plot_clusters.py
2.95 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
'''
Take a file and plot its data onto a 2d or 3d axis depending on the data.
'''
import os
import numpy as np
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
import argparse
import json
import pandas as pd
# Defining useful functions
'''
Read the file whose content is metas and vectors.
Returns two numpy array : (metas, vectors)
'''
def read_vector_file(filename, toy_version=False):
vectors = np.empty((0, 1), np.float32)
metas = np.empty((0, 4), np.float32)
with open(filename, "r") as f:
for i, line in enumerate(f):
if toy_version == True and i > 100:
break
spl_line = line.split(" ")
if(len(vectors) == 0):
vectors = np.empty((0, len(spl_line[1:])), np.float32)
metas = np.append(
metas,
np.asarray([spl_line[0].split(",")]),
axis=0)
vectors = np.append(
vectors,
np.asarray([spl_line[1:]], dtype=np.float32),
axis=0)
return (metas, vectors)
'''
Check if the two given files have the same order.
'''
def check_files(vector_file, cluster_file):
with open(vector_file, "r") as f1, open(cluster_file, "r") as f2:
for line1, line2 in zip(f1, f2):
line1_str = line1.strip()
line2_str = line2.strip()
metas1 = line1_str.split(" ")[0].split(",")
metas2 = line2_str.split(" ")[0].split(",")
if(not metas1[0] == metas2[0] or not metas1[3] == metas2[3]):
return False
return True
from data import read_file, index_by_id
# Defining argparse
parser = argparse.ArgumentParser(prog='Plotter', description='Plot a file of 2d ou 3d dimension')
parser.add_argument('clusterfile', type=str,
help='the path of the cluster file')
parser.add_argument('vectorfile', type=str,
help='the path of the vectors file')
parser.add_argument('-o-', '--output', type=str,
default='plot.pdf',
help='the path of the ploted file')
args = parser.parse_args()
# Editing global variable
CLUSTERFILE_PATH=args.clusterfile
VECTORFILE_PATH=args.vectorfile
OUTFILE_PATH = args.output
data_vector = read_file(VECTORFILE_PATH)
features = np.asarray([x[1] for x in data_vector])
features_T = np.transpose(features)
data_cluster = read_file(CLUSTERFILE_PATH)
data_cluster_ind = index_by_id(data_cluster)
clusters = [data_cluster_ind[x[0][0]][x[0][3]][0][1] for x in data_vector]
# TODO: compute tsne file
# TODO: adapt the script for the new library
df = pd.DataFrame(dict(
x=features_T[0],
y=features_T[1],
cluster=np.transpose(clusters)[0]
))
exit(1)
# Get Vectors
metas, vectors = read_vector_file(VECTORFILE_PATH, toy_version = TOY_VERSION)
vectors_T = np.transpose(vectors)
# Get Clusters
metas, clusters = read_vector_file(CLUSTERFILE_PATH, toy_version = TOY_VERSION)
#print(np.transpose(clusters)[0])
#print(np.transpose(metas)[0])
groups = df.groupby('cluster')
# Plot
fig, ax = plt.subplots()
for cluster, group in groups:
ax.plot(group.x, group.y, marker='o', linestyle='', ms=2, label=cluster)
ax.legend()
plt.savefig(OUTFILE_PATH)