nataliaElv HF staff commited on
Commit
e9c936c
·
1 Parent(s): 263c694

updated data

Browse files
app.py CHANGED
@@ -23,6 +23,7 @@ def build_dataframes(covered_language_codes):
23
 
24
  # Create a dataframe for languages with a lead
25
  languages_with_lead = clean_languages[clean_languages['Code'].isin(covered_language_codes)].sort_values(by='Code')
 
26
 
27
  # Create a dataframe for languages without a lead
28
  languages_without_lead = clean_languages[~clean_languages['Code'].isin(covered_language_codes)].sort_values(by='Code')
 
23
 
24
  # Create a dataframe for languages with a lead
25
  languages_with_lead = clean_languages[clean_languages['Code'].isin(covered_language_codes)].sort_values(by='Code')
26
+ languages_with_lead.to_csv('data/languages_with_lead.csv', index=False)
27
 
28
  # Create a dataframe for languages without a lead
29
  languages_without_lead = clean_languages[~clean_languages['Code'].isin(covered_language_codes)].sort_values(by='Code')
data/covered_languages.txt CHANGED
@@ -68,6 +68,7 @@ Ido
68
  Chewa, Tumbuka
69
  Awadhi, Odia, Sindhi
70
  Kashmiri
 
71
  Kazakh
72
  Uzbek
73
  Asturian
@@ -90,6 +91,8 @@ Lithuanian
90
  Catalan
91
  Spanish
92
  Standard Arabic, Egyptian Arabic, Moroccan Arabic
 
 
93
  Basque
94
  Galician
95
  Paraguayan Guaraní
@@ -118,4 +121,8 @@ Goan Konkani
118
  North Azerbaijani
119
  Rusyn
120
  Ancient Greek
121
- Romanian
 
 
 
 
 
68
  Chewa, Tumbuka
69
  Awadhi, Odia, Sindhi
70
  Kashmiri
71
+ Kashmiri
72
  Kazakh
73
  Uzbek
74
  Asturian
 
91
  Catalan
92
  Spanish
93
  Standard Arabic, Egyptian Arabic, Moroccan Arabic
94
+ Moroccan Arabic
95
+ Egyptian Arabic
96
  Basque
97
  Galician
98
  Paraguayan Guaraní
 
121
  North Azerbaijani
122
  Rusyn
123
  Ancient Greek
124
+ Romanian
125
+ Kongo, Luganda
126
+ Luganda
127
+ Nahuatl
128
+ Greek
data/languages_with_lead.csv ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Language,Code
2
+ Afrikaans,afr
3
+ Amharic,amh
4
+ Amis,ami
5
+ Standard Arabic,arb
6
+ Najdi Arabic,ars
7
+ Moroccan Arabic,ary
8
+ Egyptian Arabic,arz
9
+ Assamese,asm
10
+ Asturian,ast
11
+ Awadhi,awa
12
+ North Azerbaijani,azj
13
+ Bashkir,bak
14
+ Bengali,ben
15
+ Bhojpuri,bho
16
+ Catalan,cat
17
+ Czech,ces
18
+ Chuvash,chv
19
+ Mandarin Chinese,cmn
20
+ Crimean Tatar,crh
21
+ Dagbani,dag
22
+ Danish,dan
23
+ German,deu
24
+ Greek,ell
25
+ Basque,eus
26
+ Ewe,ewe
27
+ Persian,fas
28
+ Fante,fat
29
+ Fijian,fij
30
+ Filipino,fil
31
+ French,fra
32
+ Nigerian Fulfulde,fuv
33
+ Scottish Gaelic,gla
34
+ Galician,glg
35
+ Gilaki,glk
36
+ Goan Konkani,gom
37
+ Ancient Greek (to 1453),grc
38
+ Swiss German,gsw
39
+ Paraguayan Guaraní,gug
40
+ Gujarati,guj
41
+ Hausa,hau
42
+ Hebrew,heb
43
+ Hindi,hin
44
+ Igbo,ibo
45
+ Ido,ido
46
+ Italian,ita
47
+ Japanese,jpn
48
+ Karakalpak,kaa
49
+ Kannada,kan
50
+ Kashmiri,kas
51
+ Kazakh,kaz
52
+ Kikuyu,kik
53
+ Kinyarwanda,kin
54
+ Kirghiz,kir
55
+ Northern Kurdish,kmr
56
+ Kongo,kng
57
+ Korean,kor
58
+ Kamba,ktu
59
+ Lingala,lin
60
+ Lithuanian,lit
61
+ Lombard,lmo
62
+ Luganda,lug
63
+ Standard Latvian,lvs
64
+ Maithili,mai
65
+ Malayalam,mal
66
+ Marathi,mar
67
+ Mari,mhr
68
+ Nahuatl,nah
69
+ Low German,nds
70
+ Dutch,nld
71
+ Nepali,npi
72
+ Chewa,nya
73
+ Odia,ory
74
+ Ossetian,oss
75
+ Punjabi,pan
76
+ Southern Pashto,pbt
77
+ Nigerian Pidgin,pcm
78
+ Pijin,pis
79
+ Plateau Malagasy,plt
80
+ Polish,pol
81
+ Portuguese,por
82
+ Romanian,ron
83
+ Rusyn,rue
84
+ Rundi,run
85
+ Russian,rus
86
+ Yakut,sah
87
+ Sanskrit,san
88
+ Sinhala,sin
89
+ Saraiki,skr
90
+ Slovak,slk
91
+ Sindhi,snd
92
+ Somali,som
93
+ Spanish,spa
94
+ Sranan Tongo,srn
95
+ Swati,ssw
96
+ Sundanese,sun
97
+ Swedish,swe
98
+ Swahili,swh
99
+ Tahitian,tah
100
+ Tamil,tam
101
+ Tatar,tat
102
+ Telugu,tel
103
+ Thai,tha
104
+ Tigrinya,tir
105
+ Tumbuka,tum
106
+ Turkish,tur
107
+ Twi,twi
108
+ Tuvan,tyv
109
+ Udmurt,udm
110
+ Ukrainian,ukr
111
+ Urdu,urd
112
+ Northern Uzbek,uzn
113
+ Venetian,vec
114
+ Vietnamese,vie
115
+ Wolof,wol
116
+ Xhosa,xho
117
+ Yoruba,yor
118
+ Chinese (Yue/Cantonese),yue
119
+ Standard Malay,zsm
120
+ Zulu,zul
121
+ Min Nan Chinese,nan