49 lines
467 B
Python
49 lines
467 B
Python
import pandas as pd
|
|
import re
|
|
mapping = {s.split()[0]: s.split()[1] for s in """
|
|
AA AA
|
|
AE AE
|
|
AH UX
|
|
AO AO
|
|
AW AW
|
|
AY AY
|
|
B b
|
|
CH C
|
|
D d
|
|
DH D
|
|
EH EH
|
|
ER UXr
|
|
EY EY
|
|
F f
|
|
G g
|
|
HH h
|
|
IH IH
|
|
IY IY
|
|
JH J
|
|
K k
|
|
L l
|
|
M m
|
|
N n
|
|
NG N
|
|
OW OW
|
|
OY OY
|
|
P p
|
|
R r
|
|
S s
|
|
SH S
|
|
T t
|
|
TH T
|
|
UH UH
|
|
UW UW
|
|
V v
|
|
W w
|
|
Y y
|
|
Z z
|
|
ZH Z
|
|
""".strip().split('\n')}
|
|
|
|
mapping
|
|
sim_mat = pd.read_csv('./similarity.csv',header=0,index_col=0)
|
|
[mapping[re.sub('[0-9]','',i)] for i in sim_mat.index.tolist()]
|
|
# sim_mat.loc
|