DBSCAN.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

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

# file = "data/mexico/Mexico2015-2018APR.txt"
file = "data/lagos/Apr2017-Oct2019.txt"
data = pd.read_csv(file, sep='\t')
data = data.dropna()


data = data[data["displacement"] != 0]

dataCoh = data[data["coh"] > 0.3]

X = StandardScaler().fit_transform(dataCoh)

# 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)
n_noise_ = list(labels).count(-1)

print('Estimated number of clusters: %d' % n_clusters_)
print('Estimated number of noise points: %d' % n_noise_)
# 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

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

    class_member_mask = (labels == k)

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

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

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

plt.get_figure().savefig('dbscan.png', bbox_inches='tight')