def parse_input(self, X): """Parse and create features for the `subgraph_matching` kernel. Parameters ---------- X : iterable For the input to pass the test, we must have: Each element must be an iterable with at most three features and at least one. The first that is obligatory is a valid graph structure (adjacency matrix or edge_dictionary) while the second is node_labels and the third edge_labels (that correspond to the given graph format). A valid input also consists of graph type objects. Returns ------- out : list The extracted adjacency matrices for any given input. """ if not isinstance(X, collections.Iterable): raise TypeError('input must be an iterable\n') else: i = 0 out = list() for (idx, x) in enumerate(iter(X)): is_iter = False if isinstance(x, collections.Iterable): is_iter = True x = list(x) if type(x) is Graph: g = Graph( x.get_adjacency_matrix(), x.get_labels(purpose="adjacency"), x.get_labels(purpose="adjacency", label_type="edge"), self._graph_format) elif is_iter and len(x) in [0, 3]: x = list(x) if len(x) == 0: warnings.warn('Ignoring empty element' + ' on index: ' + str(idx)) continue elif len(x) == 3: g = Graph(x[0], x[1], x[2], "adjacency") g.change_format(self._graph_format) else: raise TypeError('each element of X must be either a ' + 'graph object or a list with at least ' + 'a graph like object and node, ' + 'edge labels dict \n') n = g.nv() E = g.get_edge_dictionary() L = g.get_labels(purpose="dictionary", return_none=(self.kv is None)) Le = g.get_labels(purpose="dictionary", label_type="edge", return_none=(self.ke is None)) Er = set( (a, b) for a in E.keys() for b in E[a].keys() if a != b) i += 1 out.append((n, Er, L, Le)) if i == 0: raise ValueError('parsed input is empty') return out
def parse_input(self, X): """Parse input for weisfeiler lehman. Parameters ---------- X : iterable For the input to pass the test, we must have: Each element must be an iterable with at most three features and at least one. The first that is obligatory is a valid graph structure (adjacency matrix or edge_dictionary) while the second is node_labels and the third edge_labels (that correspond to the given graph format). A valid input also consists of graph type objects. Returns ------- base_kernel : object Returns base_kernel. """ if self._method_calling not in [1, 2]: raise ValueError('method call must be called either from fit ' + 'or fit-transform') elif hasattr(self, '_X_diag'): # Clean _X_diag value delattr(self, '_X_diag') # Input validation and parsing if not isinstance(X, collections.Iterable): raise TypeError('input must be an iterable\n') else: nx = 0 Gs_ed, L, distinct_values, extras = dict(), dict(), set(), dict() for (idx, x) in enumerate(iter(X)): is_iter = isinstance(x, collections.Iterable) if is_iter: x = list(x) if is_iter and (len(x) == 0 or len(x) >= 2): if len(x) == 0: warnings.warn('Ignoring empty element on index: ' + str(idx)) continue else: if len(x) > 2: extra = tuple() if len(x) > 3: extra = tuple(x[3:]) x = Graph(x[0], x[1], x[2], graph_format=self._graph_format) extra = (x.get_labels(purpose=self._graph_format, label_type="edge", return_none=True), ) + extra else: x = Graph(x[0], x[1], {}, graph_format=self._graph_format) extra = tuple() elif type(x) is Graph: x.desired_format(self._graph_format) el = x.get_labels(purpose=self._graph_format, label_type="edge", return_none=True) if el is None: extra = tuple() else: extra = (el, ) else: raise TypeError('each element of X must be either a ' + 'graph object or a list with at least ' + 'a graph like object and node labels ' + 'dict \n') Gs_ed[nx] = x.get_edge_dictionary() L[nx] = x.get_labels(purpose="dictionary") extras[nx] = extra distinct_values |= set(itervalues(L[nx])) nx += 1 if nx == 0: raise ValueError('parsed input is empty') # Save the number of "fitted" graphs. self._nx = nx # get all the distinct values of current labels WL_labels_inverse = dict() # assign a number to each label label_count = 0 for dv in sorted(list(distinct_values)): WL_labels_inverse[dv] = label_count label_count += 1 # Initalize an inverse dictionary of labels for all iterations self._inv_labels = dict() self._inv_labels[0] = WL_labels_inverse def generate_graphs(label_count, WL_labels_inverse): new_graphs = list() for j in range(nx): new_labels = dict() for k in L[j].keys(): new_labels[k] = WL_labels_inverse[L[j][k]] L[j] = new_labels # add new labels new_graphs.append((Gs_ed[j], new_labels) + extras[j]) yield new_graphs for i in range(1, self._n_iter): label_set, WL_labels_inverse, L_temp = set(), dict(), dict() for j in range(nx): # Find unique labels and sort # them for both graphs # Keep for each node the temporary L_temp[j] = dict() for v in Gs_ed[j].keys(): credential = str(L[j][v]) + "," + \ str(sorted([L[j][n] for n in Gs_ed[j][v].keys()])) L_temp[j][v] = credential label_set.add(credential) label_list = sorted(list(label_set)) for dv in label_list: WL_labels_inverse[dv] = label_count label_count += 1 # Recalculate labels new_graphs = list() for j in range(nx): new_labels = dict() for k in L_temp[j].keys(): new_labels[k] = WL_labels_inverse[L_temp[j][k]] L[j] = new_labels # relabel new_graphs.append((Gs_ed[j], new_labels) + extras[j]) self._inv_labels[i] = WL_labels_inverse yield new_graphs base_kernel = { i: self._base_kernel(**self._params) for i in range(self._n_iter) } if self._parallel is None: if self._method_calling == 1: for (i, g) in enumerate( generate_graphs(label_count, WL_labels_inverse)): base_kernel[i].fit(g) elif self._method_calling == 2: K = np.sum( (base_kernel[i].fit_transform(g) for (i, g) in enumerate( generate_graphs(label_count, WL_labels_inverse))), axis=0) else: if self._method_calling == 1: self._parallel( joblib.delayed(efit)(base_kernel[i], g) for (i, g) in enumerate( generate_graphs(label_count, WL_labels_inverse))) elif self._method_calling == 2: K = np.sum(self._parallel( joblib.delayed(efit_transform)(base_kernel[i], g) for (i, g) in enumerate( generate_graphs(label_count, WL_labels_inverse))), axis=0) if self._method_calling == 1: return base_kernel elif self._method_calling == 2: return K, base_kernel
def transform(self, X): """Calculate the kernel matrix, between given and fitted dataset. Parameters ---------- X : iterable Each element must be an iterable with at most three features and at least one. The first that is obligatory is a valid graph structure (adjacency matrix or edge_dictionary) while the second is node_labels and the third edge_labels (that fitting the given graph format). If None the kernel matrix is calculated upon fit data. The test samples. Returns ------- K : numpy array, shape = [n_targets, n_input_graphs] corresponding to the kernel matrix, a calculation between all pairs of graphs between target an features """ self._method_calling = 3 # Check is fit had been called check_is_fitted(self, ['X', '_nx', '_inv_labels']) # Input validation and parsing if X is None: raise ValueError('transform input cannot be None') else: if not isinstance(X, collections.Iterable): raise ValueError('input must be an iterable\n') else: nx = 0 distinct_values = set() Gs_ed, L = dict(), dict() for (i, x) in enumerate(iter(X)): is_iter = isinstance(x, collections.Iterable) if is_iter: x = list(x) if is_iter and len(x) in [0, 2, 3]: if len(x) == 0: warnings.warn('Ignoring empty element on index: ' + str(i)) continue elif len(x) in [2, 3]: x = Graph(x[0], x[1], {}, self._graph_format) elif type(x) is Graph: x.desired_format("dictionary") else: raise ValueError('each element of X must have at ' + 'least one and at most 3 elements\n') Gs_ed[nx] = x.get_edge_dictionary() L[nx] = x.get_labels(purpose="dictionary") # Hold all the distinct values distinct_values |= set(v for v in itervalues(L[nx]) if v not in self._inv_labels[0]) nx += 1 if nx == 0: raise ValueError('parsed input is empty') nl = len(self._inv_labels[0]) WL_labels_inverse = { dv: idx for (idx, dv) in enumerate(sorted(list(distinct_values)), nl) } def generate_graphs(WL_labels_inverse, nl): # calculate the kernel matrix for the 0 iteration new_graphs = list() for j in range(nx): new_labels = dict() for (k, v) in iteritems(L[j]): if v in self._inv_labels[0]: new_labels[k] = self._inv_labels[0][v] else: new_labels[k] = WL_labels_inverse[v] L[j] = new_labels # produce the new graphs new_graphs.append([Gs_ed[j], new_labels]) yield new_graphs for i in range(1, self._n_iter): new_graphs = list() L_temp, label_set = dict(), set() nl += len(self._inv_labels[i]) for j in range(nx): # Find unique labels and sort them for both graphs # Keep for each node the temporary L_temp[j] = dict() for v in Gs_ed[j].keys(): credential = str(L[j][v]) + "," + \ str(sorted([L[j][n] for n in Gs_ed[j][v].keys()])) L_temp[j][v] = credential if credential not in self._inv_labels[i]: label_set.add(credential) # Calculate the new label_set WL_labels_inverse = dict() if len(label_set) > 0: for dv in sorted(list(label_set)): idx = len(WL_labels_inverse) + nl WL_labels_inverse[dv] = idx # Recalculate labels new_graphs = list() for j in range(nx): new_labels = dict() for (k, v) in iteritems(L_temp[j]): if v in self._inv_labels[i]: new_labels[k] = self._inv_labels[i][v] else: new_labels[k] = WL_labels_inverse[v] L[j] = new_labels # Create the new graphs with the new labels. new_graphs.append([Gs_ed[j], new_labels]) yield new_graphs if self._parallel is None: # Calculate the kernel matrix without parallelization K = np.sum( (self.X[i].transform(g) for (i, g) in enumerate(generate_graphs(WL_labels_inverse, nl))), axis=0) else: # Calculate the kernel marix with parallelization K = np.sum(self._parallel( joblib.delayed(etransform)(self.X[i], g) for (i, g) in enumerate(generate_graphs(WL_labels_inverse, nl))), axis=0) self._is_transformed = True if self.normalize: X_diag, Y_diag = self.diagonal() old_settings = np.seterr(divide='ignore') K = np.nan_to_num(np.divide(K, np.sqrt(np.outer(Y_diag, X_diag)))) np.seterr(**old_settings) return K
def parse_input( self, X, ): """Parse input for weisfeiler lehman. Parameters ---------- X : iterable For the input to pass the test, we must have: Each element must be an iterable with at most three features and at least one. The first that is obligatory is a valid graph structure (adjacency matrix or edge_dictionary) while the second is node_labels and the third edge_labels (that correspond to the given graph format). A valid input also consists of graph type objects. return_embedding_only: bool Whether to return the embedding of the graphs only, instead of computing the kernel all the way to the end. Returns ------- base_graph_kernel : object Returns base_graph_kernel. """ if self._method_calling not in [1, 2]: raise ValueError('method call must be called either from fit ' + 'or fit-transform') elif hasattr(self, '_X_diag'): # Clean _X_diag value delattr(self, '_X_diag') # Input validation and parsing if not isinstance(X, collections.Iterable): raise TypeError('input must be an iterable\n') else: nx = 0 Gs_ed, L, distinct_values, extras = dict(), dict(), set(), dict() for (idx, x) in enumerate(iter(X)): is_iter = isinstance(x, collections.Iterable) if is_iter: x = list(x) if is_iter and (len(x) == 0 or len(x) >= 2): if len(x) == 0: warnings.warn('Ignoring empty element on index: ' + str(idx)) continue else: if len(x) > 2: extra = tuple() if len(x) > 3: extra = tuple(x[3:]) x = Graph(x[0], x[1], x[2], graph_format=self._graph_format) extra = (x.get_labels(purpose=self._graph_format, label_type="edge", return_none=True), ) + extra else: x = Graph(x[0], x[1], {}, graph_format=self._graph_format) extra = tuple() elif type(x) is Graph: x.desired_format(self._graph_format) el = x.get_labels(purpose=self._graph_format, label_type="edge", return_none=True) if el is None: extra = tuple() else: extra = (el, ) else: raise TypeError('each element of X must be either a ' + 'graph object or a list with at least ' + 'a graph like object and node labels ' + 'dict \n') Gs_ed[nx] = x.get_edge_dictionary() L[nx] = x.get_labels(purpose="dictionary") extras[nx] = extra distinct_values |= set(itervalues(L[nx])) nx += 1 if nx == 0: raise ValueError('parsed input is empty') # Save the number of "fitted" graphs. self._nx = nx WL_labels_inverse = OrderedDict() # assign a number to each label label_count = 0 for dv in sorted(list(distinct_values)): WL_labels_inverse[dv] = label_count label_count += 1 # Initalize an