from weka.core.converters import Loader, Saver
from weka.core.dataset import Instances
from weka.filters import Filter
jvm.start()
# load weather.nominal
fname = data_dir + os.sep + "weather.nominal.arff"
print("\nLoading dataset: " + fname + "\n")
loader = Loader(classname="weka.core.converters.ArffLoader")
data = loader.load_file(fname)
# output header
print(Instances.template_instances(data))
# remove attribute no 3
print("\nRemove attribute no 3")
fltr = Filter(classname="weka.filters.unsupervised.attribute.Remove", options=["-R", "3"])
fltr.inputformat(data)
filtered = fltr.filter(data)
# output header
print(Instances.template_instances(filtered))
# save modified dataset
saver = Saver(classname="weka.core.converters.ArffSaver")
saver.save_file(filtered, data_dir + os.sep + "weather.nominal-filtered.arff")
jvm.stop()
def save_Arff(self, data, outputPath):
saver = Saver()
saver.save_file(data, outputPath)
def getFunctionFeaturesArff(self, wholeSetArff, functionFeatureArff):
data = self.load_Arff(wholeSetArff)
filteredData = self.getSetDataBySetIndex(data, 2)
saver = Saver()
saver.save_file(filteredData, functionFeatureArff)
def main():
"""
Runs a filter from the command-line. Calls JVM start/stop automatically.
Use -h to see all options.
"""
parser = argparse.ArgumentParser(
description='Executes a filter from the command-line. Calls JVM start/stop automatically.')
parser.add_argument("-j", metavar="classpath", dest="classpath", help="additional classpath, jars/directories")
parser.add_argument("-X", metavar="heap", dest="heap", help="max heap size for jvm, e.g., 512m")
parser.add_argument("-i", metavar="input1", dest="input1", required=True, help="input file 1")
parser.add_argument("-o", metavar="output1", dest="output1", required=True, help="output file 1")
parser.add_argument("-r", metavar="input2", dest="input2", help="input file 2")
parser.add_argument("-s", metavar="output2", dest="output2", help="output file 2")
parser.add_argument("-c", metavar="classindex", default="-1", dest="classindex", help="1-based class attribute index")
parser.add_argument("filter", help="filter classname, e.g., weka.filters.AllFilter")
parser.add_argument("option", nargs=argparse.REMAINDER, help="additional filter options")
parsed = parser.parse_args()
if parsed.input2 is None and not parsed.output2 is None:
raise Exception("No second input file provided ('-r ...')!")
jars = []
if not parsed.classpath is None:
jars = parsed.classpath.split(os.pathsep)
params = []
if not parsed.input1 is None:
params.extend(["-i", parsed.input1])
if not parsed.output1 is None:
params.extend(["-o", parsed.output1])
if not parsed.input2 is None:
params.extend(["-r", parsed.input2])
if not parsed.output2 is None:
params.extend(["-s", parsed.output2])
if not parsed.classindex is None:
params.extend(["-c", parsed.classindex])
jvm.start(jars, max_heap_size=parsed.heap, packages=True)
logger.debug("Commandline: " + utils.join_options(sys.argv[1:]))
try:
flter = Filter(parsed.filter)
if len(parsed.option) > 0:
flter.set_options(parsed.option)
loader = Loader(classname="weka.core.converters.ArffLoader")
in1 = loader.load_file(parsed.input1)
cls = parsed.classindex
if str(parsed.classindex) == "first":
cls = "0"
if str(parsed.classindex) == "last":
cls = str(in1.num_attributes() - 1)
in1.set_class_index(int(cls))
flter.set_inputformat(in1)
out1 = flter.filter(in1)
saver = Saver(classname="weka.core.converters.ArffSaver")
saver.save_file(out1, parsed.output1)
if not parsed.input2 is None:
in2 = loader.load_file(parsed.input2)
in2.set_class_index(int(cls))
out2 = flter.filter(in2)
saver.save_file(out2, parsed.output2)
except Exception, e:
print(e)
#Filter function
from weka.filters import Filter
print("Filter operation")
remove = Filter(classname="weka.filters.unsupervised.attribute.RemoveUseless",
options=["-M", "99.0"])
remove.inputformat(data)
filtered = remove.filter(data)
print(filtered)
#EM imputation function
em = Filter(
classname="weka.filters.unsupervised.attribute.ReplaceMissingValues")
em.inputformat(filtered)
em_imputed = em.filter(filtered)
print(em_imputed)
#weka.filters.unsupervised.attribute.EMImputation -N -1 -E 1.0E-4 -Q 1.0E-8
#Saver arff to csv
saver = Saver(classname="weka.core.converters.CSVSaver")
saver.save_file(em_imputed, "./Dataset/hepatitis.csv")
saver.save_file(filtered, "./Dataset/hepatitis_removed_useless.csv")
#saver.save_file(data, "./Dataset/hepatitis_weka.csv")
#converters.save_any_file("./final_small_em.csv")
#converters.save_any_file("/some/where/else/iris.csv")
#converters.save_any_file("/some/where/else/iris.csv")
#cls =Classifier(classname="weka.classifiers.trees.J48")
#print(cls)
jvm.stop()
def save_dataset(self,filepath):
saver = Saver(classname="weka.core.converters.CSVSaver")
saver.save_file(self.dataset, filepath)
