def test_compute_stats_single():
for G, distances, betas in network_generator():
data_dict = mock.mock_data_dict(G)
numeric_data = mock.mock_numerical_data(len(data_dict), num_arrs=1)
# easy version
N_easy = networks.Network_Layer_From_nX(G, distances)
D_easy = layers.Data_Layer_From_Dict(data_dict)
D_easy.assign_to_network(N_easy, max_dist=500)
D_easy.compute_stats_single('boo', numeric_data[0])
# custom version
N_full = networks.Network_Layer_From_nX(G, distances)
D_full = layers.Data_Layer_From_Dict(data_dict)
D_full.assign_to_network(N_full, max_dist=500)
D_full.compute_aggregated(stats_keys=['boo'],
stats_data_arrs=numeric_data)
# compare
for n_label in ['boo']:
for s_label in [
'max', 'min', 'mean', 'mean_weighted', 'variance',
'variance_weighted'
]:
for dist in distances:
assert np.allclose(
N_easy.metrics['stats'][n_label][s_label][dist],
N_full.metrics['stats'][n_label][s_label][dist],
equal_nan=True,
atol=0.001,
rtol=0)
# check that non-single dimension arrays are caught
with pytest.raises(ValueError):
D_easy.compute_stats_single('boo', numeric_data)
def test_check_data_map():
G = mock.mock_graph()
G = graphs.nX_simple_geoms(G)
N = networks.Network_Layer_From_nX(G, distances=[500])
data_dict = mock.mock_data_dict(G)
data_uids, data_map = layers.data_map_from_dict(data_dict)
# should throw error if not assigned
with pytest.raises(ValueError):
checks.check_data_map(data_map)
# should work if flag set to False
checks.check_data_map(data_map, check_assigned=False)
# assign then check that it runs as intended
data_map = data.assign_to_network(data_map,
N._node_data,
N._edge_data,
N._node_edge_map,
max_dist=400)
checks.check_data_map(data_map)
# catch zero length data arrays
empty_2d_arr = np.full((0, 4), np.nan)
with pytest.raises(ValueError):
checks.check_data_map(empty_2d_arr)
# catch invalid dimensionality
with pytest.raises(ValueError):
checks.check_data_map(data_map[:, :-1])
def test_metrics_to_dict():
G = mock.mock_graph()
G = graphs.nX_simple_geoms(G)
# create a network layer and run some metrics
N = networks.Network_Layer_From_nX(G, distances=[500, 1000])
# check with no metrics
metrics_dict = N.metrics_to_dict()
dict_check(metrics_dict, N)
# check with centrality metrics
N.compute_centrality(measures=['node_harmonic'])
metrics_dict = N.metrics_to_dict()
dict_check(metrics_dict, N)
# check with data metrics
data_dict = mock.mock_data_dict(G)
landuse_labels = mock.mock_categorical_data(len(data_dict))
numerical_data = mock.mock_numerical_data(len(data_dict))
# TODO:
'''
D = layers.Data_Layer_From_Dict(data_dict)
D.assign_to_network(N, max_dist=400)
D.compute_aggregated(landuse_labels,
mixed_use_keys=['hill', 'shannon'],
accessibility_keys=['a', 'c'],
qs=[0, 1],
stats_keys=['boo'],
stats_data_arrs=numerical_data)
'''
metrics_dict = N.metrics_to_dict()
dict_check(metrics_dict, N)
def test_compute_stats_multiple():
for G, distances, betas in network_generator():
data_dict = mock.mock_data_dict(G)
numeric_data = mock.mock_numerical_data(len(data_dict), num_arrs=2)
# easy version
N_easy = networks.Network_Layer_From_nX(G, distances)
D_easy = layers.Data_Layer_From_Dict(data_dict)
D_easy.assign_to_network(N_easy, max_dist=500)
D_easy.compute_stats_multiple(['boo', 'baa'], numeric_data)
# custom version
N_full = networks.Network_Layer_From_nX(G, distances)
D_full = layers.Data_Layer_From_Dict(data_dict)
D_full.assign_to_network(N_full, max_dist=500)
D_full.compute_aggregated(stats_keys=['boo', 'baa'],
stats_data_arrs=numeric_data)
