def CV5x2(dataset, algo, num_datasets):
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(dataset)
data.class_is_last()
cls = Classifier(classname=algo)
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, 2, Random(5))
print(evl.summary("=== " +str(algo)+ " on" + str(dataset) + " ===",False))
print(evl.matrix("=== on click prediction(confusion matrix) ==="))
print("For Algo"+ str(algo)+"areaUnderROC/1: for CV5x2 " + str(evl.area_under_roc(1)))
return evl.area_under_roc(1)
def crossTest(this, trainingFile, classifier, testFile):
loader = Loader(classname="weka.core.converters.ArffLoader")
data1 = loader.load_file(trainingFile)
data1.class_is_last()
cls = Classifier(classname=classifier)
cls.build_classifier(data1)
data2 = loader.load_file(testFile)
data2.class_is_last()
classes = [str(code) for code in data2.class_attribute.values]
header = ["Accuracy"]
for name in classes:
header += [name + " TP", name + " FP", name + " AUC ROC"]
values = []
evl = Evaluation(data2)
evl.test_model(cls, data2)
values.append(evl.percent_correct)
for name in classes:
index = classes.index(name)
values += [
evl.true_positive_rate(index) * 100,
evl.false_positive_rate(index) * 100,
evl.area_under_roc(index)
]
this.values = values
this.header = header
def runCV(this, arffFile, classifier, folds):
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(arffFile)
data.class_is_last()
classes = [str(code) for code in data.class_attribute.values]
header = ["Accuracy"]
for name in classes:
header += [name + " TP", name + " FP", name + " AUC ROC"]
values = []
cls = Classifier(classname=classifier)
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, folds, Random(1))
values.append(evl.percent_correct)
for name in classes:
index = classes.index(name)
values += [
evl.true_positive_rate(index) * 100,
evl.false_positive_rate(index) * 100,
evl.area_under_roc(index)
]
this.values = values
this.header = header
def HOV(dataset, algo, num_datasets):
#Executing HOV \_*-*_/
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(dataset)
data.class_is_last()
train, test = data.train_test_split(70.0, Random(10))
cls = Classifier(classname=algo)
cls.build_classifier(train)
evl = Evaluation(train)
evl.test_model(cls, test)
print(evl.summary("=== " +str(algo)+ " on" + str(dataset) + " ===",False))
print(evl.matrix("=== on click prediction(confusion matrix) ==="))
print("For Algo"+ str(algo)+"areaUnderROC/1: for HOV " + str(evl.area_under_roc(1)))
return evl.area_under_roc(1)
def ClassifyWithDT(f3, test, tree, fileOut):
eval = Evaluation(f3)
tree.build_classifier(f3)
eval.test_model(tree, test)
print("\n\nSelf-Training data========" +
str((1 - eval.error_rate) * 100) + " number of instances==" +
str(f3.num_instances) + "\n")
print("\n Error Rate==" + str(eval.error_rate) + "\n")
print("\n precision recall areaUnderROC \n\n")
for i in range(test.get_instance(0).num_classes):
print(
str(eval.precision(i)) + " " + str(eval.recall(i)) + " " +
str(eval.area_under_roc(i)) + "\n")
return eval
def CV10(dataset, algo):
print "inside 10cv"
print("dataset ----" + dataset)
print("algorithm ----" + algo)
#Executing 10FCV
# jvm.start(packages=True)
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(dataset)
data.class_is_last()
#print(data)
cls = Classifier(classname=algo)
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, 2, Random(5))
print("areaUnderROC/1: " + str(evl.area_under_roc(1)))
def weka_bayesnet(filearffpath='data/datatobayes.arff'):
"""Simple calling of the bayesian network from python.
"""
#Preparing the data
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file('data/datatobayes.arff')
#data = loader.load_file('data/Full.arff')
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove",
options=["-R", "first"])
remove.inputformat(data)
filtered = data #remove.filter(data)
#Classifier test
from weka.classifiers import Classifier, Evaluation
from weka.core.classes import Random
filtered.class_is_last()
classifier = Classifier(classname="weka.classifiers.bayes.BayesNet",
options=['-D']) #
evaluation = Evaluation(filtered)
evaluation.crossvalidate_model(classifier, filtered, 10, Random(42))
return evaluation.area_under_roc(class_index=0) #ROC, no std of kfold
def HOV(dataset, algo):
print "inside hov"
print("dataset ----" + dataset)
print("algorithm ----" + algo)
#Executing HOV \_*-*_/
# jvm.start(packages=True)
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(dataset)
data.class_is_last()
train, test = data.train_test_split(70.0, Random(10))
cls = Classifier(classname=algo)
cls.build_classifier(train)
evl = Evaluation(train)
evl.test_model(cls, test)
return (str(evl.area_under_roc(1)))
dataLastTrain.class_is_last()
dataLastTest.class_is_last()
from weka.classifiers import Evaluation
from weka.core.classes import Random
from weka.classifiers import Classifier
if classifier == 0:
for kernel in range(0,2):
if kernel == 0:
mapper = Classifier(classname="weka.classifiers.misc.InputMappedClassifier", options=["-M","-W", "weka.classifiers.bayes.NaiveBayes"])
