def main(c = "decision_tree", option = "IG", dataset = "iris", ratio = 0.8):
classifier_types = {0: "decision_tree", 1: "naive_bayes", 2: "neural_net"}
options = {0:["IG", "IGR"], 1:["normal"], 2:["shallow", "medium"]}
ratio = float(ratio)
if dataset == "monks":
(training, test) = load_data.load_monks(ratio)
elif dataset == "congress":
(training, test) = load_data.load_congress_data(ratio)
elif dataset == "iris":
(training, test) = load_data.load_iris(ratio)
else:
print "Error: Cannot find dataset name."
return
print "Training... Please hold."
# classifier_types = {0: "decision_tree", 2: "neural_net"}
# options = {0:["IG", "IGR"], 2:["shallow", "medium"]}
# (training, test) = load_data.load_iris(0.8)
# nn_classifier = Classifier(classifier_type="neural_net", option = "medium")
# nn_classifier.train(training)
# nn_classifier.test(test)
# print test
# (training, test) = load_data.load_congress_data(0.8)
# print test
# (training, test) = load_data.load_monks(1)
# print test
# (training, test) = load_data.load_iris(0.8)
# print training
# "option = IG/IGR"
# dt_classifier = Classifier(classifier_type="decision_tree", weights=[], option="IG")
# dt_classifier.train(training)
# dt_classifier.test(test)
# for i, c in classifier_types.iteritems():
# for option in options[i]:
print " "
print "================================================================="
print "Dataset = ", dataset
print "Classifier = ", c
print "Option = ", option
classifier = Classifier(classifier_type=c, weights = [], option = option)
classifier.train(training)
classifier.test(test)
print "================================================================="
print " "
# option value could be either shallow(3 layers) or medium(5)
# nn_classifier = Classifier(classifier_type="neural_net", option = "medium")
# nn_classifier.train(training)
# nn_classifier.test(test)
return
def trainNtest(args):
classifierType = ["decision_tree", "naive_bayes", "neural_network"]
data_set = ["congress", "monk", "iris"]
data = ""
if len(args) == 4:
if args[0][3:] == "congress":
data = ld.load_congress_data(int(args[1][3:]) / 100.0)
num_input = 16
num_output = 2
elif args[0][3:] == "monk":
data = ld.load_monks(int(args[1]))
num_input = 6
num_output = 2
elif args[0][3:] == "iris":
data = ld.load_iris(int(args[1][3:]) / 100.0)
num_input = 4
num_output = 3
else:
print "INVALID DATA NAME"
return
method_num = int(args[2][3])
kwargs = {}
if method_num == 0 or method_num == 2:
kwargs[1] = args[2][5]
kwargs[2] = args[2][7]
classifier = Classifier(classifierType[int(args[2][3])], one=args[2][5], two=args[2][7], num_input=num_input, num_output=num_output)
else:
classifier = Classifier(classifierType[int(args[2][3])])
else:
print "ERROR: NEED 4 PARAMETERS"
return
#pdb.set_trace()
#nb = Naive_Bayes("naive_bayes")
#classifier = Classifier(classifierType[1])
#data = ld.load_congress_data(.85)
#data = ld.load_iris(.70)
#pdb.set_trace()
classifier.train(data[0])
if args[3] == "-test":
classifier.test(data[1])
else:
classifier.test(data[0])
from nb import GNB from tree import DT import random import math import numpy.matlib # number of class of each data set ncIris = 3 ncCongress = 2 ncMonks = 2 # Dataset reading trainSetIris = np.matrix(load_iris(0.7)[0]) testSetIris = np.matrix(load_iris(0.7)[1]) trainSetCongress = np.matrix(load_congress_data(0.7)[0]) testSetCongress = np.matrix(load_congress_data(0.7)[1]) trainM1 = np.matrix(load_monks(1)[0]) testM1 = np.matrix(load_monks(1)[1]) trainM2 = np.matrix(load_monks(2)[0]) testM2 = np.matrix(load_monks(2)[1]) trainM3 = np.matrix(load_monks(3)[0]) testM3 = np.matrix(load_monks(3)[1]) # Decision Tree on Congress using IG print "1. DT, Congress, IG--------------------------------" model0 = DT() model0.train(trainSetCongress, ncCongress, 1) model0.test(testSetCongress, ncCongress, 1) # Prune model0.prune(trainSetCongress, ncCongress) print "2. -----------prune----------" model0.test(testSetCongress, ncCongress, 1)
data = sys.argv[2]
params = dict()
(train_data, test_data) = (None, None)
if data=="congress":
(train_data, test_data) = load_data.load_congress_data(0.7)
elif data=="iris":
(train_data, test_data) = load_data.load_iris(0.7)
elif data=="monk":
i = 3
if classifier_type == "decision_tree":
i = 4
numb = sys.argv[i]
(train_data, test_data) = load_data.load_monks(int(numb))
params = dict()
if classifier_type == "neural_network":
i=3
if data=="monk":
i=4
if len(sys.argv) >= (i+1):
params["activation"] = sys.argv[i]
if len(sys.argv) >= (i+2):
params["learning_rate"] = float(sys.argv[i+1])
if len(sys.argv) >= (i+3):
params["epochs"] = int(sys.argv[i+2])