# compare
for n_label in ['boo', 'baa']:
for s_label in [
'max', 'min', 'mean', 'mean_weighted', 'variance',
'variance_weighted'
]:
for dist in distances:
assert np.allclose(
N_easy.metrics['stats'][n_label][s_label][dist],
N_full.metrics['stats'][n_label][s_label][dist],
equal_nan=True,
atol=0.001,
rtol=0)
def test_dict_wgs_to_utm():
# check that node coordinates are correctly converted
G_utm = mock.mock_graph()
data_dict_utm = mock.mock_data_dict(G_utm)
# create a test dictionary
test_dict = copy.deepcopy(data_dict_utm)
# cast to lat, lon
for k, v in test_dict.items():
easting = v['x']
northing = v['y']
# be cognisant of parameter and return order
# returns in lat lng order
lat, lng = utm.to_latlon(easting, northing, 30, 'U')
test_dict[k]['x'] = lng
test_dict[k]['y'] = lat
# convert back
dict_converted = layers.dict_wgs_to_utm(test_dict)
# check that round-trip converted match with reasonable proximity given rounding errors
for k in data_dict_utm.keys():
# rounding can be tricky
assert np.allclose(data_dict_utm[k]['x'],
dict_converted[k]['x'],
atol=0.1,
rtol=0) # relax precision
assert np.allclose(data_dict_utm[k]['y'],
dict_converted[k]['y'],
atol=0.1,
rtol=0) # relax precision
# check that missing node attributes throw an error
for attr in ['x', 'y']:
G_wgs = mock.mock_graph(wgs84_coords=True)
data_dict_wgs = mock.mock_data_dict(G_wgs)
for k in data_dict_wgs.keys():
del data_dict_wgs[k][attr]
break
# check that missing attribute throws an error
with pytest.raises(AttributeError):
layers.dict_wgs_to_utm(data_dict_wgs)
# check that non WGS coordinates throw error
with pytest.raises(AttributeError):
layers.dict_wgs_to_utm(data_dict_utm)
def test_Data_Layer():
G = mock.mock_graph()
data_dict = mock.mock_data_dict(G)
data_uids, data_map = layers.data_map_from_dict(data_dict)
x_arr = data_map[:, 0]
y_arr = data_map[:, 1]
# test against Data_Layer internal process
D = layers.Data_Layer(data_uids, data_map)
assert D.uids == data_uids
assert np.allclose(D._data, data_map, equal_nan=True, atol=0.001, rtol=0)
assert np.allclose(D.x_arr, x_arr, atol=0.001, rtol=0)
assert np.allclose(D.y_arr, y_arr, atol=0.001, rtol=0)
def test_data_map_from_dict():
# generate mock data
G = mock.mock_graph()
data_dict = mock.mock_data_dict(G)
data_uids, data_map = layers.data_map_from_dict(data_dict)
assert len(data_uids) == len(data_map) == len(data_dict)
for d_label, d in zip(data_uids, data_map):
assert d[0] == data_dict[d_label]['x']
assert d[1] == data_dict[d_label]['y']
assert np.isnan(d[2])
assert np.isnan(d[3])
# check that missing attributes throw errors
for attr in ['x', 'y']:
for k in data_dict.keys():
del data_dict[k][attr]
with pytest.raises(AttributeError):
layers.data_map_from_dict(data_dict)
def test_compute_accessibilities():
for G, distances, betas in network_generator():
data_dict = mock.mock_data_dict(G)
landuse_labels = mock.mock_categorical_data(len(data_dict))
# easy version
N_easy = networks.Network_Layer_From_nX(G, distances)
D_easy = layers.Data_Layer_From_Dict(data_dict)
D_easy.assign_to_network(N_easy, max_dist=500)
D_easy.compute_accessibilities(landuse_labels, ['c'])
# custom version
N_full = networks.Network_Layer_From_nX(G, distances)
D_full = layers.Data_Layer_From_Dict(data_dict)
D_full.assign_to_network(N_full, max_dist=500)
D_full.compute_aggregated(landuse_labels, accessibility_keys=['c'])
# compare
for d in distances:
for wt in ['weighted', 'non_weighted']:
assert np.allclose(N_easy.metrics['accessibility'][wt]['c'][d],