Class = 'NaiveBayes'
mapper.build_classifier(dataTrain)
evaluation = Evaluation(dataTrain)
evaluation.test_model(mapper,dataTest)
Scores.write(str(evaluation.area_under_roc(1)*100) + ',')
recall_NB.append(evaluation.recall(1)*100)
precision_NB.append(evaluation.precision(1)*100)
mapper.build_classifier(dataLastTrain)
evaluation = Evaluation(dataLastTrain)
evaluation.test_model(mapper, dataLastTest)
ScoresLast.write(str(evaluation.area_under_roc(1) * 100)+',')
else:
mapper = Classifier(classname="weka.classifiers.misc.InputMappedClassifier",
options=["-M","-W", "weka.classifiers.bayes.NaiveBayes", "--", "-K"])
Class = 'NaiveBayes'
eval = Evaluation(labledDataSet)
eval.test_model(tree, test)
fileOut.write("Labeled data======== " + str((1.0 - eval.error_rate )* 100) + " number of instances== " + str(labledDataSet.num_instances) + "\n")
Newtrainpool = LabeledUnlabeldata(labledDataSet, UnlabledDataSet, tree, y )
# Newtrainpool = LabeledUnlabeldata(labledDataSet, UnlabledDataSet, tree, y , cal_method=Method)
fileOut.write("\n\nLabeled data======== " + str((1.0 - eval.error_rate )* 100) + " number of instances== " + str(labledDataSet.num_instances) + "\n")
fileOut.write(" Decision Tree \n")
fileOut.write("\n precision recall areaUnderROC \n\n")
for i in range(test.get_instance(0).num_classes) :
fileOut.write(str(eval.precision(i)) +" "+str(eval.recall(i)) + " " + str(eval.area_under_roc(i))+"\n")
ClassifyWithDT(Newtrainpool, test, tree, fileOut )
fileOut.write("\n")
fileOut.write("########################################################\n")
fileOut.write("\n")
except Exception as e:
raise e
fileOut.write("\n")
fileOut.write("\n")
fileOut.write("########################################################\n")
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()
# classifier help
helper.print_title("Creating help string")
classifier = Classifier(classname="weka.classifiers.trees.J48")
print(classifier.to_help())
# partial classname
helper.print_title("Creating classifier from partial classname")
clsname = ".J48"
classifier = Classifier(classname=clsname)
print(clsname + " --> " + classifier.classname)
# classifier from commandline
helper.print_title("Creating SMO from command-line string")
cmdline = 'weka.classifiers.functions.SMO -K "weka.classifiers.functions.supportVector.NormalizedPolyKernel -E 3.0"'
classifier = from_commandline(cmdline, classname="weka.classifiers.Classifier")
classifier.build_classifier(iris_data)
print("input: " + cmdline)
print("output: " + classifier.to_commandline())
print("model:\n" + str(classifier))
# kernel classifier
helper.print_title("Creating SMO as KernelClassifier")
kernel = Kernel(classname="weka.classifiers.functions.supportVector.RBFKernel", options=["-G", "0.001"])
classifier = KernelClassifier(classname="weka.classifiers.functions.SMO", options=["-M"])
classifier.kernel = kernel
classifier.build_classifier(iris_data)
print("classifier: " + classifier.to_commandline())
print("model:\n" + str(classifier))
# build a classifier and output model
helper.print_title("Training J48 classifier on iris")
classifier = Classifier(classname="weka.classifiers.trees.J48")
# Instead of using 'options=["-C", "0.3"]' in the constructor, we can also set the "confidenceFactor"
# property of the J48 classifier itself. However, being of type float rather than double, we need
# to convert it to the correct type first using the double_to_float function:
classifier.set_property("confidenceFactor", typeconv.double_to_float(0.3))
classifier.build_classifier(iris_data)
print(classifier)
print(classifier.graph)
print(classifier.to_source("MyJ48"))
plot_graph.plot_dot_graph(classifier.graph)
# evaluate model on test set
helper.print_title("Evaluating J48 classifier on iris")
evaluation = Evaluation(iris_data)
evl = evaluation.test_model(classifier, iris_data)
print(evl)
print(evaluation.summary())
# evaluate model on train/test split
helper.print_title("Evaluating J48 classifier on iris (random split 66%)")
classifier = Classifier(classname="weka.classifiers.trees.J48", options=["-C", "0.3"])
evaluation = Evaluation(iris_data)
evaluation.evaluate_train_test_split(classifier, iris_data, 66.0, Random(1))
print(evaluation.summary())
# load a dataset incrementally and build classifier incrementally
helper.print_title("Build classifier incrementally on iris")
helper.print_info("Loading dataset: " + iris_file)
loader = Loader("weka.core.converters.ArffLoader")
iris_inc = loader.load_file(iris_file, incremental=True)
iris_inc.class_is_last()
classifier = Classifier(classname="weka.classifiers.bayes.NaiveBayesUpdateable")
classifier.build_classifier(iris_inc)
for inst in loader:
classifier.update_classifier(inst)
print(classifier)
# construct meta-classifiers
helper.print_title("Meta classifiers")
# generic FilteredClassifier instantiation
print("generic FilteredClassifier instantiation")
meta = SingleClassifierEnhancer(classname="weka.classifiers.meta.FilteredClassifier")
