def find_distinct_distance(normalized_data_set):
"""
find the median of distance which can distinguish the data.
:param normalized_data_set: dataset to calculate. The dataset must be normalized
:return: float-distance
"""
n = len(normalized_data_set)
# find out all kinds of classes in the dataset
classes = list(set([i[-1]for i in normalized_data_set]))
assert len(classes) > 1, "unfortunately all data selected are in same class."
classes_index = dict()
for c in classes:
classes_index[c] = [index for index, i in enumerate(normalized_data_set) if i[-1] == c]
distances = []
for data in normalized_data_set:
c = data[-1]
diff_class_data_indices = [index for index in range(n) if index not in classes_index[c]]
distances.append(min([toolkit.euclidean_dist(data, normalized_data_set[index])
for index in diff_class_data_indices]))
import numpy
median_dist = numpy.median(numpy.array(distances))
logging.debug("The distinguish distance is %f" % median_dist)
return median_dist
def find_distinct_distance(normalized_data_set):
"""
find the median of distance which can distinguish the data.
:param normalized_data_set: dataset to calculate. The dataset must be normalized
:return: float-distance
"""
n = len(normalized_data_set)
# find out all kinds of classes in the dataset
classes = list(set([i[-1] for i in normalized_data_set]))
assert len(
classes) > 1, "unfortunately all data selected are in same class."
classes_index = dict()
for c in classes:
classes_index[c] = [
index for index, i in enumerate(normalized_data_set) if i[-1] == c
]
distances = []
for data in normalized_data_set:
c = data[-1]
diff_class_data_indices = [
index for index in range(n) if index not in classes_index[c]
]
distances.append(
min([
toolkit.euclidean_dist(data, normalized_data_set[index])
for index in diff_class_data_indices
]))
median_dist = numpy.median(numpy.array(distances))
logging.debug("The distinguish distance is %f" % median_dist)
return median_dist
def whether_add_to_private_cache(data_instance, existed_cache, distinguish_distance):
"""
:param data_instance: this should be normalized
:param existed_cache: this should be normalized
:param distinguish_distance:
:return:
"""
# TODO whether need to check the class?!
for data in existed_cache:
if toolkit.euclidean_dist(data_instance, data) <= distinguish_distance:
return False
return True
def whether_add_to_private_cache(data_instance, existed_cache,
distinguish_distance):
"""
:param data_instance: this should be normalized
:param existed_cache: this should be normalized
:param distinguish_distance:
:return:
"""
# TODO whether need to check the class?!
for data in existed_cache:
if toolkit.euclidean_dist(data_instance, data) <= distinguish_distance:
return False
return True
def simplify_morph(data, alpha, beta):
"""
same as MOPRH. But require
1) data is handled, no header, class at last column
2) data has been normalized
"""
classes = map(list, zip(*data))[-1]
data = [i for i in data]
for row_index, row in enumerate(data): # for each row
heterogeneous_index = [
i for i in range(len(classes)) if classes[i] != classes[row_index]
]
boundary_dist = min([
toolkit.euclidean_dist(row, data[heg])
for heg in heterogeneous_index
])
boundary_dist /= math.sqrt(len(data[0]) - 2)
for i in range(len(row)):
data[row_index][i] += boundary_dist * random.uniform(
alpha, beta) * random.choice([1, -1]) # shake
return data
def morph(attribute_names,
data_matrix,
independent_attrs,
objective_attr,
objective_as_binary=False,
data_has_normalized=False,
alpha=0.15,
beta=0.35):
"""
morph is a instance mutation which can shake the instance within the class boundary
:param attribute_names: the names of attributes, should match the data_matrix
:param data_matrix: original data
:param independent_attrs: set up the independent attributes in the dataset. Note: 'name', 'id', etc. might not be
considered as independent attributes
:param objective_attr: marking which attribute is the objective to be considered
:param objective_as_binary: signal to set up whether treat the objective as a binary attribute. Default: False
:param data_has_normalized: telling whether the data matrix has been normalized.
:param alpha: morph algorithm parameter
:param beta: morph algorithm parameter
:return:
"""
dataset_t = map(list, zip(*data_matrix))
dataset = list()
classes = list()
for d, a in zip(dataset_t, attribute_names):
if a in independent_attrs:
dataset.append(d)
if a == objective_attr:
classes = list(d)
dataset = map(list, zip(*dataset))
dataset = [map(toolkit.str2num, row) for row in dataset] # str to numeric
classes = map(toolkit.str2num, classes)
if objective_as_binary:
classes = [1 if i > 0 else 0 for i in classes]
else:
classes = toolkit.apply_bin_range(classes)
is_int = [type(i) is int for i in dataset[0]
] # save. for better representation of the output table
if data_has_normalized:
# adding two instance (all zeros and all ones) so that the normalization and de-normalization process
# do not damage the original data
dataset.append([0] * len(dataset[0]))
dataset.append([1] * len(dataset[0]))
'''dataset transposed mode begins...'''
dataset = map(list, zip(*dataset)) # transpose.
norm_funcs = []
denorm_funcs = []
# normalizing
for attr_index, attr_elements in enumerate(
dataset): # for each attribute elements
f1, f2 = toolkit.attr_norm(attr_elements)
norm_funcs.append(f1)
denorm_funcs.append(f2)
dataset[attr_index] = map(f1, attr_elements)
'''dataset mode recover...'''
