def setUp(self):
self.data = data.fromfile(testfile('testdata10.txt'))
self.neteval = evaluator.NetworkEvaluator(
self.data,
network.fromdata(self.data),
prior.UniformPrior(self.data.variables.size))
self.neteval.network.edges.add_many([(1,0),(2,0),(3,0)])
def setUp(self):
a,b,c,d,e = 0,1,2,3,4
self.data = data.fromfile(testfile('testdata9.txt'))
self.net = network.fromdata(self.data)
self.net.edges.add_many([(a,c), (b,c), (c,d), (c,e)])
self.neteval1 = self.neteval_type(self.data, self.net, max_iterations="10*n**2")
def setUp(self):
dat = data.fromfile(testfile("testdata5.txt"))
dat.discretize()
g = greedy.GreedyLearner(dat, max_iterations=100)
g.run()
self.result = g.result
self.tempdir = tempfile.mkdtemp()
self.result.tohtml(self.tempdir)
def test_arity_checking2():
try:
# arity specified is MORE than number of unique values. this is ok.
dataset = data.fromfile(testfile('testdata7.txt'))
except:
assert False
assert [v.arity for v in dataset.variables] == [3,4,3,6]
def test_arity_checking():
try:
# arity specified is less than number of unique values!!
dataset = data.fromfile(testfile('testdata6.txt'))
except data.IncorrectArityError:
assert True
else:
assert False
def test_arity_checking2():
try:
# arity specified is MORE than number of unique values. this is ok.
dataset = data.fromfile(testfile('testdata7.txt'))
except:
assert False
assert [v.arity for v in dataset.variables] == [3, 4, 3, 6]
def test_tc(self):
d = data.fromfile(testfile("testdata5.txt"))
d.discretize()
tasks = [greedy.GreedyLearner(d) for x in range(5)]
tc = ipy1.IPython1Controller("127.0.0.1:10113")
results = tc.run(tasks)
results = result.merge(results)
assert isinstance(results, result.LearnerResult)
def test_arity_checking():
try:
# arity specified is less than number of unique values!!
dataset = data.fromfile(testfile('testdata6.txt'))
except data.IncorrectArityError:
assert True
else:
assert False
def setUp(self):
self.data = data.fromfile(testfile('testdata4.txt')) # no tab before variable names
self.expected_observations = N.array([[0, 0], [1, 1], [1,2]])
self.expected_missing = N.array([[0, 0], [0, 0], [0, 0]], dtype=bool)
self.expected_interventions = N.array([[1, 1], [0, 1], [0, 0]], dtype=bool)
self.expected_varnames = ['shh', 'ptchp']
self.expected_samplenames = ['sample1', 'sample2', 'sample3']
self.expected_arities = [2,3]
self.expected_dtype = N.dtype(int)
def setUp(self):
a, b, c, d, e = 0, 1, 2, 3, 4
self.data = data.fromfile(testfile('testdata9.txt'))
self.net = network.fromdata(self.data)
self.net.edges.add_many([(a, c), (b, c), (c, d), (c, e)])
self.neteval1 = self.neteval_type(self.data,
self.net,
max_iterations="10*n**2")
def test_example1(self):
outdir = os.path.join(self.tmpdir, "example1-result")
dataset = data.fromfile(testfile("pebl-tutorial-data1.txt"))
dataset.discretize()
learner = greedy.GreedyLearner(dataset)
ex1result = learner.run()
ex1result.tohtml(outdir)
assert os.path.exists(os.path.join(outdir, 'index.html'))
def setUp(self):
self.data = data.fromfile(testfile('testdata3.txt'))
self.expected_observations = N.array([[0, 0], [1, 1], [1, 2]])
