def test_model(self, test_data, empty_solution, evaluate = False):
model_weka = None
if os.path.isfile(self.prediction_file):
print 'Model ' + self.name + ' already tested.'
elif not os.path.isfile(self.model_file):
print 'Impossible testing this model. It should be trained first.'
return
else:
print 'Starting to test_model model ' + self.name + '.'
model_weka = Classifier(jobject = serialization.read(self.model_file))
evaluation = Evaluation(data = test_data)
evaluation.test_model(classifier = model_weka, data = test_data)
predictions = evaluation.predictions()
rows = read_sheet(file_name = empty_solution)
solutions = []
for row in rows:
solution = [row['userid'], row['tweetid'], predictions.pop(0).predicted()]
solutions.append(solution)
write_the_solution_file(solutions, self.prediction_file)
print 'Model ' + self.name + ' tested.'
if evaluate == True:
if os.path.isfile(self.evaluation_file):
print 'Model ' + self.name + ' already evaluated.'
return
elif model_weka == None:
model_weka = Classifier(jobject = serialization.read(self.model_file))
evaluation = Evaluation(data = test_data)
evaluation.test_model(classifier = model_weka, data = test_data)
save_file(file_name = self.evaluation_file, content = evaluation.to_summary())
print 'Model ' + self.name + ' evaluated.'
if data_dir is None:
data_dir = "." + os.sep + "data"
import os
import weka.core.jvm as jvm
from weka.core.converters import Loader
from weka.core.classes import Random
from weka.classifiers import Classifier, Evaluation
from weka.filters import Filter
jvm.start()
# load weather.nominal
loader = Loader(classname="weka.core.converters.ArffLoader")
fname = data_dir + os.sep + "weather.nominal.arff"
print("\nLoading dataset: " + fname + "\n")
data = loader.load_file(fname)
data.set_class_index(data.num_attributes() - 1)
# perform 10-fold cross-validation
cls = Classifier(classname="weka.classifiers.rules.OneR")
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, 10, Random(1))
print("10-fold cross-validation:\n" + evl.to_summary())
# build model on full dataset and output it
cls.build_classifier(data)
print("Model:\n\n" + str(cls))
jvm.stop()
# Use the WEKAMOOC_DATA environment variable to set the location
# for the datasets
import os
data_dir = os.environ.get("WEKAMOOC_DATA")
if data_dir is None:
data_dir = "." + os.sep + "data"
import os
import weka.core.jvm as jvm
from weka.core.converters import Loader
from weka.core.classes import Random
from weka.classifiers import Classifier, Evaluation
jvm.start()
# load glass
loader = Loader(classname="weka.core.converters.ArffLoader")
fname = data_dir + os.sep + "glass.arff"
print("\nLoading dataset: " + fname + "\n")
data = loader.load_file(fname)
data.set_class_index(data.num_attributes() - 1)
for k in [1, 5, 20]:
# cross-validate IBk, display model
cls = Classifier(classname="weka.classifiers.lazy.IBk", options=["-K", str(k)])
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, 10, Random(1))
print("10-fold cross-validation (k=" + str(k) + "):\n" + evl.to_summary())
jvm.stop()
data.set_class_index(data.num_attributes() - 1)
# 1a filter data
print("Filtering data...")
fltr = Filter("weka.filters.unsupervised.attribute.StringToWordVector")
fltr.set_inputformat(data)
filtered = fltr.filter(data)
filtered.set_class_index(0)
# 1b build classifier
print("Building/evaluating classifier...")
cls = Classifier(classname="weka.classifiers.trees.J48")
cls.build_classifier(filtered)
evl = Evaluation(filtered)
evl.test_model(cls, filtered)
print(evl.to_summary())
print(str(cls))
plg.plot_dot_graph(cls.graph())
# 2. filtered classifier
fname = data_dir + os.sep + "simpletext-test.arff"
print("\nLoading dataset: " + fname + "\n")
loader = Loader(classname="weka.core.converters.ArffLoader")
test = loader.load_file(fname)
test.set_class_index(test.num_attributes() - 1)
print("Building/evaluating filtered classifier...")