dataset = map(list, zip(*dataset)) # transpose again.
for row_index, row in enumerate(dataset): # for each row
heterogeneous_index = [
i for i in range(len(classes)) if classes[i] != classes[row_index]
]
boundary_dist = min([
toolkit.euclidean_dist(row, dataset[heg])
for heg in heterogeneous_index
])
boundary_dist /= math.sqrt(len(independent_attrs) - 1)
for i in range(len(row)):
dataset[row_index][i] += boundary_dist * random.uniform(
alpha, beta) * random.choice([1, -1]) # shake
'''dataset transposed mode begins...'''
dataset = map(list, zip(*dataset)) # transpose.
for attr_index, attr_elements in enumerate(
dataset): # for each attribute elements
dataset[attr_index] = map(denorm_funcs[attr_index],
attr_elements) # scale to the original
for i in range(len(dataset[attr_index])):
if is_int[attr_index]:
dataset[attr_index][i] = int(round(
dataset[attr_index][i])) # rounding when needed
else:
dataset[attr_index][i] = round(dataset[attr_index][i], 4)
morphed = map(list,
zip(*dataset)) # recover to the original mode and finish.
'''!!morph done!!'''
if data_has_normalized:
morphed = morphed[:-2]
res = list()
for x, dm in zip(morphed, data_matrix):
row = list()
tmp = 0
for attri, attr in enumerate(attribute_names):
if attr in independent_attrs:
row.append(x[tmp])
tmp += 1
elif attr == objective_attr:
row.append(toolkit.str2num(dm[attri]))
else:
row.append(dm[attri])
res.append(row)
return res
def MORPH(database, db_folder='not_from_csv_file', write_out_folder=None,
db_has_normalized=False, effect_scope=[0, -1]):
"""
MORPH is a instance mutator which can shake the instance within the class boundary
:param database: original data.
:param db_folder: from where database fetch. by default, the database is a list of list
:param write_out_folder: specify the writing out folder. None means no writing
:param db_has_normalized: whether the database has been normalized
:param effect_scope: specify the scope in the database to be morphed. Any data beyond the scope will remain the same
:return: the morphed data
"""
alpha = settings.MORPH_alpha
beta = settings.MORPH_beta
# load the database
if db_folder != 'not_from_csv_file':
with open(db_folder + '/' + database + '.csv', 'r') as db:
reader = csv.reader(db)
attributes = next(reader) # including the last one--class tag
dataset = []
for line in reader:
dataset.append(line)
dataset = [map(toolkit.str2num, row) for row in dataset] # str to numeric
else:
dataset = database
attributes = ['foo'] * len(dataset[0])
# backup the no-need-to-morphed data
if effect_scope[1] < 0:
effect_scope[1] += len(dataset)+1
backup_data_set = copy.deepcopy(dataset[effect_scope[0]:effect_scope[1]])
if db_has_normalized:
# adding two instance (all zeros and all ones) so that the normalization and de-normalization process
# do not damage the original data
dataset.append([0]*len(dataset[0]))
dataset.append([1]*len(dataset[0]))
is_int = [type(i) is int for i in dataset[0]] # save. for better representation of the output table
classes = [row[-1] for row in dataset] # fetch the classes
dataset = [row[:-1] for row in dataset] # separating the raw data and class
'''dataset transposed mode begins...'''
dataset = map(list, zip(*dataset)) # transpose.
norm_funcs = []
denorm_funcs = []
# normalizing
for attr_index, attr_elements in enumerate(dataset): # for each attribute elements
f1, f2 = toolkit.attr_norm(attr_elements)
norm_funcs.append(f1)
denorm_funcs.append(f2)
dataset[attr_index] = map(f1, attr_elements)
'''dataset mode recover...'''
dataset = map(list, zip(*dataset)) # transpose again.
for row_index, row in enumerate(dataset): # for each row
heterogeneous_index = [i for i in range(len(classes)) if classes[i] != classes[row_index]]
boundary_dist = min([toolkit.euclidean_dist(row, dataset[heg]) for heg in heterogeneous_index])
boundary_dist /= math.sqrt(len(attributes)-1)
for i in range(len(row)):
dataset[row_index][i] += boundary_dist*random.uniform(alpha, beta)*random.choice([1, -1]) # shake
'''dataset transposed mode begins...'''
dataset = map(list, zip(*dataset)) # transpose.
for attr_index, attr_elements in enumerate(dataset): # for each attribute elements
dataset[attr_index] = map(denorm_funcs[attr_index], attr_elements) # scale to the original
for i in range(len(dataset[attr_index])):
if is_int[attr_index]:
dataset[attr_index][i] = int(round(dataset[attr_index][i])) # rounding when needed
morphed = map(list, zip(*dataset)) # recover to the original mode and finish.
'''!!MORPH done!!'''
# writing out and output the results
for row_index in range(len(morphed)):
morphed[row_index].append(classes[row_index])
if db_folder != 'not_from_csv_file':
morphed.insert(0, attributes)
if write_out_folder:
with open(write_out_folder + '/'+database+'.csv', 'wb') as f:
writer = csv.writer(f)
writer.writerows(morphed)
if db_has_normalized:
morphed = morphed[:-2]
# recover the unmorphed data
for backup, row_index in zip(backup_data_set, range(effect_scope[0], effect_scope[1])):
morphed[row_index] = backup
return morphed
