def setup_dataset(self):
"""
Creates a corpus of primes. Returns the dataset,
the attributes getter and the target getter.
"""
size = 105 # Magic number, chosen to avoid an "error" that cannot be
# patched in Dtree Pseudo (with modifing the pseudocode).
dataset = []
for i in range(size):
dataset.append([i % 2 == 0, i % 3 == 0, i % 5 == 0, i % 7 == 0, self.isprime(i)])
problem = VectorDataClassificationProblem(dataset, target_index=-1)
problem.distance = euclidean_vector_distance
self.corpus = dataset
self.problem = problem
def setup_dataset(self):
"""
Creates a corpus with the iris dataset. Returns the dataset,
the attributes getter and the target getter.
"""
dataset = []
with open(self.IRIS_PATH) as filehandler:
file_data = filehandler.read()
for line in file_data.split("\n"):
line_data = [round(float(x)) for x in line.split()]
if line_data:
dataset.append(line_data)
problem = VectorDataClassificationProblem(dataset, target_index=4)
problem.distance = euclidean_vector_distance
self.corpus = dataset
self.problem = problem
def setup_dataset(self):
"""
Creates a corpus of primes. Returns the dataset,
the attributes getter and the target getter.
"""
size = 105 # Magic number, chosen to avoid an "error" that cannot be
# patched in Dtree Pseudo (with modifing the pseudocode).
dataset = []
for i in xrange(size):
dataset.append([
i % 2 == 0, i % 3 == 0, i % 5 == 0, i % 7 == 0,
self.isprime(i)
])
problem = VectorDataClassificationProblem(dataset, target_index=-1)
problem.distance = euclidean_vector_distance
self.corpus = dataset
self.problem = problem
def setup_dataset(self):
"""
Creates a corpus with the iris dataset. Returns the dataset,
the attributes getter and the target getter.
"""
dataset = []
with open(self.IRIS_PATH) as filehandler:
file_data = filehandler.read()
for line in file_data.split("\n"):
line_data = [round(float(x)) for x in line.split()]
if line_data:
dataset.append(line_data)
problem = VectorDataClassificationProblem(dataset, target_index=4)
problem.distance = euclidean_vector_distance
self.corpus = dataset
self.problem = problem
def setup_dataset(self):
"""
Creates a corpus with n k-bit examples of the parity problem:
k random bits followed by a 1 if an odd number of bits are 1, else 0
"""
k = 2
n = 100
dataset = []
for i in xrange(n):
# Pseudo random generation of bits
bits = [(((i + j) * 1223) % (n + 1)) % 2 for j in xrange(k)]
bits.append(sum(bits) % 2)
dataset.append(bits)
problem = VectorDataClassificationProblem(dataset, target_index=k)
self.corpus = dataset
self.problem = problem
