def Bag_J48(data, rnm):
data.class_is_last()
fc1 = FilteredClassifier()
fc1.classifier = Classifier(classname="weka.classifiers.trees.J48", options=["-C", "0.25", "-M", "2"])
fc1.filter = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "first"])
fc2 = SingleClassifierEnhancer(classname="weka.classifiers.meta.Bagging", options=["-P", "100", "-S", "1", "-I", "10"])
fc2.classifier = fc1
pred_output = PredictionOutput(classname = "weka.classifiers.evaluation.output.prediction.CSV", options=["-p", "1"] )
folds = 10
fc2.build_classifier(data)
evaluation = Evaluation(data)
evaluation.crossvalidate_model(fc2, data, folds, Random(1), pred_output)
f0 = open(rnm + '_Bag_J48_Tree.txt', 'w')
print >> f0, "Filename: ", rnm
print >> f0, '\n\n'
print >> f0, str(fc2)
f0.close()
f1 = open(rnm + '_Bag_J48_Prediction.txt', 'w')
print >> f1, 'Filename:', rnm
print >> f1, 'Prediction Summary:', (pred_output.buffer_content())
f1.close()
f2 = open(rnm + '_Bag_j48_Evaluation.txt', 'w')
print >> f2, 'Filename:', rnm
print >> f2, 'Evaluation Summary:', (evaluation.summary())
print >> f2, '\n\n\n'
print >> f2, (evaluation.class_details())
f2.close()
plot_roc(evaluation, class_index=[0,1], title=rnm, key_loc='best', outfile=rnm + '_Bag_J48_ROC.png', wait=False)
value_Bag_J48 = str(evaluation.percent_correct)
return value_Bag_J48
def RandomForest(data, rnm):
data.class_is_last()
fc = FilteredClassifier()
fc.classifier = Classifier(classname="weka.classifiers.trees.RandomForest", options=["-I", "100", "-K", "0", "-S", "1"])
fc.filter = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "first"])
pred_output = PredictionOutput(classname="weka.classifiers.evaluation.output.prediction.CSV", options=["-p", "1"])
folds = 10
evl = Evaluation(data)
evl.crossvalidate_model(fc, data, folds, Random(1), pred_output)
fc.build_classifier(data)
f0 = open(rnm + '_RF_Tree.txt', 'w')
print >> f0, "Filename: ", rnm
print >> f0, '\n\n'
print >> f0, str(fc)
f0.close()
f1 = open(rnm + '_RF_Prediction.txt', 'w')
print >> f1, 'Filename:', rnm
print >> f1, 'Prediction Summary:', (pred_output.buffer_content())
f1.close()
f2 = open(rnm + '_RF_Evaluation.txt', 'w')
print >> f2, 'Filename:', rnm
print >> f2, 'Evaluation Summary:', (evl.summary())
print >> f2, '\n\n\n'
print >> f2, (evl.class_details())
f2.close()
plot_roc(evl, class_index=[0,1], title=rnm, key_loc='best', outfile=rnm+'_RF_ROC.png', wait=False)
value_RF = str(evl.percent_correct)
return value_RF
def fitness(toeval : Individual):
cls = Classifier(classname="weka.classifiers.functions.MultilayerPerceptron", options=toeval.settings())
fc = FilteredClassifier()
fc.filter = remove
fc.classifier = cls
evl = Evaluation(data)
evl.crossvalidate_model(fc, data, 10, Random(1))
return evl.percent_correct
print(group)
train = data_dir + os.sep + group + "_Cal.arff"
test = data_dir + os.sep + group + "_Test.arff"
pred = data_dir + os.sep + group + "_Val.arff"
loader = Loader(classname="weka.core.converters.ArffLoader")
print(train)
train_data = loader.load_file(train)
train_data.class_index = train_data.attribute_by_name(
"reference value").index
print(test)
test_data = loader.load_file(test)
test_data.class_index = test_data.attribute_by_name(
"reference value").index
print(pred)
pred_data = loader.load_file(pred)
pred_data.class_index = pred_data.attribute_by_name(
"reference value").index
cls = FilteredClassifier()
cls.classifier = Classifier(
classname="weka.classifiers.functions.LinearRegression",
options=["-S", "1", "-C"])
cls.filter = Filter(classname="weka.filters.unsupervised.attribute.Remove",
options=["-R", "first"])
cls.build_classifier(train_data)
evl = Evaluation(train_data)
evl.test_model(cls, test_data)
print(evl.summary())
jvm.stop()
def main():
"""
Just runs some example code.
