def __init__(self, data, param): self.param = param self.differ = Differential(self.param.Seed) self.mapp = None self.root = KNode() self.realData = data self.root.n_box = None self.root.n_budget = Params.maxHeight
def __init__(self, data, param): self.param = param self.differ = Differential(self.param.Seed) # ## initialize the root self.root = KNode() self.root.n_data = data self.root.n_box = np.array([Params.LOW, Params.HIGH]) self.root.n_budget = Params.maxHeight
def buildIndex(self): """ Function to build the tree structure, fanout = 4 by default for spatial (2D) data """ budget_c = self.getCountBudget() self.root.n_count = self.getCount(self.root, budget_c[0]) # ## add noisy count to root stack = deque() stack.append(self.root) nleaf = 0 # ## leaf counter max_depth = -1 # ## main loop while len(stack) > 0: curr = stack.popleft() if curr.n_depth > max_depth: max_depth = curr.n_depth if self.testLeaf(curr) is True: # ## curr is a leaf node if curr.n_depth < Params.maxHeight: # ## if a node ends up earlier than maxHeight, it should be able to use the remaining count budget remainingEps = sum(budget_c[curr.n_depth + 1:]) curr.n_count = self.getCount(curr, remainingEps) nleaf += 1 curr.n_isLeaf = True self.cell_setLeaf(curr) else: # ## curr needs to split curr.n_budget -= 1 # ## some budget will be used regardless the split is successful or not tmp = self.getCoordinates(curr) nw_node, ne_node, sw_node, se_node = KNode(), KNode(), KNode(), KNode() # create sub-nodes nw_coord, ne_coord, nw_node.n_data, ne_node.n_data, sw_node.n_data, se_node.n_data = tmp x_nw, y_nw = nw_coord x_se, y_se = ne_coord # ## update bounding box, depth, count, budget for the four subnodes nw_node.n_box = np.array([[curr.n_box[0, 0], y_nw], [x_nw, curr.n_box[1, 1]]]) ne_node.n_box = np.array([[x_nw, y_se], [curr.n_box[1, 0], curr.n_box[1, 1]]]) sw_node.n_box = np.array([[curr.n_box[0, 0], curr.n_box[0, 1]], [x_se, y_nw]]) se_node.n_box = np.array([[x_se, curr.n_box[0, 1]], [curr.n_box[1, 0], y_se]]) for sub_node in [nw_node, ne_node, sw_node, se_node]: sub_node.n_depth = curr.n_depth + 1 # if (sub_node.n_depth == Params.maxHeight and sub_node.n_data is not None): # print len(sub_node.n_data[0]) sub_node.n_count = self.getCount(sub_node, budget_c[sub_node.n_depth]) sub_node.n_budget = curr.n_budget stack.append(sub_node) curr.n_data = None # ## do not need the data points coordinates now curr.nw, curr.ne, curr.sw, curr.se = nw_node, ne_node, sw_node, se_node # end of while logging.debug("number of leaves: %d" % nleaf) logging.debug("max depth: %d" % max_depth)
def buildIndex(self): stack = deque() stack.append(self.root) nleaf = 0 # leaf counter max_depth = -1 self.root.n_count = np.sum(self.mapp) while len(stack) > 0: curr = stack.popleft() if curr.n_depth > max_depth: max_depth = curr.n_depth if self.testLeaf(curr) is True: # curr is a leaf node nleaf += 1 curr.n_isLeaf = True self.cell_setLeaf(curr) else: # curr needs to split curr.n_budget -= 1 tmp = self.getCoordinates(curr) nw_node, ne_node, sw_node, se_node = KNode(), KNode(), KNode(), KNode() # create sub-nodes nw_coord, ne_coord, count_tmp = tmp x_nw, y_nw = nw_coord x_se, y_se = ne_coord nw_node.n_box = np.array([[curr.n_box[0, 0], y_nw], [x_nw, curr.n_box[1, 1]]]) ne_node.n_box = np.array([[x_nw, y_se], [curr.n_box[1, 0], curr.n_box[1, 1]]]) sw_node.n_box = np.array([[curr.n_box[0, 0], curr.n_box[0, 1]], [x_se, y_nw]]) se_node.n_box = np.array([[x_se, curr.n_box[0, 1]], [curr.n_box[1, 0], y_se]]) c_t = 0 for sub_node in [nw_node, ne_node, sw_node, se_node]: sub_node.n_depth = curr.n_depth + 1 sub_node.n_count = count_tmp[c_t] sub_node.n_budget = curr.n_budget stack.append(sub_node) c_t += 1 curr.nw, curr.ne, curr.sw, curr.se = nw_node, ne_node, sw_node, se_node # end of while logging.debug("number of leaves: %d" % nleaf) logging.debug("max depth: %d" % max_depth)
def buildIndex(self): """ Function to build the tree structure, fanout = 4 by default for spatial (2D) data """ budget_c = self.getCountBudget() self.root.n_count = self.getCount( self.root, budget_c[0]) # ## add noisy count to root stack = deque() stack.append(self.root) nleaf = 0 # ## leaf counter max_depth = -1 # ## main loop while len(stack) > 0: curr = stack.popleft() if curr.n_depth > max_depth: max_depth = curr.n_depth if self.testLeaf(curr) is True: # ## curr is a leaf node if curr.n_depth < Params.maxHeight: # ## if a node ends up earlier than maxHeight, it should be able to use the remaining count budget remainingEps = sum(budget_c[curr.n_depth + 1:]) curr.n_count = self.getCount(curr, remainingEps) nleaf += 1 curr.n_isLeaf = True self.cell_setLeaf(curr) else: # ## curr needs to