self.expected_missing = N.array([[0, 0], [0, 0], [0, 0]], dtype=bool)
self.expected_interventions = N.array([[1, 1], [0, 1], [0, 0]],
dtype=bool)
self.expected_varnames = ['shh', 'ptchp']
self.expected_samplenames = ['sample1', 'sample2', 'sample3']
self.expected_arities = [2, 3]
self.expected_dtype = N.dtype(int)
def test_example1(self):
outdir = os.path.join(self.tmpdir, "example1-result")
dataset = data.fromfile(testfile("pebl-tutorial-data1.txt"))
dataset.discretize()
learner = greedy.GreedyLearner(dataset)
ex1result = learner.run()
ex1result.tohtml(outdir)
assert os.path.exists(os.path.join(outdir, 'index.html'))
def bayesian_structure():
# dataset = data.fromfile("/home/work/pebl-tutorial-data2.txt")
# dataset = Dataset(points.transpose(), None, None, ['in','tar'], None, None)
dataset = data.fromfile('/home/work/Projects/EclipseProjects/thesis/Scripts/elements.csv')
dataset.discretize()
# dataset.discretize()
# learners = [ greedy.GreedyLearner(dataset, max_iterations=1000000) for i in range(5) ] + \
# [ simanneal.SimulatedAnnealingLearner(dataset) for i in range(5) ]
# merged_result = result.merge([learner.run() for learner in learners])
learner = greedy.GreedyLearner(dataset)
merged_result = learner.run()
merged_result.tohtml("example-result")
def setUp(self):
self.data = data.fromfile(testfile('testdata1.txt'))
self.expected_observations = N.array([[2.5, 0., 1.7], [1.1, 1.7, 2.3],
[4.2, 999.3, 12.]])
self.expected_dtype = N.dtype(float)
self.expected_varnames = ['var1', 'var2', 'var3']
self.expected_missing = N.array(
[[False, True, False], [False, False, False],
[False, False, False]],
dtype=bool)
self.expected_interventions = N.array(
[[True, True, False], [False, True, False], [False, False, False]],
dtype=bool)
self.expected_arities = [-1, -1, -1]
def setUp(self):
self.data = data.fromfile(testfile('testdata2.txt'))
self.expected_observations = N.array([[ 0. , 0. , 1.25, 0. ],
[ 1. , 1. , 1.1 , 1. ],
[ 1. , 2. , 0.45, 1. ]])
self.expected_dtype = N.dtype(float) # because one continuous variable
self.expected_varnames = ['shh', 'ptchp', 'smo', 'outcome']
self.expected_interventions = N.array([[ True, True, False, False],
[False, True, False, False],
[False, False, False, False]], dtype=bool)
self.expected_missing = N.array([[False, False, False, False],
[False, False, False, False],
[False, False, False, False]], dtype=bool)
self.expected_arities = [2, 3, -1, 2]
def setUp(self):
self.data = data.fromfile(testfile('testdata1.txt'))
self.expected_observations = N.array([[ 2.5, 0. , 1.7],
[ 1.1, 1.7, 2.3],
[ 4.2, 999.3, 12. ]])
self.expected_dtype = N.dtype(float)
self.expected_varnames = ['var1', 'var2', 'var3']
self.expected_missing = N.array([[False, True, False],
[False, False, False],
[False, False, False]], dtype=bool)
self.expected_interventions = N.array([[ True, True, False],
[False, True, False],
[False, False, False]], dtype=bool)
self.expected_arities = [-1,-1,-1]
def setUp(self):
self.data = data.fromfile(testfile('testdata2.txt'))
self.expected_observations = N.array([[0., 0., 1.25, 0.],
[1., 1., 1.1, 1.],
[1., 2., 0.45, 1.]])
