cbruinsm commited on
Commit
b6b6666
1 Parent(s): 833a6e7

Update spaCy pipeline

Browse files
Files changed (7) hide show
  1. README.md +13 -14
  2. en_Coff_Ev1-any-py3-none-any.whl +2 -2
  3. meta.json +29 -23
  4. ner/model +0 -0
  5. ner/moves +1 -1
  6. tok2vec/model +1 -1
  7. vocab/strings.json +37 -0
README.md CHANGED
@@ -4,7 +4,6 @@ tags:
4
  - token-classification
5
  language:
6
  - en
7
- license: mit
8
  model-index:
9
  - name: en_Coff_Ev1
10
  results:
@@ -14,37 +13,37 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.9910941476
18
  - name: NER Recall
19
  type: recall
20
- value: 0.9917250159
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.9914094814
24
  ---
25
- A natural language processor API for coffee drinks in all forms built from nearly 500+ different coffee drinks for Starbucks and your local coffee shop
26
 
27
  | Feature | Description |
28
  | --- | --- |
29
  | **Name** | `en_Coff_Ev1` |
30
- | **Version** | `1.1.3` |
31
  | **spaCy** | `>=3.4.3,<3.5.0` |
32
  | **Default Pipeline** | `tok2vec`, `ner` |
33
  | **Components** | `tok2vec`, `ner` |
34
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
35
  | **Sources** | n/a |
36
- | **License** | `MIT` |
37
  | **Author** | [Chris Bruinsma,Iris Chi,Jack Felciano,Jeffrey Li,Dustin Paden]() |
38
 
39
  ### Label Scheme
40
 
41
  <details>
42
 
43
- <summary>View label scheme (15 labels for 1 components)</summary>
44
 
45
  | Component | Labels |
46
  | --- | --- |
47
- | **`ner`** | `Anti`, `add-on`, `drink`, `extra`, `milk`, `milk texture`, `pump quantity`, `roast`, `shot quality`, `shot quantity`, `size`, `syrup`, `temperature`, `toppings`, `upside-down` |
48
 
49
  </details>
50
 
@@ -52,8 +51,8 @@ A natural language processor API for coffee drinks in all forms built from nearl
52
 
53
  | Type | Score |
54
  | --- | --- |
55
- | `ENTS_F` | 99.14 |
56
- | `ENTS_P` | 99.11 |
57
- | `ENTS_R` | 99.17 |
58
- | `TOK2VEC_LOSS` | 62470.35 |
59
- | `NER_LOSS` | 178521.47 |
 
4
  - token-classification
5
  language:
6
  - en
 
7
  model-index:
8
  - name: en_Coff_Ev1
9
  results:
 
13
  metrics:
14
  - name: NER Precision
15
  type: precision
16
+ value: 0.9919703521
17
  - name: NER Recall
18
  type: recall
19
+ value: 0.9913580247
20
  - name: NER F Score
21
  type: f_score
22
+ value: 0.9916640939
23
  ---
24
+ Your Coffee at the Speed of Sound
25
 
26
  | Feature | Description |
27
  | --- | --- |
28
  | **Name** | `en_Coff_Ev1` |
29
+ | **Version** | `1.1.4` |
30
  | **spaCy** | `>=3.4.3,<3.5.0` |
31
  | **Default Pipeline** | `tok2vec`, `ner` |
32
  | **Components** | `tok2vec`, `ner` |
33
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
34
  | **Sources** | n/a |
35
+ | **License** | n/a |
36
  | **Author** | [Chris Bruinsma,Iris Chi,Jack Felciano,Jeffrey Li,Dustin Paden]() |
37
 
38
  ### Label Scheme
39
 
40
  <details>
41
 
42
+ <summary>View label scheme (16 labels for 1 components)</summary>
43
 
44
  | Component | Labels |
45
  | --- | --- |
46
+ | **`ner`** | `Anti`, `Brew Style`, `add-on`, `drink`, `extra`, `milk`, `milk texture`, `pump quantity`, `roast`, `shot quality`, `shot quantity`, `size`, `syrup`, `temperature`, `toppings`, `upside-down` |
47
 