N_full.metrics['accessibility'][wt]['c'][d],
atol=0.001,
rtol=0)
def test_hill_diversity():
for G, distances, betas in network_generator():
data_dict = mock.mock_data_dict(G)
landuse_labels = mock.mock_categorical_data(len(data_dict))
# easy version
N_easy = networks.Network_Layer_From_nX(G, distances)
D_easy = layers.Data_Layer_From_Dict(data_dict)
D_easy.assign_to_network(N_easy, max_dist=500)
D_easy.hill_diversity(landuse_labels, qs=[0, 1, 2])
# custom version
N_full = networks.Network_Layer_From_nX(G, distances)
D_full = layers.Data_Layer_From_Dict(data_dict)
D_full.assign_to_network(N_full, max_dist=500)
D_full.compute_aggregated(landuse_labels,
mixed_use_keys=['hill'],
qs=[0, 1, 2])
# compare
for d in distances:
for q in [0, 1, 2]:
assert np.allclose(N_easy.metrics['mixed_uses']['hill'][q][d],
N_full.metrics['mixed_uses']['hill'][q][d],
atol=0.001,
rtol=0)
base_path = path.dirname(__file__)
#
#
# INTRO PLOT
G = mock.mock_graph()
plot.plot_nX(G, path='graph.png', labels=True, dpi=150)
# INTRO EXAMPLE PLOTS
G = graphs.nX_simple_geoms(G)
G = graphs.nX_decompose(G, 20)
N = networks.Network_Layer_From_nX(G, distances=[400, 800])
N.compute_centrality(measures=['segment_harmonic'])
data_dict = mock.mock_data_dict(G, random_seed=25)
D = layers.Data_Layer_From_Dict(data_dict)
D.assign_to_network(N, max_dist=400)
landuse_labels = mock.mock_categorical_data(len(data_dict), random_seed=25)
D.hill_branch_wt_diversity(landuse_labels, qs=[0])
G_metrics = N.to_networkX()
segment_harmonic_vals = []
mixed_uses_vals = []
for node, data in G_metrics.nodes(data=True):
segment_harmonic_vals.append(
data['metrics']['centrality']['segment_harmonic'][800])
mixed_uses_vals.append(
data['metrics']['mixed_uses']['hill_branch_wt'][0][400])
# custom colourmap
def test_nX_from_graph_maps():
# also see test_networks.test_to_networkX for tests on implementation via Network layer
# check round trip to and from graph maps results in same graph
G = mock.mock_graph()
G = graphs.nX_simple_geoms(G)
# explicitly set live params for equality checks
# graph_maps_from_networkX generates these implicitly if missing
for n in G.nodes():
G.nodes[n]['live'] = bool(np.random.randint(0, 1))
# test directly from and to graph maps
node_uids, node_data, edge_data, node_edge_map = graphs.graph_maps_from_nX(G)
G_round_trip = graphs.nX_from_graph_maps(node_uids, node_data, edge_data, node_edge_map)
assert list(G_round_trip.nodes) == list(G.nodes)
assert list(G_round_trip.edges) == list(G.edges)
# check with metrics dictionary
N = networks.Network_Layer_From_nX(G, distances=[500, 1000])
N.compute_centrality(measures=['node_harmonic'])
data_dict = mock.mock_data_dict(G)
landuse_labels = mock.mock_categorical_data(len(data_dict))
D = layers.Data_Layer_From_Dict(data_dict)
D.assign_to_network(N, max_dist=400)
D.compute_aggregated(landuse_labels,
mixed_use_keys=['hill', 'shannon'],
accessibility_keys=['a', 'c'],
qs=[0, 1])
metrics_dict = N.metrics_to_dict()
# without backbone
G_round_trip_data = graphs.nX_from_graph_maps(node_uids,
node_data,
edge_data,
node_edge_map,
metrics_dict=metrics_dict)
for uid, metrics in metrics_dict.items():
assert G_round_trip_data.nodes[uid]['metrics'] == metrics
# with backbone
G_round_trip_data = graphs.nX_from_graph_maps(node_uids,
node_data,
edge_data,
node_edge_map,
networkX_graph=G,
metrics_dict=metrics_dict)
for uid, metrics in metrics_dict.items():
assert G_round_trip_data.nodes[uid]['metrics'] == metrics
# test with decomposed
G_decomposed = graphs.nX_decompose(G, decompose_max=20)