meta.classifier = Classifier(classname="weka.classifiers.functions.LinearRegression")
flter = Filter("weka.filters.unsupervised.attribute.Remove")
flter.options = ["-R", "first"]
meta.set_property("filter", flter.jobject)
print(meta.to_commandline())
# direct FilteredClassifier instantiation
print("direct FilteredClassifier instantiation")
meta = FilteredClassifier()
meta.classifier = Classifier(classname="weka.classifiers.functions.LinearRegression")
flter = Filter("weka.filters.unsupervised.attribute.Remove")
flter.options = ["-R", "first"]
meta.filter = flter
print(meta.to_commandline())
# generic Vote
print("generic Vote instantiation")
meta = MultipleClassifiersCombiner(classname="weka.classifiers.meta.Vote")
classifiers = [
Classifier(classname="weka.classifiers.functions.SMO"),
Classifier(classname="weka.classifiers.trees.J48")
]
meta.classifiers = classifiers
print(meta.to_commandline())
# cross-validate nominal classifier
helper.print_title("Cross-validating NaiveBayes on diabetes")
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()
classifier = Classifier(classname="weka.classifiers.bayes.NaiveBayes")
pred_output = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.PlainText", options=["-distribution"])
evaluation = Evaluation(diabetes_data)
evaluation.crossvalidate_model(classifier, diabetes_data, 10, Random(42), output=pred_output)
print(evaluation.summary())
print(evaluation.class_details())
print(evaluation.matrix())
print("areaUnderPRC/0: " + str(evaluation.area_under_prc(0)))
print("weightedAreaUnderPRC: " + str(evaluation.weighted_area_under_prc))
print("areaUnderROC/1: " + str(evaluation.area_under_roc(1)))
print("weightedAreaUnderROC: " + str(evaluation.weighted_area_under_roc))
print("avgCost: " + str(evaluation.avg_cost))
print("totalCost: " + str(evaluation.total_cost))
print("confusionMatrix: " + str(evaluation.confusion_matrix))
print("correct: " + str(evaluation.correct))
print("pctCorrect: " + str(evaluation.percent_correct))
print("incorrect: " + str(evaluation.incorrect))
print("pctIncorrect: " + str(evaluation.percent_incorrect))
print("unclassified: " + str(evaluation.unclassified))
print("pctUnclassified: " + str(evaluation.percent_unclassified))
print("coverageOfTestCasesByPredictedRegions: " + str(evaluation.coverage_of_test_cases_by_predicted_regions))
print("sizeOfPredictedRegions: " + str(evaluation.size_of_predicted_regions))
print("falseNegativeRate: " + str(evaluation.false_negative_rate(1)))
print("weightedFalseNegativeRate: " + str(evaluation.weighted_false_negative_rate))
print("numFalseNegatives: " + str(evaluation.num_false_negatives(1)))
print("trueNegativeRate: " + str(evaluation.true_negative_rate(1)))
print("weightedTrueNegativeRate: " + str(evaluation.weighted_true_negative_rate))
print("numTrueNegatives: " + str(evaluation.num_true_negatives(1)))
print("falsePositiveRate: " + str(evaluation.false_positive_rate(1)))
print("weightedFalsePositiveRate: " + str(evaluation.weighted_false_positive_rate))
print("numFalsePositives: " + str(evaluation.num_false_positives(1)))
print("truePositiveRate: " + str(evaluation.true_positive_rate(1)))
print("weightedTruePositiveRate: " + str(evaluation.weighted_true_positive_rate))
print("numTruePositives: " + str(evaluation.num_true_positives(1)))
print("fMeasure: " + str(evaluation.f_measure(1)))
print("weightedFMeasure: " + str(evaluation.weighted_f_measure))
print("unweightedMacroFmeasure: " + str(evaluation.unweighted_macro_f_measure))
print("unweightedMicroFmeasure: " + str(evaluation.unweighted_micro_f_measure))
print("precision: " + str(evaluation.precision(1)))
print("weightedPrecision: " + str(evaluation.weighted_precision))
print("recall: " + str(evaluation.recall(1)))
print("weightedRecall: " + str(evaluation.weighted_recall))
print("kappa: " + str(evaluation.kappa))
print("KBInformation: " + str(evaluation.kb_information))
print("KBMeanInformation: " + str(evaluation.kb_mean_information))
print("KBRelativeInformation: " + str(evaluation.kb_relative_information))
print("SFEntropyGain: " + str(evaluation.sf_entropy_gain))
print("SFMeanEntropyGain: " + str(evaluation.sf_mean_entropy_gain))
print("SFMeanPriorEntropy: " + str(evaluation.sf_mean_prior_entropy))
print("SFMeanSchemeEntropy: " + str(evaluation.sf_mean_scheme_entropy))
print("matthewsCorrelationCoefficient: " + str(evaluation.matthews_correlation_coefficient(1)))
print("weightedMatthewsCorrelation: " + str(evaluation.weighted_matthews_correlation))
print("class priors: " + str(evaluation.class_priors))
print("numInstances: " + str(evaluation.num_instances))
print("meanAbsoluteError: " + str(evaluation.mean_absolute_error))
print("meanPriorAbsoluteError: " + str(evaluation.mean_prior_absolute_error))
print("relativeAbsoluteError: " + str(evaluation.relative_absolute_error))
print("rootMeanSquaredError: " + str(evaluation.root_mean_squared_error))
