-
Notifications
You must be signed in to change notification settings - Fork 0
/
drawing.py
87 lines (73 loc) · 2.76 KB
/
drawing.py
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
"""
drawing.py
Copyright (C) 2020 Elodie Escriva, Kaduceo <[email protected]>
Copyright (C) 2020 Jean-Baptiste Excoffier, Kaduceo <[email protected]>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
"""
import pandas as pd
import matplotlib.pyplot as plt
def draw_avg_influence_per_class(influences, labels, labels_name):
"""
Draws the absolute average influence for each class.
Parameters
----------
influences :
Influences to show.
labels : pandas.DataFrame
The label values to split data.
labels_name : list
Class names.
"""
complete_datas = influences.copy()
complete_datas["labels"] = labels
avg_infs_per_class = pd.DataFrame(columns=influences.columns)
for c in range(labels.nunique()):
temp_avg = (
abs(complete_datas[complete_datas.labels == c])
.mean()
.drop(["labels"])
.rename(labels_name[c])
)
avg_infs_per_class = avg_infs_per_class.append(temp_avg)
avg_infs_per_class.T.plot.barh(rot=0, title="Average attribute influence by class")
plt.xlabel("Mean absolute influence", fontweight="bold")
plt.show()
def draw_influence_instance(influences, label, labels_name, id_instance, problem_type):
"""
Draws the influence of the instance of interess.
Parameters
----------
influences : pandas.DataFrame
Influences to show.
labels : pandas.DataFrame
The label values to split data.
labels_name : list
Class names.
id_instance : int
Index of the instance to show.
problem_type : {"classification", "regression"}
Type of machine learning problem.
"""
infs_instance = influences.loc[id_instance].sort_values(ascending=True)
colors = ["green" if x > 0 else "red" for x in infs_instance]
if problem_type == "Regression":
title_ = "Patient : {} ; True Value : {}".format(
id_instance, label[id_instance]
)
else:
title_ = "Patient : {} ; True Class : {}".format(
id_instance, labels_name[label[id_instance]]
)
plt.title(title_)
plt.xlabel("Influences")
infs_instance.plot.barh(color=colors)
plt.show()