1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
| import pandas as pd
from pandas import read_csv
import numpy as np
from matplotlib import pyplot as plt
from pylab import rcParams
from scipy.cluster.hierarchy import dendrogram
from sklearn.cluster import AgglomerativeClustering, KMeans
# figure size
rcParams['figure.figsize'] = 70, 40
def plot_dendrogram(model, labels, **kwargs):
""" Create linkage matrix and then plot the dendrogram """
# create the counts of samples under each node
counts = np.zeros(model.children_.shape[0])
n_samples = len(model.labels_)
for i, merge in enumerate(model.children_):
current_count = 0
for child_idx in merge:
if child_idx < n_samples:
current_count += 1 # leaf node
else:
current_count += counts[child_idx - n_samples]
counts[i] = current_count
linkage_matrix = np.column_stack([model.children_, model.distances_,
counts]).astype(float)
# Plot the corresponding dendrogram
dendrogram(linkage_matrix, labels=labels, **kwargs)
def main(sim_mat, names):
# load the similarity matrix
df = pd.read_csv(sim_mat, delimiter=";", header=None)
matrix = df.to_numpy()
# perform the clustering
model_1 = AgglomerativeClustering(n_clusters=None, affinity="precomputed",
linkage="average", distance_threshold=0)
# NOTE the number of clusters is here!!
model_2 = KMeans(n_clusters=40)
# get the names
de = pd.read_csv(names, encoding="latin-1", header=None)
labels = de[0].to_list()
# print("Sizes:", matrix.shape, len(labels))
model_1 = model_1.fit(matrix)
model_2 = model_2.fit(matrix)
return model_1, model_2, labels
if __name__ == "__main__":
model_1, model_2, labels = main(sim_mat='C:/Users/click/Desktop/doctorat/rfiddd/fichier trouvé resultats/2020-07-22/FDA_matrice_bisim.csv',
names='C:/Users/click/Desktop/doctorat/rfiddd/fichier trouvé resultats/2020-07-22/FDA_med-unique.csv')
# print the KMeans results
print("KMeans results")
for name, cluster in zip(labels, model_2.labels_):
print(f"- {name:<25}: {cluster}")
# plot the top three levels of the dendrogram
print("\nCreating the dendrogram...")
plot_dendrogram(model_1, labels=labels, truncate_mode='level')
plt.savefig("dendrogram.png")
print("Done!") |