self.expected_dtype = N.dtype(float) # because one continuous variable
self.expected_varnames = ['shh', 'ptchp', 'smo', 'outcome']
self.expected_interventions = N.array(
[[True, True, False, False], [False, True, False, False],
[False, False, False, False]],
dtype=bool)
self.expected_missing = N.array(
[[False, False, False, False], [False, False, False, False],
[False, False, False, False]],
dtype=bool)
self.expected_arities = [2, 3, -1, 2]
def setUp(self):
self.data = data.fromfile(testfile('testdata5m.txt'))
self.data.discretize()
self.expected_original = \
N.array([[ 1.2, 1.4, 2.1, 2.2, 1.1],
[ 2.3, 1.1, 2.1, 3.2, 1.3],
[ 3.2, 0. , 1.2, 2.5, 1.6],
[ 4.2, 2.4, 3.2, 2.1, 2.8],
[ 2.7, 1.5, 0. , 1.5, 1.1],
[ 1.1, 2.3, 2.1, 1.7, 3.2],
[ 2.3, 1.1, 4.3, 2.3, 1.1],
[ 3.2, 2.6, 1.9, 1.7, 1.1],
[ 2.1, 1.5, 3. , 1.4, 1.1],
[ 0. , 0. , 0. , 0. , 0. ],
[ 0. , 0. , 0. , 0. , 0. ],
[ 0. , 0. , 0. , 0. , 0. ]])
self.expected_discretized = \
N.array([[0, 1, 1, 1, 0],
[1, 0, 1, 2, 1],
[2, 0, 0, 2, 2],
[2, 2, 2, 1, 2],
[1, 1, 0, 0, 0],
[0, 2, 1, 0, 2],
[1, 0, 2, 2, 0],
[2, 2, 0, 0, 0],
[0, 1, 2, 0, 0],
[0, 0, 0, 0, 0],
[0, 0, 0, 0, 0],
[0, 0, 0, 0, 0]])
self.expected_arities = [3,3,3,3,3]
self.expected_missing = N.array([[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[True , True , True , True , True ],
[True , True , True , True , True ],
[True , True , True , True , True ]],
dtype=bool)
def setUp(self):
self.data = data.fromfile(testfile('testdata5m.txt'))
self.data.discretize()
self.expected_original = \
N.array([[ 1.2, 1.4, 2.1, 2.2, 1.1],
[ 2.3, 1.1, 2.1, 3.2, 1.3],
[ 3.2, 0. , 1.2, 2.5, 1.6],
[ 4.2, 2.4, 3.2, 2.1, 2.8],
[ 2.7, 1.5, 0. , 1.5, 1.1],
[ 1.1, 2.3, 2.1, 1.7, 3.2],
[ 2.3, 1.1, 4.3, 2.3, 1.1],
[ 3.2, 2.6, 1.9, 1.7, 1.1],
[ 2.1, 1.5, 3. , 1.4, 1.1],
[ 0. , 0. , 0. , 0. , 0. ],
[ 0. , 0. , 0. , 0. , 0. ],
[ 0. , 0. , 0. , 0. , 0. ]])
self.expected_discretized = \
N.array([[0, 1, 1, 1, 0],
[1, 0, 1, 2, 1],
[2, 0, 0, 2, 2],
[2, 2, 2, 1, 2],
[1, 1, 0, 0, 0],
[0, 2, 1, 0, 2],
[1, 0, 2, 2, 0],
[2, 2, 0, 0, 0],
[0, 1, 2, 0, 0],
[0, 0, 0, 0, 0],
[0, 0, 0, 0, 0],
[0, 0, 0, 0, 0]])
self.expected_arities = [3, 3, 3, 3, 3]
self.expected_missing = N.array(
[[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[True, True, True, True, True], [True, True, True, True, True],
[True, True, True, True, True]],
dtype=bool)
def setUp(self):
self.data = data.fromfile(testfile('testdata5.txt'))
self.data.discretize(excludevars=[0, 1])
self.expected_original = \
N.array([[ 1.2, 1.4, 2.1, 2.2, 1.1],
[ 2.3, 1.1, 2.1, 3.2, 1.3],
[ 3.2, 0. , 1.2, 2.5, 1.6],
[ 4.2, 2.4, 3.2, 2.1, 2.8],
[ 2.7, 1.5, 0. , 1.5, 1.1],
[ 1.1, 2.3, 2.1, 1.7, 3.2],
[ 2.3, 1.1, 4.3, 2.3, 1.1],
[ 3.2, 2.6, 1.9, 1.7, 1.1],
[ 2.1, 1.5, 3. , 1.4, 1.1]])
self.expected_discretized = \
N.array([[ 1.2, 1.4, 1. , 1. , 0. ],
[ 2.3, 1.1, 1. , 2. , 1. ],
[ 3.2, 0. , 0. , 2. , 2. ],
[ 4.2, 2.4, 2. , 1. , 2. ],
[ 2.7, 1.5, 0. , 0. , 0. ],
[ 1.1, 2.3, 1. , 0. , 2. ],
[ 2.3, 1.1, 2. , 2. , 0. ],
[ 3.2, 2.6, 0. , 0. , 0. ],
[ 2.1, 1.5, 2. , 0. , 0. ]])
self.expected_arities = [-1, -1, 3, 3, 3]
def setUp(self):
self.data = data.fromfile(testfile('testdata5.txt'))
self.data.discretize()
self.expected_original = \
N.array([[ 1.2, 1.4, 2.1, 2.2, 1.1],
