def main():
with open("json/{}.json".format(METRIC)) as data:
json_obj = json.load(data)
created_clusters = clusters.read_json(json_obj)
labels = make_vectors.get_list("data/itemIndex.txt")
hierarchy, level1_set, level2_set = get_hierarchy("data/itemHierarchy.csv")
list_nodes = prune(
created_clusters,
len(level1_set)) # Prune so that there are len(level1_set) nodes
# Evaluate which items belong to which clusters in the len(level1_set) nodes
for node in list_nodes:
evaluate_cluster(node, labels, hierarchy)
clusters.printhclust(created_clusters, labels)
import clusters
docs, words, data = clusters.readfile('titles_vectors.txt')
rdata = clusters.rotatematrix(data)
clust = clusters.hcluster(rdata, distance=clusters.pearson)
print('clusters by pearson correlation')
clusters.printhclust(clust, labels=words)
clusters.drawdendrogram(clust, words, jpeg='wordsclustpearson.jpg')
clust = clusters.hcluster(rdata, distance=clusters.tanimoto)
print('clusters by tanimoto coefficient')
clusters.printhclust(clust, labels=words)
clusters.drawdendrogram(clust, words, jpeg='wordsclusttanimoto.jpg')
clust = clusters.hcluster(rdata, distance=clusters.euclidean)
print('clusters by euclidean distance')
clusters.printhclust(clust, labels=words)
clusters.drawdendrogram(clust, words, jpeg='wordsclusteuclidean.jpg')
import clusters
docs, words, data = clusters.readfile('titles_vectors.txt')
clust = clusters.hcluster(data, distance=clusters.pearson)
print('clusters by pearson correlation')
clusters.printhclust(clust, labels=docs)
clusters.drawdendrogram(clust, docs, jpeg='docsclust_pearson.jpg')
clust = clusters.hcluster(data, distance=clusters.tanimoto)
print('clusters by tanimoto coefficient')
clusters.printhclust(clust, labels=docs)
clusters.drawdendrogram(clust, docs, jpeg='docsclust_tanimoto.jpg')
clust = clusters.hcluster(data, distance=clusters.euclidean)
print('clusters by euclidean distance')
clusters.printhclust(clust, labels=docs)
clusters.drawdendrogram(clust, docs, jpeg='docsclust_euclidean.jpg')
clust = clusters.hcluster(data, distance=clusters.cosine)
print('clusters by euclidean distance')
clusters.printhclust(clust, labels=docs)
clusters.drawdendrogram(clust, docs, jpeg='docsclust_cosine.jpg')
import clusters
row_names, column_names, data = clusters.readfile('dataset_vectors.txt')
clust = clusters.hcluster(data)
print('clusters by euclidean distance')
clusters.printhclust(clust, labels=row_names)
clusters.drawdendrogram(clust,
row_names,
jpeg='hcluster_euclidean_centroid.jpg')
print()
clust = clusters.hcluster(data, clusters.find_by_min)
print('clusters by euclidean distance')
clusters.printhclust(clust, labels=row_names)
clusters.drawdendrogram(clust, row_names, jpeg='hcluster_euclidean_min.jpg')
print()
clust = clusters.hcluster(data, clusters.find_by_max)
print('clusters by euclidean distance')
clusters.printhclust(clust, labels=row_names)
clusters.drawdendrogram(clust, row_names, jpeg='hcluster_euclidean_max.jpg')
import clusters, data_processing
'''Import Dataset'''
data = data_processing.open_csv_file('dataset.csv')
'''Create a list of countries in the order of the similarity matrix'''
countries_list = data_processing.get_country_names(data)
'''Create numerical attributes matrix'''
attr_matrix = data_processing.create_attribute_matrix(data)
data_processing.str_to_float(attr_matrix)
'''hierachical clustering: euclidean distance'''
num_cluster = 3
resulting_clusters = clusters.hcluster(attr_matrix,
distance=clusters.euclidean)
print('clusters by euclidean distance')
clusters.printhclust(resulting_clusters, labels=countries_list)
clusters.drawdendrogram(resulting_clusters,
countries_list,
jpeg='Euclidean Cluster.jpg')
'''hierachical clustering: tanimoto coefficient'''
resulting_clusters = clusters.hcluster(attr_matrix, distance=clusters.tanimoto)
print('clusters by tanimoto coefficient')
clusters.printhclust(resulting_clusters, labels=countries_list)
clusters.drawdendrogram(resulting_clusters,
countries_list,
jpeg='Tanimoto Cluster.jpg')
print()
'''hierachical clustering: pearson similarity'''
resulting_clusters = clusters.hcluster(attr_matrix, distance=clusters.pearson)
print('clusters by pearson correlation')
clusters.printhclust(resulting_clusters, labels=countries_list)
clusters.drawdendrogram(resulting_clusters,
countries_list,