cbruinsm commited on
Commit
00b47b3
1 Parent(s): 6efaeb3

Update spaCy pipeline

Browse files
Files changed (10) hide show
  1. README.md +3 -48
  2. config.cfg +1 -4
  3. en_Coff_Ev1-any-py3-none-any.whl +2 -2
  4. meta.json +73 -70
  5. ner/cfg +1 -2
  6. ner/model +0 -0
  7. ner/moves +0 -0
  8. tok2vec/model +1 -1
  9. tokenizer +0 -0
  10. vocab/strings.json +21 -11
README.md CHANGED
@@ -4,7 +4,6 @@ tags:
4
  - token-classification
5
  language:
6
  - en
7
- license: cc-by-nc-sa-3.0
8
  model-index:
9
  - name: en_Coff_Ev1
10
  results:
@@ -14,55 +13,11 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.9673151751
18
  - name: NER Recall
19
  type: recall
20
- value: 0.9872915012
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.9772012579
24
  ---
25
- Your Coffee Ordered at the Speed of Sound
26
-
27
- For citations please use the included ```refs.bib``` this project was a collaboration between five students with a common goal of simplifying the ordering process.
28
-
29
- You *are permitted* to use this software for any projects, however this is *not permitted* for use in any commerical instances under our ```cc-by-nc-sa-3.0``` <br>
30
- license without explicit permissions from the author(s).
31
-
32
-
33
-
34
- | Feature | Description |
35
- | --- | --- |
36
- | **Name** | `en_Coff_Ev1` |
37
- | **Version** | `1.3.2` |
38
- | **spaCy** | `>=3.4.3,<3.5.0` |
39
- | **Default Pipeline** | `tok2vec`, `ner` |
40
- | **Components** | `tok2vec`, `ner` |
41
- | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
42
- | **Sources** | n/a |
43
- | **License** | `cc-by-nc-sa-3.0` |
44
- | **Author** | [C.Bruinsma,I.Chi,J.Feliciano,J.Li,D.Paden]() |
45
-
46
- *THIS SOFTWARE IS PROVIDED AS IS BY ITS AUTHORS UNDER NO WARRANTY OF ITS FUNCTION.*
47
-
48
- ### Label Scheme
49
-
50
- <details>
51
-
52
- <summary>View label scheme (20 labels for 1 components)</summary>
53
-
54
- | Component | Labels |
55
- | --- | --- |
56
- | **`ner`** | `Anti`, `Blended`, `Brew Style`, `Coffee Varietal`, `add-on`, `drink`, `extra`, `hot breakfast`, `milk`, `milk texture`, `pastry`, `pump quantity`, `roast`, `shot quality`, `shot quantity`, `size`, `syrup`, `temperature`, `toppings`, `upside-down` |
57
-
58
- </details>
59
-
60
- ### Accuracy
61
-
62
- | Type | Score |
63
- | --- | --- |
64
- | `ENTS_F` | 97.72 |
65
- | `ENTS_P` | 96.73 |
66
- | `ENTS_R` | 98.73 |
67
- | `TOK2VEC_LOSS` | 54858.85 |
68
- | `NER_LOSS` | 427986.33 |
 
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: 0.9771888628
17
  - name: NER Recall
18
  type: recall
19
+ value: 0.9771888628
20
  - name: NER F Score
21
  type: f_score
22
+ value: 0.9771888628
23
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.cfg CHANGED
@@ -22,9 +22,7 @@ tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
22
 
23
  [components.ner]
24
  factory = "ner"
25
- incorrect_spans_key = null
26
  moves = null
27
- scorer = {"@scorers":"spacy.ner_scorer.v1"}
28
  update_with_oracle_cut_size = 100
29
 
30
  [components.ner.model]
@@ -91,7 +89,6 @@ max_epochs = 0
91
  max_steps = 20000
92
  eval_frequency = 200
93
  frozen_components = []
94
- annotating_components = []
95
  before_to_disk = null
96
 
97
  [training.batcher]
@@ -120,7 +117,7 @@ L2 = 0.01
120
  grad_clip = 1.0
121
  use_averages = false
122
  eps = 0.00000001
123
- learn_rate = 0.001
124
 
125
  [training.score_weights]
126
  ents_f = 1.0
 
22
 
23
  [components.ner]
24
  factory = "ner"
 
25
  moves = null
 
26
  update_with_oracle_cut_size = 100
27
 
28
  [components.ner.model]
 