inverse dictionary of labels for all iterations self._inv_labels = OrderedDict( ) # Inverse dictionary of labels, in term of the *previous layer* self._inv_labels[0] = deepcopy(WL_labels_inverse) self.feature_dims.append( len(WL_labels_inverse)) # Update the zeroth iteration feature dim # self._inv_label_node_attr = OrderedDict() # Inverse dictionary of labels, in term of the *node attribute* # self._label_node_attr = OrderedDict() # Same as above, but with key and value inverted # self._label_node_attr[0], self._inv_label_node_attr[0] = self.translate_label(WL_labels_inverse, 0) # if self.node_weights is not None: # self._feature_weight = OrderedDict() # # Ensure the order is the same # self._feature_weight[0] = self._compute_feature_weight(self.node_weights, 0, WL_labels_inverse)[1] # else: # self._feature_weight = None def generate_graphs(label_count, WL_labels_inverse): new_graphs = list() for j in range(self._nx): new_labels = dict() for k in L[j].keys(): new_labels[k] = WL_labels_inverse[L[j][k]] L[j] = new_labels # add new labels new_graphs.append((Gs_ed[j], new_labels) + extras[j]) yield new_graphs for i in range(1, self._h): label_set, WL_labels_inverse, L_temp = set(), dict(), dict() for j in range(nx): # Find unique labels and sort # them for both graphs # Keep for each node the temporary L_temp[j] = dict() for v in Gs_ed[j].keys(): credential = str(L[j][v]) + "," + \ str(sorted([L[j][n] for n in Gs_ed[j][v].keys()])) L_temp[j][v] = credential label_set.add(credential) label_list = sorted(list(label_set)) for dv in label_list: WL_labels_inverse[dv] = label_count label_count += 1 # Recalculate labels new_graphs = list() for j in range(nx): new_labels = dict() for k in L_temp[j].keys(): new_labels[k] = WL_labels_inverse[L_temp[j][k]] L[j] = new_labels # relabel new_graphs.append((Gs_ed[j], new_labels) + extras[j]) self._inv_labels[i] = WL_labels_inverse # Compute the translated inverse node label # self._label_node_attr[i], self._inv_label_node_attr[i] = self.translate_label(WL_labels_inverse, i, self._label_node_attr[i - 1]) # self.feature_dims.append(self.feature_dims[-1] + len(self._label_node_attr[i])) # Compute the feature weight of the current layer # if self.node_weights is not None: # self._feature_weight[i] = self._compute_feature_weight(self.node_weights, i, self._inv_label_node_attr[i])[1] # assert len(self._feature_weight[i] == len(WL_labels_inverse)) yield new_graphs # Initialise the base graph kernel. base_graph_kernel = {} K = [] for (i, g) in enumerate(generate_graphs(label_count, WL_labels_inverse)): param = self._params # if self._feature_weight is not None: # print(self._feature_weight) # param.update({'mahalanobis_precision': self._feature_weight[i]}) base_graph_kernel.update({i: self._base_graph_kernel(**param)}) # if return_embedding_only: # K.append(base_graph_kernel[i].parse_input( # g, label_start_idx=self.feature_dims[i], label_end_idx=self.feature_dims[i + 1])) # else: if self._method_calling == 1: base_graph_kernel[i].fit(g, ) else: K.append(base_graph_kernel[i].fit_transform(g, )) # if return_embedding_only: # return K if self._method_calling == 1: return base_graph_kernel elif self._method_calling == 2: # if self.as_tensor: # K = torch.stack(K, dim=0).sum(dim=0) # return K, base_graph_kernel return np.sum(K, axis=0), base_graph_kernel
def parse_input(self, X): """Parse and create features for the NSPD kernel. Parameters ---------- X : iterable For the input to pass the test, we must have: Each element must be an iterable with at most three features and at least one. The first that is obligatory is a valid graph structure (adjacency matrix or edge_dictionary) while the second is node_labels and the third edge_labels (that correspond to the given graph format). A valid input also consists of graph type objects. Returns ------- M : dict A dictionary with keys all the distances from 0 to self.d and values the the np.arrays with rows corresponding to the non-null input graphs and columns to the enumerations of tuples consisting of pairs of hash values and radius, from all the given graphs of the input (plus the fitted