# set live explicitly
for n in G_decomposed.nodes():
G_decomposed.nodes[n]['live'] = bool(np.random.randint(0, 1))
node_uids_d, node_data_d, edge_data_d, node_edge_map_d = graphs.graph_maps_from_nX(G_decomposed)
G_round_trip_d = graphs.nX_from_graph_maps(node_uids_d, node_data_d, edge_data_d, node_edge_map_d)
assert list(G_round_trip_d.nodes) == list(G_decomposed.nodes)
for n, node_data in G_round_trip.nodes(data=True):
assert n in G_decomposed
assert node_data['live'] == G_decomposed.nodes[n]['live']
assert node_data['x'] == G_decomposed.nodes[n]['x']
assert node_data['y'] == G_decomposed.nodes[n]['y']
assert G_round_trip_d.edges == G_decomposed.edges
# error checks for when using backbone graph:
# mismatching numbers of nodes
corrupt_G = G.copy()
corrupt_G.remove_node(0)
with pytest.raises(ValueError):
graphs.nX_from_graph_maps(node_uids, node_data, edge_data, node_edge_map, networkX_graph=corrupt_G)
# mismatching node uid
with pytest.raises(ValueError):
corrupt_node_uids = list(node_uids)
corrupt_node_uids[0] = 'boo'
graphs.nX_from_graph_maps(corrupt_node_uids, node_data, edge_data, node_edge_map, networkX_graph=G)
def test_compute_aggregated_B():
'''
Test stats component
'''
G = mock.mock_graph()
G = graphs.nX_simple_geoms(G)
betas = np.array([-0.01, -0.005])
distances = networks.distance_from_beta(betas)
# network layer
N = networks.Network_Layer_From_nX(G, distances)
node_map = N._node_data
edge_map = N._edge_data
node_edge_map = N._node_edge_map
# data layer
data_dict = mock.mock_data_dict(G)
qs = np.array([0, 1, 2])
D = layers.Data_Layer_From_Dict(data_dict)
# check single metrics independently against underlying for some use-cases, e.g. hill, non-hill, accessibility...
D.assign_to_network(N, max_dist=500)
# generate some mock landuse data
mock_numeric = mock.mock_numerical_data(len(data_dict), num_arrs=2)
# generate stats
D.compute_aggregated(stats_keys=['boo', 'baa'],
stats_data_arrs=mock_numeric)
# test against underlying method
data_map = D._data
mu_data_hill, mu_data_other, ac_data, ac_data_wt, \
stats_sum, stats_sum_wt, stats_mean, stats_mean_wt, stats_variance, stats_variance_wt, stats_max, stats_min = \
data.local_aggregator(node_map,
edge_map,
node_edge_map,
data_map,
distances,
betas,
numerical_arrays=mock_numeric)
stats_keys = [
'max', 'min', 'sum', 'sum_weighted', 'mean', 'mean_weighted',
'variance', 'variance_weighted'
]
stats_data = [
stats_max, stats_min, stats_sum, stats_sum_wt, stats_mean,
stats_mean_wt, stats_variance, stats_variance_wt
]
for num_idx, num_label in enumerate(['boo', 'baa']):
for s_key, stats in zip(stats_keys, stats_data):
for d_idx, d_key in enumerate(distances):
assert np.allclose(N.metrics['stats'][num_label][s_key][d_key],
stats[num_idx][d_idx],
atol=0.001,
rtol=0)
# check that mismatching label and array lengths are caught
for labels, arrs in (
(['a'], mock_numeric), # mismatching lengths
(['a', 'b'], None), # missing arrays
(None, mock_numeric)): # missing labels
with pytest.raises(ValueError):
D.compute_aggregated(stats_keys=labels, stats_data_arrs=arrs)
def test_compute_aggregated_A():
G = mock.mock_graph()
G = graphs.nX_simple_geoms(G)
betas = np.array([-0.01, -0.005])
distances = networks.distance_from_beta(betas)
# network layer
N = networks.Network_Layer_From_nX(G, distances)
node_map = N._node_data
edge_map = N._edge_data
node_edge_map = N._node_edge_map
# data layer
data_dict = mock.mock_data_dict(G)
qs = np.array([0, 1, 2])
D = layers.Data_Layer_From_Dict(data_dict)