split curr.n_budget -= 1 # ## some budget will be used regardless the split is successful or not tmp = self.getCoordinates(curr) nw_node, ne_node, sw_node, se_node = KNode(), KNode(), KNode( ), KNode() # create sub-nodes nw_coord, ne_coord, nw_node.n_data, ne_node.n_data, sw_node.n_data, se_node.n_data = tmp x_nw, y_nw = nw_coord x_se, y_se = ne_coord # ## update bounding box, depth, count, budget for the four subnodes nw_node.n_box = np.array([[curr.n_box[0, 0], y_nw], [x_nw, curr.n_box[1, 1]]]) ne_node.n_box = np.array([[x_nw, y_se], [curr.n_box[1, 0], curr.n_box[1, 1]]]) sw_node.n_box = np.array([[curr.n_box[0, 0], curr.n_box[0, 1]], [x_se, y_nw]]) se_node.n_box = np.array([[x_se, curr.n_box[0, 1]], [curr.n_box[1, 0], y_se]]) for sub_node in [nw_node, ne_node, sw_node, se_node]: sub_node.n_depth = curr.n_depth + 1 # if (sub_node.n_depth == Params.maxHeight and sub_node.n_data is not None): # print len(sub_node.n_data[0]) sub_node.n_count = self.getCount( sub_node, budget_c[sub_node.n_depth]) sub_node.n_budget = curr.n_budget stack.append(sub_node) curr.n_data = None # ## do not need the data points coordinates now curr.nw, curr.ne, curr.sw, curr.se = nw_node, ne_node, sw_node, se_node # end of while logging.debug("number of leaves: %d" % nleaf) logging.debug("max depth: %d" % max_depth)
def buildIndex(self): stack = deque() stack.append(self.root) nleaf = 0 # leaf counter max_depth = -1 self.root.n_count = np.sum(self.mapp) while len(stack) > 0: curr = stack.popleft() if curr.n_depth > max_depth: max_depth = curr.n_depth if self.testLeaf(curr) is True: # curr is a leaf node nleaf += 1 curr.n_isLeaf = True self.cell_setLeaf(curr) else: # curr needs to split curr.n_budget -= 1 tmp = self.getCoordinates(curr) nw_node, ne_node, sw_node, se_node = KNode(), KNode(), KNode( ), KNode() # create sub-nodes nw_coord, ne_coord, count_tmp = tmp x_nw, y_nw = nw_coord x_se, y_se = ne_coord nw_node.n_box = np.array([[curr.n_box[0, 0], y_nw], [x_nw, curr.n_box[1, 1]]]) ne_node.n_box = np.array([[x_nw, y_se], [curr.n_box[1, 0], curr.n_box[1, 1]]]) sw_node.n_box = np.array([[curr.n_box[0, 0], curr.n_box[0, 1]], [x_se, y_nw]]) se_node.n_box = np.array([[x_se, curr.n_box[0, 1]], [curr.n_box[1, 0], y_se]]) c_t = 0 for sub_node in [nw_node, ne_node, sw_node, se_node]: sub_node.n_depth = curr.n_depth + 1 sub_node.n_count = count_tmp[c_t] sub_node.n_budget = curr.n_budget stack.append(sub_node) c_t += 1 curr.nw, curr.ne, curr.sw, curr.se = nw_node, ne_node, sw_node, se_node # end of while logging.debug("number of leaves: %d" % nleaf) logging.debug("max depth: %d" % max_depth)
class Kd_cell(Kd_pure): """ Kd tree based on syntatic data generation and a grid structure. See Y. Xiao, L. Xiong, and C. Yuan, Differentially private data release through multidimensional partitioning, in SDM Workshop, VLDB, 2010 """ def __init__(self, data, param): self.param = param self.differ = Differential(self.param.Seed) self.mapp = None self.root = KNode() self.realData = data self.root.n_box = None self.root.n_budget = Params.maxHeight def getCountBudget(self): count_eps = self.param.Eps * 0.5 H = Params.maxHeight if self.param.geoBudget == 'none': return [count_eps / (H + 1) for _ in range(H + 1)] elif self.param.geoBudget == 'aggressive': unit = count_eps / (2**(H + 1) - 1) return [unit * 2**i for i in range(H + 1)] elif self.param.geoBudget == 'quadratic': unit = count_eps * (np.sqrt(2) - 1) / (2**(0.5 * (H + 1)) - 1) return [unit * 2**(0.5 * i) for i in range(H + 1)] elif self.param.geoBudget == 'optimal': unit = count_eps * ((2**(1.0 / 3)) - 1) / (2**((1.0 / 3) * (H + 1)) - 1) return [unit * 2**((1.0 / 3) * i) for i in range(H + 1)] elif self.param.geoBudget == 'quartic': unit = count_eps * ((2**(1.0 / 4)) - 1) / (2**((1.0 / 4) * (H + 1)) - 1) return [unit * 2**((1.0 / 4) * i) for i in range(H + 1)] else: logging.error('No such geoBudget scheme') sys.exit(1) def synthetic_gen(self): """Apply a grid structure on the domain and perturb the count using half of the available privacy budget """ logging.debug('generating synthetic map...') data = self.realData unit = Params.unitGrid x_min = np.floor(Params.LOW[0] / unit) * unit x_max = np.ceil(Params.HIGH[0] / unit) * unit y_min = np.floor(Params.LOW[1] / unit) * unit y_max = np.ceil(Params.HIGH[1] / unit) * unit x_CELL = int(np.rint((x_max - x_min) / unit)) y_CELL = int(np.rint((y_max - y_min) / unit)) self.root.n_box = np.array([[x_min, y_min], [x_max, y_max]]) self.mapp = np.zeros( (x_CELL, y_CELL)) - 1 # ## initialize every cell with -1 for i in range(Params.NDATA): # ## populate the map point = data[:, i] cell_x = int(np.floor((point[0] - x_min) / unit)) cell_y = int(np.floor((point[1] - y_min) / unit)) if self.mapp[cell_x, cell_y] != -1: self.mapp[cell_x, cell_y] += 1 else: self.mapp[cell_x, cell_y] = 1 for i in range(x_CELL): # ## perturb the counts for j in range(y_CELL): if self.mapp[i, j] != -1: self.mapp[i, j] += np.rint( self.differ.getNoise(1, 0.5 * self.param.Eps)) else: self.mapp[i, j] = np.rint( self.differ.getNoise(1, 0.5 * self.param.Eps)) # if noisy count is negative, ignore the noise and generate no points if self.mapp[i, j] < 0: self.mapp[i, j] = 0 def cell_setLeaf(self, curr): """ Throw away the counts based on the syntatic data """ curr.n_count = 0 return def testLeaf(self, curr): if (curr.n_count <= self.param.minPartSize) or ( curr.n_depth == Params.maxHeight) or (self.uniform_test( curr, self.param.cellDistance)): return True return False def uniform_test(self, curr, distance): """ One of the stopping conditions: cell is uniform according to some threshold 'distance') """ unit = Params.unitGrid x_min = int(np.rint((curr.n_box[0, 0] - self.root.n_box[0, 0]) / unit)) x_max = int(np.rint((curr.n_box[1, 0] - self.root.n_box[0, 0]) / unit)) y_min = int(np.rint((curr.n_box[0, 1] - self.root.n_box[0, 1]) / unit)) y_max = int(np.rint((curr.n_box[1, 1] - self.root.n_box[0, 1]) / unit)) data = self.mapp[x_min:x_max, y_min:y_max] total = np.sum(data) avg = total / ((x_max - x_min) * (y_max - y_min)) dist = np.sum(np.abs(data - avg)) if dist > distance: return False else: return True def buildIndex(self): stack = deque() stack.append(self.root) nleaf = 0 # leaf counter max_depth = -1 self.root.n_count = np.sum(self.mapp) while len(stack) > 0: curr = stack.popleft() if curr.n_depth > max_depth: max_depth = curr.n_depth if self.testLeaf(curr) is True: # curr is a leaf node nleaf += 1 curr.n_isLeaf = True self.cell_setLeaf(curr) else: # curr needs to split curr.n_budget -= 1 tmp = self.getCoordinates(curr) nw_node, ne_node, sw_node, se_node = KNode(), KNode(), KNode( ), KNode() # create sub-nodes nw_coord, ne_coord, count_tmp = tmp x_nw, y_nw = nw_coord x_se, y_se = ne_coord nw_node.n_box = np.array([[curr.n_box[0, 0], y_nw], [x_nw, curr.n_box[1, 1]]]) ne_node.n_box = np.array([[x_nw, y_se], [curr.n_box[1, 0], curr.n_box[1, 1]]]) sw_node.n_box = np.array([[curr.n_box[0, 0], curr.n_box[0, 1]], [x_se, y_nw]]) se_node.n_box = np.array([[x_se, curr.n_box[0, 1]], [curr.n_box[1, 0], y_se]]) c_t = 0 for sub_node in [nw_node, ne_node, sw_node, se_node]: sub_node.n_depth = curr.n_depth + 1 sub_node.n_count = count_tmp[c_t] sub_node.n_budget = curr.n_budget stack.append(sub_node) c_t += 1 curr.nw, curr.ne, curr.sw, curr.se = nw_node, ne_node, sw_node, se_node # end of while logging.debug("number of leaves: %d" % nleaf) logging.debug("max depth: %d" % max_depth) def getCoordinates(self, curr): dim_1 = curr.n_depth % Params.NDIM # primary split dimension UNIT = Params.unitGrid x_min = int(np.rint((curr.n_box[0, 0] - self.root.n_box[0, 0]) / UNIT)) x_max = int(np.rint((curr.n_box[1, 0] - self.root.n_box[0, 0]) / UNIT)) y_min = int(np.rint((curr.n_box[0, 1] - self.root.n_box[0, 1]) / UNIT)) y_max = int(np.rint((curr.n_box[1, 1] - self.root.n_box[0, 1]) / UNIT)) total = np.sum(self.mapp[x_min:x_max, y_min:y_max]) if dim_1 == 0: for i in range(x_max - x_min): if np.sum(self.mapp[x_min:x_min + i + 1, y_min:y_max]) >= total / 2: break split_prm = (x_min + i + 1) * UNIT + self.root.n_box[0, 0] half_1 = np.sum(self.mapp[x_min:x_min + i + 1, y_min:y_max]) half_2 = np.sum(self.mapp[x_min + i + 1:x_max, y_min:y_max]) for j in range(y_max - y_min): if np.sum(self.mapp[x_min:x_min + i + 1, y_min:y_min + j + 1]) >= half_1 / 2: break split_sec1 = self.root.n_box[0, 1] + (y_min + j + 1) * UNIT n_sw = np.sum(self.mapp[x_min:x_min + i + 1, y_min:y_min + j + 1]) n_nw = np.sum(self.mapp[x_min:x_min + i + 1, y_min + j + 1:y_max]) for k in range(y_max - y_min): if np.sum(self.mapp[x_min + i + 1:x_max, y_min:y_min + k + 1]) >= half_2 / 2: break split_sec2 = self.root.n_box[0, 1] + (y_min + k + 1) * UNIT n_se = np.sum(self.mapp[x_min + i + 1:x_max, y_min:y_min + k + 1]) n_ne = np.sum(self.mapp[x_min + i + 1:x_max, y_min + k + 1:y_max]) return (split_prm, split_sec1), (split_prm, split_sec2), (n_nw, n_ne, n_sw, n_se) else: for i in range(y_max - y_min): if np.sum(self.mapp[x_min:x_max, y_min:y_min + i + 1]) >= total / 2: break split_prm = self.root.n_box[0, 1] + (y_min + i + 1) * UNIT half_1 = np.sum(self.mapp[x_min:x_max, y_min:y_min + i + 1]) half_2 = np.sum(self.mapp[x_min:x_max, y_min + i + 1:y_max]) for j in range(x_max - x_min): if np.sum(self.mapp[x_min:x_min + j + 1, y_min:y_min + i + 1]) >= half_1 / 2: break split_sec1 = (x_min + j + 1) * UNIT + self.root.n_box[0, 