48
  </details>
49
 
 
51
 
52
  | Type | Score |
53
  | --- | --- |
54
+ | `ENTS_F` | 99.17 |
55
+ | `ENTS_P` | 99.20 |
56
+ | `ENTS_R` | 99.14 |
57
+ | `TOK2VEC_LOSS` | 47651.16 |
58
+ | `NER_LOSS` | 161260.06 |
en_Coff_Ev1-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ab795075d2902de967c2f19410b3a4c1a29ef5e2aaa653cdde6daaed4d42a99
3
- size 5676083
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f7f8ebb1f6bf8d71de4ca929f3e36765deb1720175435db10f74f86cf42c59
3
+ size 5676022
meta.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "lang":"en",
3
  "name":"Coff_Ev1",
4
- "version":"1.1.3",
5
- "description":"A natural language processor API for coffee drinks in all forms built from nearly 500+ different coffee drinks for Starbucks and your local coffee shop",
6
  "author":"Chris Bruinsma,Iris Chi,Jack Felciano,Jeffrey Li,Dustin Paden",
7
- "email":"christopher.j.bruinsma@outlook.com",
8
  "url":"",
9
- "license":"MIT",
10
  "spacy_version":">=3.4.3,<3.5.0",
11
  "spacy_git_version":"63673a792",
12
  "vectors":{
@@ -21,6 +21,7 @@
21
  ],
22
  "ner":[
23
  "Anti",
 
24
  "add-on",
25
  "drink",
26
  "extra",
@@ -49,20 +50,25 @@
49
 
50
  ],
51
  "performance":{
52
- "ents_f":0.9914094814,
53
- "ents_p":0.9910941476,
54
- "ents_r":0.9917250159,
55
  "ents_per_type":{
 
 
 
 
 
 
 
 
 
 
56
  "size":{
57
  "p":0.9971671388,
58
  "r":0.9971671388,
59
  "f":0.9971671388
60
  },
61
- "drink":{
62
- "p":0.9922178988,
63
- "r":0.9941520468,
64
- "f":0.9931840312
65
- },
66
  "add-on":{
67
  "p":1.0,
68
  "r":0.9333333333,
@@ -79,9 +85,9 @@
79
  "f":1.0
80
  },
81
  "syrup":{
82
- "p":0.9824561404,
83
- "r":1.0,
84
- "f":0.9911504425
85
  },
86
  "pump quantity":{
87
  "p":1.0,
@@ -99,9 +105,9 @@
99
  "f":0.9927007299
100
  },
101
  "shot quality":{
102
- "p":0.9565217391,
103
- "r":0.9565217391,
104
- "f":0.9565217391
105
  },
106
  "milk":{
107
  "p":1.0,
@@ -109,9 +115,9 @@
109
  "f":1.0
110
  },
111
  "shot quantity":{
112
- "p":0.8965517241,
113
- "r":0.962962963,
114
- "f":0.9285714286
115
  },
116
  "upside-down":{
117
  "p":1.0,
@@ -129,8 +135,8 @@
129
  "f":0.9756097561
130
  }
131
  },
132
- "tok2vec_loss":624.7035384163,
133
- "ner_loss":1785.2147412348
134
  },
135
  "requirements":[
136
 
 
1
  {
2
  "lang":"en",
3
  "name":"Coff_Ev1",
4
+ "version":"1.1.4",
5
+ "description":"Your Coffee at the Speed of Sound",
6
  "author":"Chris Bruinsma,Iris Chi,Jack Felciano,Jeffrey Li,Dustin Paden",
7
+ "email":"",
8
  "url":"",
9
+ "license":"",
10
  "spacy_version":">=3.4.3,<3.5.0",
11
  "spacy_git_version":"63673a792",
12
  "vectors":{
 
21
  ],
22
  "ner":[
23
  "Anti",
24
+ "Brew Style",
25
  "add-on",
26
  "drink",
27
  "extra",
 