# check single metrics independently against underlying for some use-cases, e.g. hill, non-hill, accessibility...
D.assign_to_network(N, max_dist=500)
# generate some mock landuse data
landuse_labels = mock.mock_categorical_data(len(data_dict))
landuse_classes, landuse_encodings = layers.encode_categorical(
landuse_labels)
# compute hill mixed uses
D.compute_aggregated(landuse_labels,
mixed_use_keys=['hill_branch_wt'],
qs=qs)
# test against underlying method
data_map = D._data
mu_data_hill, mu_data_other, ac_data, ac_data_wt, \
stats_sum, stats_sum_wt, stats_mean, stats_mean_wt, stats_variance, stats_variance_wt, stats_max, stats_min = \
data.local_aggregator(node_map,
edge_map,
node_edge_map,
data_map,
distances,
betas,
landuse_encodings,
qs=qs,
mixed_use_hill_keys=np.array([1]))
for q_idx, q_key in enumerate(qs):
for d_idx, d_key in enumerate(distances):
assert np.allclose(
N.metrics['mixed_uses']['hill_branch_wt'][q_key][d_key],
mu_data_hill[0][q_idx][d_idx],
atol=0.001,
rtol=0)
# gini simpson
D.compute_aggregated(landuse_labels, mixed_use_keys=['gini_simpson'])
# test against underlying method
data_map = D._data
mu_data_hill, mu_data_other, ac_data, ac_data_wt, \
stats_sum, stats_sum_wt, stats_mean, stats_mean_wt, stats_variance, stats_variance_wt, stats_max, stats_min = \
data.local_aggregator(node_map,
edge_map,
node_edge_map,
data_map,
distances,
betas,
landuse_encodings,
mixed_use_other_keys=np.array([1]))
for d_idx, d_key in enumerate(distances):
assert np.allclose(N.metrics['mixed_uses']['gini_simpson'][d_key],
mu_data_other[0][d_idx],
atol=0.001,
rtol=0)
# accessibilities
D.compute_aggregated(landuse_labels, accessibility_keys=['c'])
# test against underlying method
data_map = D._data
mu_data_hill, mu_data_other, ac_data, ac_data_wt, \
stats_sum, stats_sum_wt, stats_mean, stats_mean_wt, stats_variance, stats_variance_wt, stats_max, stats_min = \
data.local_aggregator(node_map,
edge_map,
node_edge_map,
data_map,
distances,
betas,
landuse_encodings,
accessibility_keys=np.array([landuse_classes.index('c')]))
for d_idx, d_key in enumerate(distances):
assert np.allclose(
N.metrics['accessibility']['non_weighted']['c'][d_key],
ac_data[0][d_idx],
atol=0.001,
rtol=0)
assert np.allclose(N.metrics['accessibility']['weighted']['c'][d_key],
ac_data_wt[0][d_idx],
atol=0.001,
rtol=0)
# also check the number of returned types for a few assortments of metrics
mixed_uses_hill_types = np.array([
'hill', 'hill_branch_wt', 'hill_pairwise_wt', 'hill_pairwise_disparity'
])
mixed_use_other_types = np.array(
['shannon', 'gini_simpson', 'raos_pairwise_disparity'])
ac_codes = np.array(landuse_classes)
mu_hill_random = np.arange(len(mixed_uses_hill_types))
np.random.shuffle(mu_hill_random)
mu_other_random = np.arange(len(mixed_use_other_types))
np.random.shuffle(mu_other_random)
ac_random = np.arange(len(landuse_classes))
np.random.shuffle(ac_random)