89
  max_steps = 20000
90
  eval_frequency = 200
91
  frozen_components = []
 
92
  before_to_disk = null
93
 
94
  [training.batcher]
 
117
  grad_clip = 1.0
118
  use_averages = false
119
  eps = 0.00000001
120
+ learn_rate = 0.0001
121
 
122
  [training.score_weights]
123
  ents_f = 1.0
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:c4bbc79a519d0bcfe1ad1badb8809a7aa6841444b3045b9842f05943978c586e
3
- size 5694492
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51562437ac686ba7646d19b60ae67e9384bc037a2574e7bcb3747b9a5de93b0d
3
+ size 5681594
meta.json CHANGED
@@ -2,13 +2,13 @@
2
  "lang":"en",
3
  "name":"Coff_Ev1",
4
  "version":"1.4.0",
5
- "description":"Last version was terrible, so it had to be updated",
6
- "author":"",
7
  "email":"",
8
  "url":"",
9
  "license":"",
10
- "spacy_version":">=3.4.3,<3.5.0",
11
- "spacy_git_version":"63673a792",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
@@ -24,7 +24,7 @@
24
  "Blended",
25
  "Brew Style",
26
  "Coffee Varietal",
27
- "add-on",
28
  "drink",
29
  "extra",
30
  "hot breakfast",
@@ -33,13 +33,14 @@
33
  "pastry",
34
  "pump quantity",
35
  "roast",
 
36
  "shot quality",
37
  "shot quantity",
38
  "size",
39
  "syrup",
40
  "temperature",
41
  "toppings",
42
- "upside-down"
43
  ]
44
  },
45
  "pipeline":[
@@ -54,90 +55,105 @@
54
 
55
  ],
56
  "performance":{
57
- "ents_f":0.9762673249,
58
- "ents_p":0.9794285714,
59
- "ents_r":0.9731264194,
60
  "ents_per_type":{
61
  "size":{
62
- "p":0.9911894273,
63
- "r":0.974025974,
64
- "f":0.9825327511
65
- },
66
- "temperature":{
67
- "p":0.9945652174,
68
- "r":0.9631578947,
69
- "f":0.9786096257
70
- },
71
- "syrup":{
72
- "p":0.9766081871,
73
- "r":0.9823529412,
74
- "f":0.9794721408
75
  },
76
  "drink":{
77
- "p":0.9792960663,
78
- "r":0.9742533471,
79
- "f":0.9767681982
80
  },
81
- "milk":{
 
 
 
 
 
82
  "p":0.9806451613,
83
  "r":0.9806451613,
84
  "f":0.9806451613
85
  },
86
- "toppings":{
87
- "p":0.9831932773,
88
- "r":0.975,
89
- "f":0.9790794979
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90
  },
91
  "Anti":{
92
- "p":0.9761904762,
93
- "r":0.9318181818,
94
- "f":0.9534883721
 
 
 
 
 
 
 
 
 
 
95
  },
96
  "Blended":{
97
  "p":1.0,
98
  "r":1.0,
99
  "f":1.0
100
  },
101
- "extra":{
102
- "p":0.7692307692,
103
  "r":1.0,
104
- "f":0.8695652174
105
  },
106
  "add-on":{
107
  "p":1.0,
108
  "r":0.9636363636,
109
  "f":0.9814814815
110
  },
111
- "shot quantity":{
112
- "p":0.9428571429,
113
- "r":0.9428571429,
114
- "f":0.9428571429
115
- },
116
  "Brew Style":{
117
  "p":0.9714285714,
118
  "r":1.0,
119
  "f":0.9855072464
120
  },
121
- "milk texture":{
122
- "p":0.8888888889,
123
- "r":1.0,
124
- "f":0.9411764706
125
- },
126
  "pump quantity":{
127
- "p":1.0,
128
- "r":0.9117647059,
129
- "f":0.9538461538
130
  },
131
  "Coffee Varietal":{
132
  "p":0.9411764706,
133
  "r":1.0,
134
  "f":0.9696969697
135
  },
136
- "roast":{
137
- "p":1.0,
138
- "r":0.9130434783,
139
- "f":0.9545454545
140
- },
141
  "pastry":{
142
  "p":1.0,
143
  "r":1.0,
@@ -147,22 +163,9 @@
147
  "p":1.0,
148
  "r":1.0,
149
  "f":1.0
150
- },
151
- "shot quality":{
152
- "p":0.9565217391,
153
- "r":0.9565217391,
154
- "f":0.9565217391
155
- },
156
- "upside-down":{
157
- "p":1.0,
158
- "r":1.0,
159
- "f":1.0
160
  }
161
  },
162
- "tok2vec_loss":972.4425642409,
163
- "ner_loss":4971.6640156421
164
- },
165
- "requirements":[
166
-
167
- ]
168
  }
 