one's on transform). """ if not isinstance(X, collections.Iterable): raise TypeError('input must be an iterable\n') else: # Hold the number of graphs ng = 0 # Holds all the data for combinations of r, d data = collections.defaultdict(dict) # Index all keys for combinations of r, d all_keys = collections.defaultdict(dict) for (idx, x) in enumerate(iter(X)): is_iter = False if isinstance(x, collections.Iterable): is_iter, x = True, list(x) if is_iter and len(x) in [0, 3]: if len(x) == 0: warnings.warn('Ignoring empty element' + ' on index: ' + str(idx)) continue else: g = Graph(x[0], x[1], x[2]) g.change_format("adjacency") elif type(x) is Graph: g = Graph( x.get_adjacency_matrix(), x.get_labels(purpose="adjacency", label_type="vertex"), x.get_labels(purpose="adjacency", label_type="edge")) else: raise TypeError('each element of X must have either ' + 'a graph with labels for node and edge ' + 'or 3 elements consisting of a graph ' + 'type object, labels for vertices and ' + 'labels for edges.') # Bring to the desired format g.change_format(self._graph_format) # Take the vertices vertices = set(g.get_vertices(purpose=self._graph_format)) # Extract the dicitionary ed = g.get_edge_dictionary() # Convert edges to tuples edges = {(j, k) for j in ed.keys() for k in ed[j].keys()} # Extract labels for nodes Lv = g.get_labels(purpose=self._graph_format) # and for edges Le = g.get_labels(purpose=self._graph_format, label_type="edge") # Produce all the neighborhoods and the distance pairs # up to the desired radius and maximum distance N, D, D_pair = g.produce_neighborhoods(self.r, purpose="dictionary", with_distances=True, d=self.d) # Hash all the neighborhoods H = self._hash_neighborhoods(vertices, edges, Lv, Le, N, D_pair) if self._method_calling == 1: for d in filterfalse(lambda x: x not in D, range(self.d + 1)): for (A, B) in D[d]: for r in range(self.r + 1): key = (H[r, A], H[r, B]) keys = all_keys[r, d] idx = keys.get(key, None) if idx is None: idx = len(keys) keys[key] = idx data[r, d][ng, idx] = data[r, d].get( (ng, idx), 0) + 1 elif self._method_calling == 3: for d in filterfalse(lambda x: x not in D, range(self.d + 1)): for (A, B) in D[d]: # Based on the edges of the bidirected graph for r in range(self.r + 1): keys = all_keys[r, d] fit_keys = self._fit_keys[r, d] key = (H[r, A], H[r, B]) idx = fit_keys.get(key, None) if idx is None: idx = keys.get(key, None) if idx is None: idx = len(keys) + len(fit_keys) keys[key] = idx data[r, d][ng, idx] = data[r, d].get( (ng, idx), 0) + 1 ng += 1 if ng == 0: raise ValueError('parsed input is empty') if self._method_calling == 1: # A feature matrix for all levels M = dict() for (key, d) in filterfalse(lambda a: len(a[1]) == 0, iteritems(data)): indexes, data = zip(*iteritems(d)) rows, cols = zip(*indexes) M[key] = csr_matrix((data, (rows, cols)), shape=(ng, len(all_keys[key])), dtype=np.int64) self._fit_keys = all_keys self._ngx = ng elif self._method_calling == 3: # A feature matrix for all levels M = dict() for (key, d) in filterfalse(lambda a: len(a[1]) == 0, iteritems(data)): indexes, data = zip(*iteritems(d)) rows, cols = zip(*indexes) M[key] = csr_matrix( (data, (rows, cols)), shape=(ng, len(all_keys[key]) + len(self._fit_keys[key])), dtype=np.int64) self._ngy = ng return M
def parse_input(self, X): """Parse input and create features, while initializing and/or calculating sub-kernels. Parameters ---------- X : iterable For the input to pass the test, we must have: Each element must be an iterable with at most three features and at least one. The first that is obligatory is a valid graph structure (adjacency matrix or edge_dictionary) while the second is node_labels and the third edge_labels (that correspond to the given graph format). A valid input also consists of graph type objects. Returns ------- base_graph_kernel : object Returns base_graph_kernel. Only if called from `fit` or `fit_transform`. K : np.array Returns the kernel matrix. Only if called from `transform` or `fit_transform`. """ if self.base_graph_kernel_ is None: raise ValueError('User must provide a base_graph_kernel') # Input validation and