0] n_sw = np.sum(self.mapp[x_min:x_min + j + 1, y_min:y_min + i + 1]) n_se = np.sum(self.mapp[x_min + j + 1:x_max, y_min:y_min + i + 1]) for k in range(x_max - x_min): if np.sum(self.mapp[x_min:x_min + k + 1, y_min + i + 1:y_max]) >= half_2 / 2: break split_sec2 = (x_min + k + 1) * UNIT + self.root.n_box[0, 0] n_nw = np.sum(self.mapp[x_min:x_min + k + 1, y_min + i + 1:y_max]) n_ne = np.sum(self.mapp[x_min + k + 1:x_max, y_min + i + 1:y_max]) return (split_sec2, split_prm), (split_sec1, split_prm), (n_nw, n_ne, n_sw, n_se) def populate_synthetic_tree(self): """ Populate real data to the synthetic tree """ logging.debug('populating synthetic tree...') a_data = self.realData ndata = a_data.shape[1] for i in range(ndata): ptx = a_data[0, i] pty = a_data[1, i] leaf = self.root.find_subnode(ptx, pty) leaf.n_count += 1 # traverse the tree and update leaf counts stack = deque() stack.append(self.root) while len(stack) > 0: cur_node = stack.popleft() if cur_node.n_isLeaf is True: # leaf cur_node.n_count += self.differ.getNoise( 1, 0.5 * self.param.Eps) else: stack.append(cur_node.nw) stack.append(cur_node.ne) stack.append(cur_node.sw) stack.append(cur_node.se)
class KTree(object): """Generic tree template""" def __init__(self, data, param): self.param = param self.differ = Differential(self.param.Seed) # ## initialize the root self.root = KNode() self.root.n_data = data self.root.n_box = np.array([Params.LOW, Params.HIGH]) self.root.n_budget = Params.maxHeight def getSplitBudget(self): """return a list of h budget values for split""" raise NotImplementedError def getCountBudget(self): """return a list of (h+1) budget values for noisy count""" raise NotImplementedError def getNoisyMedian(self, array, left, right, epsilon): """return the split value of an array""" raise NotImplementedError def getCoordinates(self, curr): """ return the coordinate of lower-right point of the NW sub-node and the upper-left point of the SW sub-node and the data points in the four subnodes, i.e. return (x_nw,y_nw),(x_se,y_se), nw_data, ne_data, sw_data, se_data """ raise NotImplementedError def getSplit(self, array, left, right, epsilon): """ return the split point given an array, may be data-independent or true median or noisy median, depending on the type of the tree """ raise NotImplementedError def getCount(self, curr, epsilon): """ return true count or noisy count of a node, depending on epsilon""" if curr.n_data is None: count = 0 else: count = curr.n_data.shape[1] if epsilon < 10 ** (-6): return count else: return count + self.differ.getNoise(1, epsilon) def testLeaf(self, curr): """ test whether a node should be a leaf node """ if (curr.n_depth == Params.maxHeight) or \ (curr.n_budget <= 0) or \ (curr.n_data is None or curr.n_data.shape[1] == 0) or \ (curr.n_count <= self.param.minPartSize): return True return False def cell_setLeaf(self, curr): """ will be overrided in kd_cell """ return def buildIndex(self): """ Function to build the tree structure, fanout = 4 by default for spatial (2D) data """ budget_c = self.getCountBudget() self.root.n_count = self.getCount(self.root, budget_c[0]) # ## add noisy count to root stack = deque() stack.append(self.root) nleaf = 0 # ## leaf counter max_depth = -1 # ## main loop while len(stack) > 0: curr = stack.popleft() if curr.n_depth > max_depth: max_depth = curr.n_depth if self.testLeaf(curr) is True: # ## curr is a leaf node if curr.n_depth < Params.maxHeight: # ## if a node ends up earlier than maxHeight, it should be able to use the remaining count budget remainingEps = sum(budget_c[curr.n_depth + 1:]) curr.n_count = self.getCount(curr, remainingEps) nleaf += 1 curr.n_isLeaf = True self.cell_setLeaf(curr) else: # ## curr needs to split curr.n_budget -= 1 # ## some budget will be used regardless the split is successful or not tmp = self.getCoordinates(curr) nw_node, ne_node, sw_node, se_node = KNode(), KNode(), KNode(), KNode() # create sub-nodes nw_coord, ne_coord, nw_node.n_data, ne_node.n_data, sw_node.n_data, se_node.n_data = tmp x_nw, y_nw = nw_coord x_se, y_se = ne_coord # ## update bounding box, depth, count, budget for the four subnodes nw_node.n_box = np.array([[curr.n_box[0, 0], y_nw], [x_nw, curr.n_box[1, 1]]]) ne_node.n_box = np.array([[x_nw, y_se], [curr.n_box[1, 0], curr.n_box[1, 1]]]) sw_node.n_box = np.array([[curr.n_box[0, 0], curr.n_box[0, 1]], [x_se, y_nw]]) se_node.n_box = np.array([[x_se, curr.n_box[0, 1]], [curr.n_box[1, 0], y_se]]) for sub_node in [nw_node, ne_node, sw_node, se_node]: sub_node.n_depth = curr.n_depth + 1 # if (sub_node.n_depth == Params.maxHeight and sub_node.n_data is not None): # print len(sub_node.n_data[0]) sub_node.n_count = self.getCount(sub_node, budget_c[sub_node.n_depth]) sub_node.n_budget = curr.n_budget stack.append(sub_node) curr.n_data = None # ## do not need the data points coordinates now curr.nw, curr.ne, curr.sw, curr.se = nw_node, ne_node, sw_node, se_node # end of while logging.debug("number of leaves: %d" % nleaf) logging.debug("max depth: %d" % max_depth) def rect_intersect(self, hrect, query): """ checks if the hyper-rectangle intersects with the hyper-rectangle defined by the query in every dimension """ bool_m1 = query[0, :] >= hrect[1, :] bool_m2 = query[1, :] <= hrect[0, :] bool_m = np.logical_or(bool_m1, bool_m2) if np.any(bool_m): return False else: return True def rangeCount(self, query): """ Query answering function. Find the number of data points within a query rectangle. """ stack = deque() stack.append(self.root) count = 0.0 # ## Below are three variables recording the number of 1) whole leaf 2) partial leaf 3) whole internal node, # ## respectively, which contribute to the query answer. For debug purpose only. l_whole, l_part, i_whole = 0, 0, 0 while len(stack) > 0: curr = stack.popleft() _box = curr.n_box if curr.n_isLeaf is True: frac = 1 if self.rect_intersect(_box, query): for i in range(_box.shape[1]): if _box[1, i] == _box[0, i] or Params.WorstCase == True: frac *= 1 else: frac *= (min(query[1, i], _box[1, i]) - max(query[0, i], _box[0, i])) / ( _box[1, i] - _box[0, i]) count += curr.n_count * frac if 1.0 - frac < 10 ** (-6): l_whole += 1 else: l_part += 1 else: # ## if not leaf bool_matrix = np.zeros((2, query.shape[1])) bool_matrix[0, :] = query[0, :] <= _box[0, :] bool_matrix[1, :] = query[1, :] >= _box[1, :] if np.all(bool_matrix) and self.param.useLeafOnly is False: # ## if query range contains node range count += curr.n_count i_whole += 1 else: if self.rect_intersect(curr.nw.n_box, query): stack.append(curr.nw) if self.rect_intersect(curr.ne.n_box, query): stack.append(curr.ne) if self.rect_intersect(curr.sw.n_box, query): stack.append(curr.sw) if self.rect_intersect(curr.se.n_box, query): stack.append(curr.se) return float(count) # , i_whole, l_whole, l_part def adjustConsistency(self): """ Post processing for uniform noise across levels. Due to Michael Hay, Vibhor Rastogi, Gerome Miklau, Dan Suciu, Boosting the Accuracy of Differentially-Private Histograms Through Consistency, VLDB 2010 """ logging.debug('adjusting consistency...') # ## upward pass self.root.get_z() # ## downward pass queue = deque() queue.append(self.root) while len(queue) > 0: curr = queue.popleft() if curr.n_isLeaf is False: adjust = (curr.n_count - curr.nw.n_count - curr.ne.n_count - curr.sw.n_count - curr.se.n_count) / 4.0 for subnode in [curr.nw, curr.ne, curr.sw, curr.se]: subnode.n_count += adjust queue.append(subnode) def postProcessing(self): """ Post processing for general noise distribution across levels. Due to G. Cormode, M. Procopiuc, E. Shen, D. Srivastava and T. Yu, Differentially Private Spatial Decompositions, ICDE 2012. """ logging.debug("post-processing...") budget = self.getCountBudget() # ## count budget for h+1 levels H = Params.maxHeight # ## Phase 1 (top-down) queue = deque() self.root.n_count *= budget[self.root.n_depth] ** 2 queue.append(self.root) while len(queue) > 0: curr = queue.popleft() if curr.n_isLeaf is False: for subnode in [curr.nw, curr.ne, curr.sw, curr.se]: subnode.n_count = curr.n_count + subnode.n_count * (budget[subnode.n_depth] ** 2) queue.append(subnode) # ## Phase 2 (bottom-up) self.root.update_count() # ## Phase 3 (top-down) queue = deque() E_root = 0 for i in range(H + 1): E_root += 4 ** i * budget[H - i] * budget[H - i] self.root.n_count /= E_root self.root.n_F = 0 queue.append(self.root) while len(queue) > 0: curr = queue.popleft() if curr.n_isLeaf is False: h = H - curr.n_depth - 1 # ## height of curr's children E_h = 0 for i in range(h + 1): E_h += 4 ** i * budget[H - i] * budget[H - i] for subnode in [curr.nw, curr.ne, curr.sw, curr.se]: subnode.n_F = curr.n_F + curr.n_count * (budget[curr.n_depth] ** 2) subnode.n_count = (subnode.n_count - 4 ** h * subnode.n_F) / E_h queue.append(subnode) def pruning(self): """ If the tree is grown without the stopping condition of minLeafSize, prune it here after post processing """ logging.debug("pruning...") queue = deque() queue.append(self.root) while len(queue) > 0: curr = queue.popleft() if curr.n_isLeaf is False: if curr.n_count <= self.param.minPartSize: curr.n_isLeaf = True else: queue.append(curr.nw) queue.append(curr.ne) queue.append(curr.sw) queue.append(curr.se)
