def _load_legacy_hdf5_v2(root, remove_duplicate_positions):
# Get the coalescence records
trees_group = root["trees"]
old_timestamp = datetime.datetime.min.isoformat()
provenances = tskit.ProvenanceTable()
provenances.add_row(
timestamp=old_timestamp,
record=_get_v2_provenance("generate_trees", trees_group.attrs),
)
num_rows = trees_group["node"].shape[0]
index = np.arange(num_rows, dtype=int)
parent = np.zeros(2 * num_rows, dtype=np.int32)
parent[2 * index] = trees_group["node"]
parent[2 * index + 1] = trees_group["node"]
left = np.zeros(2 * num_rows, dtype=np.float64)
left[2 * index] = trees_group["left"]
left[2 * index + 1] = trees_group["left"]
right = np.zeros(2 * num_rows, dtype=np.float64)
right[2 * index] = trees_group["right"]
right[2 * index + 1] = trees_group["right"]
child = np.array(trees_group["children"], dtype=np.int32).flatten()
tables = tskit.TableCollection(np.max(right))
tables.edges.set_columns(left=left,
right=right,
parent=parent,
child=child)
cr_node = np.array(trees_group["node"], dtype=np.int32)
num_nodes = max(np.max(child), np.max(cr_node)) + 1
sample_size = np.min(cr_node)
flags = np.zeros(num_nodes, dtype=np.uint32)
population = np.zeros(num_nodes, dtype=np.int32)
time = np.zeros(num_nodes, dtype=np.float64)
flags[:sample_size] = tskit.NODE_IS_SAMPLE
cr_population = np.array(trees_group["population"], dtype=np.int32)
cr_time = np.array(trees_group["time"])
time[cr_node] = cr_time
population[cr_node] = cr_population
if "samples" in root:
samples_group = root["samples"]
population[:sample_size] = samples_group["population"]
if "time" in samples_group:
time[:sample_size] = samples_group["time"]
tables.nodes.set_columns(flags=flags, population=population, time=time)
_set_populations(tables)
if "mutations" in root:
mutations_group = root["mutations"]
_convert_hdf5_mutations(mutations_group, tables.sites,
tables.mutations, remove_duplicate_positions)
provenances.add_row(
timestamp=old_timestamp,
record=_get_v2_provenance("generate_mutations",
mutations_group.attrs),
)
tables.provenances.add_row(_get_upgrade_provenance(root))
tables.sort()
return tables.tree_sequence()
def provenance_timestamp_only_example():
ts = msprime.simulate(10, random_seed=1)
tables = ts.dump_tables()
provenances = tskit.ProvenanceTable()
provenances.add_row(timestamp="12345", record="")
return tables.tree_sequence()