print("rootMeanPriorSquaredError: " + str(evaluation.root_mean_prior_squared_error))
print("rootRelativeSquaredError: " + str(evaluation.root_relative_squared_error))
print("prediction output:\n" + str(pred_output))
plot_cls.plot_roc(
evaluation, title="ROC diabetes",
class_index=range(0, diabetes_data.class_attribute.num_values), wait=False)
plot_cls.plot_prc(
evaluation, title="PRC diabetes",
class_index=range(0, diabetes_data.class_attribute.num_values), wait=False)
# load a numeric dataset
bolts_file = helper.get_data_dir() + os.sep + "bolts.arff"
helper.print_info("Loading dataset: " + bolts_file)
loader = Loader("weka.core.converters.ArffLoader")
bolts_data = loader.load_file(bolts_file)
bolts_data.class_is_last()
# build a classifier and output model
helper.print_title("Training LinearRegression on bolts")
classifier = Classifier(classname="weka.classifiers.functions.LinearRegression", options=["-S", "1", "-C"])
classifier.build_classifier(bolts_data)
print(classifier)
# cross-validate numeric classifier
helper.print_title("Cross-validating LinearRegression on bolts")
classifier = Classifier(classname="weka.classifiers.functions.LinearRegression", options=["-S", "1", "-C"])
evaluation = Evaluation(bolts_data)
evaluation.crossvalidate_model(classifier, bolts_data, 10, Random(42))
print(evaluation.summary())
print("correlationCoefficient: " + str(evaluation.correlation_coefficient))
print("errorRate: " + str(evaluation.error_rate))
helper.print_title("Header - bolts")
print(str(evaluation.header))
helper.print_title("Predictions on bolts")
for index, pred in enumerate(evaluation.predictions):
print(str(index+1) + ": " + str(pred) + " -> error=" + str(pred.error))
plot_cls.plot_classifier_errors(evaluation.predictions, wait=False)
# learning curve
cls = [
Classifier(classname="weka.classifiers.trees.J48"),
Classifier(classname="weka.classifiers.bayes.NaiveBayesUpdateable")]
plot_cls.plot_learning_curve(
cls, diabetes_data, increments=0.05, label_template="[#] !", metric="percent_correct", wait=True)
# access classifier's Java API
labor_file = helper.get_data_dir() + os.sep + "labor.arff"
helper.print_info("Loading dataset: " + labor_file)
loader = Loader("weka.core.converters.ArffLoader")
labor_data = loader.load_file(labor_file)
labor_data.class_is_last()
helper.print_title("Using JRip's Java API to access rules")
jrip = Classifier(classname="weka.classifiers.rules.JRip")
jrip.build_classifier(labor_data)
rset = jrip.jwrapper.getRuleset()
for i in range(rset.size()):
r = rset.get(i)
print(str(r.toString(labor_data.class_attribute.jobject)))
if classifier == 0:
for kernel in range(0, 1):
if kernel == 0:
mapper = Classifier(
classname=
"weka.classifiers.misc.InputMappedClassifier",
options=[
'-M', "-W",
"weka.classifiers.bayes.NaiveBayes"
])
Class = 'NaiveBayes'
mapper.build_classifier(dataTrain)
evaluation = Evaluation(dataTrain)
evaluation.test_model(mapper, dataTest)
roc_aux_NB.append(
evaluation.area_under_roc(1) * 100)
recall_aux_NB.append(
evaluation.recall(1) * 100)
precision_aux_NB.append(
evaluation.precision(1) * 100)
elif classifier == 1:
for degree in range(3, 4):
mapper = Classifier(
classname=
"weka.classifiers.misc.InputMappedClassifier",
options=[
'-M', "-W",
"weka.classifiers.functions.SMO",
"--", "-K",
"weka.classifiers.functions.supportVector.PolyKernel -E "
import weka.core.jvm as jvm
import weka.core.converters as conv
from weka.classifiers import Evaluation, Classifier
from weka.core.classes import Random
import weka.plot.classifiers as plcls # NB: matplotlib is required
import os
data_dir = "/home/suruchi/Desktop/BTECH Pro/new/click_prediction/"
jvm.start(packages=True)
from weka.core.converters import Loader
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(data_dir + "click_prediction.arff")
data.class_is_last()
#print(data)
cls = Classifier(classname="weka.classifiers.bayes.NaiveBayes")
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, 2, Random(5))
print(evl.summary("=== NaiveBayes on click prediction (stats) ===", False))
print(evl.matrix("=== NaiveBayes on click prediction(confusion matrix) ==="))
#plcls.plot_classifier_errors(evl.predictions, absolute=False,wait = True)
plcls.plot_roc(evl, class_index=[0, 1], wait=True)
print("areaUnderROC/1: " + str(evl.area_under_roc(1)))
jvm.stop()
for kernel in range(0, 1):
if kernel == 0:
mapper = Classifier(
classname=
"weka.classifiers.misc.InputMappedClassifier",
options=[
"-M", "-W",
"weka.classifiers.bayes.NaiveBayes"
])
Class = 'NaiveBayes'
mapper.build_classifier(dataTrainSlow)
evaluation = Evaluation(dataTrainSlow)
evaluation.test_model(mapper, dataTestSlow)
NB_AUC[seed - 1, fold - 1,
0] = (evaluation.area_under_roc(1) *
100)
NB_Recall[seed - 1, fold - 1,
0] = (evaluation.recall(yIndexSlow) *
100)
NB_Precision[seed - 1, fold - 1, 0] = (
evaluation.precision(yIndexSlow) * 100)
if window == 365:
mapper = Classifier(
classname=
"weka.classifiers.misc.InputMappedClassifier",
options=[
"-M", "-W",
"weka.classifiers.bayes.NaiveBayes",
