technical_drawings_extraction/dbscan_clustering.py

print(__doc__)

import numpy as np
import pandas

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


# #############################################################################
data_df = pandas.read_csv("values.csv", sep=",")
data_df.head(3)
data = data_df[["X1","Y1","X2","Y2"]]
print(data)
data = StandardScaler().fit_transform(data)

# #############################################################################
# Compute DBSCAN
db = DBSCAN(eps=0.15, min_samples=1).fit(data)
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
labels = db.labels_
print(data[labels == 0])
data_df["cluster"] = 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("Silhouette Coefficient: %0.3f"
      % metrics.silhouette_score(data, labels))

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

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

    xy = data[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()

print(data_df.head(3))
data_df.to_csv("values_clustered.csv")
data_df.groupby('cluster')['Text'].apply(' '.join).reset_index().to_csv("text_merged.csv")