Update spaCy pipeline
Browse files- .gitattributes +1 -0
- README.md +11 -0
- config.cfg +126 -0
- fr_eff_hd_textcat_multi1pcd-any-py3-none-any.whl +0 -0
- meta.json +211 -0
- textcat_multilabel/cfg +32 -0
- textcat_multilabel/model +3 -0
- tokenizer +0 -0
- vocab/key2row +1 -0
- vocab/lookups.bin +3 -0
- vocab/strings.json +0 -0
- vocab/vectors +0 -0
- vocab/vectors.cfg +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
textcat_multilabel/model filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- spacy
|
4 |
+
- text-classification
|
5 |
+
language:
|
6 |
+
- fr
|
7 |
+
license: mit
|
8 |
+
model-index:
|
9 |
+
- name: fr_eff_hd_textcat_multi1pcd
|
10 |
+
results: []
|
11 |
+
---
|
config.cfg
ADDED
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[paths]
|
2 |
+
train = "..\\test\\train_multi1pcd.spacy"
|
3 |
+
dev = "..\\test\\dev_multi1pcd.spacy"
|
4 |
+
vectors = null
|
5 |
+
init_tok2vec = null
|
6 |
+
|
7 |
+
[system]
|
8 |
+
gpu_allocator = null
|
9 |
+
seed = 0
|
10 |
+
|
11 |
+
[nlp]
|
12 |
+
lang = "fr"
|
13 |
+
pipeline = ["textcat_multilabel"]
|
14 |
+
batch_size = 1000
|
15 |
+
disabled = []
|
16 |
+
before_creation = null
|
17 |
+
after_creation = null
|
18 |
+
after_pipeline_creation = null
|
19 |
+
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
20 |
+
|
21 |
+
[components]
|
22 |
+
|
23 |
+
[components.textcat_multilabel]
|
24 |
+
factory = "textcat_multilabel"
|
25 |
+
scorer = {"@scorers":"spacy.textcat_multilabel_scorer.v1"}
|
26 |
+
threshold = 0.5
|
27 |
+
|
28 |
+
[components.textcat_multilabel.model]
|
29 |
+
@architectures = "spacy.TextCatBOW.v2"
|
30 |
+
exclusive_classes = false
|
31 |
+
ngram_size = 1
|
32 |
+
no_output_layer = false
|
33 |
+
nO = null
|
34 |
+
|
35 |
+
[corpora]
|
36 |
+
|
37 |
+
[corpora.dev]
|
38 |
+
@readers = "spacy.Corpus.v1"
|
39 |
+
path = ${paths.dev}
|
40 |
+
max_length = 0
|
41 |
+
gold_preproc = false
|
42 |
+
limit = 0
|
43 |
+
augmenter = null
|
44 |
+
|
45 |
+
[corpora.train]
|
46 |
+
@readers = "spacy.Corpus.v1"
|
47 |
+
path = ${paths.train}
|
48 |
+
max_length = 0
|
49 |
+
gold_preproc = false
|
50 |
+
limit = 0
|
51 |
+
augmenter = null
|
52 |
+
|
53 |
+
[training]
|
54 |
+
dev_corpus = "corpora.dev"
|
55 |
+
train_corpus = "corpora.train"
|
56 |
+
seed = ${system.seed}
|
57 |
+
gpu_allocator = ${system.gpu_allocator}
|
58 |
+
dropout = 0.1
|
59 |
+
accumulate_gradient = 1
|
60 |
+
patience = 1600
|
61 |
+
max_epochs = 0
|
62 |
+
max_steps = 20000
|
63 |
+
eval_frequency = 200
|
64 |
+
frozen_components = []
|
65 |
+
annotating_components = []
|
66 |
+
before_to_disk = null
|
67 |
+
|
68 |
+
[training.batcher]
|
69 |
+
@batchers = "spacy.batch_by_words.v1"
|
70 |
+
discard_oversize = false
|
71 |
+
tolerance = 0.2
|
72 |
+
get_length = null
|
73 |
+
|
74 |
+
[training.batcher.size]
|
75 |
+
@schedules = "compounding.v1"
|
76 |
+
start = 100
|
77 |