50
 
51
  ],
52
  "performance":{
53
+ "ents_f":0.9916640939,
54
+ "ents_p":0.9919703521,
55
+ "ents_r":0.9913580247,
56
  "ents_per_type":{
57
+ "Brew Style":{
58
+ "p":1.0,
59
+ "r":1.0,
60
+ "f":1.0
61
+ },
62
+ "drink":{
63
+ "p":0.9925788497,
64
+ "r":0.9944237918,
65
+ "f":0.9935004643
66
+ },
67
  "size":{
68
  "p":0.9971671388,
69
  "r":0.9971671388,
70
  "f":0.9971671388
71
  },
 
 
 
 
 
72
  "add-on":{
73
  "p":1.0,
74
  "r":0.9333333333,
 
85
  "f":1.0
86
  },
87
  "syrup":{
88
+ "p":0.9867256637,
89
+ "r":0.9955357143,
90
+ "f":0.9911111111
91
  },
92
  "pump quantity":{
93
  "p":1.0,
 
105
  "f":0.9927007299
106
  },
107
  "shot quality":{
108
+ "p":1.0,
109
+ "r":0.9130434783,
110
+ "f":0.9545454545
111
  },
112
  "milk":{
113
  "p":1.0,
 
115
  "f":1.0
116
  },
117
  "shot quantity":{
118
+ "p":0.8709677419,
119
+ "r":1.0,
120
+ "f":0.9310344828
121
  },
122
  "upside-down":{
123
  "p":1.0,
 
135
  "f":0.9756097561
136
  }
137
  },
138
+ "tok2vec_loss":476.511606351,
139
+ "ner_loss":1612.6005824097
140
  },
141
  "requirements":[
142
 
ner/model CHANGED
Binary files a/ner/model and b/ner/model differ
 
ner/moves CHANGED
@@ -1 +1 @@
1
- ��moves��{"0":{},"1":{"drink":905,"size":357,"syrup":354,"milk":187,"toppings":160,"temperature":130,"Anti":59,"pump quantity":58,"add-on":42,"shot quality":35,"shot quantity":34,"roast":24,"extra":18,"upside-down":12,"milk texture":9},"2":{"drink":905,"size":357,"syrup":354,"milk":187,"toppings":160,"temperature":130,"Anti":59,"pump quantity":58,"add-on":42,"shot quality":35,"shot quantity":34,"roast":24,"extra":18,"upside-down":12,"milk texture":9},"3":{"drink":905,"size":357,"syrup":354,"milk":187,"toppings":160,"temperature":130,"Anti":59,"pump quantity":58,"add-on":42,"shot quality":35,"shot quantity":34,"roast":24,"extra":18,"upside-down":12,"milk texture":9},"4":{"drink":905,"size":357,"syrup":354,"milk":187,"toppings":160,"temperature":130,"Anti":59,"pump quantity":58,"add-on":42,"shot quality":35,"shot quantity":34,"roast":24,"extra":18,"upside-down":12,"milk texture":9,"":1},"5":{"":1}}�cfg��neg_key�
 
1
+ ��moves��{"0":{},"1":{"drink":958,"size":357,"syrup":354,"milk":187,"toppings":160,"temperature":130,"Anti":59,"pump quantity":58,"add-on":42,"shot quality":35,"shot quantity":34,"roast":24,"Brew Style":24,"extra":18,"upside-down":12,"milk texture":9},"2":{"drink":958,"size":357,"syrup":354,"milk":187,"toppings":160,"temperature":130,"Anti":59,"pump quantity":58,"add-on":42,"shot quality":35,"shot quantity":34,"roast":24,"Brew Style":24,"extra":18,"upside-down":12,"milk texture":9},"3":{"drink":958,"size":357,"syrup":354,"milk":187,"toppings":160,"temperature":130,"Anti":59,"pump quantity":58,"add-on":42,"shot quality":35,"shot quantity":34,"roast":24,"Brew Style":24,"extra":18,"upside-down":12,"milk texture":9},"4":{"drink":958,"size":357,"syrup":354,"milk":187,"toppings":160,"temperature":130,"Anti":59,"pump quantity":58,"add-on":42,"shot quality":35,"shot quantity":34,"roast":24,"Brew Style":24,"extra":18,"upside-down":12,"milk texture":9,"":1},"5":{"":1}}�cfg��neg_key�
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c94701c981b78caf26ef42041e53eb64517d66383e0e42854263b51f230383b
3
  size 6009091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db3499df3285b948cb6f2dbce0e6988f781203af24aa341e6a7ce882c0c49b77
3
  size 6009091
vocab/strings.json CHANGED
@@ -282,6 +282,7 @@
282
  "Acai",
283
  "Adm",
284
  "Adm.",
 
