def neighbors_plot(self):
import gc
from numpy import histogram
import numpy as np
from sklearn.neighbors import radius_neighbors_graph
start_pos, end_pos, paths = FileSplitter.points()
del start_pos, end_pos
gc.collect()
neighbors = radius_neighbors_graph(paths, radius=0.005)
del paths
gc.collect()
neighbors = neighbors.toarray()
x = np.matrix(neighbors)
x = x.sum(axis=1)
counts = [d[0, 0] for d in x]
hist, edges = histogram(counts, bins=10, density=False)
self.plot_on_bokeh_hist('neighbors_hist.html', '# of Neighbors',
'# of Occurrance', 'Neighbors Within Radius',
hist, edges)
pass
def trajectories_hdbscan(self, min_cluster_size):
def centroids(paths):
# distances = euclidean_distances(paths)
# distances = cdist(paths, paths, 'euclidean')
clusterer = hdbscan.HDBSCAN(min_cluster_size=min_cluster_size)
cluster_labels = clusterer.fit_predict(paths)
num_clusters = len(
set(cluster_labels)) - (1 if -1 in cluster_labels else 0)
unique_labels = set(cluster_labels)
clusters = [[] for n in range(num_clusters)]
logging.info('Number of clusters: %s', num_clusters)
for i, v in enumerate(paths):
if cluster_labels[i] != -1:
clusters[cluster_labels[i]].append(v)
return clusters
start_pos, end_pos, paths = FileSplitter.points()
clusters = centroids(
paths) # Array of [start_lat, start_lon, end_lat, end_lon]
gc = self.createGeometry(clusters)
self.createJsonFile(gc)