'--', '-K'
y,
cal_method=Method)
print("\n\nLabeled data======== " +
str((1.0 - eval.error_rate) * 100) +
" number of instances== " +
str(labledDataSet.num_instances) + "\n")
print(" Decision Tree \n")
print(
"\n precision recall areaUnderROC \n\n")
for i in range(test.get_instance(0).num_classes):
print(
str(eval.precision(i)) + " " + str(eval.recall(i)) +
" " + str(eval.area_under_roc(i)) + "\n")
ClassifyWithDT(Newtrainpool, test, tree, fileOut)
print("\n")
print("########################################################\n")
print("\n")
except Exception as e:
raise e
print("\n")
print("\n")
print("########################################################\n")
print("########################################################\n")
print("########################################################\n")
RF = Classifier(
classname="weka.classifiers.misc.InputMappedClassifier",
options=[
"-M", "-W", "weka.classifiers.trees.RandomForest", "--",
"-I", '20'
])
Class = 'NaiveBayes'
RF.build_classifier(dataTrain)
evaluationRF = Evaluation(dataTrain)
evaluationRF.test_model(RF, dataTest)
if dataset == 'First':
Scores.write(
str(window) + ',' +
str(np.round(evaluationNB.area_under_roc(1) * 100, 2)) +
',' +
str(np.round(evaluationRF.area_under_roc(1) * 100, 2)) +
'\n')
else:
ScoresLast.write(
str(window) + ',' +
str(np.round(evaluationNB.area_under_roc(1) * 100, 2)) +
',' +
str(np.round(evaluationRF.area_under_roc(1) * 100, 2)) +
'\n')
if ntp == 2 and dataset == 'First':
Perf.write(
'\multirow{8}{*}{' + str(window) + 'd}' + ' & ' +
# #print(cls.options)
# cls.build_classifier(dataTrain)
from weka.classifiers import Evaluation
#print("Evaluating NB classifier")
evaluation = Evaluation(dataTrain)
evl = evaluation.test_model(mapper, dataTest)
print('Window' + str(Window[window]) + '_S' + str(seed) +
'_Fold' + str(fold) + ': Performance')
#print(evaluation.summary())
#print(evaluation.class_details())
#print(evaluation.matrix())
#print(evaluation.summary())
#print(evaluation.class_details())
#print(evaluation.matrix())
roc.append(evaluation.area_under_roc(1))
sens.append(evaluation.true_positive_rate(1))
spec.append(evaluation.true_negative_rate(1))
if fold == 10 and seed == 5:
print('Window' + str(Window[window]) + '_S' + str(seed) +
'_Fold' + str(fold) + ': Performance')
print('AUC: ' + str(np.mean(roc)))
print('Sens: ' + str(np.mean(sens)))
print('Spec:' + str(np.mean(spec)))
Perf.write('Window' + str(Window[window]) +
': Performance\n\n')
Perf.write('AUC: ' + str(np.mean(roc)) + '\n')
Perf.write('Sens: ' + str(np.mean(sens)) + '\n')
Perf.write('Spec:' + str(np.mean(spec)) + '\n')
except:
RF = Classifier(classname="weka.classifiers.misc.InputMappedClassifier",
options=["-M", "-W", "weka.classifiers.bayes.NaiveBayes"])
# Class = 'NaiveBayes'
# NB.build_classifier(dataTrain)
# evaluationNB = Evaluation(dataTrain)
# evaluationNB.test_model(NB, dataTest)
# RF = Classifier(classname="weka.classifiers.misc.InputMappedClassifier",
# options=["-M", "-W", "weka.classifiers.trees.RandomForest", "--", "-I",
# '20'])
Class = 'NaiveBayes'
RF.build_classifier(dataTrain)
evaluationRF = Evaluation(dataTrain)
evaluationRF.test_model(RF, dataTest)
print(evaluationRF.area_under_roc(1))
if ntp == 2 and dataset == 'Slow':
Perf.write(
'\multirow{6}{*}{' + str(window) + 'd}' + ' & ' + '\multirow{3}{*}{' + str(ntp) + '}' + ' & ' + dataset + ' & ' + str(np.round(evaluationRF.area_under_roc(1) * 100, 2)) + ' & ' + str(np.round(evaluationRF.precision(yIndex) * 100, 2)) + ' & ' + str(np.round(evaluationRF.recall(yIndex) * 100, 2)) + '\\\\\n')
# Precision.write(
# '\multirow{8}{*}{' + str(window) + 'd}' + ' & ' + '\multirow{2}{*}{' + str(
# ntp) + '}' + ' & ' + dataset + ' & ' + str(
# np.round(evaluationNB.precision(yIndex) * 100, 2)) + ' & ' + str(
# np.round(evaluationRF.precision(yIndex) * 100, 2)) + '\\\\\n')
#
# Recall.write('\multirow{8}{*}{' + str(window) + 'd}' + ' & ' + '\multirow{2}{*}{' + str(
# ntp) + '}' + ' & ' + dataset + ' & ' + str(np.round(evaluationNB.recall(yIndex) * 100, 2)) + ' & ' + str(
# np.round(evaluationRF.recall(yIndex) * 100, 2)) + '\\\\\n')
from weka.classifiers import Classifier
if classifier == 0:
SMOTE = Filter(classname="weka.filters.supervised.instance.SMOTE", options=['-P', str(smote)])
SMOTE.inputformat(dataTrain)
dataTrain = SMOTE.filter(dataTrain)
SMOTE.inputformat(dataLastTrain)
dataLastTrain = SMOTE.filter(dataLastTrain)
for kernel in range(0,1):
if kernel == 0:
mapper = Classifier(classname="weka.classifiers.misc.InputMappedClassifier", options=["-M","-W", "weka.classifiers.bayes.NaiveBayes"])
Class = 'NaiveBayes'
mapper.build_classifier(dataTrain)
evaluation = Evaluation(dataTrain)
evaluation.test_model(mapper,dataTest)
roc_NB.append(evaluation.area_under_roc(1)*100)
recall_NB.append(evaluation.recall(yIndex)*100)
precision_NB.append(evaluation.precision(yIndex)*100)
mapper.build_classifier(dataLastTrain)
evaluation = Evaluation(dataLastTrain)
evaluation.test_model(mapper, dataLastTest)