# mock disparity matrix
mock_disparity_wt_matrix = np.full(
(len(landuse_classes), len(landuse_classes)), 1)
# not necessary to do all labels, first few should do
for mu_h_min in range(3):
mu_h_keys = np.array(mu_hill_random[mu_h_min:])
for mu_o_min in range(3):
mu_o_keys = np.array(mu_other_random[mu_o_min:])
for ac_min in range(3):
ac_keys = np.array(ac_random[ac_min:])
# in the final case, set accessibility to a single code otherwise an error would be raised
if len(mu_h_keys) == 0 and len(mu_o_keys) == 0 and len(
ac_keys) == 0:
ac_keys = np.array([0])
# randomise order of keys and metrics
mu_h_metrics = mixed_uses_hill_types[mu_h_keys]
mu_o_metrics = mixed_use_other_types[mu_o_keys]
ac_metrics = ac_codes[ac_keys]
N_temp = networks.Network_Layer_From_nX(G, distances)
D_temp = layers.Data_Layer_From_Dict(data_dict)
D_temp.assign_to_network(N_temp, max_dist=500)
D_temp.compute_aggregated(
landuse_labels,
mixed_use_keys=list(mu_h_metrics) + list(mu_o_metrics),
accessibility_keys=ac_metrics,
cl_disparity_wt_matrix=mock_disparity_wt_matrix,
qs=qs)
# test against underlying method
mu_data_hill, mu_data_other, ac_data, ac_data_wt, stats_sum, stats_sum_wt, \
stats_mean, stats_mean_wt, stats_variance, stats_variance_wt, stats_max, stats_min = \
data.local_aggregator(node_map,
edge_map,
node_edge_map,
data_map,
distances,
betas,
landuse_encodings,
qs=qs,
mixed_use_hill_keys=mu_h_keys,
mixed_use_other_keys=mu_o_keys,
accessibility_keys=ac_keys,
cl_disparity_wt_matrix=mock_disparity_wt_matrix)
for mu_h_idx, mu_h_met in enumerate(mu_h_metrics):
for q_idx, q_key in enumerate(qs):
for d_idx, d_key in enumerate(distances):
assert np.allclose(
N_temp.metrics['mixed_uses'][mu_h_met][q_key]
[d_key],
mu_data_hill[mu_h_idx][q_idx][d_idx],
atol=0.001,
rtol=0)
for mu_o_idx, mu_o_met in enumerate(mu_o_metrics):
for d_idx, d_key in enumerate(distances):
assert np.allclose(
N_temp.metrics['mixed_uses'][mu_o_met][d_key],
mu_data_other[mu_o_idx][d_idx],
atol=0.001,
rtol=0)
for ac_idx, ac_met in enumerate(ac_metrics):
for d_idx, d_key in enumerate(distances):
assert np.allclose(N_temp.metrics['accessibility']
['non_weighted'][ac_met][d_key],
ac_data[ac_idx][d_idx],
atol=0.001,
rtol=0)
assert np.allclose(N_temp.metrics['accessibility']
['weighted'][ac_met][d_key],
ac_data_wt[ac_idx][d_idx],
atol=0.001,
rtol=0)
# most integrity checks happen in underlying method, though check here for mismatching labels length and typos
with pytest.raises(ValueError):
D.compute_aggregated(landuse_labels[-1], mixed_use_keys=['shannon'])
with pytest.raises(ValueError):
D.compute_aggregated(landuse_labels, mixed_use_keys=['spelling_typo'])
# don't check accessibility_labels for typos - because only warning is triggered (not all labels will be in all data)
# check that unassigned data layer flags
with pytest.raises(ValueError):
D_new = layers.Data_Layer_From_Dict(data_dict)
D_new.compute_aggregated(landuse_labels, mixed_use_keys=['shannon'])