def buildIndex(self): budget_c = self.getCountBudget() logging.debug('encoding coordinates...') RES = self.param.Res # order of Hilbert curve ndata = self.realData.shape[1] hidx = np.zeros(ndata) for i in range(ndata): hx, hy = self.get_Hcoord(self.realData[0, i], self.realData[1, i], RES) hidx[i] = self.h_encode(hx, hy, RES) hidx = np.sort(hidx) logging.debug('building index...') self.root.n_data = hidx self.root.n_box = (0, 2**(2 * RES) - 1) self.root.n_count = self.getCount(self.root, budget_c[0]) stack = deque() stack.append(self.root) tree = [self.root] leaf_li = [] # storage of all leaves nleaf = 0 # leaf counter max_depth = -1 while len(stack) > 0: curr = stack.popleft() if curr.n_depth > max_depth: max_depth = curr.n_depth if self.testLeaf(curr) is True: # curr is a leaf node if curr.n_depth < Params.maxHeight: remainingEps = sum(budget_c[curr.n_depth + 1:]) curr.n_count = self.getCount(curr, remainingEps) nleaf += 1 curr.n_isLeaf = True leaf_li.append(curr) else: # curr needs to split curr.n_budget -= 1 tmp = self.getCoordinates(curr) if tmp is False: # if split fails stack.append(curr) continue nw_node, ne_node, sw_node, se_node = KNode(), KNode(), KNode( ), KNode() # create sub-nodes split_prm, split_sec1, split_sec2, nw_node.n_data, ne_node.n_data, sw_node.n_data, se_node.n_data = tmp nw_node.n_box = (curr.n_box[0], split_sec1) ne_node.n_box = (split_sec1, split_prm) sw_node.n_box = (split_prm, split_sec2) se_node.n_box = (split_sec2, curr.n_box[1]) for sub_node in [nw_node, ne_node, sw_node, se_node]: sub_node.n_depth = curr.n_depth + 1 sub_node.n_count = self.getCount( sub_node, budget_c[sub_node.n_depth]) sub_node.n_budget = curr.n_budget stack.append(sub_node) tree.append(sub_node) curr.n_data = None curr.nw, curr.ne, curr.sw, curr.se = nw_node, ne_node, sw_node, se_node # end of while logging.debug("number of leaves: %d" % nleaf) logging.debug("max depth: %d" % max_depth) # # convert hilbert values in leaf nodes to real coordinates and update bounding box logging.debug('decoding and updating bounding box...') for leaf in leaf_li: bbox = np.array([[1000.0, 1000.0], [-1000.0, -1000.0]], dtype='float64') for hvalue in leaf.n_data: hx, hy = self.h_decode(int(hvalue), RES) x, y = self.get_Rcoord(hx, hy, RES) bbox[0, 0] = x if x < bbox[0, 0] else bbox[0, 0] bbox[1, 0] = x if x > bbox[1, 0] else bbox[1, 0] bbox[0, 1] = y if y < bbox[0, 1] else bbox[0, 1] bbox[1, 1] = y if y > bbox[1, 1] else bbox[1, 1] leaf.n_box = bbox # # update bounding box bottom-up tree = sorted(tree, cmp=self.cmp_node) logging.debug('updating box for each node in the tree...') for node in tree: if node.n_data is None: node.n_box = np.zeros((2, 2)) node.n_box[0, 0] = min(node.ne.n_box[0, 0], node.nw.n_box[0, 0], node.se.n_box[0, 0], node.sw.n_box[0, 0]) node.n_box[0, 1] = min(node.ne.n_box[0, 1], node.nw.n_box[0, 1], node.se.n_box[0, 1], node.sw.n_box[0, 1]) node.n_box[1, 0] = max(node.ne.n_box[1, 0], node.nw.n_box[1, 0], node.se.n_box[1, 0], node.sw.n_box[1, 0]) node.n_box[1, 1] = max(node.ne.n_box[1, 1], node.nw.n_box[1, 1], node.se.n_box[1, 1], node.sw.n_box[1, 1])
def buildIndex(self): budget_c = self.getCountBudget() logging.debug('encoding coordinates...') RES = self.param.Res # order of Hilbert curve ndata = self.realData.shape[1] hidx = np.zeros(ndata) for i in range(ndata): hx, hy = self.get_Hcoord(self.realData[0, i], self.realData[1, i], RES) hidx[i] = self.h_encode(hx, hy, RES) hidx = np.sort(hidx) logging.debug('building index...') self.root.n_data = hidx self.root.n_box = (0, 2 ** (2 * RES) - 1) self.root.n_count = self.getCount(self.root, budget_c[0]) stack = deque() stack.append(self.root) tree = [self.root] leaf_li = [] # storage of all leaves nleaf = 0 # leaf counter max_depth = -1 while len(stack) > 0: curr = stack.popleft() if curr.n_depth > max_depth: max_depth = curr.n_depth if self.testLeaf(curr) is True: # curr is a leaf node if curr.n_depth < Params.maxHeight: remainingEps = sum(budget_c[curr.n_depth + 1:]) curr.n_count = self.getCount(curr, remainingEps) nleaf += 1 curr.n_isLeaf = True leaf_li.append(curr) else: # curr needs to split curr.n_budget -= 1 tmp = self.getCoordinates(curr) if tmp is False: # if split fails stack.append(curr) continue nw_node, ne_node, sw_node, se_node = KNode(), KNode(), KNode(), KNode() # create sub-nodes split_prm, split_sec1, split_sec2, nw_node.n_data, ne_node.n_data, sw_node.n_data, se_node.n_data = tmp nw_node.n_box = (curr.n_box[0], split_sec1) ne_node.n_box = (split_sec1, split_prm) sw_node.n_box = (split_prm, split_sec2) se_node.n_box = (split_sec2, curr.n_box[1]) for sub_node in [nw_node, ne_node, sw_node, se_node]: sub_node.n_depth = curr.n_depth + 1 sub_node.n_count = self.getCount(sub_node, budget_c[sub_node.n_depth]) sub_node.n_budget = curr.n_budget