[ 2.3, 1.1, 2.1, 3.2, 1.3],
[ 3.2, 0. , 1.2, 2.5, 1.6],
[ 4.2, 2.4, 3.2, 2.1, 2.8],
[ 2.7, 1.5, 0. , 1.5, 1.1],
[ 1.1, 2.3, 2.1, 1.7, 3.2],
[ 2.3, 1.1, 4.3, 2.3, 1.1],
[ 3.2, 2.6, 1.9, 1.7, 1.1],
[ 2.1, 1.5, 3. , 1.4, 1.1]])
self.expected_discretized = \
N.array([[0, 1, 1, 1, 0],
[1, 0, 1, 2, 1],
[2, 0, 0, 2, 2],
[2, 2, 2, 1, 2],
[1, 1, 0, 0, 0],
[0, 2, 1, 0, 2],
[1, 0, 2, 2, 0],
[2, 2, 0, 0, 0],
[0, 1, 2, 0, 0]])
self.expected_arities = [3, 3, 3, 3, 3]
def setUp(self):
self.data = data.fromfile(testfile('testdata5.txt'))
self.data.discretize()
self.expected_original = \
N.array([[ 1.2, 1.4, 2.1, 2.2, 1.1],
[ 2.3, 1.1, 2.1, 3.2, 1.3],
[ 3.2, 0. , 1.2, 2.5, 1.6],
[ 4.2, 2.4, 3.2, 2.1, 2.8],
[ 2.7, 1.5, 0. , 1.5, 1.1],
[ 1.1, 2.3, 2.1, 1.7, 3.2],
[ 2.3, 1.1, 4.3, 2.3, 1.1],
[ 3.2, 2.6, 1.9, 1.7, 1.1],
[ 2.1, 1.5, 3. , 1.4, 1.1]])
self.expected_discretized = \
N.array([[0, 1, 1, 1, 0],
[1, 0, 1, 2, 1],
[2, 0, 0, 2, 2],
[2, 2, 2, 1, 2],
[1, 1, 0, 0, 0],
[0, 2, 1, 0, 2],
[1, 0, 2, 2, 0],
[2, 2, 0, 0, 0],
[0, 1, 2, 0, 0]])
self.expected_arities = [3,3,3,3,3]
def setUp(self):
self.data = data.fromfile(testfile('testdata5.txt'))
self.data.discretize(excludevars=[0,1])
self.expected_original = \
N.array([[ 1.2, 1.4, 2.1, 2.2, 1.1],
[ 2.3, 1.1, 2.1, 3.2, 1.3],
[ 3.2, 0. , 1.2, 2.5, 1.6],
[ 4.2, 2.4, 3.2, 2.1, 2.8],
[ 2.7, 1.5, 0. , 1.5, 1.1],
[ 1.1, 2.3, 2.1, 1.7, 3.2],
[ 2.3, 1.1, 4.3, 2.3, 1.1],
[ 3.2, 2.6, 1.9, 1.7, 1.1],
[ 2.1, 1.5, 3. , 1.4, 1.1]])
self.expected_discretized = \
N.array([[ 1.2, 1.4, 1. , 1. , 0. ],
[ 2.3, 1.1, 1. , 2. , 1. ],
[ 3.2, 0. , 0. , 2. , 2. ],
[ 4.2, 2.4, 2. , 1. , 2. ],
[ 2.7, 1.5, 0. , 0. , 0. ],
[ 1.1, 2.3, 1. , 0. , 2. ],
[ 2.3, 1.1, 2. , 2. , 0. ],
[ 3.2, 2.6, 0. , 0. , 0. ],
[ 2.1, 1.5, 2. , 0. , 0. ]])
self.expected_arities = [-1,-1,3,3,3]
def setUp(self):
self.data = data.fromfile(testfile('testdata10.txt'))
self.neteval = evaluator.NetworkEvaluator(
self.data, network.fromdata(self.data),
prior.UniformPrior(self.data.variables.size))
self.neteval.network.edges.add_many([(1, 0), (2, 0), (3, 0)])
def setUp(self):
config.set('evaluator.missingdata_evaluator', 'exact')
self.data = data.fromfile(
testfile('testdata13.txt')).subset(samples=range(5))
self.learner = greedy.GreedyLearner(self.data, max_iterations=10)
def setUp(self):
config.set('evaluator.missingdata_evaluator', self.missing_evaluator)
self.data = data.fromfile(testfile('testdata13.txt'))
self.learner = self.learnertype(self.data)
def setUp(self):
self.data = data.fromfile(
testfile('testdata5.txt')).subset(samples=range(5))
self.data.discretize()
self.learner = self.learnertype(self.data)
def setUp(self):
self.data = data.fromfile(testfile('testdata5.txt'))
self.data.discretize()
print "=" * 80
print "test statistics: "
if verbose:
fail_breakdown(merged_result.detail)
print "Max score: %s" % max(scores)
print "Min score: %s" % min(scores)
avg_score = sum(scores) / len(scores)
print "Average score: %s" % avg_score
# final_score = sum([r.num_pass for r in results])/\
# float(sum([r.num_testcase for r in results]))
final_score = merged_result.score(score_type)[1]
print "Normalized score: %s" % final_score
return final_score
if __name__ == "__main__":