parsing if not isinstance(X, collections.Iterable): raise TypeError('input must be an iterable\n') else: nx, labels = 0, list() if self._method_calling in [1, 2]: nl, labels_enum, base_graph_kernel = 0, dict(), dict() for kidx in range(self.n_iter): base_graph_kernel[kidx] = self.base_graph_kernel_[0]( **self.base_graph_kernel_[1]) elif self._method_calling == 3: nl, labels_enum, base_graph_kernel = len( self._labels_enum), dict(self._labels_enum), self.X inp = list() neighbors = list() for (idx, x) in enumerate(iter(X)): is_iter = False if isinstance(x, collections.Iterable): x, is_iter = list(x), True if is_iter and (len(x) == 0 or len(x) >= 2): if len(x) == 0: warnings.warn('Ignoring empty element on index: ' + str(idx)) continue else: if len(x) > 2: extra = tuple() if len(x) > 3: extra = tuple(x[3:]) x = Graph(x[0], x[1], x[2], graph_format=self._graph_format) extra = (x.get_labels(purpose='any', label_type="edge", return_none=True), ) + extra else: x = Graph(x[0], x[1], {}, graph_format=self._graph_format) extra = tuple() elif type(x) is Graph: el = x.get_labels(purpose=self._graph_format, label_type="edge", return_none=True) if el is None: extra = tuple() else: extra = (el, ) else: raise TypeError('each element of X must be either a ' + 'graph object or a list with at least ' + 'a graph like object and node labels ' + 'dict \n') label = x.get_labels(purpose='any') inp.append((x.get_graph_object(), extra)) neighbors.append(x.get_edge_dictionary()) labels.append(label) for v in set(itervalues(label)): if v not in labels_enum: labels_enum[v] = nl nl += 1 nx += 1 if nx == 0: raise ValueError('parsed input is empty') # Calculate the hadamard matrix H = hadamard(int(2**(ceil(log2(nl))))) def generate_graphs(labels): # Intial labeling of vertices based on their corresponding Hadamard code (i-th row of the # Hadamard matrix) where i is the i-th label on enumeration new_graphs, new_labels = list(), list() for ((obj, extra), label) in zip(inp, labels): new_label = dict() for (k, v) in iteritems(label): new_label[k] = H[labels_enum[v], :] new_graphs.append( (obj, {i: tuple(j) for (i, j) in iteritems(new_label)}) + extra) new_labels.append(new_label) yield new_graphs # Main for i in range(1, self.n_iter): new_graphs, labels, new_labels = list(), new_labels, list() for ((obj, extra), neighbor, old_label) in zip(inp, neighbors, labels): # Find unique labels and sort them for both graphs and keep for each node # the temporary new_label = dict() for (k, ns) in iteritems(neighbor): new_label[k] = old_label[k] for q in ns: new_label[k] = np.add(new_label[k], old_label[q]) new_labels.append(new_label) new_graphs.append( (obj, {i: tuple(j) for (i, j) in iteritems(new_label)}) + extra) yield new_graphs if self._method_calling in [1, 2]: base_graph_kernel = { i: self.base_graph_kernel_[0](**self.base_graph_kernel_[1]) for i in range(self.n_iter) } if self._parallel is None: # Add the zero iteration element if self._method_calling == 1: for (i, g) in enumerate(generate_graphs(labels)): base_graph_kernel[i].fit(g) elif self._method_calling == 2: K = np.sum((base_graph_kernel[i].fit_transform(g) for (i, g) in enumerate(generate_graphs(labels))), axis=0) elif self._method_calling == 3: # Calculate the kernel matrix without parallelization K = np.sum((self.X[i].transform(g) for (i, g) in enumerate(generate_graphs(labels))), axis=0) else: if self._method_calling == 1: self._parallel( joblib.delayed(efit)(base_graph_kernel[i], g) for (i, g) in enumerate(generate_graphs(labels))) elif self._method_calling == 2: # Calculate the kernel marix with parallelization K = np.sum(self._parallel( joblib.delayed(efit_transform)(base_graph_kernel[i], g) for (i, g) in enumerate(generate_graphs(labels))), axis=0) elif self._method_calling == 3: # Calculate the kernel marix with parallelization K = np.sum(self._parallel( joblib.delayed(etransform)(self.X[i], g) for (i, g) in enumerate(generate_graphs(labels))), axis=0) if self._method_calling == 1: self._labels_enum = labels_enum return base_graph_kernel elif self._method_calling == 2: self._labels_enum = labels_enum return K, base_graph_kernel elif self._method_calling == 3: return K
