def get_sorted_distances_from_cluster(cluster_number):
'''
get clusters in order of least-greatest distance from
a certain cluster
:param cluster_number: the reference cluster
:return: list of clusters ordered by distance
'''
kmeans_clusters_request = get_kmeans_clusters()
if kmeans_clusters_request["error"]:
print(kmeans_clusters_request["error"])
return None
kmeans_clusters = kmeans_clusters_request["data"]
cluster = None
distances = {}
sorted_distances = []
for c in kmeans_clusters:
if c.cluster_number == cluster_number:
cluster = c
if cluster == None:
return {}
for other_cluster in kmeans_clusters:
if other_cluster.cluster_number != cluster.cluster_number:
distances[
other_cluster.cluster_number] = distance_between_coordinates(
cluster.get_coordinates(), other_cluster.get_coordinates())
for key, value in sorted(distances.items(), key=lambda item: item[1]):
sorted_distances.append(key)
return sorted_distances
def find_closest_cluster(cluster_number):
'''
Find the closest cluster to a specific cluster
:param cluster_number: reference cluster
:return: number of closest cluster
'''
cluster_request = get_kmeans_cluster(cluster_number)
clusters_request = get_kmeans_clusters()
closest_cluster = cluster_number
min_distance = sys.maxint
if cluster_request["error"]:
print(cluster_request["error"])
return closest_cluster
if clusters_request["error"]:
print(clusters_request["error"])
return closest_cluster
cluster = cluster_request["data"]
clusters = clusters_request["data"]
cluster_coordinates = cluster.get_coordinates()
if not cluster:
return closest_cluster
for c in clusters:
if cluster.cluster_number != c.cluster_number:
distance = distance_between_coordinates(cluster_coordinates,
c.get_coordinates())
if distance < min_distance:
min_distance = distance
closest_cluster = c.cluster_number
return closest_cluster
def cluster_size_upper_threshold():
'''
get the size threshold for compatible clusters
calculations
:return: size threshold
'''
clusters_request = get_kmeans_clusters()
if clusters_request["error"]:
print(clusters_request["error"])
return 0
clusters = clusters_request["data"]
cluster_lengths = [len(cluster.ingredients) for cluster in clusters]
kmeans_stats = find_stats(cluster_lengths)
return kmeans_stats["mean"]
def largest_cluster_size():
'''
Get the largest cluster size
:return: size of largest cluster
'''
clusters_request = get_kmeans_clusters()
max_size = 0
if clusters_request["error"]:
print(clusters_request["error"])
return max_size
clusters = clusters_request["data"]
for cluster in clusters:
if len(cluster.ingredients) < max_size:
max_size = len(cluster.ingredients)
return max_size
def smallest_cluster_size():
'''
Find the size of the smallest cluster
:return: size of smallest cluster
'''
clusters_request = get_kmeans_clusters()
min_size = sys.maxint
if clusters_request["error"]:
print(clusters_request["error"])
return min_size
clusters = clusters_request["data"]
for cluster in clusters:
if len(cluster.ingredients) < min_size:
min_size = len(cluster.ingredients)
return min_size
def create_mean_shift_clusters():
clusters_request = get_kmeans_clusters()
if clusters_request["error"]:
return None
clusters = clusters_request["data"]
keys = []
mean_shift_coordinates = []
for cluster in clusters:
mean_shift_coordinates.append(cluster.get_coordinates_list())
keys.append(cluster.cluster_number)
mean_shift_array = np.array(mean_shift_coordinates)
bandwidth = estimate_bandwidth(mean_shift_array, quantile=0.1)
clustering = MeanShift(bandwidth=bandwidth).fit(mean_shift_array)
for i, key in enumerate(keys):
print(str(key) + ": " + str(clustering.labels_[i]))
def kmeans_test():
'''
:return:
'''
clusters_request = get_kmeans_clusters()
if clusters_request["error"] != None:
raise (clusters_request["error"])
clusters = clusters_request["data"]
cluster_distances = get_all_kmeans_cluster_distances_dictionary()
cluster_lengths = [len(cluster.ingredients) for cluster in clusters]
kmeans_stats = find_stats(cluster_lengths)
with open(os.getcwd() + '/app/test/kmeans_clusters.txt', 'w') as textfile:
textfile.write("Size stats\n")
textfile.write("-------------------------\n")
textfile.write("Mean: " + str(kmeans_stats["mean"]))
textfile.write("\n")
textfile.write("Median: " + str(kmeans_stats["median"]))
textfile.write("\n")
textfile.write("St Dev: " + str(kmeans_stats["stdev"]))
textfile.write("\n")
textfile.write("Quartile 1: " + str(kmeans_stats["qt1"]))
textfile.write("\n")
textfile.write("Quartile 2: " + str(kmeans_stats["qt2"]))
textfile.write("\n")
textfile.write("-------------------------\n")
textfile.write("\n")
for x, cluster in enumerate(clusters):
textfile.write("Cluster " + str(x) + "\n")
textfile.write("-------------------------\n")
textfile.write("Cluster size: " + str(len(cluster.ingredients)) +
"\n")
textfile.write(",".join(cluster.get_ingredient_strings()) + "\n")
textfile.write("-------------------------\n")
textfile.write("\n")
textfile.write("\n")
for i, entry in enumerate(cluster_distances):
textfile.write("Distances from Cluster " + str(i) + "\n")
textfile.write("-------------------------\n")
for key, value in sorted(entry.items(), key=lambda item: item[1]):
textfile.write("%s: %s \n" % (key, value))
textfile.write("-------------------------\n")
textfile.write("\n")
def get_all_kmeans_cluster_distances():
'''
get the distances from each k-means cluster to the other
:return: list of cluster distances with indices
corresponding to cluster number
'''
kmeans_clusters_request = get_kmeans_clusters()
if kmeans_clusters_request["error"]:
print(kmeans_clusters_request["error"])
return None
kmeans_clusters = kmeans_clusters_request["data"]
cluster_distances = [None] * len(kmeans_clusters)
for c1 in kmeans_clusters:
distances = [None] * len(kmeans_clusters)
for c2 in kmeans_clusters:
distances[c2.cluster_number] = distance_between_coordinates(
c1.get_coordinates(), c2.get_coordinates())
cluster_distances[c1.cluster_number] = distances
return cluster_distances