v = walk
walks.append(walk_sequence)
return walks
c = get_config()
# init region
region_grid = RegionGrid(config=c)
def e_distance(d):
import math
return math.exp(-d * 1.5)
distance_matrix = region_grid.get_distance_mtx(transform=e_distance)
W, t = region_grid.create_flow_matrix(c['raw_flow_file'],
region_name=c['city_name'],
time=8)
size = region_grid.grid_size * region_grid.grid_size
distance_sequences = random_walk_distance(distance_matrix, size)
time_sequences = random_walk_time(t, size)
sequences = []
for seq in distance_sequences + time_sequences:
sequences.append(" ".join([str(id) for id in seq]))
print(sequences)
# Adjacency Average Model
mse, mse_std, mae, mae_std, err_adj = cv_adj_mean(
region_grid.regions, region_grid.matrix_idx_map, y_house)
results.append(['adjacent avg', mse, mse_std, mae, mae_std])
y_is_valid = np.where(~np.isnan(y_house))[0]
y_house = y_house[y_is_valid]
# Global Avg Model
global_avg = SimilarityModel(y_house)
mse, mse_std, mae, mae_std, err_euclidean = cv_naive_mean(y_house)
results.append(['global avg', mse, mse_std, mae, mae_std])
# euclidean model
D_euclidean = region_grid.get_distance_mtx()
D_euclidean = D_euclidean[y_is_valid, :]
D_euclidean = D_euclidean[:, y_is_valid]
mod_euclidean = SimilarityModel(y_house, D_euclidean)
mse, mse_std, mae, mae_std, err_euclidean = mod_euclidean.cv_ols()
results.append(['euclidean', mse, mse_std, mae, mae_std])
# Run with Taxi flow as weighted edges
W = region_grid.weighted_mtx
W = W[y_is_valid, :]
W = W[:, y_is_valid]
mod_flow = SimilarityModel(y_house, W)
mse, mse_std, mae, mae_std, err_flow = mod_flow.cv_ols()