gameState.getPacmanPosition()[0] - 1, gameState.getPacmanPosition()[1])) + "," +\
str(gameState.hasWall(gameState.getPacmanPosition()[0], gameState.getPacmanPosition()[1] - 1)) + "," +\
str(gameState.hasWall(gameState.getPacmanPosition()[0] + 1, gameState.getPacmanPosition()[1])) + "," +\
str(gameState.hasWall(gameState.getPacmanPosition()[0], gameState.getPacmanPosition()[1] + 1)) + ",?"
line = str(int(BustersAgent.getScore5(self, gameState))) + ","+\
str(int(BustersAgent.getScore2(self, gameState))) + "," +\
str(gameState.data.score) + "," + line
file.write(line)
file.close()
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file("data/instances.arff")
data.class_is_last() # set class attribute
for index, inst in enumerate(data):
pred = cls.classify_instance(inst)
return pred
from weka.classifiers import PredictionOutput
from weka.classifiers import Evaluation
from weka.core.classes import Random
import pandas as pd
# In[2]:
loader = Loader(classname="weka.core.converters.ArffLoader")
data_dir = "D:\\Rahul\\HealthCare ChatBot\\healthcare-dataset-stroke-data\\"
objects = serialization.read_all("J48.model")
csr = Classifier(jobject=objects[0])
#print(classifier)
# In[3]:
f= open("instances.arff","a")
#enter attributes
st= "\nFemale,54,1,0,Yes,Private,Urban,72.93,35.7,'never smoked',?"
f.write(st)
f.close()
def python_wrapper(mImage, prefix, file_name, pre_prefix, dir, permanent_dir,
model):
# Initialization of weka machine learning library
weka_machine_learning = WML.WekaMachineLearning()
# tokenization of images
token = re.split('RGB_|.png', mImage)
ir_directory = token[0] + 'IR_' + token[1] + '.pgm'
mat_directory = token[0] + 'Mat_' + token[1]
# get mat and ir image
image = segmentor.getImage(ir_directory)
mat = segmentor.readMatFile(mat_directory)
# image processing
edges = segmentor.edgeDetector(image)
type = segmentor.getTypeOfFruit(image)
segmentation = segmentor.segmentation(image, type)
filter = segmentor.filterImageFromSegmentation(image, segmentation)
output_seg = segmentor.imageMapping(filter, mat['IR'])
####################-Anomaly Detection via INFLO-###################
# file prefix creation for the csv file to save
prefix_csv = prefix + "\\" + file_name
# if folder is not there then create it
# and right the csv to the folder
if not os.path.exists(prefix):
os.mkdir(prefix)
csv = segmentor.writeToCSV(output_seg, prefix_csv)
print "file is written"
#else simply write the csv to the folder
else:
csv = segmentor.writeToCSV(output_seg, prefix_csv)
print "file is written"
#call the INFLO.bat after segmenting the image
#for anomaly detection
run_batch_file("rapid_miner_pro_ifruitlfy.bat")
############################-Clustering-############################
# image file directory is stored in ir_directory
# mat file directory is stored in mat_directory
# and need to get the INFLO file
# directory for INFLO file is prefix_csv
anomaly_file = prefix_csv + '.csv_INFLO.csv'
# directory for the temperorary files is made so
# some results can be stored and processed auto-
# matically by the rapid miner 5, this folder is
demo_printing_picture(permanent_dir, prefix, mImage, pre_prefix, dir,
file_name)
print(
"END OF ANOMALY DETECTION CLICK TRAIN AND SHOW RESULT FOR PROCESSING")
write_temp_dir = permanent_dir + "\\"
print prefix
print file_name
# Clean the junk of the output files
if os.path.exists(permanent_dir + "//output.csv"):
os.remove(permanent_dir + "//output.csv")
features = iFruitFly_clustering.cluster_analysis.cluster_analysis(
ir_directory, permanent_dir + "\\output_INFLO.csv", mat_directory,
dir + "\\" + file_name, prefix, file_name, permanent_dir)