2
  "lang":"en",
3
  "name":"Coff_Ev1",
4
  "version":"1.4.0",
5
+ "description":"Your Coffee ordered, at the speed of sound",
6
+ "author":"C.Bruinsma,I.Chi,J.Feliciano,J.Li,D.Paden",
7
  "email":"",
8
  "url":"",
9
  "license":"",
10
+ "spacy_version":">=3.0.9,<3.1.0",
11
+ "spacy_git_version":"c83dfa23d",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
 
24
  "Blended",
25
  "Brew Style",
26
  "Coffee Varietal",
27
+ "add",
28
  "drink",
29
  "extra",
30
  "hot breakfast",
 
33
  "pastry",
34
  "pump quantity",
35
  "roast",
36
+ "room",
37
  "shot quality",
38
  "shot quantity",
39
  "size",
40
  "syrup",
41
  "temperature",
42
  "toppings",
43
+ "upside"
44
  ]
45
  },
46
  "pipeline":[
 
55
 
56
  ],
57
  "performance":{
58
+ "ents_f":0.9771888628,
59
+ "ents_p":0.9771888628,
60
+ "ents_r":0.9771888628,
61
  "ents_per_type":{
62
  "size":{
63
+ "p":0.987755102,
64
+ "r":0.9758064516,
65
+ "f":0.9817444219
 
 
 
 
 
 
 
 
 
 
66
  },
67
  "drink":{
68
+ "p":0.9705611776,
69
+ "r":0.9832246039,
70
+ "f":0.9768518519
71
  },
72
+ "room":{
73
+ "p":1.0,
74
+ "r":1.0,
75
+ "f":1.0
76
+ },
77
+ "toppings":{
78
  "p":0.9806451613,
79
  "r":0.9806451613,
80
  "f":0.9806451613
81
  },
82
+ "syrup":{
83
+ "p":0.9847328244,
84
+ "r":0.9797468354,
85
+ "f":0.9822335025
86
+ },
87
+ "temperature":{
88
+ "p":0.9914529915,
89
+ "r":0.9707112971,
90
+ "f":0.9809725159
91
+ },
92
+ "shot quality":{
93
+ "p":0.96,
94
+ "r":0.96,
95
+ "f":0.96
96
+ },
97
+ "shot quantity":{
98
+ "p":0.972972973,
99
+ "r":0.9230769231,
100
+ "f":0.9473684211
101
+ },
102
+ "roast":{
103
+ "p":1.0,
104
+ "r":0.9333333333,
105
+ "f":0.9655172414
106
+ },
107
+ "milk":{
108
+ "p":0.9825581395,
109
+ "r":0.9768786127,
110
+ "f":0.9797101449
111
  },
112
  "Anti":{
113
+ "p":1.0,
114
+ "r":0.9259259259,
115
+ "f":0.9615384615
116
+ },
117
+ "milk texture":{
118
+ "p":0.9230769231,
119
+ "r":1.0,
120
+ "f":0.96
121
+ },
122
+ "extra":{
123
+ "p":0.7931034483,
124
+ "r":0.9583333333,
125
+ "f":0.8679245283
126
  },
127
  "Blended":{
128
  "p":1.0,
129
  "r":1.0,
130
  "f":1.0
131
  },
132
+ "upside-down":{
133
+ "p":1.0,
134
  "r":1.0,
135
+ "f":1.0
136
  },
137
  "add-on":{
138
  "p":1.0,
139
  "r":0.9636363636,
140
  "f":0.9814814815
141
  },
 
 
 
 
 
142
  "Brew Style":{
143
  "p":0.9714285714,
144
  "r":1.0,
145
  "f":0.9855072464
146
  },
 
 
 
 
 
147
  "pump quantity":{
148
+ "p":0.9189189189,
149
+ "r":1.0,
150
+ "f":0.9577464789
151
  },
152
  "Coffee Varietal":{
153
  "p":0.9411764706,
154
  "r":1.0,
155
  "f":0.9696969697
156
  },
 
 
 
 
 
157
  "pastry":{
158
  "p":1.0,
159
  "r":1.0,
 
163
  "p":1.0,
164
  "r":1.0,
165
  "f":1.0
 
 
 
