def clusterData(data, clust, results, to_plot):
plot_sample_size = 6000
if clust['clustering_type'] == 'kmeans':
#TODO kmeans works well even on 2.000.000 questions
kmeans = KMeans(init='k-means++', n_clusters=clust['n_clusters'], n_init=10)
kmeans.fit(data)
clust['centers'] = kmeans.cluster_centers_
results['cluster_labels'] = kmeans.labels_
if to_plot:
plot.PlotData(data, kmeans, plot_sample_size, clust['exp'])
if clust['clustering_type'] == 'spectral':
spectral = cluster.SpectralClustering(n_clusters=clust['n_clusters'],
eigen_solver='arpack',
affinity="nearest_neighbors")
spectral.fit(data)
plot.PlotData(data, spectral, plot_sample_size, clust['exp'])
if clust['clustering_type'] == 'birch':
birch = cluster.Birch(n_clusters=results['n_clusters'])
birch.fit(data)
results['cluster_labels'] = birch.labels_
print 'number of entries clustered', len(results['cluster_labels'])
plot.PlotData(data, birch, plot_sample_size, clust['exp'])
if clust['clustering_type'] == 'dbscan':
dbscan = cluster.DBSCAN(eps=.2)
dbscan.fit(data)
results['cluster_labels'] = dbscan.labels_
plot.PlotData(data, dbscan, plot_sample_size, clust['exp'])
if clust['clustering_type'] == 'affinity_propagation':
affinity_propagation = cluster.AffinityPropagation(damping=.9, preference=-200)
affinity_propagation.fit(data)
plot.PlotData(data, affinity_propagation, plot_sample_size, clust['exp'])
if clust['clustering_type'] == 'ward':
# connectivity matrix for structured Ward
connectivity = kneighbors_graph(data, n_neighbors=10, include_self=False)
# make connectivity symmetric
connectivity = 0.5 * (connectivity + connectivity.T)
ward = cluster.AgglomerativeClustering(n_clusters=clust['n_clusters'], linkage='ward',
connectivity=connectivity)
ward.fit(data)
results['cluster_labels'] = ward.labels_
plot.PlotData(data, ward, plot_sample_size, clust['exp'])
if clust['clustering_type'] == 'average_linkage':
# connectivity matrix for structured Ward
connectivity = kneighbors_graph(data, n_neighbors=10, include_self=False)
# make connectivity symmetric
connectivity = 0.5 * (connectivity + connectivity.T)
average_linkage = cluster.AgglomerativeClustering(
linkage="average", affinity="cityblock", n_clusters=clust['n_clusters'],
connectivity=connectivity)
average_linkage.fit(data)
results['cluster_labels'] = average_linkage.labels_
plot.PlotData(data, average_linkage, plot_sample_size, clust['exp'])
df = csr.clustDfFromRes(results)
stats = csr.clusterResults(df, clust)
return df, stats
def clusterData(data, clust, results, to_plot):
plot_sample_size = 6000
if clust['clustering_type'] == 'kmeans':
#TODO kmeans works well even on 2.000.000 questions
kmeans = KMeans(init='k-means++',
n_clusters=clust['n_clusters'],
n_init=10)
kmeans.fit(data)
clust['centers'] = kmeans.cluster_centers_
results['cluster_labels'] = kmeans.labels_
if to_plot:
plot.PlotData(data, kmeans, plot_sample_size, clust['exp'])
if clust['clustering_type'] == 'spectral':
spectral = cluster.SpectralClustering(n_clusters=clust['n_clusters'],
eigen_solver='arpack',
affinity="nearest_neighbors")
spectral.fit(data)
plot.PlotData(data, spectral, plot_sample_size, clust['exp'])
if clust['clustering_type'] == 'birch':
birch = cluster.Birch(n_clusters=results['n_clusters'])
birch.fit(data)
results['cluster_labels'] = birch.labels_
print 'number of entries clustered', len(results['cluster_labels'])
plot.PlotData(data, birch, plot_sample_size, clust['exp'])
if clust['clustering_type'] == 'dbscan':
dbscan = cluster.DBSCAN(eps=.2)
dbscan.fit(data)
results['cluster_labels'] = dbscan.labels_
plot.PlotData(data, dbscan, plot_sample_size, clust['exp'])
if clust['clustering_type'] == 'affinity_propagation':
affinity_propagation = cluster.AffinityPropagation(damping=.9,
preference=-200)
affinity_propagation.fit(data)
plot.PlotData(data, affinity_propagation, plot_sample_size,
clust['exp'])
if clust['clustering_type'] == 'ward':
# connectivity matrix for structured Ward
connectivity = kneighbors_graph(data,
n_neighbors=10,
include_self=False)
# make connectivity symmetric
connectivity = 0.5 * (connectivity + connectivity.T)
ward = cluster.AgglomerativeClustering(n_clusters=clust['n_clusters'],
linkage='ward',
connectivity=connectivity)
ward.fit(data)
results['cluster_labels'] = ward.labels_
plot.PlotData(data, ward, plot_sample_size, clust['exp'])
if clust['clustering_type'] == 'average_linkage':
# connectivity matrix for structured Ward
connectivity = kneighbors_graph(data,
n_neighbors=10,
include_self=False)
# make connectivity symmetric
connectivity = 0.5 * (connectivity + connectivity.T)
average_linkage = cluster.AgglomerativeClustering(
linkage="average",
affinity="cityblock",
n_clusters=clust['n_clusters'],
connectivity=connectivity)
average_linkage.fit(data)
results['cluster_labels'] = average_linkage.labels_
plot.PlotData(data, average_linkage, plot_sample_size, clust['exp'])
df = csr.clustDfFromRes(results)
stats = csr.clusterResults(df, clust)
return df, stats