if (features == None):
print("Image cant be segmented due to poor calibiration")
#other files are stored for the user in the junk
else:
print "printing images->>>>>>> ", prefix + file_name
image_plotter(features, ir_directory, prefix + file_name)
import csv
# Weka Machine Learning Inclusion on 5/30/2017
# adding one extra column
with open(permanent_dir + "\\output.csv", 'r') as csvinput:
with open(permanent_dir + "\\output_n.csv", 'w') as csvoutput:
writer = csv.writer(csvoutput, lineterminator='\n')
reader = csv.reader(csvinput)
all = []
row = next(reader)
row.append('result')
all.append(row)
for row in reader:
row.append(0)
all.append(row)
writer.writerows(all)
#model = "J:\iFruitFly\Python Scripts\Model 1\\model.model"
data_dir = permanent_dir + "\\output_n.csv"
#data_dir_open = open(data_dir)
#r = csv.reader(data_dir_open)
jvm.start()
loader = Loader(classname="weka.core.converters.CSVLoader")
data = loader.load_file(data_dir)
# using the serialization library for
# opening the model
objects = serialization.read_all(model)
classifier = Classifier(jobject=objects[0])
print "Model Classified"
print classifier
data.class_is_last()
for index, inst in enumerate(data):
pred = classifier.classify_instance(inst)
dist = classifier.distribution_for_instance(inst)
print pred
def predictionFromModel():
import weka.core.serialization as serialization
from weka.classifiers import Classifier
from weka.classifiers import Evaluation
predictionsPath = outputPrediction
models_dir = inputModel
modelsList = os.listdir(inputModel)
data_dir = input
folderList = os.listdir(inputModel)
i = 0
loader = Loader(classname="weka.core.converters.ArffLoader")
from weka.core.classes import Random
from weka.core.dataset import Instances
data = loader.load_file(os.path.join(inputModel, "genderTest.arff"))
data.class_is_last()
modelName = "GenderModel.model"
objects = serialization.read_all(os.path.join(inputModel, modelName))
trainedModel = Classifier(jobject=objects[0])
genderFile = open(os.path.join(outputPrediction, 'Gender_Predictions.csv'),
'w')
with genderFile:
j = -1
fieldnames = ['Test_Author_Profile_Id', 'Gender']
writer = csv.DictWriter(genderFile, fieldnames=fieldnames)
writer.writeheader()
for index, inst in enumerate(data):
j = j + 1
pred = trainedModel.classify_instance(inst)
dist = trainedModel.distribution_for_instance(inst)
print(
str(index + 1) + ": label index=" + str(pred) +
", class distribution=" + str(dist))
if (str(pred) == '0.0'):
writer.writerow({
'Test_Author_Profile_Id': my_list[j],
'Gender': 'male'
})
if (str(pred) == '1.0'):
writer.writerow({
'Test_Author_Profile_Id': my_list[j],
'Gender': 'female'
})
data = loader.load_file(os.path.join(inputModel, "ageTest.arff"))
data.class_is_last()
modelName = "AgeModel.model"
objects = serialization.read_all(os.path.join(inputModel, modelName))
trainedModel = Classifier(jobject=objects[0])
ageFile = open(os.path.join(outputPrediction, 'Age_Predictions.csv'), 'w')
with ageFile:
j = -1
fieldnames = ['Test_Author_Profile_Id', 'Age']
writer = csv.DictWriter(ageFile, fieldnames=fieldnames)
writer.writeheader()
for index, inst in enumerate(data):
j = j + 1
pred = trainedModel.classify_instance(inst)
dist = trainedModel.distribution_for_instance(inst)
print(
str(index + 1) + ": label index=" + str(pred) +
", class distribution=" + str(dist))
if (str(pred) == '0.0'):
writer.writerow({
'Test_Author_Profile_Id': my_list[j],
'Age': '15-19'
})
if (str(pred) == '1.0'):
writer.writerow({
'Test_Author_Profile_Id': my_list[j],
'Age': '20-24'
})
if (str(pred) == '2.0'):
writer.writerow({
'Test_Author_Profile_Id': my_list[j],
'Age': '25-xx'
})
os._exit(0)