cls = FilteredClassifier()
cls.set_classifier(Classifier(classname="weka.classifiers.trees.J48"))
cls.set_filter(Filter(classname="weka.filters.unsupervised.attribute.StringToWordVector"))
cls.build_classifier(data)
pout = PredictionOutput(classname="weka.classifiers.evaluation.output.prediction.PlainText")
jvm.start()
# load diabetes
loader = Loader(classname="weka.core.converters.ArffLoader")
fname = data_dir + os.sep + "diabetes.arff"
print("\nLoading dataset: " + fname + "\n")
data = loader.load_file(fname)
data.set_class_index(data.num_attributes() - 1)
for classifier in ["weka.classifiers.bayes.NaiveBayes", "weka.classifiers.rules.ZeroR", "weka.classifiers.trees.J48"]:
# train/test split 90% using classifier
cls = Classifier(classname=classifier)
evl = Evaluation(data)
evl.evaluate_train_test_split(cls, data, 90.0, Random(1))
print("\n" + classifier + " train/test split (90%):\n" + evl.to_summary())
cls.build_classifier(data)
print(classifier + " model:\n\n" + str(cls))
# calculate mean/stdev over 10 cross-validations
for classifier in [
"weka.classifiers.meta.ClassificationViaRegression", "weka.classifiers.bayes.NaiveBayes",
"weka.classifiers.rules.ZeroR", "weka.classifiers.trees.J48", "weka.classifiers.functions.Logistic"]:
accuracy = []
for i in xrange(1,11):
cls = Classifier(classname=classifier)
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, 10, Random(i))
accuracy.append(evl.percent_correct())
nacc = numpy.array(accuracy)
print("%s: %0.2f +/-%0.2f" % (classifier, numpy.mean(nacc), numpy.std(nacc)))
from weka.core.classes import Random
from weka.classifiers import Classifier, Evaluation
jvm.start()
for dataset in ["diabetes.arff", "breast-cancer.arff"]:
# load dataset
loader = Loader(classname="weka.core.converters.ArffLoader")
fname = data_dir + os.sep + dataset
print("\nLoading dataset: " + fname + "\n")
data = loader.load_file(fname)
data.set_class_index(data.num_attributes() - 1)
# cross-validate default J48, display model
cls = Classifier(classname="weka.classifiers.trees.J48")
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, 10, Random(1))
print("10-fold cross-validation (default):\n" + evl.to_summary())
cls.build_classifier(data)
print("Model (default):\n\n" + str(cls))
# cross-validate unpruned J48, display model
cls = Classifier(classname="weka.classifiers.trees.J48", options=["-U"])
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, 10, Random(1))
print("10-fold cross-validation (unpruned):\n" + evl.to_summary())
cls.build_classifier(data)
print("Model (unpruned):\n\n" + str(cls))
jvm.stop()
wfilter = Filter(classname="weka.filters.unsupervised.attribute.StringToNominal", options=["-R", "last"])
wfilter.set_inputformat(data)
data = wfilter.filter(data)
# convert content to string
wfilter = Filter(classname="weka.filters.unsupervised.attribute.NominalToString", options=["-C", "first"])
wfilter.set_inputformat(data)
data = wfilter.filter(data)
# set class attribute
data.set_class_index(data.num_attributes() - 1)
# generate baseline
zeror = Classifier(classname="weka.classifiers.rules.ZeroR")
evaluation = Evaluation(data)
evaluation.crossvalidate_model(zeror, data, 10, Random(1))
print("\nBaseline:\n" + evaluation.to_summary())
# perform text mining
j48 = Classifier(classname="weka.classifiers.trees.J48")
stwv = Filter(
classname="weka.filters.unsupervised.attribute.StringToWordVector",
options=["-R", "1", "-P", "att-"])
stwv.set_inputformat(data)
data = stwv.filter(data)
evaluation = Evaluation(data)
evaluation.crossvalidate_model(j48, data, 10, Random(1))
print("\nJ48:\n" + evaluation.to_summary())
# stop JVM
jvm.stop()
# load a dataset
iris_file = "HairEyeColor.csv"
print("Loading dataset: " + iris_file)
loader = Loader(classname="weka.core.converters.CSVLoader")
iris_data = loader.load_file(iris_file)
print (iris_data.num_attributes)
iris_data.set_class_index(iris_data.num_attributes() - 1)
# build a classifier and output model
print ("Training J48 classifier on iris")
classifier = Classifier(classname="weka.test.Regression")
#classifier = Classifier(classname="weka.classifiers.trees.J48", options=["-C", "0.5"])
# 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())
#plot_graph.plot_dot_graph(classifier.graph())
evaluation = Evaluation(iris_data) # initialize with priors
evaluation.crossvalidate_model(classifier, iris_data, 10, Random(42)) # 10-fold CV
print(evaluation.to_summary())
print("pctCorrect: " + str(evaluation.percent_correct()))
print("incorrect: " + str(evaluation.incorrect()))
jvm.stop()
data = wfilter.filter(data)
# convert content to string
wfilter = Filter(
classname="weka.filters.unsupervised.attribute.NominalToString",
options=["-C", "first"])
wfilter.set_inputformat(data)
data = wfilter.filter(data)
# set class attribute
data.set_class_index(data.num_attributes() - 1)
# generate baseline
zeror = Classifier(classname="weka.classifiers.rules.ZeroR")
evaluation = Evaluation(data)
evaluation.crossvalidate_model(zeror, data, 10, Random(1))
print("\nBaseline:\n" + evaluation.to_summary())
# perform text mining
j48 = Classifier(classname="weka.classifiers.trees.J48")
stwv = Filter(
classname="weka.filters.unsupervised.attribute.StringToWordVector",
options=["-R", "1", "-P", "att-"])
stwv.set_inputformat(data)
data = stwv.filter(data)
evaluation = Evaluation(data)
evaluation.crossvalidate_model(j48, data, 10, Random(1))
print("\nJ48:\n" + evaluation.to_summary())
# stop JVM
jvm.stop()
from weka.classifiers import Classifier, Evaluation
jvm.start()
# load weather.nominal
loader = Loader(classname="weka.core.converters.ArffLoader")
fname = data_dir + os.sep + "weather.nominal.arff"
print("\nLoading dataset: " + fname + "\n")
data = loader.load_file(fname)
data.set_class_index(data.num_attributes() - 1)
# perform 10-fold cross-validation
cls = Classifier(classname="weka.classifiers.rules.OneR")
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, 10, Random(1))
print("10-fold cross-validation (full):\n" + evl.to_summary())
cls.build_classifier(data)
print("Model:\n\n" + str(cls))
# remove attribute "outlook"
print("Removing attribute 'outlook'")
data.delete_attribute(data.get_attribute_by_name("outlook").get_index())
# perform 10-fold cross-validation (reduced dataset)
cls = Classifier(classname="weka.classifiers.rules.OneR")
evl = Evaluation(data)
evl.crossvalidate_model(cls, data, 10, Random(1))
print("10-fold cross-validation (without 'outlook'):\n" + evl.to_summary())
cls.build_classifier(data)
print("Model:\n\n" + str(cls))