# run a cross validation
from pebl import data
# test parameters
data_file = "/home/drli/code/ml/iris.pebl"
classifier_type = "tan"
test_ratio = 0.3
runs = 2
verbose = True
dataset = data.fromfile(data_file)
# dataset.discretize(numbins=3, excludevars=[dataset.variables.size-1])
cross_validate(dataset, classifier_type, test_ratio, runs, verbose)
args = parser.parse_args()
for f in os.listdir(args.directory)[args.start:args.end]:
if 'struct' in f:
continue
structfile = open(args.directory + '/' + f.replace('.txt', '_struct.txt'))
peblfile = open(args.directory + '/' + f)
nodenames = peblfile.readline().strip().split('\t')
peblfile.close()
if len(nodenames) > 30:
continue
nodes = [data.Variable(name) for name in nodenames]
edges = [[int(x) for x in l.strip().split('\t')] for l in structfile.readlines()]
print 'Doing %s' % f
print nodes
print edges
net = network.Network(nodes, edges=edges)
dataset = data.fromfile(args.directory + '/' + f)
try:
dataset.discretize()
if len(nodenames) <= 10:
learner = greedy.GreedyLearner(dataset, seed=net)
else:
learner = greedy.GreedyLearner(dataset)
res = learner.run()
# res.outdir = args.directory + '/'
res.tohtml(args.prefix + '/' + f.replace('.txt', '_html'))
except Exception as e:
print 'Could not process %s: exception was %s' % (f, e)
def setUp(self):
self.data = data.fromfile(testfile("greedytest1-200.txt"))
def setUp(self):
config.set('evaluator.missingdata_evaluator', 'exact')
self.data = data.fromfile(testfile('testdata13.txt')).subset(samples=range(5))
self.learner = greedy.GreedyLearner(self.data, max_iterations=10)
def setUp(self):
self.data = data.fromfile(testfile('testdata5.txt')).subset(samples=range(5))
self.data.discretize()
self.learner = self.learnertype(self.data)
def setUp(self):
config.set('evaluator.missingdata_evaluator', self.missing_evaluator)
self.data = data.fromfile(testfile('testdata13.txt'))
self.learner = self.learnertype(self.data)
start_time = time.time()
classifyUsingNB(trainList, classVariable, testList, testClassVariable)
elapsed_time = time.time() - start_time
print("Time elapsed Gaussian Naive Bayes : ", elapsed_time)
#Decision tree
start_time = time.time()
classifyUsingDecisionTree(trainList, classVariable, testList,
testClassVariable)
elapsed_time = time.time() - start_time
print("Time elapsed Decision : ", elapsed_time)
#logistic regression
solver = 'sag'
multiclass = 'ovr'
start_time = time.time()
classifyUsingLogisticRegression(trainList, classVariable, testList,
testClassVariable, solver, multiclass)
elapsed_time = time.time() - start_time
print("Time elapsed Logistic Regression : ", elapsed_time)
#Bayesian Network using PEBL for the data
start_time = time.time()
dataset = data.fromfile(trainFileNameForBayesian)
dataset.discretize()
learner = greedy.GreedyLearner(dataset)
ex1result = learner.run()
ex1result.tohtml("dataset")
elapsed_time = time.time() - start_time
print("Time elapsed Bayesian Network : ", elapsed_time)
def setUp(self):
self.data = data.fromfile(testfile("greedytest1-200.txt"))
def setUp(self):
self.data = data.fromfile(testfile('testdata10.txt'))
self.neteval = evaluator.NetworkEvaluator(self.data,
network.fromdata(self.data))
self.neteval.network.edges.add_many([(1, 0), (2, 0),
(3, 0)]) # {1,2,3} --> 0
