Skip to content

Commit df7c8c0

Browse files
Replaced duplicate_feature_sets.py with a JSON file of the same name
1 parent eb4e9df commit df7c8c0

4 files changed

Lines changed: 194 additions & 142 deletions

File tree

urielplus/base_uriel.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -165,7 +165,7 @@ def set_distance_metric(self, distance_metric):
165165
166166
167167
Args:
168-
distance_metric (bool): The distance metric to use for distance calculations.
168+
distance_metric (str): The distance metric to use for distance calculations.
169169
170170
Logging:
171171
Error: Logs an error if the provided distance metric value is invalid.
Lines changed: 138 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,138 @@
1+
{
2+
"uriel": [
3+
{ "target": "S_SUBJECT_BEFORE_VERB", "threshold": 1.0, "sources": ["S_SVO", "S_OSV"] },
4+
{ "target": "S_SUBJECT_AFTER_VERB", "threshold": 1.0, "sources": ["S_VSO", "S_OVS"] },
5+
{ "target": "S_OBJECT_AFTER_VERB", "threshold": 1.0, "sources": ["S_SVO", "S_VOS", "S_VOX", "S_XVO"] },
6+
{ "target": "S_OBJECT_BEFORE_VERB", "threshold": 1.0, "sources": ["S_SOV", "S_OVS", "S_XOV", "S_OVX"] },
7+
{ "target": "S_SUBJECT_BEFORE_OBJECT", "threshold": 1.0, "sources": ["S_SOV", "S_VSO"] },
8+
{ "target": "S_SUBJECT_AFTER_OBJECT", "threshold": 1.0, "sources": ["S_VOS", "S_OSV"] },
9+
10+
{ "target": "P_VOICED_PLOSIVES", "sources": [
11+
"INV_VOICED_BILABIAL_PLOSIVE",
12+
"INV_VOICED_BILABIAL_PLOSIVE_WITH_VOICED_LABIODENTAL_FRICATIVE",
13+
"INV_VOICED_BILABIAL_PLOSIVE_WITH_VOICED_BILABIAL_FRICATIVE",
14+
"INV_VOICED_ALVEOLAR_PLOSIVE",
15+
"INV_VOICED_ALVEOLAR_PLOSIVE_WITH_VOICED_DENTAL_FRICATIVE",
16+
"INV_VOICED_ALVEOLAR_PLOSIVE_WITH_VOICED_ALVEOLAR_LATERAL_FRICATIVE",
17+
"INV_VOICED_ALVEOLAR_PLOSIVE_WITH_VOICED_ALVEOPALATAL_FRICATIVE",
18+
"INV_VOICED_ALVEOLAR_PLOSIVE_WITH_VOICED_POSTALVEOLAR_FRICATIVE",
19+
"INV_VOICED_RETROFLEX_PLOSIVE",
20+
"INV_VOICED_RETROFLEX_PLOSIVE_WITH_VOICED_RETROFLEX_FRICATIVE",
21+
"INV_VOICED_PALATAL_PLOSIVE",
22+
"INV_VOICED_PALATAL_PLOSIVE_WITH_VOICED_PALATAL_FRICATIVE",
23+
"INV_VOICED_VELAR_PLOSIVE_WITH_VOICED_BILABIAL_PLOSIVE",
24+
"INV_VOICED_VELAR_PLOSIVE_WITH_VOICED_VELAR_FRICATIVE",
25+
"INV_VOICED_UVULAR_PLOSIVE"
26+
] },
27+
28+
{ "target": "P_VOICED_FRICATIVES", "sources": [
29+
"INV_VOICED_LABIODENTAL_FRICATIVE",
30+
"INV_VOICED_DENTAL_FRICATIVE",
31+
"INV_VOICED_RETROFLEX_FRICATIVE",
32+
"INV_VOICED_PALATAL_FRICATIVE",
33+
"INV_VOICED_VELAR_FRICATIVE",
34+
"INV_VOICED_GLOTTAL_FRICATIVE",
35+
"INV_VOICED_ALVEOLAR_LATERAL_FRICATIVE",
36+
"INV_VOICED_ALVEOPALATAL_FRICATIVE",
37+
"INV_VOICED_POSTALVEOLAR_FRICATIVE",
38+
"INV_VOICED_PHARYNGEAL_FRICATIVE",
39+
"INV_VOICED_BILABIAL_FRICATIVE",
40+
"INV_VOICED_UVULAR_FRICATIVE"
41+
] },
42+
43+
{ "target": "P_IMPLOSIVES", "sources": [
44+
"INV_VOICED_BILABIAL_IMPLOSIVE",
45+
"INV_VOICED_ALVEOLAR_IMPLOSIVE",
46+
"INV_VOICED_VELAR_IMPLOSIVE",
47+
"INV_VOICED_PALATAL_IMPLOSIVE"
48+
] },
49+
50+
{ "target": "P_UVULARS", "sources": [
51+
"INV_VOICELESS_UVULAR_PLOSIVE",
52+
"INV_VOICED_UVULAR_PLOSIVE",
53+
"INV_UVULAR_NASAL",
54+
"INV_UVULAR_TRILL",
55+
"INV_UVULAR_APPROXIMANT",
56+
"INV_VOICED_UVULAR_FRICATIVE"
57+
] },
58+
59+
{ "target": "P_LATERALS", "sources": [
60+
"INV_ALVEOLAR_LATERAL_APPROXIMANT",
61+
"INV_VOICED_RETROFLEX_LATERAL_APPROXIMANT",
62+