285
  "Ai",
286
  "Ak",
287
  "Ak.",
@@ -313,9 +314,11 @@
313
  "Big",
314
  "Biscotti",
315
  "Black",
 
316
  "Blended",
317
  "Blonde",
318
  "Brew",
 
319
  "Bros",
320
  "Bros.",
321
  "Brown",
@@ -335,12 +338,15 @@
335
  "Carmel",
336
  "Cause",
337
  "Chai",
 
338
  "Chesnut",
339
  "Chip",
340
  "Chocolate",
341
  "Chocolatey",
 
342
  "Co",
343
  "Co.",
 
344
  "Coconut",
345
  "Coffee",
346
  "Cold",
@@ -355,6 +361,7 @@
355
  "Corp",
356
  "Corp.",
357
  "Cos",
 
358
  "Could",
359
  "Coz",
360
  "Cream",
@@ -365,6 +372,7 @@
365
  "D.",
366
  "D.C.",
367
  "Dare",
 
368
  "Dec",
369
  "Dec.",
370
  "December",
@@ -388,6 +396,7 @@
388
  "E.g.",
389
  "Emperor",
390
  "Espresso",
 
391
  "Extra",
392
  "F",
393
  "F.",
@@ -436,6 +445,7 @@
436
  "He's",
437
  "He\u2019s",
438
  "Hi",
 
439
  "Honey",
440
  "Hot",
441
  "How",
@@ -487,6 +497,7 @@
487
  "Kans.",
488
  "Kansas",
489
  "Kentucky",
 
490
  "Kids",
491
  "Kiwi",
492
  "Ky",
@@ -501,6 +512,7 @@
501
  "Let",
502
  "Let's",
503
  "Let\u2019s",
 
504
  "London",
505
  "Louisiana",
506
  "Lovin",
@@ -641,7 +653,9 @@
641
  "Rep.",
642
  "Rev",
643
  "Rev.",
 
644
  "Ristretto",
 
645
  "Room",
646
  "S",
647
  "S'mores",
@@ -696,6 +710,7 @@
696
  "There\u2019s",
697
  "These",
698
  "They",
 
699
  "This",
700
  "This's",
701
  "This\u2019s",
@@ -711,6 +726,7 @@
711
  "Va.",
712
  "Vanilla",
713
  "Venti",
 
714
  "Virginia",
715
  "W",
716
  "WM",
@@ -766,9 +782,11 @@
766
  "Xxx'x",
767
  "Xxx.",
768
  "Xxxx",
 
769
  "Xxxx'",
770
  "Xxxx'x",
771
  "Xxxx.",
 
772
  "Xxxxx",
773
  "Xxxxx'",
774
  "Xxxxx'x",
@@ -824,6 +842,7 @@
824
  "adm",
825
  "adm.",
826
  "ado",
 
827
  "afe",
828
  "aff",
829
  "affagato",
@@ -886,6 +905,7 @@
886
  "biscotti",
887
  "black",
888
  "ble",
 
889
  "blended",
890
  "blonde",
891
  "bon",
@@ -894,6 +914,7 @@
894
  "br.",
895
  "breakfast",
896
  "brew",
 
897
  "brewed",
898
  "bros",
899
  "bros.",
@@ -928,6 +949,7 @@
928
  "ch.",
929
  "cha",
930
  "chai",
 
931
  "chesnut",
932
  "chestnut",
933
  "chia",
@@ -940,9 +962,11 @@
940
  "cks",
941
  "classic",
942
  "cloud",
 
