created triplet code wip

create_triplets.py

@@ -0,0 +1,10 @@
+import pandas as pd
+
+audio_file = pd.read_csv('./outputs/audio.csv',names=['word','voice','rate','type','filename'])
+word_goups = audio_file.groupby('word')
+# audio
+lst = [1, 2, 3, 1, 2, 3]
+s = pd.Series([1, 2, 3, 10, 20, 30], lst)
+df3 = pd.DataFrame({'X' : ['A', 'B', 'A', 'B'], 'Y' : [1, 4, 3, 2]})
+df3
+s.groupby(level=0).sum()

generate_similar.py

@@ -1,3 +1,48 @@
 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')}
 
-pd.read_csv('./similarity.csv')
+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