+
stop = 1000
|
78 |
+
compound = 1.001
|
79 |
+
t = 0.0
|
80 |
+
|
81 |
+
[training.logger]
|
82 |
+
@loggers = "spacy.WandbLogger.v3"
|
83 |
+
project_name = "pat-hd_models"
|
84 |
+
remove_config_values = ["paths.train","paths.dev","corpora.train.path","corpora.dev.path"]
|
85 |
+
log_dataset_dir = "./corpus"
|
86 |
+
model_log_interval = 1000
|
87 |
+
entity = null
|
88 |
+
run_name = null
|
89 |
+
|
90 |
+
[training.optimizer]
|
91 |
+
@optimizers = "Adam.v1"
|
92 |
+
beta1 = 0.9
|
93 |
+
beta2 = 0.999
|
94 |
+
L2_is_weight_decay = true
|
95 |
+
L2 = 0.01
|
96 |
+
grad_clip = 1.0
|
97 |
+
use_averages = false
|
98 |
+
eps = 0.00000001
|
99 |
+
learn_rate = 0.001
|
100 |
+
|
101 |
+
[training.score_weights]
|
102 |
+
cats_score = 1.0
|
103 |
+
cats_score_desc = null
|
104 |
+
cats_micro_p = null
|
105 |
+
cats_micro_r = null
|
106 |
+
cats_micro_f = null
|
107 |
+
cats_macro_p = null
|
108 |
+
cats_macro_r = null
|
109 |
+
cats_macro_f = null
|
110 |
+
cats_macro_auc = null
|
111 |
+
cats_f_per_type = null
|
112 |
+
cats_macro_auc_per_type = null
|
113 |
+
|
114 |
+
[pretraining]
|
115 |
+
|
116 |
+
[initialize]
|
117 |
+
vectors = ${paths.vectors}
|
118 |
+
init_tok2vec = ${paths.init_tok2vec}
|
119 |
+
vocab_data = null
|
120 |
+
lookups = null
|
121 |
+
before_init = null
|
122 |
+
after_init = null
|
123 |
+
|
124 |
+
[initialize.components]
|
125 |
+
|
126 |
+
[initialize.tokenizer]
|
fr_eff_hd_textcat_multi1pcd-any-py3-none-any.whl
ADDED
Binary file (821 kB). View file
|
|
meta.json
ADDED
@@ -0,0 +1,211 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"lang":"fr",
|
3 |
+
"name":"eff_hd_textcat_multi1pcd",
|
4 |
+
"version":"2023.6.0",
|
5 |
+
"description":"Modele de classement des incidents du Support 2424",
|
6 |
+
"author":"Gilles LANTERI",
|
7 |
+
"email":"gilles.lanteri@malakoffhumanis.com",
|
8 |
+
"url":"",
|
9 |
+
"license":"MIT",
|
10 |
+
"spacy_version":">=3.4.4,<3.5.0",
|
11 |
+
"spacy_git_version":"77833bfef",
|
12 |
+
"vectors":{
|
13 |
+
"width":0,
|
14 |
+
"vectors":0,
|
15 |
+
"keys":0,
|
16 |
+
"name":null
|
17 |
+
},
|
18 |
+
"labels":{
|
19 |
+
"textcat_multilabel":[
|
20 |
+
"Citrix",
|
21 |
+
"Lecteur",
|
22 |
+
"Mot de passe",
|
23 |
+
"PC portable",
|
24 |
+
"P\u00e9riph\u00e9rique",
|
25 |
+
"VPN",
|
26 |
+
"Assistance",
|
27 |
+
"Incident",
|
28 |
+
"",
|
29 |
+
"Aide changement MDP expir\u00e9",
|
30 |
+
"Aide suite \u00e0 la migration",
|
31 |
+
"Aide \u00e0 l'utilisation",
|
32 |
+
"Ajout lecteur",
|
33 |
+
"Bascule version simplifi\u00e9 en Workspace",
|
34 |
+
"Changement de mot de passe",
|
35 |
+
"Changement numero MFA",
|
36 |
+
"Demande Informations",
|
37 |
+
"Demande Myaccess a faire/en attente",
|
38 |
+
"Demande Myaccess a faire/en cours",
|
39 |
+
"Erreur/oublie de MDP/Login",
|
40 |
+
"Mot de passe expir\u00e9",
|
41 |
+
"Oublie de connecter le VPN",
|
42 |
+
"Parametre Affichage",
