Update spaCy pipeline

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+nl_Echocardiogram_SpanCategorizer_rv_dil-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+tok2vec/model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,45 @@
+---
+tags:
+- spacy
+language:
+- nl
+license: cc-by-sa-4.0
+model-index:
+- name: nl_Echocardiogram_SpanCategorizer_rv_dil
+  results: []
+---
+Package to classify spans for the presence and severity of right ventricular dilatation in Dutch echocardiogram reports.
+
+| Feature | Description |
+| --- | --- |
+| **Name** | `nl_Echocardiogram_SpanCategorizer_rv_dil` |
+| **Version** | `1.0.0` |
+| **spaCy** | `>=3.7.4,<3.8.0` |
+| **Default Pipeline** | `tok2vec`, `spancat` |
+| **Components** | `tok2vec`, `spancat` |
+| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Sources** | n/a |
+| **License** | `cc-ny-sa-4.0` |
+| **Author** | [Bauke Arends]() |
+
+### Label Scheme
+
+<details>
+
+<summary>View label scheme (5 labels for 1 components)</summary>
+
+| Component | Labels |
+| --- | --- |
+| **`spancat`** | `rv_dil_normal`, `rv_dil_severe`, `rv_dil_mild`, `rv_dil_moderate`, `rv_dil_present` |
+
+</details>
+
+### Accuracy
+
+| Type | Score |
+| --- | --- |
+| `SPANS_SC_F` | 90.06 |
+| `SPANS_SC_P` | 92.59 |
+| `SPANS_SC_R` | 87.67 |
+| `TOK2VEC_LOSS` | 59.40 |
+| `SPANCAT_LOSS` | 16044.83 |

config.cfg

@@ -0,0 +1,159 @@
+[paths]
+train = "./spacy_data/rv_dil//train.spacy"
+dev = "./spacy_data/rv_dil//test.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = null
+seed = 0
+
+[nlp]
+lang = "nl"
+pipeline = ["tok2vec","spancat"]
+batch_size = 1000
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+vectors = {"@vectors":"spacy.Vectors.v1"}
+
+[components]
+
+[components.spancat]
+factory = "spancat_singlelabel"
+allow_overlap = true
+negative_weight = 0.6
+scorer = {"@scorers":"spacy.spancat_scorer.v1"}
+spans_key = "sc"
+
+[components.spancat.model]
+@architectures = "spacy.SpanCategorizer.v1"
+
+[components.spancat.model.reducer]
+@layers = "spacy.mean_max_reducer.v1"
+hidden_size = 128
+
+[components.spancat.model.scorer]
+@layers = "spacy.LinearLogistic.v1"
+nO = null
+nI = null
+
+[components.spancat.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+upstream = "*"
+
+[components.spancat.suggester]
+@misc = "spacy.ngram_range_suggester.v1"
+min_size = 1
+max_size = 25
+
+[components.tok2vec]
+factory = "tok2vec"
+
+[components.tok2vec.model]
+@architectures = "spacy.Tok2Vec.v2"
+
+[components.tok2vec.model.embed]
+@architectures = "spacy.MultiHashEmbed.v2"
+width = ${components.tok2vec.model.encode.width}
+attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
+rows = [5000,1000,2500,2500]
+include_static_vectors = false
+
+[components.tok2vec.model.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v2"
+width = 96
+depth = 4
+window_size = 1
+maxout_pieces = 3
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[training]
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+accumulate_gradient = 1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+before_to_disk = null
+before_update = null
+
+[training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
+tolerance = 0.2
+get_length = null
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+t = 0.0
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = false
+eps = 0.00000001
+learn_rate = 0.001
+
+[training.score_weights]
+spans_sc_f = 1.0
+spans_sc_p = 0.0
+spans_sc_r = 0.0
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.components.spancat]
+
+[initialize.components.spancat.labels]
+@readers = "spacy.read_labels.v1"
+path = "corpus/labels/spancat.json"
+require = false
+
+[initialize.tokenizer]

