clustering.py
6.22 KB
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
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
import argparse
from os import path, mkdir
from utils import SubCommandRunner
from core.data import read_features, read_lst, read_labels
import numpy as np
from sklearn.cluster import KMeans
import pickle
from clustering_modules.kmeans import kmeans
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import v_measure_score
import core.measures
CLUSTERING_METHODS = {
"k-means": kmeans()
}
EVALUATION_METHODS = {
"entropy": core.measures.entropy_score,
"v-measure": v_measure_score
}
def disequilibrium_run():
pass
def measure_run(measure: str, features: str, lst: str, truelabels: str, model: str, modeltype: str):
module = CLUSTERING_METHODS[modeltype]
module.load(model)
evaluation = EVALUATION_METHODS[measure]
feats_dict = read_features(features)
labels_dict = read_labels(truelabels)
lst_dict = read_lst(lst)
lst_keys = [key for key in lst_dict]
feats = np.asarray([feats_dict[key] for key in lst_keys])
Y_pred = module.predict(feats)
Y_truth = [labels_dict[key][0] for key in lst_keys]
le = LabelEncoder()
le.fit(Y_truth)
Y_truth = le.transform(Y_truth)
eval = evaluation(Y_truth, Y_pred)
print(eval)
def kmeans_run(features: str, lst: str, k:int, kmax: int, klist, output: str):
"""
@param features: output features
@param lst: list file
@param k: k (kmin if kmax specified)
@param kmax: maximum k to compute
@param klist: list of k values to compute, ignore k value
@param output: output file if kmax not specified, else, output directory
"""
# -- READ FILES --
features_dict = read_features(features)
lst_dict = read_lst(lst)
X = np.asarray([features_dict[x] for x in lst_dict])
# Exception cases
if kmax is None and klist is None and path.isdir(output):
raise Exception("The \"output\" is an existing directory while the system is waiting the path of a file.")
if (kmax is not None or klist is not None) and path.isfile(output):
raise Exception("The \"output\" is an existing file while the system is waiting the path of a directory.")
# Mono value case
if kmax is None and klist is None:
print(f"Computing clustering with k={k}")
kmeans = KMeans(n_clusters=k, n_init=10, random_state=0).fit(X)
preds = kmeans.predict(X)
pickle.dump(kmeans, open(output, "wb"))
# Multi values case with kmax
if kmax is not None:
if not path.isdir(output):
mkdir(output)
Ks = range(k, kmax + 1)
for i in Ks:
print(f"Computing clustering with k={i}")
kmeans = KMeans(n_clusters=i, n_init=10, random_state=0).fit(X)
preds = kmeans.predict(X)
pickle.dump(kmeans, open(path.join(output, "clustering_" + str(i) + ".pkl"), "wb"))
# Second multi values case with klist
if klist is not None:
if not path.isdir(output):
mkdir(output)
for k in klist:
k = int(k)
print(f"Computing clustering with k={k}")
kmeans = KMeans(n_clusters=k, n_init=10, random_state=0).fit(X)
preds = kmeans.predict(X)
pickle.dump(kmeans, open(path.join(output, "clustering_" + str(k) + ".pkl"), "wb"))
if __name__ == "__main__":
# Main parser
parser = argparse.ArgumentParser(description="Clustering methods to apply")
subparsers = parser.add_subparsers(title="action")
# kmeans
parser_kmeans = subparsers.add_parser(
"kmeans", help="Compute clustering using k-means algorithm")
parser_kmeans.add_argument("--features", required=True, type=str, help="Features file (works with list)")
parser_kmeans.add_argument("--lst", required=True, type=str, help="List file (.lst)")
parser_kmeans.add_argument("-k", default=2, type=int,
help="number of clusters to compute. It is kmin if kmax is specified.")
parser_kmeans.add_argument("--kmax", default=None, type=int, help="if specified, k is kmin.")
parser_kmeans.add_argument("--klist", nargs="+",
help="List of k values to test. As kmax, activate the multi values mod.")
parser_kmeans.add_argument("--output", default=".kmeans", help="output file if only k. Output directory if multiple kmax specified.")
parser_kmeans.set_defaults(which="kmeans")
# measure
parser_measure = subparsers.add_parser(
"measure", help="compute the entropy")
parser_measure.add_argument("--measure",
required=True,
type=str,
choices=[key for key in EVALUATION_METHODS],
help="...")
parser_measure.add_argument("--features", required=True, type=str, help="...")
parser_measure.add_argument("--lst", required=True, type=str, help="...")
parser_measure.add_argument("--truelabels", required=True, type=str, help="...")
parser_measure.add_argument("--model", required=True, type=str, help="...")
parser_measure.add_argument("--modeltype",
required=True,
choices=[key for key in CLUSTERING_METHODS],
help="type of model for learning")
parser_measure.set_defaults(which="measure")
# disequilibrium
parser_disequilibrium = subparsers.add_parser(
"disequilibrium", help="...")
parser_disequilibrium.add_argument("--features", required=True, type=str, help="...")
parser_disequilibrium.add_argument("--lstrain", required=True, type=str, help="...")
parser_disequilibrium.add_argument("--lstest", required=True, type=str, help="...")
parser_disequilibrium.add_argument("--model", required=True, type=str, help="...")
parser_disequilibrium.add_argument("--model-type",
required=True,
choices=["kmeans", "2", "3"],
help="...")
parser_disequilibrium.set_defaults(which="disequilibrium")
# Parse
args = parser.parse_args()
# Run commands
runner = SubCommandRunner({
"kmeans": kmeans_run,
"measure": measure_run,
"disequilibrium": disequilibrium_run
})
runner.run(args.which, args.__dict__, remove="which")