roc_NB_Last.append(evaluation.area_under_roc(1) * 100)
recall_NB_Last.append(evaluation.recall(yIndex) * 100)
precision_NB_Last.append(evaluation.precision(yIndex) * 100)
elif classifier == 1:
for degree in [2]:
mapper = Classifier(classname="weka.classifiers.misc.InputMappedClassifier", options=["-M","-W", "weka.classifiers.functions.SMO", "--", "-K","weka.classifiers.functions.supportVector.PolyKernel -E " + str(degree)])
Class = 'SVM'
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()
# classifier help
helper.print_title("Creating help string")
classifier = Classifier(classname="weka.classifiers.trees.J48")
print(classifier.to_help())
# partial classname
helper.print_title("Creating classifier from partial classname")
clsname = ".J48"
classifier = Classifier(classname=clsname)
print(clsname + " --> " + classifier.classname)
# classifier from commandline
helper.print_title("Creating SMO from command-line string")
cmdline = 'weka.classifiers.functions.SMO -K "weka.classifiers.functions.supportVector.NormalizedPolyKernel -E 3.0"'
classifier = from_commandline(cmdline,
classname="weka.classifiers.Classifier")
classifier.build_classifier(iris_data)
print("input: " + cmdline)
print("output: " + classifier.to_commandline())
print("model:\n" + str(classifier))
# kernel classifier
helper.print_title("Creating SMO as KernelClassifier")
kernel = Kernel(
classname="weka.classifiers.functions.supportVector.RBFKernel",
options=["-G", "0.001"])
classifier = KernelClassifier(classname="weka.classifiers.functions.SMO",
options=["-M"])
classifier.kernel = kernel
classifier.build_classifier(iris_data)
print("classifier: " + classifier.to_commandline())
print("model:\n" + str(classifier))
# build a classifier and output model
helper.print_title("Training J48 classifier on iris")
classifier = Classifier(classname="weka.classifiers.trees.J48")
# Instead of using 'options=["-C", "0.3"]' in the constructor, we can also set the "confidenceFactor"
# property of the J48 classifier itself. However, being of type float rather than double, we need
# to convert it to the correct type first using the double_to_float function:
classifier.set_property("confidenceFactor", types.double_to_float(0.3))
classifier.build_classifier(iris_data)
print(classifier)
print(classifier.graph)
print(classifier.to_source("MyJ48"))
plot_graph.plot_dot_graph(classifier.graph)
# evaluate model on test set
helper.print_title("Evaluating J48 classifier on iris")
evaluation = Evaluation(iris_data)
evl = evaluation.test_model(classifier, iris_data)
print(evl)
print(evaluation.summary())
# evaluate model on train/test split
helper.print_title("Evaluating J48 classifier on iris (random split 66%)")
classifier = Classifier(classname="weka.classifiers.trees.J48",
options=["-C", "0.3"])
evaluation = Evaluation(iris_data)
evaluation.evaluate_train_test_split(classifier, iris_data, 66.0,
Random(1))
print(evaluation.summary())
# load a dataset incrementally and build classifier incrementally
helper.print_title("Build classifier incrementally on iris")
helper.print_info("Loading dataset: " + iris_file)
loader = Loader("weka.core.converters.ArffLoader")
iris_inc = loader.load_file(iris_file, incremental=True)
iris_inc.class_is_last()
classifier = Classifier(
classname="weka.classifiers.bayes.NaiveBayesUpdateable")
classifier.build_classifier(iris_inc)
for inst in loader:
classifier.update_classifier(inst)
print(classifier)
# construct meta-classifiers
helper.print_title("Meta classifiers")
# generic FilteredClassifier instantiation
print("generic FilteredClassifier instantiation")
meta = SingleClassifierEnhancer(
classname="weka.classifiers.meta.FilteredClassifier")
meta.classifier = Classifier(
classname="weka.classifiers.functions.LinearRegression")
flter = Filter("weka.filters.unsupervised.attribute.Remove")
flter.options = ["-R", "first"]
meta.set_property("filter", flter.jobject)
print(meta.to_commandline())
# direct FilteredClassifier instantiation
print("direct FilteredClassifier instantiation")
meta = FilteredClassifier()
meta.classifier = Classifier(
classname="weka.classifiers.functions.LinearRegression")
flter = Filter("weka.filters.unsupervised.attribute.Remove")
flter.options = ["-R", "first"]
meta.filter = flter
print(meta.to_commandline())
# generic Vote
print("generic Vote instantiation")
meta = MultipleClassifiersCombiner(classname="weka.classifiers.meta.Vote")
classifiers = [
Classifier(classname="weka.classifiers.functions.SMO"),
Classifier(classname="weka.classifiers.trees.J48")
]
meta.classifiers = classifiers
print(meta.to_commandline())
# cross-validate nominal classifier
helper.print_title("Cross-validating NaiveBayes on diabetes")
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()
classifier = Classifier(classname="weka.classifiers.bayes.NaiveBayes")
pred_output = PredictionOutput(
classname="weka.classifiers.evaluation.output.prediction.PlainText",
options=["-distribution"])
evaluation = Evaluation(diabetes_data)