"""
#case=["selected_chi100","selected_chi150","selected_chi200","selected_chi250","selected_chi300","selected_chi350","selected_fe100","selected_fe150","selected_fe200","selected_fe250","selected_fe300","selected_fe350","selected_sfm100","selected_sfm150","selected_sfm200","selected_sfm250","selected_sfm300","selected_sfm350","selected_sfmt100","selected_sfmt150","selected_sfmt200","selected_sfmt250","selected_sfmt300","selected_sfmt350","selected_cs100","selected_cs150","selected_cs200","selected_cs250","selected_cs300","selected_cs350"]
#case=["feature_vector100","feature_vector110","feature_vector120","feature_vector130","feature_vector140","feature_vector150","feature_vector90","feature_vector80","feature_vector70","feature_vector60","feature_vector50","feature_vector40","feature_vector30","feature_vector20","feature_vector10","feature_vector5"]
case = [
"selected_chi100", "selected_chi150", "selected_chi200",
"selected_chi250", "selected_chi300", "selected_chi350",
"selected_fe100", "selected_fe150", "selected_fe200", "selected_fe250",
"selected_fe300", "selected_fe350", "selected_sfm100",
"selected_sfm150", "selected_sfm200", "selected_sfm250",
"selected_sfm300", "selected_sfm350", "selected_sfmt100",
"selected_sfmt150", "selected_sfmt200", "selected_sfmt250",
"selected_sfmt300", "selected_sfmt350"
]
#case=["selected_chi100","selected_chi150","selected_chi200","selected_fe100","selected_fe150","selected_fe200","selected_sfm100","selected_sfm150","selected_sfm200","selected_sfmt100","selected_sfmt150","selected_sfmt200","selected_cs100","selected_cs150","selected_cs200",]
for nomefile in case:
print(nomefile)
feature_vector = "./selected_vectors30/" + nomefile + ".arff" # legge il file in formato arff
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(feature_vector)
data.class_is_last()
#print(data)
f = open("./selected_vectors30/risultati/" + nomefile + ".txt",
"w+") # file risultati in txt
#intestazione excel
intest = [
"Correlation coefficient", "Mean absolute error",
"Root mean squared error", "Relative absolute error",
"Root relative squared error", "Total Number of Instances"
]
workbook = xlsxwriter.Workbook("./selected_vectors30/risultati/" +
nomefile + ".xlsx") # file excel
worksheet = workbook.add_worksheet()
for col_num, dati in enumerate(intest):
worksheet.write(0, col_num + 1, dati)
riga = 1
#lista degli algoritmi da eseguire
#alg=["meta.Bagging","meta.RandomSubSpace","rules.M5Rules","trees.M5P","trees.RandomForest"]
alg = [
"bayes.NaiveBayes", "bayes.NaiveBayesUpdateable",
"functions.Logistic", "functions.SGD", "functions.SimpleLogistic",
"functions.SMO", "functions.VotedPerceptron", "meta.AdaBoostM1",
"meta.AttributeSelectedClassifier", "meta.Bagging",
"meta.ClassificationViaRegression",
"meta.IterativeClassifierOptimizer", "meta.LogitBoost",
"meta.RandomCommittee", "meta.RandomSubSpace",
"rules.DecisionTable", "rules.JRip", "rules.OneR",
"trees.DecisionStump", "trees.J48", "trees.RandomForest",
"trees.REPTree"
]
for row_num, dati in enumerate(alg):
worksheet.write(row_num + 1, 0, dati)
for i in alg:
remove = Filter(
classname="weka.filters.unsupervised.attribute.Remove")
cls = Classifier(classname="weka.classifiers." + i)
fc = FilteredClassifier()
fc.filter = remove
fc.classifier = cls
evl = Evaluation(data)
evl.crossvalidate_model(fc, data, 10,
Random(1)) # 10 fold cross validation
#evl.evaluate_train_test_split(fc,data,50,None,None) # 50% split cross validation
k = evl.summary()
#scrittura sui file
f.write(i + "\n")
f.write(k + "\n")
my_list = k.split('\n')
for col_num, dati in enumerate(my_list):
worksheet.write(riga, col_num, dati[-10:])
print(i)
riga += 1
f.close()
workbook.close()
print("Train/test/predict...")