943
  "co",
944
  "co.",
945
  "coa",
 
946
  "cocoa",
947
  "coconut",
948
  "coffee",
@@ -958,6 +982,7 @@
958
  "corp.",
959
  "cortado",
960
  "cos",
 
961
  "couch",
962
  "could",
963
  "coz",
@@ -1043,6 +1068,7 @@
1043
  "emperor",
1044
  "en",
1045
  "en.",
 
1046
  "english",
1047
  "enn",
1048
  "enough",
@@ -1056,6 +1082,7 @@
1056
  "ess",
1057
  "est",
1058
  "eta",
 
1059
  "ev.",
1060
  "extra",
1061
  "e\u2019s",
@@ -1135,6 +1162,7 @@
1135
  "hio",
1136
  "hip",
1137
  "his",
 
1138
  "honey",
1139
  "hot",
1140
  "how",
@@ -1178,6 +1206,7 @@
1178
  "in\u2019",
1179
  "ion",
1180
  "ips",
 
1181
  "irish",
1182
  "is",
1183
  "is.",
@@ -1219,6 +1248,7 @@
1219
  "kans",
1220
  "kans.",
1221
  "ken",
 
1222
  "ket",
1223
  "kid",
1224
  "kids",
@@ -1286,6 +1316,7 @@
1286
  "mer",
1287
  "messrs",
1288
  "messrs.",
 
1289
  "mich",
1290
  "mich.",
1291
  "mid",
@@ -1471,6 +1502,7 @@
1471
  "quad",
1472
  "r",
1473
  "r.",
 
1474
  "raspberry",
1475
  "raw",
1476
  "re",
@@ -1488,6 +1520,7 @@
1488
  "rey",
1489
  "rge",
1490
  "ribbon",
 
1491
  "ristretto",
1492
  "riz",
1493
  "rk.",
@@ -1551,6 +1584,7 @@
1551
  "sso",
1552
  "st",
1553
  "st.",
 
1554
  "star",
1555
  "starberry",
1556
  "starbucks",
@@ -1593,6 +1627,7 @@
1593
  "there\u2019s",
1594
  "these",
1595
  "they",
 
1596
  "this",
1597
  "this's",
1598
  "this\u2019s",
@@ -1744,6 +1779,8 @@
1744
  "y's",
1745
  "y.",
1746
  "yal",
 
 
1747
  "you",
1748
  "y\u2019",
1749
  "y\u2019s",
 
282
  "Acai",
283
  "Adm",
284
  "Adm.",
285
+ "AeroPress",
286
  "Ai",
287
  "Ak",
288
  "Ak.",
 
314
  "Big",
315
  "Biscotti",
316
  "Black",
317
+ "Blend",
318
  "Blended",
319
  "Blonde",
320
  "Brew",
321
+ "Brew Style",
322
  "Bros",
323
  "Bros.",
324
  "Brown",
 
338
  "Carmel",
339
  "Cause",
340
  "Chai",
341
+ "Chemex",
342
  "Chesnut",
343
  "Chip",
344
  "Chocolate",
345
  "Chocolatey",
346
+ "Clover",
347
  "Co",
348
  "Co.",
349
+ "Coast",
350
  "Coconut",
351
  "Coffee",
352
  "Cold",
 
361
  "Corp",
362
  "Corp.",
363
  "Cos",
364
+ "Costa",
365
  "Could",
366
  "Coz",
367
  "Cream",
 
372
  "D.",
373
  "D.C.",
374
  "Dare",
375
+ "Dark",
376
  "Dec",
377
  "Dec.",
378
  "December",
 
396
  "E.g.",
397
  "Emperor",
398
  "Espresso",
399
+ "Ethiopian",
400
  "Extra",
401
  "F",
402
  "F.",
 
445
  "He's",
446
  "He\u2019s",
447
  "Hi",
448
+ "Honduras",
449
  "Honey",
450
  "Hot",
451
  "How",
 
497
  "Kans.",
498
  "Kansas",
499
  "Kentucky",
500
+ "Kenyan",
501
  "Kids",
502
  "Kiwi",
503
  "Ky",
 