'''
from pebl import data, result
from pebl.learner import *
from pebl_interface import graph2pebl
from pebl_interface import render_pebl_graph
import numpy as np
from time import gmtime, strftime
#TODO: this should take as arguments
# data : txt file
# labels: node names and types of attributes
# conf : configuration file - type of learnerm number of learners
if __name__ == "__main__":
dataset = data.fromfile('../datasets/diabetes/diabetes_pebl_train.txt')
dataset.discretize(numbins=5)
learner = greedy.GreedyLearner(dataset, max_iterations = 10000)
#nodes_list = ["SAT","Difficulty","Intelligence","Grade","Letter"]
#adjacency_matrix = np.array([[0,0,0,0,0],[0,0,0,1,0],[1,0,0,1,0],[0,0,0,0,1],[0,0,0,0,0]])
#g = graph2pebl(nodes_list, adjacency_matrix)
#learner.seed = g
#render_pebl_graph(learner.seed,"initial")
#~ learners = [ greedy.GreedyLearner(dataset, max_iterations=1000000) for i in range(5) ] + \
#~ [ simanneal.SimulatedAnnealingLearner(dataset) for i in range(5) ]
#~ merged_result = result.merge([learner.run() for learner in learners])
results = learner.run()
result_folder_str = "../experiments/diabetes_" + strftime("%Y-%m-%d_%H:%M:%S", gmtime())
results.tohtml(result_folder_str)
DATA_PATH = "data/HR_tab_sep.pebl.tsv"
import numpy as np
from pebl import data
from pebl.prior import Prior
dataset = data.fromfile(DATA_PATH)
n_vars = len(dataset.variables)
def prohibit_from_left(energy): return energy[6].sum() <= 0
for i in range(n_vars):
if type(dataset.variables[i]) == data.ContinuousVariable:
dataset.discretize(i, numbins=10)
if type(dataset.variables[i]) == data.ClassVariable:
dataset.discretize(i, numbins=dataset.variables[i].arity)
prohibited_edges = [ (6, i) for i in range(6) + range(6, 10) ]
prior = Prior(len(dataset.variables),
#np.ones((n_vars, n_vars)) / (n_vars * n_vars))
#constraints=[prohibit_from_left])
prohibited_edges=prohibited_edges)
from pebl import data, result
from pebl.learner import greedy, simanneal
import numpy as np
from pebl.taskcontroller import multiprocess
dataset = data.fromfile("zinc.txt")
dataset.discretize()
learner1 = greedy.GreedyLearner(dataset, max_iterations=1000)
result1 = learner1.run()
learner2 = greedy.GreedyLearner(dataset, max_iterations=1000)
result2 = learner2.run()
#learners = [ greedy.GreedyLearner(dataset, max_iterations=100) for i in range(5) ] #+ \
# [ simanneal.SimulatedAnnealingLearner(dataset) for i in range(5) ]
result1.tohtml('example2.out')
result2.tohtml('example3.out')
merged_result = result.merge(result1, result2)
merged_result.tohtml("zinc",)
merged_result.tofile('example.out')
from pebl import data
from pebl import prior
from pebl.learner import greedy
dataset = data.fromfile("output.txt")
dataset.discretize(numbins=3)
node_src = [32 for ii in range(32)] + [3 for ii in range(32)] + [
30 for ii in range(32)
] + [31 for ii in range(32)]
node_dest = range(32) + range(32) + range(32) + range(32)
prior = prior.Prior(33, prohibited_edges=zip(node_src, node_dest))
learner = greedy.GreedyLearner(dataset, prior, max_iterations=120000)
result = learner.run()
result.tohtml()
from pebl.learner import greedy
from pebl.taskcontroller import ec2
from pebl.test import testfile
help = """Test the EC2 TaskController.