 
 
 
 
 
 
 
166
  }
167
  },
168
+ "tok2vec_loss":2564.122341513,
169
+ "ner_loss":6447.7986571693
170
+ }
 
 
 
171
  }
ner/cfg CHANGED
@@ -8,6 +8,5 @@
8
  "learn_tokens":false,
9
  "beam_width":1,
10
  "beam_density":0.0,
11
- "beam_update_prob":0.0,
12
- "incorrect_spans_key":null
13
  }
 
8
  "learn_tokens":false,
9
  "beam_width":1,
10
  "beam_density":0.0,
11
+ "beam_update_prob":0.0
 
12
  }
ner/model CHANGED
Binary files a/ner/model and b/ner/model differ
 
ner/moves CHANGED
Binary files a/ner/moves and b/ner/moves differ
 
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1486fb8021f0667924a768462f82fdc90325d131ba38e6ade30ae6a8774cfbc1
3
  size 6009091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09f8808c97f534ea5623576318b4722f0d7181d1b4faf4bc6609392562d3c67c
3
  size 6009091
tokenizer CHANGED
The diff for this file is too large to render. See raw diff
 
vocab/strings.json CHANGED
@@ -349,7 +349,6 @@
349
  "C",
350
  "C'm",
351
  "C++",
352
- "C.",
353
  "Ca",
354
  "Cafe",
355
  "Calif",
@@ -444,7 +443,6 @@
444
  "Extra",
445
  "Eye",
446
  "F",
447
- "F.",
448
  "Feb",
449
  "Feb.",
450
  "February",
@@ -482,6 +480,7 @@
482
  "Gov",
483
  "Gov.",
484
  "Grade",
 
485
  "Grande",
486
  "Grapefruit",
487
  "Greek",
@@ -551,7 +550,6 @@
551
  "Jun.",
552
  "June",
553
  "K",
554
- "K.",
555
  "Kan",
556
  "Kan.",
557
  "Kans",
@@ -604,6 +602,7 @@
604
  "Massachusetts",
605
  "Matcha",
606
  "May",
 
607
  "Ma\u2019am",
608
  "Md",
609
  "Md.",
@@ -808,12 +807,16 @@
808
  "There's",
809
  "There\u2019s",
810
  "These",
 
 
811
  "They",
812
  "Third",
813
  "This",
814
  "This's",
815
  "This\u2019s",
816
  "Those",
 
 
817
  "Toffee",
818
  "Trenta",
819
  "Turkish",
@@ -826,6 +829,7 @@
826
  "V_V",
827
  "Va",
828
  "Va.",
 
829
  "Vainilla",
830
  "Vanilla",
831
  "Venti",
@@ -1020,6 +1024,7 @@
1020
  "ave",
1021
  "avellana",
1022
  "avy",
 
1023
  "azu",
1024
  "a\u00e7ai",
1025
  "a\u00e7a\u00ed",
@@ -1332,6 +1337,7 @@
1332
  "gov",
1333
  "gov.",
1334
  "grade",
 
1335
  "granda",
1336
  "grande",
1337
  "grapefruit",
@@ -1495,6 +1501,7 @@
1495
  "led",
1496
  "lemon",
1497
  "lemonade",
 
1498
  "less",
1499
  "let",
1500
  "let's",
@@ -1545,6 +1552,7 @@
1545
  "massive",
1546
  "matcha",
1547
  "may",
 
1548
  "ma\u2019am",
1549
  "md",
1550
  "md.",
@@ -1785,6 +1793,7 @@
1785
  "refresher",
1786
  "refreshers",
1787
  "reindeer",
 
1788
  "rep",
1789
  "rep.",
1790
  "res",
@@ -1848,6 +1857,8 @@
1848
  "should",
1849
  "sic",
1850
  "single",
 
 
1851
  "size",
1852
  "sized",
1853
  "skinny",
@@ -1865,10 +1876,12 @@
1865
  "soy",
1866
  "soymilk",
1867
  "space",
 
1868
  "spice",
1869
  "spiced",
1870
  "spinach",
1871
  "splash",
 
1872
  "srs",
1873
  "ss.",
1874
  "sso",
@@ -1924,12 +1937,16 @@
1924
  "there's",
1925
  "there\u2019s",
1926
  "these",
 
 
1927
  "they",
1928
  "third",
1929
  "this",
1930
  "this's",
1931
  "this\u2019s",
1932
  "those",
 