512
  "Let",
513
  "Let's",
514
  "Let\u2019s",
515
+ "Light",
516
  "London",
517
  "Louisiana",
518
  "Lovin",
 
653
  "Rep.",
654
  "Rev",
655
  "Rev.",
656
+ "Rican",
657
  "Ristretto",
658
+ "Roast",
659
  "Room",
660
  "S",
661
  "S'mores",
 
710
  "There\u2019s",
711
  "These",
712
  "They",
713
+ "Third",
714
  "This",
715
  "This's",
716
  "This\u2019s",
 
726
  "Va.",
727
  "Vanilla",
728
  "Venti",
729
+ "Veranda",
730
  "Virginia",
731
  "W",
732
  "WM",
 
782
  "Xxx'x",
783
  "Xxx.",
784
  "Xxxx",
785
+ "Xxxx Xxxxx",
786
  "Xxxx'",
787
  "Xxxx'x",
788
  "Xxxx.",
789
+ "XxxxXxxxx",
790
  "Xxxxx",
791
  "Xxxxx'",
792
  "Xxxxx'x",
 
842
  "adm",
843
  "adm.",
844
  "ado",
845
+ "aeropress",
846
  "afe",
847
  "aff",
848
  "affagato",
 
905
  "biscotti",
906
  "black",
907
  "ble",
908
+ "blend",
909
  "blended",
910
  "blonde",
911
  "bon",
 
914
  "br.",
915
  "breakfast",
916
  "brew",
917
+ "brew style",
918
  "brewed",
919
  "bros",
920
  "bros.",
 
949
  "ch.",
950
  "cha",
951
  "chai",
952
+ "chemex",
953
  "chesnut",
954
  "chestnut",
955
  "chia",
 
962
  "cks",
963
  "classic",
964
  "cloud",
965
+ "clover",
966
  "co",
967
  "co.",
968
  "coa",
969
+ "coast",
970
  "cocoa",
971
  "coconut",
972
  "coffee",
 
982
  "corp.",
983
  "cortado",
984
  "cos",
985
+ "costa",
986
  "couch",
987
  "could",
988
  "coz",
 
1068
  "emperor",
1069
  "en",
1070
  "en.",
1071
+ "end",
1072
  "english",
1073
  "enn",
1074
  "enough",
 
1082
  "ess",
1083
  "est",
1084
  "eta",
1085
+ "ethiopian",
1086
  "ev.",
1087
  "extra",
1088
  "e\u2019s",
 
1162
  "hio",
1163
  "hip",
1164
  "his",
1165
+ "honduras",
1166
  "honey",
1167
  "hot",
1168
  "how",
 
1206
  "in\u2019",
1207
  "ion",
1208
  "ips",
1209
+ "ird",
1210
  "irish",
1211
  "is",
1212
  "is.",
 
1248
  "kans",
1249
  "kans.",
1250
  "ken",
1251
+ "kenyan",
1252
  "ket",
1253
  "kid",
1254
  "kids",
 
1316
  "mer",
1317
  "messrs",
1318
  "messrs.",
1319
+ "mex",
1320
  "mich",
1321
  "mich.",
1322
  "mid",
 
1502
  "quad",
1503
  "r",
1504
  "r.",
1505
+ "ras",
1506
  "raspberry",
1507
  "raw",
1508
  "re",
 
1520
  "rey",
1521
  "rge",
1522
  "ribbon",
1523
+ "rican",
1524
  "ristretto",
1525
  "riz",
1526
  "rk.",
 
1584
  "sso",
1585
  "st",
1586
  "st.",
1587
+ "sta",
1588
  "star",
1589
  "starberry",
1590
  "starbucks",
 
1627
  "there\u2019s",
1628
  "these",
1629
  "they",
1630
+ "third",
1631
  "this",
1632
  "this's",
1633
  "this\u2019s",
 
1779
  "y's",
1780
  "y.",
1781
  "yal",
1782
+ "yan",
1783
+ "yle",
1784
  "you",
1785
  "y\u2019",
1786
  "y\u2019s",