stack.append(sub_node) tree.append(sub_node) curr.n_data = None curr.nw, curr.ne, curr.sw, curr.se = nw_node, ne_node, sw_node, se_node # end of while logging.debug("number of leaves: %d" % nleaf) logging.debug("max depth: %d" % max_depth) # # convert hilbert values in leaf nodes to real coordinates and update bounding box logging.debug('decoding and updating bounding box...') for leaf in leaf_li: bbox = np.array([[1000.0, 1000.0], [-1000.0, -1000.0]], dtype='float64') for hvalue in leaf.n_data: hx, hy = self.h_decode(int(hvalue), RES) x, y = self.get_Rcoord(hx, hy, RES) bbox[0, 0] = x if x < bbox[0, 0] else bbox[0, 0] bbox[1, 0] = x if x > bbox[1, 0] else bbox[1, 0] bbox[0, 1] = y if y < bbox[0, 1] else bbox[0, 1] bbox[1, 1] = y if y > bbox[1, 1] else bbox[1, 1] leaf.n_box = bbox # # update bounding box bottom-up tree = sorted(tree, cmp=self.cmp_node) logging.debug('updating box for each node in the tree...') for node in tree: if node.n_data is None: node.n_box = np.zeros((2, 2)) node.n_box[0, 0] = min(node.ne.n_box[0, 0], node.nw.n_box[0, 0], node.se.n_box[0, 0], node.sw.n_box[0, 0]) node.n_box[0, 1] = min(node.ne.n_box[0, 1], node.nw.n_box[0, 1], node.se.n_box[0, 1], node.sw.n_box[0, 1]) node.n_box[1, 0] = max(node.ne.n_box[1, 0], node.nw.n_box[1, 0], node.se.n_box[1, 0], node.sw.n_box[1, 0]) node.n_box[1, 1] = max(node.ne.n_box[1, 1], node.nw.n_box[1, 1], node.se.n_box[1, 1], node.sw.n_box[1, 1])
class Kd_cell(Kd_pure): """ Kd tree based on syntatic data generation and a grid structure. See Y. Xiao, L. Xiong, and C. Yuan, Differentially private data release through multidimensional partitioning, in SDM Workshop, VLDB, 2010 """ def __init__(self, data, param): self.param = param self.differ = Differential(self.param.Seed) self.mapp = None self.root = KNode() self.realData = data self.root.n_box = None self.root.n_budget = Params.maxHeight def getCountBudget(self): count_eps = self.param.Eps * 0.5 H = Params.maxHeight if self.param.geoBudget == 'none': return [count_eps / (H + 1) for _ in range(H + 1)] elif self.param.geoBudget == 'aggressive': unit = count_eps / (2 ** (H + 1) - 1) return [unit * 2 ** i for i in range(H + 1)] elif self.param.geoBudget == 'quadratic': unit = count_eps * (np.sqrt(2) - 1) / (2 ** (0.5 * (H + 1)) - 1) return [unit * 2 ** (0.5 * i) for i in range(H + 1)] elif self.param.geoBudget == 'optimal': unit = count_eps * ((2 ** (1.0 / 3)) - 1) / (2 ** ((1.0 / 3) * (H + 1)) - 1) return [unit * 2 ** ((1.0 / 3) * i) for i in range(H + 1)] elif self.param.geoBudget == 'quartic': unit = count_eps * ((2 ** (1.0 / 4)) - 1) / (2 ** ((1.0 / 4) * (H + 1)) - 1) return [unit * 2 ** ((1.0 / 4) * i) for i in range(H + 1)] else: logging.error('No such geoBudget scheme') sys.exit(1) def synthetic_gen(self): """Apply a grid structure on the domain and perturb the count using half of the available privacy budget """ logging.debug('generating synthetic map...') data = self.realData unit = Params.unitGrid x_min = np.floor(Params.LOW[0] / unit) * unit x_max = np.ceil(Params.HIGH[0] / unit) * unit y_min = np.floor(Params.LOW[1] / unit) * unit y_max = np.ceil(Params.HIGH[1] / unit) * unit x_CELL = int(np.rint((x_max - x_min) / unit)) y_CELL = int(np.rint((y_max - y_min) / unit)) self.root.n_box = np.array([[x_min, y_min], [x_max, y_max]]) self.mapp = np.zeros((x_CELL, y_CELL)) - 1 # ## initialize every cell with -1 for i in range(Params.NDATA): # ## populate the map point = data[:, i] cell_x = int(np.floor((point[0] - x_min) / unit)) cell_y = int(np.floor((point[1] - y_min) / unit)) if self.mapp[cell_x, cell_y] != -1: self.mapp[cell_x, cell_y] += 1 else: self.mapp[cell_x, cell_y] = 1 for i in range(x_CELL): # ## perturb the counts for j in range(y_CELL): if self.mapp[i, j] != -1: self.mapp[i, j] += np.rint(self.differ.getNoise(1, 0.5 * self.param.Eps)) else: self.mapp[i, j] = np.rint(self.differ.getNoise(1, 0.5 * self.param.Eps)) # if noisy count is negative, ignore the noise and generate no points if self.mapp[i, j] < 0: self.mapp[i, j] = 0 def cell_setLeaf(self, curr): """ Throw away the counts based on the syntatic data """ curr.n_count = 0 return def testLeaf(self, curr): if (curr.n_count <= self.param.minPartSize) or (curr.n_depth == Params.maxHeight) or ( self.uniform_test(curr, self.param.cellDistance)): return True return False def uniform_test(self, curr, distance): """ One of the stopping conditions: cell is uniform according to some threshold 'distance') """ unit = Params.unitGrid x_min = int(np.rint((curr.n_box[0, 0] - self.root.n_box[0, 0]) / unit)) x_max = int(np.rint((curr.n_box[1, 0] - self.root.n_box[0, 0]) / unit)) y_min = int(np.rint((curr.n_box[0, 1] - self.root.n_box[0, 