|
43 |
+
"Pas connect\u00e9 \u00e0 internet",
|
44 |
+
"Reglage Affichage",
|
45 |
+
"Restauration dossier/fichier",
|
46 |
+
"VPN non connect\u00e9"
|
47 |
+
]
|
48 |
+
},
|
49 |
+
"pipeline":[
|
50 |
+
"textcat_multilabel"
|
51 |
+
],
|
52 |
+
"components":[
|
53 |
+
"textcat_multilabel"
|
54 |
+
],
|
55 |
+
"disabled":[
|
56 |
+
|
57 |
+
],
|
58 |
+
"performance":{
|
59 |
+
"cats_score":0.7164608016,
|
60 |
+
"cats_score_desc":"macro AUC",
|
61 |
+
"cats_micro_p":0.8013013013,
|
62 |
+
"cats_micro_r":0.7280582083,
|
63 |
+
"cats_micro_f":0.7629258995,
|
64 |
+
"cats_macro_p":0.4105767019,
|
65 |
+
"cats_macro_r":0.3202640974,
|
66 |
+
"cats_macro_f":0.3506143374,
|
67 |
+
"cats_macro_auc":0.7164608016,
|
68 |
+
"cats_f_per_type":{
|
69 |
+
"Citrix":{
|
70 |
+
"p":0.9292035398,
|
71 |
+
"r":0.8333333333,
|
72 |
+
"f":0.8786610879
|
73 |
+
},
|
74 |
+
"Lecteur":{
|
75 |
+
"p":0.9509803922,
|
76 |
+
"r":0.8660714286,
|
77 |
+
"f":0.9065420561
|
78 |
+
},
|
79 |
+
"Mot de passe":{
|
80 |
+
"p":0.8309859155,
|
81 |
+
"r":0.8194444444,
|
82 |
+
"f":0.8251748252
|
83 |
+
},
|
84 |
+
"PC portable":{
|
85 |
+
"p":0.6538461538,
|
86 |
+
"r":0.3695652174,
|
87 |
+
"f":0.4722222222
|
88 |
+
},
|
89 |
+
"P\u00e9riph\u00e9rique":{
|
90 |
+
"p":0.8717948718,
|
91 |
+
"r":0.85,
|
92 |
+
"f":0.8607594937
|
93 |
+
},
|
94 |
+
"VPN":{
|
95 |
+
"p":0.9206349206,
|
96 |
+
"r":0.9027237354,
|
97 |
+
"f":0.9115913556
|
98 |
+
},
|
99 |
+
"Assistance":{
|
100 |
+
"p":0.6220095694,
|
101 |
+
"r":0.5752212389,
|
102 |
+
"f":0.5977011494
|
103 |
+
},
|
104 |
+
"Incident":{
|
105 |
+
"p":0.8131212724,
|
106 |
+
"r":0.8067061144,
|
107 |
+
"f":0.8099009901
|
108 |
+
},
|
109 |
+
"":{
|
110 |
+
"p":0.8121330724,
|
111 |
+
"r":0.8185404339,
|
112 |
+
"f":0.815324165
|
113 |
+
},
|
114 |
+
"Aide changement MDP expir\u00e9":{
|
115 |
+
"p":0.1111111111,
|
116 |
+
"r":0.1,
|
117 |
+
"f":0.1052631579
|
118 |
+
},
|
119 |
+
"Aide suite \u00e0 la migration":{
|
120 |
+
"p":0.5263157895,
|
121 |
+
"r":0.2380952381,
|
122 |
+
"f":0.3278688525
|
123 |
+
},
|
124 |
+
"Aide \u00e0 l'utilisation":{
|
125 |
+
"p":0.2222222222,
|
126 |
+
"r":0.1176470588,
|
127 |
+
"f":0.1538461538
|
128 |
+
},
|
129 |
+
"Ajout lecteur":{
|
130 |
+
"p":0.5,
|
131 |
+
"r":0.2857142857,
|
132 |
+
"f":0.3636363636
|
133 |
+
},
|
134 |
+
"Bascule version simplifi\u00e9 en Workspace":{
|
135 |
+
"p":0.0,
|
136 |
+
"r":0.0,
|
137 |
+
"f":0.0
|
138 |
+
},
|
139 |
+
"Changement de mot de passe":{
|
140 |
+
"p":0.4,
|
141 |
+
"r":0.1333333333,
|
142 |
+
"f":0.2
|
143 |
+
},
|
144 |
+
"Changement numero MFA":{
|
145 |
+
"p":0.0,
|
146 |
+
"r":0.0,
|
147 |
+
"f":0.0
|
148 |
+
},
|
149 |
+
"Demande Informations":{
|
150 |
+
"p":0.0,
|
151 |
+
"r":0.0,
|
152 |
+
"f":0.0
|
153 |
+
},
|
154 |
+
"Demande Myaccess a faire/en attente":{
|
155 |
+
"p":0.0,
|
156 |
+
"r":0.0,
|
157 |
+
"f":0.0
|
158 |