def parse_input(self, X): """Parse input for weisfeiler lehman optimal assignment. Parameters ---------- X : iterable For the input to pass the test, we must have: Each element must be an iterable with at most three features and at least one. The first that is obligatory is a valid graph structure (adjacency matrix or edge_dictionary) while the second is node_labels and the third edge_labels (that correspond to the given graph format). A valid input also consists of graph type objects. Returns ------- Hs : numpy array, shape = [n_input_graphs, hierarchy_size] An array where the rows contain the histograms of the graphs. """ if self._method_calling not in [1, 2]: raise ValueError('method call must be called either from fit ' + 'or fit-transform') elif hasattr(self, '_X_diag'): # Clean _X_diag value delattr(self, '_X_diag') # Input validation and parsing if not isinstance(X, collections.Iterable): raise TypeError('input must be an iterable\n') else: nx = 0 Gs_ed, L, distinct_values = dict(), dict(), set() for (idx, x) in enumerate(iter(X)): is_iter = isinstance(x, collections.Iterable) if is_iter: x = list(x) if is_iter and (len(x) == 0 or len(x) >= 2): if len(x) == 0: warnings.warn('Ignoring empty element on index: ' + str(idx)) continue else: if len(x) > 2: extra = tuple() if len(x) > 3: extra = tuple(x[3:]) x = Graph(x[0], x[1], x[2], graph_format=self._graph_format) extra = (x.get_labels(purpose=self._graph_format, label_type="edge", return_none=True), ) + extra else: x = Graph(x[0], x[1], {}, graph_format=self._graph_format) extra = tuple() elif type(x) is Graph: x.desired_format(self._graph_format) else: raise TypeError('each element of X must be either a ' + 'graph object or a list with at least ' + 'a graph like object and node labels ' + 'dict \n') Gs_ed[nx] = x.get_edge_dictionary() L[nx] = x.get_labels(purpose="dictionary") distinct_values |= set(itervalues(L[nx])) nx += 1 if nx == 0: raise ValueError('parsed input is empty') # Save the number of "fitted" graphs. self._nx = nx # Initialize hierarchy self._hierarchy = dict() self._hierarchy['root'] = dict() self._hierarchy['root']['parent'] = None self._hierarchy['root']['children'] = list() self._hierarchy['root']['w'] = 0 self._hierarchy['root']['omega'] = 0 # get all the distinct values of current labels WL_labels_inverse = dict() # assign a number to each label label_count = 0 for dv in sorted(list(distinct_values)): WL_labels_inverse[dv] = label_count self._insert_into_hierarchy(label_count, 'root') label_count += 1 # Initalize an inverse dictionary of labels for all iterations self._inv_labels = dict() self._inv_labels[0] = WL_labels_inverse for j in range(nx): new_labels = dict() for k in L[j].keys(): new_labels[k] = WL_labels_inverse[L[j][k]] L[j] = new_labels for i in range(1, self._n_iter): new_previous_label_set, WL_labels_inverse, L_temp = set(), dict(), dict() for j in range(nx): # Find unique labels and sort # them for both graphs # Keep for each node the temporary L_temp[j] = dict() for v in Gs_ed[j].keys(): credential = str(L[j][v]) + "," + \ str(sorted([L[j][n] for n in Gs_ed[j][v].keys()])) L_temp[j][v] = credential new_previous_label_set.add((credential, L[j][v])) label_list = sorted(list(new_previous_label_set), key=lambda tup: tup[0]) for dv, previous_label in label_list: WL_labels_inverse[dv] = label_count self._insert_into_hierarchy(label_count, previous_label) label_count += 1 # Recalculate labels for j in range(nx): new_labels = dict() for k in L_temp[j].keys(): new_labels[k] = WL_labels_inverse[L_temp[j][k]] L[j] = new_labels self._inv_labels[i] = WL_labels_inverse # Compute the vector representation of each graph if self.sparse: Hs = lil_matrix((nx, len(self._hierarchy))) else: Hs = np.zeros((nx, len(self._hierarchy))) for j in range(nx): for k in L[j].keys(): current_label = L[j][k] while self._hierarchy[current_label]['parent'] is not None: Hs[j, current_label] += self._hierarchy[current_label]['omega'] current_label = self._hierarchy[current_label]['parent'] return Hs