1]) / unit)) y_max = int(np.rint((curr.n_box[1, 1] - self.root.n_box[0, 1]) / unit)) data = self.mapp[x_min:x_max, y_min:y_max] total = np.sum(data) avg = total / ((x_max - x_min) * (y_max - y_min)) dist = np.sum(np.abs(data - avg)) if dist > distance: return False else: return True def buildIndex(self): stack = deque() stack.append(self.root) nleaf = 0 # leaf counter max_depth = -1 self.root.n_count = np.sum(self.mapp) while len(stack) > 0: curr = stack.popleft() if curr.n_depth > max_depth: max_depth = curr.n_depth if self.testLeaf(curr) is True: # curr is a leaf node nleaf += 1 curr.n_isLeaf = True self.cell_setLeaf(curr) else: # curr needs to split curr.n_budget -= 1 tmp = self.getCoordinates(curr) nw_node, ne_node, sw_node, se_node = KNode(), KNode(), KNode(), KNode() # create sub-nodes nw_coord, ne_coord, count_tmp = tmp x_nw, y_nw = nw_coord x_se, y_se = ne_coord nw_node.n_box = np.array([[curr.n_box[0, 0], y_nw], [x_nw, curr.n_box[1, 1]]]) ne_node.n_box = np.array([[x_nw, y_se], [curr.n_box[1, 0], curr.n_box[1, 1]]]) sw_node.n_box = np.array([[curr.n_box[0, 0], curr.n_box[0, 1]], [x_se, y_nw]]) se_node.n_box = np.array([[x_se, curr.n_box[0, 1]], [curr.n_box[1, 0], y_se]]) c_t = 0 for sub_node in [nw_node, ne_node, sw_node, se_node]: sub_node.n_depth = curr.n_depth + 1 sub_node.n_count = count_tmp[c_t] sub_node.n_budget = curr.n_budget stack.append(sub_node) c_t += 1 curr.nw, curr.ne, curr.sw, curr.se = nw_node, ne_node, sw_node, se_node # end of while logging.debug("number of leaves: %d" % nleaf) logging.debug("max depth: %d" % max_depth) def getCoordinates(self, curr): dim_1 = curr.n_depth % Params.NDIM # primary split dimension UNIT = Params.unitGrid x_min = int(np.rint((curr.n_box[0, 0] - self.root.n_box[0, 0]) / UNIT)) x_max = int(np.rint((curr.n_box[1, 0] - self.root.n_box[0, 0]) / UNIT)) y_min = int(np.rint((curr.n_box[0, 1] - self.root.n_box[0, 1]) / UNIT)) y_max = int(np.rint((curr.n_box[1, 1] - self.root.n_box[0, 1]) / UNIT)) total = np.sum(self.mapp[x_min:x_max, y_min:y_max]) if dim_1 == 0: for i in range(x_max - x_min): if np.sum(self.mapp[x_min:x_min + i + 1, y_min:y_max]) >= total / 2: break split_prm = (x_min + i + 1) * UNIT + self.root.n_box[0, 0] half_1 = np.sum(self.mapp[x_min:x_min + i + 1, y_min:y_max]) half_2 = np.sum(self.mapp[x_min + i + 1:x_max, y_min:y_max]) for j in range(y_max - y_min): if np.sum(self.mapp[x_min:x_min + i + 1, y_min:y_min + j + 1]) >= half_1 / 2: break split_sec1 = self.root.n_box[0, 1] + (y_min + j + 1) * UNIT n_sw = np.sum(self.mapp[x_min:x_min + i + 1, y_min:y_min + j + 1]) n_nw = np.sum(self.mapp[x_min:x_min + i + 1, y_min + j + 1:y_max]) for k in range(y_max - y_min): if np.sum(self.mapp[x_min + i + 1:x_max, y_min:y_min + k + 1]) >= half_2 / 2: break split_sec2 = self.root.n_box[0, 1] + (y_min + k + 1) * UNIT n_se = np.sum(self.mapp[x_min + i + 1:x_max, y_min:y_min + k + 1]) n_ne = np.sum(self.mapp[x_min + i + 1:x_max, y_min + k + 1:y_max]) return (split_prm, split_sec1), (split_prm, split_sec2), (n_nw, n_ne, n_sw, n_se) else: for i in range(y_max - y_min): if np.sum(self.mapp[x_min:x_max, y_min:y_min + i + 1]) >= total / 2: break split_prm = self.root.n_box[0, 1] + (y_min + i + 1) * UNIT half_1 = np.sum(self.mapp[x_min:x_max, y_min:y_min + i + 1]) half_2 = np.sum(self.mapp[x_min:x_max, y_min + i + 1:y_max]) for j in range(x_max - x_min): if np.sum(self.mapp[x_min:x_min + j + 1, y_min:y_min + i + 1]) >= half_1 / 2: break split_sec1 = (x_min + j + 1) * UNIT + self.root.n_box[0, 0] n_sw = np.sum(self.mapp[x_min:x_min + j + 1, y_min:y_min + i + 1]) n_se = np.sum(self.mapp[x_min + j + 1:x_max, y_min:y_min + i + 1]) for k in range(x_max - x_min): if np.sum(self.mapp[x_min:x_min + k + 1, y_min + i + 1:y_max]) >= half_2 / 2: break split_sec2 = (x_min + k + 1) * UNIT + self.root.n_box[0, 0] n_nw = np.sum(self.mapp[x_min:x_min + k + 1, y_min + i + 1:y_max]) n_ne = np.sum(self.mapp[x_min + k + 1:x_max, y_min + i + 1:y_max]) return (split_sec2, split_prm), (split_sec1, split_prm), (n_nw, n_ne, n_sw, n_se) def populate_synthetic_tree(self): """ Populate real data to the synthetic tree """ logging.debug('populating synthetic tree...') a_data = self.realData ndata = a_data.shape[1] for i in range(ndata): ptx = a_data[0, i] pty = a_data[1, i] leaf = self.root.find_subnode(ptx, pty) leaf.n_count += 1 # traverse the tree and update leaf counts stack = deque() stack.append(self.root) while len(stack) > 0: cur_node = stack.popleft() if cur_node.n_isLeaf is True: # leaf cur_node.n_count += self.differ.getNoise(1, 0.5 * self.param.Eps) else: stack.append(cur_node.nw) stack.append(cur_node.ne) stack.append(cur_node.sw) stack.append(cur_node.se)