+
},
|
159 |
+
"Demande Myaccess a faire/en cours":{
|
160 |
+
"p":0.5,
|
161 |
+
"r":0.2,
|
162 |
+
"f":0.2857142857
|
163 |
+
},
|
164 |
+
"Erreur/oublie de MDP/Login":{
|
165 |
+
"p":0.4545454545,
|
166 |
+
"r":0.1612903226,
|
167 |
+
"f":0.2380952381
|
168 |
+
},
|
169 |
+
"Mot de passe expir\u00e9":{
|
170 |
+
"p":0.0,
|
171 |
+
"r":0.0,
|
172 |
+
"f":0.0
|
173 |
+
},
|
174 |
+
"Oublie de connecter le VPN":{
|
175 |
+
"p":0.0,
|
176 |
+
"r":0.0,
|
177 |
+
"f":0.0
|
178 |
+
},
|
179 |
+
"Parametre Affichage":{
|
180 |
+
"p":0.0,
|
181 |
+
"r":0.0,
|
182 |
+
"f":0.0
|
183 |
+
},
|
184 |
+
"Pas connect\u00e9 \u00e0 internet":{
|
185 |
+
"p":0.0,
|
186 |
+
"r":0.0,
|
187 |
+
"f":0.0
|
188 |
+
},
|
189 |
+
"Reglage Affichage":{
|
190 |
+
"p":0.8,
|
191 |
+
"r":0.4444444444,
|
192 |
+
"f":0.5714285714
|
193 |
+
},
|
194 |
+
"Restauration dossier/fichier":{
|
195 |
+
"p":0.0,
|
196 |
+
"r":0.0,
|
197 |
+
"f":0.0
|
198 |
+
},
|
199 |
+
"VPN non connect\u00e9":{
|
200 |
+
"p":0.1666666667,
|
201 |
+
"r":0.125,
|
202 |
+
"f":0.1428571429
|
203 |
+
}
|
204 |
+
},
|
205 |
+
"cats_macro_auc_per_type":0.0,
|
206 |
+
"textcat_multilabel_loss":1.758717101
|
207 |
+
},
|
208 |
+
"requirements":[
|
209 |
+
|
210 |
+
]
|
211 |
+
}
|
textcat_multilabel/cfg
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"labels":[
|
3 |
+
"Citrix",
|
4 |
+
"Lecteur",
|
5 |
+
"Mot de passe",
|
6 |
+
"PC portable",
|
7 |
+
"P\u00e9riph\u00e9rique",
|
8 |
+
"VPN",
|
9 |
+
"Assistance",
|
10 |
+
"Incident",
|
11 |
+
"",
|
12 |
+
"Aide changement MDP expir\u00e9",
|
13 |
+
"Aide suite \u00e0 la migration",
|
14 |
+
"Aide \u00e0 l'utilisation",
|
15 |
+
"Ajout lecteur",
|
16 |
+
"Bascule version simplifi\u00e9 en Workspace",
|
17 |
+
"Changement de mot de passe",
|
18 |
+
"Changement numero MFA",
|
19 |
+
"Demande Informations",
|
20 |
+
"Demande Myaccess a faire/en attente",
|
21 |
+
"Demande Myaccess a faire/en cours",
|
22 |
+
"Erreur/oublie de MDP/Login",
|
23 |
+
"Mot de passe expir\u00e9",
|
24 |
+
"Oublie de connecter le VPN",
|
25 |
+
"Parametre Affichage",
|
26 |
+
"Pas connect\u00e9 \u00e0 internet",
|
27 |
+
"Reglage Affichage",
|
28 |
+
"Restauration dossier/fichier",
|
29 |
+
"VPN non connect\u00e9"
|
30 |
+
],
|
31 |
+
"threshold":0.5
|
32 |
+
}
|
textcat_multilabel/model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:719b722bac370535d11b515a8ec88a10d5cfe4466ad9931c5b773f5aa2bc6a4f
|
3 |
+
size 28312365
|
tokenizer
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vocab/key2row
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
�
|
vocab/lookups.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
|
3 |
+
size 1
|
vocab/strings.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vocab/vectors
ADDED
Binary file (128 Bytes). View file
|
|
vocab/vectors.cfg
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"mode":"default"
|
3 |
+
}
|