Na}{

File Content: `plot_dbscan.py`

# -*- coding: utf-8 -*-
"""
===================================
Demo of DBSCAN clustering algorithm
===================================

Finds core samples of high density and expands clusters from them.

"""
print(__doc__)

import numpy as np

from sklearn.cluster import DBSCAN
from sklearn import metrics
from sklearn.datasets.samples_generator import make_blobs
from sklearn.preprocessing import StandardScaler


##############################################################################
# Generate sample data
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=750, centers=centers, cluster_std=0.4,
                            random_state=0)

X = StandardScaler().fit_transform(X)

##############################################################################
# Compute DBSCAN
db = DBSCAN(eps=0.3, min_samples=10).fit(X)
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
labels = db.labels_

# Number of clusters in labels, ignoring noise if present.
n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)

print('Estimated number of clusters: %d' % n_clusters_)
print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels))
print("Completeness: %0.3f" % metrics.completeness_score(labels_true, labels))
print("V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels))
print("Adjusted Rand Index: %0.3f"
      % metrics.adjusted_rand_score(labels_true, labels))
print("Adjusted Mutual Information: %0.3f"
      % metrics.adjusted_mutual_info_score(labels_true, labels))
print("Silhouette Coefficient: %0.3f"
      % metrics.silhouette_score(X, labels))

##############################################################################
# Plot result
import matplotlib.pyplot as plt

# Black removed and is used for noise instead.
unique_labels = set(labels)
colors = plt.cm.Spectral(np.linspace(0, 1, len(unique_labels)))
for k, col in zip(unique_labels, colors):
    if k == -1:
        # Black used for noise.
        col = 'k'

    class_member_mask = (labels == k)

    xy = X[class_member_mask & core_samples_mask]
    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=col,
             markeredgecolor='k', markersize=14)

    xy = X[class_member_mask & ~core_samples_mask]
    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=col,
             markeredgecolor='k', markersize=6)

plt.title('Estimated number of clusters: %d' % n_clusters_)
plt.show()

Name	Size	Permission
README.txt	101 bytes	0644
plot_adjusted_for_chance_measures.py	4300 bytes	0644
plot_affinity_propagation.py	2304 bytes	0644
plot_agglomerative_clustering.py	2931 bytes	0644
plot_agglomerative_clustering_metrics.py	4492 bytes	0644
plot_birch_vs_minibatchkmeans.py	3694 bytes	0644
plot_cluster_comparison.py	4681 bytes	0644
plot_cluster_iris.py	2593 bytes	0644
plot_color_quantization.py	3444 bytes	0644
plot_dbscan.py	2479 bytes	0644
plot_dict_face_patches.py	2747 bytes	0644
plot_digits_agglomeration.py	1694 bytes	0644
plot_digits_linkage.py	2959 bytes	0644
plot_face_compress.py	2479 bytes	0644
plot_face_segmentation.py	2839 bytes	0644
plot_face_ward_segmentation.py	2460 bytes	0644
plot_feature_agglomeration_vs_univariate_selection.py	3903 bytes	0644
plot_kmeans_assumptions.py	2040 bytes	0644
plot_kmeans_digits.py	4524 bytes	0644
plot_kmeans_silhouette_analysis.py	5888 bytes	0644
plot_kmeans_stability_low_dim_dense.py	4324 bytes	0644
plot_mean_shift.py	1793 bytes	0644
plot_mini_batch_kmeans.py	4092 bytes	0644
plot_segmentation_toy.py	3522 bytes	0644
plot_ward_structured_vs_unstructured.py	3369 bytes	0644

File Content: plot_dbscan.py

File Content: `plot_dbscan.py`