evaluation.crossvalidate_model(classifier,
diabetes_data,
10,
Random(42),
output=pred_output)
print(evaluation.summary())
print(evaluation.class_details())
print(evaluation.matrix())
print("areaUnderPRC/0: " + str(evaluation.area_under_prc(0)))
print("weightedAreaUnderPRC: " + str(evaluation.weighted_area_under_prc))
print("areaUnderROC/1: " + str(evaluation.area_under_roc(1)))
print("weightedAreaUnderROC: " + str(evaluation.weighted_area_under_roc))
print("avgCost: " + str(evaluation.avg_cost))
print("totalCost: " + str(evaluation.total_cost))
print("confusionMatrix: " + str(evaluation.confusion_matrix))
print("correct: " + str(evaluation.correct))
print("pctCorrect: " + str(evaluation.percent_correct))
print("incorrect: " + str(evaluation.incorrect))
print("pctIncorrect: " + str(evaluation.percent_incorrect))
print("unclassified: " + str(evaluation.unclassified))
print("pctUnclassified: " + str(evaluation.percent_unclassified))
print("coverageOfTestCasesByPredictedRegions: " +
str(evaluation.coverage_of_test_cases_by_predicted_regions))
print("sizeOfPredictedRegions: " +
str(evaluation.size_of_predicted_regions))
print("falseNegativeRate: " + str(evaluation.false_negative_rate(1)))
print("weightedFalseNegativeRate: " +
str(evaluation.weighted_false_negative_rate))
print("numFalseNegatives: " + str(evaluation.num_false_negatives(1)))
print("trueNegativeRate: " + str(evaluation.true_negative_rate(1)))
print("weightedTrueNegativeRate: " +
str(evaluation.weighted_true_negative_rate))
print("numTrueNegatives: " + str(evaluation.num_true_negatives(1)))
print("falsePositiveRate: " + str(evaluation.false_positive_rate(1)))
print("weightedFalsePositiveRate: " +
str(evaluation.weighted_false_positive_rate))
print("numFalsePositives: " + str(evaluation.num_false_positives(1)))
print("truePositiveRate: " + str(evaluation.true_positive_rate(1)))
print("weightedTruePositiveRate: " +
str(evaluation.weighted_true_positive_rate))
print("numTruePositives: " + str(evaluation.num_true_positives(1)))
print("fMeasure: " + str(evaluation.f_measure(1)))
print("weightedFMeasure: " + str(evaluation.weighted_f_measure))
print("unweightedMacroFmeasure: " +
str(evaluation.unweighted_macro_f_measure))
print("unweightedMicroFmeasure: " +
str(evaluation.unweighted_micro_f_measure))
print("precision: " + str(evaluation.precision(1)))
print("weightedPrecision: " + str(evaluation.weighted_precision))
print("recall: " + str(evaluation.recall(1)))
print("weightedRecall: " + str(evaluation.weighted_recall))
print("kappa: " + str(evaluation.kappa))
print("KBInformation: " + str(evaluation.kb_information))
print("KBMeanInformation: " + str(evaluation.kb_mean_information))
print("KBRelativeInformation: " + str(evaluation.kb_relative_information))
print("SFEntropyGain: " + str(evaluation.sf_entropy_gain))
print("SFMeanEntropyGain: " + str(evaluation.sf_mean_entropy_gain))
print("SFMeanPriorEntropy: " + str(evaluation.sf_mean_prior_entropy))
print("SFMeanSchemeEntropy: " + str(evaluation.sf_mean_scheme_entropy))
print("matthewsCorrelationCoefficient: " +
str(evaluation.matthews_correlation_coefficient(1)))
print("weightedMatthewsCorrelation: " +
str(evaluation.weighted_matthews_correlation))
print("class priors: " + str(evaluation.class_priors))
print("numInstances: " + str(evaluation.num_instances))
print("meanAbsoluteError: " + str(evaluation.mean_absolute_error))
print("meanPriorAbsoluteError: " +
str(evaluation.mean_prior_absolute_error))
print("relativeAbsoluteError: " + str(evaluation.relative_absolute_error))
print("rootMeanSquaredError: " + str(evaluation.root_mean_squared_error))
print("rootMeanPriorSquaredError: " +
str(evaluation.root_mean_prior_squared_error))
print("rootRelativeSquaredError: " +
str(evaluation.root_relative_squared_error))
print("prediction output:\n" + str(pred_output))
plot_cls.plot_roc(evaluation,
title="ROC diabetes",
class_index=range(
0, diabetes_data.class_attribute.num_values),
wait=False)
plot_cls.plot_prc(evaluation,
title="PRC diabetes",
class_index=range(
0, diabetes_data.class_attribute.num_values),
wait=False)
# train 2nd classifier on diabetes dataset
classifier2 = Classifier(classname="weka.classifiers.trees.RandomForest")
evaluation2 = Evaluation(diabetes_data)
evaluation2.crossvalidate_model(classifier2, diabetes_data, 10, Random(42))
plot_cls.plot_rocs({
"NB": evaluation,
"RF": evaluation2
},
title="ROC diabetes",
class_index=0,
wait=False)
plot_cls.plot_prcs({
"NB": evaluation,
"RF": evaluation2
},
title="PRC diabetes",
class_index=0,
wait=False)
# load a numeric dataset
bolts_file = helper.get_data_dir() + os.sep + "bolts.arff"
helper.print_info("Loading dataset: " + bolts_file)
loader = Loader("weka.core.converters.ArffLoader")
bolts_data = loader.load_file(bolts_file)
bolts_data.class_is_last()
# build a classifier and output model
helper.print_title("Training LinearRegression on bolts")
classifier = Classifier(
classname="weka.classifiers.functions.LinearRegression",