"INV_PALATAL_LATERAL_APPROXIMANT",
63+
"INV_VELAR_LATERAL_APPROXIMANT"
64+
] },
65+
66+
{ "target": "P_FRONT_ROUND_VOWELS", "sources": [
67+
"INV_CLOSE_FRONT_ROUNDED_VOWEL",
68+
"INV_CLOSE_MID_FRONT_ROUNDED_VOWEL",
69+
"INV_OPEN_MID_FRONT_ROUNDED_VOWEL",
70+
"INV_OPEN_FRONT_ROUNDED_VOWEL"
71+
] },
72+
73+
{ "target": "P_NASALS", "sources": [
74+
"INV_BILABIAL_NASAL",
75+
"INV_ALVEOLAR_NASAL",
76+
"INV_VELAR_NASAL",
77+
"INV_LABIODENTAL_NASAL",
78+
"INV_PALATAL_NASAL",
79+
"INV_RETROFLEX_NASAL",
80+
"INV_UVULAR_NASAL"
81+
] },
82+
83+
{ "target": "P_CODAS", "threshold": 1.0, "sources": ["P_COMPLEX_CODAS"] }
84+
],
85+
86+
"uriel_grambank": [
87+
{ "target": "S_GENDER_MARK", "threshold": 1.0, "sources": [
88+
"S_3RD_PERSON_GENDER_DIST",
89+
"M_2ND_PERSON_GENDER_DIST",
90+
"M_1ST_PERSON_GENDER_DIST"
91+
] },
92+
{ "target": "M_FUTURE_MARK", "threshold": 1.0, "sources": ["S_FUTURE_AFFIX"] },
93+
{ "target": "S_VERB_INIT_TRANS", "threshold": 1.0, "sources": ["S_VSO", "S_VOS"] },
94+
{ "target": "S_VERB_MED_TRANS", "threshold": 1.0, "sources": ["S_SVO", "S_OVS"] },
95+
{ "target": "S_VERB_FINAL_TRANS", "threshold": 1.0, "sources": ["S_SOV", "S_OSV"] },
96+
{ "target": "M_CLAUSE_FINAL_NEG", "threshold": 1.0, "sources": ["S_NEGATIVE_WORD_FINAL", "S_NEGATIVE_SUFFIX"] },
97+
{ "target": "M_CLAUSE_INIT_NEG", "threshold": 1.0, "sources": ["S_NEGATIVE_WORD_INITIAL", "S_NEGATIVE_PREFIX"] }
98+
],
99+
100+
"uriel_apics": [
101+
{ "target": "S_NEGATIVE_BEFORE_VERB", "threshold": 1.0, "sources": ["S_NEGATIVE_WORD_BEFORE_VERB", "S_NEGATIVE_PREFIX"] },
102+
{ "target": "S_NEGATIVE_AFTER_VERB", "threshold": 1.0, "sources": ["S_NEGATIVE_WORD_AFTER_VERB", "S_NEGATIVE_SUFFIX"] },
103+
{ "target": "S_OBJECT_AFTER_VERB", "threshold": 1.0, "sources": ["S_AVO", "S_VOA"] },
104+
{ "target": "S_OBJECT_BEFORE_VERB", "threshold": 1.0, "sources": ["S_AOV", "S_OVA"] },
105+
{ "target": "S_PLURAL_MARK", "threshold": 1.0, "sources": ["M_PROD_PLURAL_MARK", "M_ASSOC_PLURAL_MARK"] }
106+
],
107+
108+
"uriel_ewave": [
109+
{ "target": "S_COPULA_PRED_LOC", "threshold": 1.0, "sources": [
110+
"M_OTHER_FORMS/PHRASES_FOR_COPULA_ʼBEʼ:_BEFORE_LOCATIVES",
111+
"S_DELETION_OF_COPULA_BE:_BEFORE_LOCATIVES"
112+
] },
113+
{ "target": "S_COPULA_PRED_ADJ", "threshold": 1.0, "sources": [
114+
"M_OTHER_FORMS/PHRASES_FOR_COPULA_ʼBEʼ:_BEFORE_ADJPS",
115+
"S_DELETION_OF_COPULA_BE:_BEFORE_ADJPS"
116+
] },
117+
{ "target": "S_COPULA_PRED_NOUN", "threshold": 1.0, "sources": [
118+
"M_OTHER_FORMS/PHRASES_FOR_COPULA_ʼBEʼ:_BEFORE_NPS",
119+
"S_DELETION_OF_COPULA_BE:_BEFORE_NPS"
120+
] },
121+
{ "target": "S_EXISTENTIAL_VERB", "threshold": 1.0, "sources": [
122+
"S_EXISTENTIAL_CONSTRUCTION_TO_EXPRESS_POSSESSIVE"
123+
] },
124+
{ "target": "S_SERIAL_VERB_CONSTR", "threshold": 1.0, "sources": [
125+
"M_SERIAL_VERBS:_GIVE_=_ʼTO,_FORʼ",
126+
"M_SERIAL_VERBS:_GO_=_ʼMOVEMENT_AWAY_FROMʼ",
127+
"M_SERIAL_VERBS:_COME_=_ʼMOVEMENT_TOWARDSʼ",
128+
"M_SERIAL_VERBS:_CONSTRUCTIONS_WITH_3_VERBS",
129+
"M_SERIAL_VERBS:_CONSTRUCTIONS_WITH_4_OR_MORE_VERBS"
130+
] },
131+
{ "target": "S_3RD_PERSON_GENDER_DIST", "threshold": 0.0, "sources": [
132+
"M_NO_GENDER_DISTINCTION_IN_THIRD_PERSON_SINGULAR"
133+
] },
134+
{ "target": "S_GENDER_MARK", "threshold": 0.0, "sources": [
135+
"M_NO_GENDER_DISTINCTION_IN_THIRD_PERSON_SINGULAR"
136+
] }
137+
]
138+
}

0 commit comments

Comments
 (0)