groups = ["DataSet1", "DataSet2"]
# groups = ["DataSet2"]
for group in groups:
print(group)
train = data_dir + os.sep + group + "_Cal.arff"
test = data_dir + os.sep + group + "_Test.arff"
pred = data_dir + os.sep + group + "_Val.arff"
loader = Loader(classname="weka.core.converters.ArffLoader")
print(train)
train_data = loader.load_file(train)
train_data.class_index = train_data.attribute_by_name("reference value").index
print(test)
test_data = loader.load_file(test)
test_data.class_index = test_data.attribute_by_name("reference value").index
print(pred)
pred_data = loader.load_file(pred)
pred_data.class_index = pred_data.attribute_by_name("reference value").index
cls = FilteredClassifier()
cls.classifier = Classifier(classname="weka.classifiers.functions.LinearRegression", options=["-S", "1", "-C"])
cls.filter = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "first"])
cls.build_classifier(train_data)
evl = Evaluation(train_data)
evl.test_model(cls, test_data)
print(evl.summary())
jvm.stop()
curve = {}
for percentage in percentages:
curve[percentage] = 0
curves[repetition] = curve
# run and add up percentage correct from repetition
for seed in xrange(repetition):
seed += 1
sys.stdout.write(".")
for percentage in percentages:
cls = Classifier(classname="weka.classifiers.trees.J48")
flt = Filter(
classname="weka.filters.unsupervised.instance.Resample",
options=["-Z", str(percentage), "-no-replacement"])
fc = FilteredClassifier()
fc.classifier = cls
fc.filter = flt
evl = Evaluation(data)
evl.crossvalidate_model(fc, data, 10, Random(seed))
curve[percentage] += (evl.percent_correct / repetition)
# progress info
sys.stdout.write("\n")
# output the results
if not plot.matplotlib_available:
print("ZeroR: " + str(baseline))
for repetition in repetitions:
y = []
for percentage in percentages:
y.append(curves[repetition][percentage])
print("Repetitions = " + str(repetition) + ":\n" + str(y))
else:
articles_collection = db.articles
article = articles_collection.find_one({"_id": article_id})
jvm.start(system_cp=True, packages=True, max_heap_size="512m")
# Train classifier
loader = Loader(classname="weka.core.converters.ArffLoader", options=["-charset", "UTF-8"])
train_data = loader.load_file(os.path.dirname(os.path.realpath(__file__)) + "/datasets/train.arff")
train_data.class_is_last()
string_to_word_vector_filter = Filter(classname="weka.filters.unsupervised.attribute.StringToWordVector")
cls = Classifier(classname="weka.classifiers.bayes.NaiveBayesMultinomial")
fc = FilteredClassifier()
fc.filter = string_to_word_vector_filter
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
)
fname = data_dir + os.sep + "ReutersGrain-test.arff"
print("\nLoading dataset: " + fname + "\n")
loader = Loader(classname="weka.core.converters.ArffLoader")
test = loader.load_file(fname)
test.class_is_last()
setups = (
("weka.classifiers.trees.J48", []),
("weka.classifiers.bayes.NaiveBayes", []),
("weka.classifiers.bayes.NaiveBayesMultinomial", []),
("weka.classifiers.bayes.NaiveBayesMultinomial", ["-C"]),
("weka.classifiers.bayes.NaiveBayesMultinomial", ["-C", "-L", "-stopwords-handler", "weka.core.stopwords.Rainbow"])
)
# cross-validate classifiers
for setup in setups:
classifier, opt = setup
print("\n--> %s (filter options: %s)\n" % (classifier, " ".join(opt)))
cls = FilteredClassifier()
cls.classifier = Classifier(classname=classifier)
cls.filter = Filter(classname="weka.filters.unsupervised.attribute.StringToWordVector", options=opt)
cls.build_classifier(data)
evl = Evaluation(test)
evl.test_model(cls, test)
print("Accuracy: %0.0f%%" % evl.percent_correct)
tcdata = plc.generate_thresholdcurve_data(evl, 0)
print("AUC: %0.3f" % plc.get_auc(tcdata))
print(evl.matrix("Matrix:"))
jvm.stop()
test = converters.load_any_file("imbalanced_test.arff")
train.class_is_last()
test.class_is_last()
# Minority Class is getting Sampled 5x
smote = Filter(classname="weka.filters.supervised.instance.SMOTE",
options=["-P", "500.0"])
# Base Classifier
cls = Classifier(classname="weka.classifiers.trees.LMT",
options=["-B", "-I", "10"])
# Filtered Classifier
fc = FilteredClassifier()
fc.filter = smote
fc.classifier = cls
# 5 Fold K cross validation
evl = Evaluation(train)
evl.crossvalidate_model(fc, train, 5, Random(1))
# Prints Out Confusion Matrix along with other summary statistics
print("LMT (SMOTE balanced classes) CV = 5 Error: %.2f%%" %
(evl.percent_incorrect))
print(evl.matrix()) #Confusion Matrix
# Plots ROC
plcls.plot_roc(evl, class_index=[0, 1], wait=True)
# Extra Summary