USAGE: test_ec2.py configfile
You need to provide the configfile for use with EC2Controller.
###############################################################################
WARNING for pebl devs:
Do NOT put your configfile under svn.
It contains sensitve information.
###############################################################################
"""
if len(sys.argv) < 2:
print help
sys.exit(1)
d = data.fromfile(testfile("testdata5.txt"))
d.discretize()
tc = ec2.EC2Controller(config=sys.argv[1], min_count=3)
results = tc.run([greedy.GreedyLearner(d, max_time=10) for i in xrange(10)])
results = result.merge(results)
print results
print[r.host for r in results.runs]
def setUp(self):
d = data.fromfile(testfile("testdata5.txt"))
d.discretize()
self.proc = subprocess.Popen("ipcluster -n 2 </dev/null 1>&0 2>&0", shell=True)
time.sleep(5)
def setUp(self):
self.data = data.fromfile(testfile('testdata10.txt'))
self.ne = evaluator.SmartNetworkEvaluator(
self.data,
network.fromdata(self.data))
def run_benchmarks(datafile):
print datafile
dat = data.fromfile(datafile)
l = greedy.GreedyLearner(dat)
l.run()
def setUp(self):
self.data = data.fromfile(testfile('testdata10.txt'))
self.ne = evaluator.SmartNetworkEvaluator(self.data,
network.fromdata(self.data))
def setUp(self):
self.data = data.fromfile(testfile('testdata10.txt'))
self.neteval = evaluator.NetworkEvaluator(self.data, network.fromdata(self.data))
self.neteval.network.edges.add_many([(1,0), (2,0), (3,0)]) # {1,2,3} --> 0
#!/usr/bin/env python
# Bayesian with five greedy and 5 simulated annearling learners serially
# http://pythonhosted.org/pebl/tutorial.html
from pebl import data, result
from pebl.learner import greedy, simanneal
from pebl.taskcontroller import multiprocess
dataset = data.fromfile("pebl-tutorial-data2.txt")
learners = [ greedy.GreedyLearner(dataset, max_iterations=1000000) for i in range(5) ] + \
[ simanneal.SimulatedAnnealingLearner(dataset) for i in range(5) ]
tc = multiprocess.MultiProcessController(poolsize=2)
results = tc.run(learners)
merged_result = result.merge(results)
merged_result.tofile("example4-result")
def setUp(self):
self.data = data.fromfile(testfile('testdata5.txt'))
self.data.discretize()
from pebl.taskcontroller import xgrid
from pebl.test import testfile
help = """Test the Xgrid TaskController.
USAGE: test_xgrid.py configfile
You need to provide the configfile for use with XGridController.
###############################################################################
WARNING for pebl devs:
Do NOT put your configfile under svn.
It contains sensitve information.
###############################################################################
"""
if len(sys.argv) < 2:
print help
sys.exit(1)
config.read(sys.argv[1])
d = data.fromfile(testfile("testdata5.txt"))
d.discretize()
tc = xgrid.XgridController()
results = tc.run([greedy.GreedyLearner(d, max_time=10) for i in xrange(10)])
results = result.merge(results)
print results
print [r.host for r in results.runs]
def setUp(self):
d = data.fromfile(testfile("testdata5.txt"))
d.discretize()
self.tc = self.tctype(*self.args)
self.tasks = [greedy.GreedyLearner(d, max_iterations=100) for i in xrange(6)]