def inner(query_features):
for features in query_features:
for feature in features:
shingles = shingle_extraction.extract_shingles(feature)
fingerprints = fingerprint.get_fingerprints(shingles)
for fp in fingerprints:
yield fp
def inner(query_features):
for features in query_features:
for feature in features:
shingles = shingle_extraction.extract_shingles(feature)
fingerprints = fingerprint.get_fingerprints(shingles)
for fp in fingerprints:
yield fp
def process_shingles(shingles, record_data_vector, wl_it):
next_shingle_id_key = "next_shingle_id" if accumulate_wl_shingles else "wl_{0}_next_shingle_id".format(wl_it)
if not fingerprints:
for shingle in shingles:
if shingle not in shingle_id_map:
shingle_id_map[shingle] = wl_state[next_shingle_id_key]
wl_state[next_shingle_id_key] += 1
record_data_vector.add((shingle_id_map[shingle], 1))
else:
shingle_ids = set(fingerprint.get_fingerprints(shingles, size=24))
record_data_vector |= set(map(lambda shingle_id: (shingle_id, 1), shingle_ids))
def build_with_w_shingles(self, w_shingle_lists, initial_sparse_matrix={}):
self.sparse_matrix = initial_sparse_matrix
i = -1
for _, record_w_shingles, _ in w_shingle_lists:
i += 1
if self.print_progress:
print "Ch.Mat.: Processing column", i, "of", self.cols_count
fingerprints = fingerprint.get_fingerprints(record_w_shingles)
for fp in fingerprints:
if not self.sparse_matrix.has_key(fp):
self.sparse_matrix[fp] = set()
self.sparse_matrix[fp].add(i)
def build(self, feature_lists):
self.sparse_matrix = {}
i = -1
for _, record_features, _ in feature_lists:
i += 1
if self.print_progress:
print "Ch.Mat.: Processing column", i, "of", self.cols_count
for feature in record_features:
shingles = shingle_extraction.extract_shingles(feature)
fingerprints = fingerprint.get_fingerprints(shingles)
for fp in fingerprints:
if not self.sparse_matrix.has_key(fp):
self.sparse_matrix[fp] = set()
self.sparse_matrix[fp].add(i)
def compute_column_fingerprints(self, record_graphs):
assert self.wl_state
features = []
for hypergraph in record_graphs:
new_features, self.wl_state = feature_extraction.extract_features(hypergraph, self.wl_iterations, self.wl_state)
features += new_features
column = set()
for feature in features:
shingles = shingle_extraction.extract_shingles(feature)
fingerprints = fingerprint.get_fingerprints(shingles)
column |= set(fingerprints)
return sorted(column)