options=["-S", "1", "-C"])
classifier.build_classifier(bolts_data)
print(classifier)
# cross-validate numeric classifier
helper.print_title("Cross-validating LinearRegression on bolts")
classifier = Classifier(
classname="weka.classifiers.functions.LinearRegression",
options=["-S", "1", "-C"])
evaluation = Evaluation(bolts_data)
evaluation.crossvalidate_model(classifier, bolts_data, 10, Random(42))
print(evaluation.summary())
print("correlationCoefficient: " + str(evaluation.correlation_coefficient))
print("errorRate: " + str(evaluation.error_rate))
helper.print_title("Header - bolts")
print(str(evaluation.header))
helper.print_title("Predictions on bolts")
for index, pred in enumerate(evaluation.predictions):
print(
str(index + 1) + ": " + str(pred) + " -> error=" + str(pred.error))
plot_cls.plot_classifier_errors(evaluation.predictions, wait=False)
# train 2nd classifier and show errors in same plot
classifier2 = Classifier(classname="weka.classifiers.functions.SMOreg")
evaluation2 = Evaluation(bolts_data)
evaluation2.crossvalidate_model(classifier2, bolts_data, 10, Random(42))
plot_cls.plot_classifier_errors(
{
"LR": evaluation.predictions,
"SMOreg": evaluation2.predictions
},
wait=False)
# learning curve
cls = [
Classifier(classname="weka.classifiers.trees.J48"),
Classifier(classname="weka.classifiers.bayes.NaiveBayesUpdateable")
]
plot_cls.plot_learning_curve(cls,
diabetes_data,
increments=0.05,
label_template="[#] !",
metric="percent_correct",
wait=True)
# access classifier's Java API
labor_file = helper.get_data_dir() + os.sep + "labor.arff"
helper.print_info("Loading dataset: " + labor_file)
loader = Loader("weka.core.converters.ArffLoader")
labor_data = loader.load_file(labor_file)
labor_data.class_is_last()
helper.print_title("Using JRip's Java API to access rules")
jrip = Classifier(classname="weka.classifiers.rules.JRip")
jrip.build_classifier(labor_data)
rset = jrip.jwrapper.getRuleset()
for i in xrange(rset.size()):
r = rset.get(i)
print(str(r.toString(labor_data.class_attribute.jobject)))
# CLASSIFIERS
classifiers = [
("Bayesian Network",
Classifier(classname="weka.classifiers.bayes.BayesNet")),
# ("Decision Tree", Classifier(classname="weka.classifiers.trees.J48")),
# ("Logistic Regression", Classifier(classname="weka.classifiers.functions.Logistic")),
# ("Multilayer Perceptron", Classifier(classname="weka.classifiers.functions.MultilayerPerceptron")),
# ("Naive Bayes", Classifier(classname="weka.classifiers.bayes.NaiveBayes")),
# ("Nearest Neighbour", Classifier(classname="weka.classifiers.lazy.IBk"))),
]
# EVALUATION
for name, cls in classifiers:
print(name)
evaluation = Evaluation(data)
evaluation.crossvalidate_model(cls, data, 10, Random(42))
print(evaluation.summary())
print(evaluation.class_details())
print("areaUnderROC/1: " + str(evaluation.area_under_roc(1)))
print("numFalseNegatives: " + str(evaluation.num_false_negatives(1)))
print("numTrueNegatives: " + str(evaluation.num_true_negatives(1)))
print("numFalsePositives: " + str(evaluation.num_false_positives(1)))
print("numTruePositives: " + str(evaluation.num_true_positives(1)))
jvm.stop()
except:
print("runtime error")
jvm.stop()
for kernel in range(0, 2):
if kernel == 0:
mapper = Classifier(
classname=
"weka.classifiers.misc.InputMappedClassifier",
options=[
"-W",
"weka.classifiers.bayes.NaiveBayes"
])
Class = 'NaiveBayes'
mapper.build_classifier(dataTrain)
evaluation = Evaluation(dataTrain)
evaluation.test_model(
mapper, dataTest)
aux1.append(
evaluation.area_under_roc(1) *
100)
if fold == 10:
title.append('NB_' +
str(begin) +
'to' + str(ntp))
roc.append(
str(round(
np.mean(aux1), 2)))
else:
mapper = Classifier(
classname=
"weka.classifiers.misc.InputMappedClassifier",
options=[
"-W",
"weka.classifiers.bayes.NaiveBayes",
NB = Classifier(
classname="weka.classifiers.misc.InputMappedClassifier",
options=["-M", "-W", "weka.classifiers.bayes.NaiveBayes"])
Class = 'NaiveBayes'
NB.build_classifier(dataTrain)
evaluationNB = Evaluation(dataTrain)
evaluationNB.test_model(NB, dataTest)
RF = Classifier(
classname="weka.classifiers.misc.InputMappedClassifier",
options=[
"-M", "-W", "weka.classifiers.trees.RandomForest", "--", "-I",
'20'
])
Class = 'NaiveBayes'
RF.build_classifier(dataTrain)
evaluationRF = Evaluation(dataTrain)
Perf.write(
str(window) + '&' + dataset + '&' +
str(np.round(evaluationNB.area_under_roc(1) * 100, 2)) + '&' +
str(np.round(evaluationNB.precision(yIndex) * 100, 2)) + '&' +
str(np.round(evaluationNB.recall(yIndex) * 100, 2)) + '\n')
Scores.write(
str(window) + ',' + dataset + ',' +
str(np.round(evaluationNB.area_under_roc(1) * 100, 2)) + '\n')
#Precision.write(str(window)+ '&' + dataset + '&' + str(np.round(evaluationNB.precision(1) * 100,2))+ '&' + str(np.round(evaluationRF.precision(1) * 100,2))+'\n')
#Recall.write(str(window)+ '&' + dataset + '&' + str(np.round(evaluationNB.recall(1) * 100,2))+ '&' + str(np.round(evaluationRF.recall(1) * 100,2))+'\n')
jvm.stop()