def transform(self, X): """Calculate the kernel matrix, between given and fitted dataset. Parameters ---------- X : iterable Each element must be an iterable with at most three features and at least one. The first that is obligatory is a valid graph structure (adjacency matrix or edge_dictionary) while the second is node_labels and the third edge_labels (that fitting the given graph format). If None the kernel matrix is calculated upon fit data. The test samples. Returns ------- K : numpy array, shape = [n_targets, n_input_graphs] corresponding to the kernel matrix, a calculation between all pairs of graphs between target an features """ self._method_calling = 3 # Check is fit had been called check_is_fitted(self, ['X', '_nx', '_hierarchy', '_inv_labels']) # Input validation and parsing if X is None: raise ValueError('transform input cannot be None') else: if not isinstance(X, collections.Iterable): raise ValueError('input must be an iterable\n') else: nx = 0 distinct_values = set() Gs_ed, L = dict(), dict() for (i, x) in enumerate(iter(X)): is_iter = isinstance(x, collections.Iterable) if is_iter: x = list(x) if is_iter and len(x) in [0, 2, 3]: if len(x) == 0: warnings.warn('Ignoring empty element on index: ' + str(i)) continue elif len(x) in [2, 3]: x = Graph(x[0], x[1], {}, self._graph_format) elif type(x) is Graph: x.desired_format("dictionary") else: raise ValueError('each element of X must have at ' + 'least one and at most 3 elements\n') Gs_ed[nx] = x.get_edge_dictionary() L[nx] = x.get_labels(purpose="dictionary") # Hold all the distinct values distinct_values |= set( v for v in itervalues(L[nx]) if v not in self._inv_labels[0]) nx += 1 if nx == 0: raise ValueError('parsed input is empty') # get all the distinct values of new labels WL_labels_inverse = dict() # assign a number to each label label_count = sum([len(self._inv_labels[i]) for i in range(len(self._inv_labels))]) for dv in sorted(list(distinct_values)): WL_labels_inverse[dv] = label_count self._insert_into_hierarchy(label_count, 'root') label_count += 1 for j in range(nx): new_labels = dict() for (k, v) in iteritems(L[j]): if v in self._inv_labels[0]: new_labels[k] = self._inv_labels[0][v] else: new_labels[k] = WL_labels_inverse[v] L[j] = new_labels for i in range(1, self._n_iter): L_temp, new_previous_label_set = dict(), set() for j in range(nx): # Find unique labels and sort them for both graphs # Keep for each node the temporary L_temp[j] = dict() for v in Gs_ed[j].keys(): credential = str(L[j][v]) + "," + \ str(sorted([L[j][n] for n in Gs_ed[j][v].keys()])) L_temp[j][v] = credential if credential not in self._inv_labels[i]: new_previous_label_set.add((credential, L[j][v])) # Calculate the new label_set WL_labels_inverse = dict() if len(new_previous_label_set) > 0: for dv, previous_label in sorted(list(new_previous_label_set), key=lambda tup: tup[0]): WL_labels_inverse[dv] = label_count self._insert_into_hierarchy(label_count, previous_label) label_count += 1 # Recalculate labels for j in range(nx): new_labels = dict() for (k, v) in iteritems(L_temp[j]): if v in self._inv_labels[i]: new_labels[k] = self._inv_labels[i][v] else: new_labels[k] = WL_labels_inverse[v] L[j] = new_labels # Compute the vector representation of each graph if self.sparse: Hs = lil_matrix((nx, len(self._hierarchy))) else: Hs = np.zeros((nx, len(self._hierarchy))) for j in range(nx): for k in L[j].keys(): current_label = L[j][k] while self._hierarchy[current_label]['parent'] is not None: Hs[j, current_label] += self._hierarchy[current_label]['omega'] current_label = self._hierarchy[current_label]['parent'] self.Y = Hs # Compute the histogram intersection kernel K = np.zeros((nx, self._nx)) if self.sparse: for i in range(self._nx): for j in range(i, self._nx): K[i, j] = np.sum(Hs[i, :self.X.shape[1]].minimum(self.X[j, :])) else: for i in range(nx): for j in range(self._nx): K[i, j] = np.sum(np.min([Hs[i, :self.X.shape[1]], self.X[j, :]], axis=0)) self._is_transformed = True if self.normalize: X_diag, Y_diag = self.diagonal() old_settings = np.seterr(divide='ignore') K = np.nan_to_num(np.divide(K, np.sqrt(np.outer(Y_diag, X_diag)))) np.seterr(**old_settings) return K