meta.json

@@ -0,0 +1,51 @@
+{
+  "lang":"nl",
+  "name":"Echocardiogram_SpanCategorizer_rv_dil",
+  "version":"1.0.0",
+  "description":"Package to classify spans for the presence and severity of right ventricular dilatation in Dutch echocardiogram reports.",
+  "author":"Bauke Arends",
+  "email":"[email protected]",
+  "url":"",
+  "license":"cc-by-sa-4.0",
+  "spacy_version":">=3.7.4,<3.8.0",
+  "spacy_git_version":"bff8725f4",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null
+  },
+  "labels":{
+    "tok2vec":[
+
+    ],
+    "spancat":[
+      "rv_dil_normal",
+      "rv_dil_severe",
+      "rv_dil_mild",
+      "rv_dil_moderate",
+      "rv_dil_present"
+    ]
+  },
+  "pipeline":[
+    "tok2vec",
+    "spancat"
+  ],
+  "components":[
+    "tok2vec",
+    "spancat"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "spans_sc_f":0.9005847953,
+    "spans_sc_p":0.9258517034,
+    "spans_sc_r":0.8766603416,
+    "tok2vec_loss":0.594011974,
+    "spancat_loss":160.448251087
+  },
+  "requirements":[
+
+  ]
+}

meta_hf.json

@@ -0,0 +1,45 @@
+{
+    "lang": "nl",
+    "name": "Echocardiogram_SpanCategorizer_rv_dil",
+    "version": "1.0.0",
+    "spacy_version": ">=3.7.4,<3.8.0",
+    "description": "Package to classify spans for the presence and severity of right ventricular dilatation in Dutch echocardiogram reports.",
+    "author": "Bauke Arends",
+    "email": "[email protected]",
+    "url": "",
+    "license": "cc-by-sa-4.0",
+    "spacy_git_version": "bff8725f4",
+    "vectors": {
+        "width": 0,
+        "vectors": 0,
+        "keys": 0,
+        "name": null,
+        "mode": "default"
+    },
+    "labels": {
+        "tok2vec": [],
+        "spancat": [
+            "rv_dil_normal",
+            "rv_dil_severe",
+            "rv_dil_mild",
+            "rv_dil_moderate",
+            "rv_dil_present"
+        ]
+    },
+    "pipeline": [
+        "tok2vec",
+        "spancat"
+    ],
+    "components": [
+        "tok2vec",
+        "spancat"
+    ],
+    "disabled": [],
+    "performance": {
+        "spans_sc_f": 0.9005847953,
+        "spans_sc_p": 0.9258517034,
+        "spans_sc_r": 0.8766603416,
+        "tok2vec_loss": 0.594011974,
+        "spancat_loss": 160.448251087
+    }
+}

nl_Echocardiogram_SpanCategorizer_rv_dil-any-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d1066100c0f86439859aedc5651bf2517b88efb43e605e8a4193d55a6000cf
+size 6255428

spancat/cfg

@@ -0,0 +1,14 @@
+{
+  "labels":[
+    "rv_dil_normal",
+    "rv_dil_severe",
+    "rv_dil_mild",
+    "rv_dil_moderate",
+    "rv_dil_present"
+  ],
+  "spans_key":"sc",
+  "threshold":null,
+  "max_positive":1,
+  "negative_weight":0.6,
+  "allow_overlap":true
+}

tok2vec/cfg

@@ -0,0 +1,3 @@
+{
+
+}

tok2vec/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dedc35144f9df3b25f9dfbea68a5b247089d81dfa152adf42ee3c373986e754
+size 6009091

vocab/key2row

@@ -0,0 +1 @@
+�

vocab/lookups.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
+size 1

vocab/vectors.cfg

@@ -0,0 +1,3 @@
+{
+  "mode":"default"
+}