def main():
"""
Just runs some example code.
"""
# load a dataset
iris = helper.get_data_dir() + os.sep + "iris.arff"
helper.print_info("Loading dataset: " + iris)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(iris)
# remove class attribute
helper.print_info("Removing class attribute")
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove",
options=["-R", "last"])
remove.inputformat(data)
filtered = remove.filter(data)
# use MultiFilter
helper.print_info("Use MultiFilter")
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove",
options=["-R", "first"])
std = Filter(classname="weka.filters.unsupervised.attribute.Standardize")
multi = MultiFilter()
multi.filters = [remove, std]
multi.inputformat(data)
filtered_multi = multi.filter(data)
# output datasets
helper.print_title("Input")
print(data)
helper.print_title("Output")
print(filtered)
helper.print_title("Output (MultiFilter)")
print(filtered_multi)
# load text dataset
text = helper.get_data_dir(
) + os.sep + "reutersTop10Randomized_1perc_shortened.arff"
helper.print_info("Loading dataset: " + text)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(text)
data.class_is_last()
# apply StringToWordVector
stemmer = Stemmer(classname="weka.core.stemmers.IteratedLovinsStemmer")
stopwords = Stopwords(classname="weka.core.stopwords.Rainbow")
tokenizer = Tokenizer(classname="weka.core.tokenizers.WordTokenizer")
s2wv = StringToWordVector(options=["-W", "10", "-L", "-C"])
s2wv.stemmer = stemmer
s2wv.stopwords = stopwords
s2wv.tokenizer = tokenizer
s2wv.inputformat(data)
filtered = s2wv.filter(data)
helper.print_title("Input (StringToWordVector)")
print(data)
helper.print_title("Output (StringToWordVector)")
print(filtered)
def predictWithWeka(csvFilenameWithInputToPredict, modelFilename):
"""
# Nota: para usar sin conocer la clase, se puede colocar una clase dummy
# e ignorar los valores actual y error de @return results.
#
# Nota: es necesario que el archivo de nombre @csvFilenameWithInputToPredict
# contenga instancias de ambas clases (spam y sanas)
#
# @csvFilenameWithInputToPredict : nombre del archivo csv con las instancias
# a predecir.
#
# @modelFilename : nombre del archivo de modelo generado por weka y
# compatible con el archivo csv de entrada
#
# @return results : lista de diccionarios con los siguientes indices
# index, actual, predicted, error y distribution
"""
loader = Loader(classname="weka.core.converters.CSVLoader")
cls = Classifier(jobject=serialization.read(modelFilename))
#print(cls)
data = loader.load_file(csvFilenameWithInputToPredict)
data.class_is_last()
multi = MultiFilter()
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove",
options=["-R", "first"])
numericToNom = Filter(
classname="weka.filters.unsupervised.attribute.NumericToNominal",
options=["-R", "8,11"])
normalize = Filter(
classname="weka.filters.unsupervised.attribute.Normalize",
options=["-S", "1.0", "-T", "0.0"])
multi.filters = [remove, numericToNom, normalize]
multi.inputformat(data)
test = multi.filter(data)
results = []
for index, inst in enumerate(test):
result = dict()
pred = cls.classify_instance(inst)
dist = cls.distribution_for_instance(inst)
result["index"] = index + 1
result["actual"] = inst.get_string_value(inst.class_index)
result["predicted"] = inst.class_attribute.value(int(pred))
result["error"] = "yes" if pred != inst.get_value(
inst.class_index) else "no"
result["distribution"] = str(dist.tolist())
results.append(result)
#print result
return results
def main():
"""
Just runs some example code.
"""
# load a dataset
iris = helper.get_data_dir() + os.sep + "iris.arff"
helper.print_info("Loading dataset: " + iris)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(iris)
# remove class attribute
helper.print_info("Removing class attribute")
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "last"])
remove.inputformat(data)
filtered = remove.filter(data)
# use MultiFilter
helper.print_info("Use MultiFilter")
remove = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "first"])
std = Filter(classname="weka.filters.unsupervised.attribute.Standardize")
multi = MultiFilter()
multi.filters = [remove, std]
multi.inputformat(data)
filtered_multi = multi.filter(data)
# output datasets
helper.print_title("Input")
print(data)
helper.print_title("Output")
print(filtered)
helper.print_title("Output (MultiFilter)")
print(filtered_multi)
# load text dataset
text = helper.get_data_dir() + os.sep + "reutersTop10Randomized_1perc_shortened.arff"
helper.print_info("Loading dataset: " + text)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(text)
data.class_is_last()
# apply StringToWordVector
stemmer = Stemmer(classname="weka.core.stemmers.IteratedLovinsStemmer")
stopwords = Stopwords(classname="weka.core.stopwords.Rainbow")
tokenizer = Tokenizer(classname="weka.core.tokenizers.WordTokenizer")
s2wv = StringToWordVector(options=["-W", "10", "-L", "-C"])
s2wv.stemmer = stemmer
s2wv.stopwords = stopwords
s2wv.tokenizer = tokenizer
s2wv.inputformat(data)
filtered = s2wv.filter(data)
helper.print_title("Input (StringToWordVector)")
print(data)
helper.print_title("Output (StringToWordVector)")
print(filtered)
# partial classname
helper.print_title("Creating filter from partial classname")
clsname = ".Standardize"
f = Filter(classname=clsname)
print(clsname + " --> " + f.classname)
# source code
helper.print_info("Generate source code")
bolts = helper.get_data_dir() + os.sep + "labor.arff"
helper.print_info("Loading dataset: " + bolts)
loader = Loader("weka.core.converters.ArffLoader")
data = loader.load_file(bolts)
replace = Filter(classname="weka.filters.unsupervised.attribute.ReplaceMissingValues")
replace.inputformat(data)
replace.filter(data)
print(replace.to_source("MyReplaceMissingValues", data))