 
1933
  "three",
1934
  "tly",
1935
  "to",
@@ -1990,6 +2007,7 @@
1990
  "v_v",
1991
  "va",
1992
  "va.",
 
1993
  "vainilla",
1994
  "vanilla",
1995
  "ve",
@@ -2120,14 +2138,6 @@
2120
  "\u00af\\(x)/\u00af",
2121
  "\u00af\\(\u30c4)/\u00af",
2122
  "\u00b0",
2123
- "\u00b0C.",
2124
- "\u00b0F.",
2125
- "\u00b0K.",
2126
- "\u00b0X.",
2127
- "\u00b0c.",
2128
- "\u00b0f.",
2129
- "\u00b0k.",
2130
- "\u00b0x.",
2131
  "\u00e4",
2132
  "\u00e4.",
2133
  "\u00e7ai",
 
349
  "C",
350
  "C'm",
351
  "C++",
 
352
  "Ca",
353
  "Cafe",
354
  "Calif",
 
443
  "Extra",
444
  "Eye",
445
  "F",
 
446
  "Feb",
447
  "Feb.",
448
  "February",
 
480
  "Gov",
481
  "Gov.",
482
  "Grade",
483
+ "Grand",
484
  "Grande",
485
  "Grapefruit",
486
  "Greek",
 
550
  "Jun.",
551
  "June",
552
  "K",
 
553
  "Kan",
554
  "Kan.",
555
  "Kans",
 
602
  "Massachusetts",
603
  "Matcha",
604
  "May",
605
+ "May.",
606
  "Ma\u2019am",
607
  "Md",
608
  "Md.",
 
807
  "There's",
808
  "There\u2019s",
809
  "These",
810
+ "These's",
811
+ "These\u2019s",
812
  "They",
813
  "Third",
814
  "This",
815
  "This's",
816
  "This\u2019s",
817
  "Those",
818
+ "Those's",
819
+ "Those\u2019s",
820
  "Toffee",
821
  "Trenta",
822
  "Turkish",
 
829
  "V_V",
830
  "Va",
831
  "Va.",
832
+ "Vailla",
833
  "Vainilla",
834
  "Vanilla",
835
  "Venti",
 
1024
  "ave",
1025
  "avellana",
1026
  "avy",
1027
+ "ay.",
1028
  "azu",
1029
  "a\u00e7ai",
1030
  "a\u00e7a\u00ed",
 
1337
  "gov",
1338
  "gov.",
1339
  "grade",
1340
+ "grand",
1341
  "granda",
1342
  "grande",
1343
  "grapefruit",
 
1501
  "led",
1502
  "lemon",
1503
  "lemonade",
1504
+ "les",
1505
  "less",
1506
  "let",
1507
  "let's",
 
1552
  "massive",
1553
  "matcha",
1554
  "may",
1555
+ "may.",
1556
  "ma\u2019am",
1557
  "md",
1558
  "md.",
 
1793
  "refresher",
1794
  "refreshers",
1795
  "reindeer",
1796
+ "ren",
1797
  "rep",
1798
  "rep.",
1799
  "res",
 
1857
  "should",
1858
  "sic",
1859
  "single",
1860
+ "siren",
1861
+ "six",
1862
  "size",
1863
  "sized",
1864
  "skinny",
 
1876
  "soy",
1877
  "soymilk",
1878
  "space",
1879
+ "spash",
1880
  "spice",
1881
  "spiced",
1882
  "spinach",
1883
  "splash",
1884
+ "sprinkles",
1885
  "srs",
1886
  "ss.",
1887
  "sso",
 
1937
  "there's",
1938
  "there\u2019s",
1939
  "these",
1940
+ "these's",
1941
+ "these\u2019s",
1942
  "they",
1943
  "third",
1944
  "this",
1945
  "this's",
1946
  "this\u2019s",
1947
  "those",
1948
+ "those's",
1949
+ "those\u2019s",
1950
  "three",
1951
  "tly",
1952
  "to",
 
2007
  "v_v",
2008
  "va",
2009
  "va.",
2010
+ "vailla",
2011
  "vainilla",
2012
  "vanilla",
2013
  "ve",
 
2138
  "\u00af\\(x)/\u00af",
2139
  "\u00af\\(\u30c4)/\u00af",
2140
  "\u00b0",
 
 
 
 
 
 
 
 
2141
  "\u00e4",
2142
  "\u00e4.",
2143
  "\u00e7ai",