Update spaCy pipeline

.gitattributes

@@ -33,3 +33,4 @@ 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
+textcat/model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,48 @@
+---
+tags:
+- spacy
+- text-classification
+language:
+- nl
+model-index:
+- name: nl_meningen
+  results: []
+---
+| Feature | Description |
+| --- | --- |
+| **Name** | `nl_meningen` |
+| **Version** | `0.0.0` |
+| **spaCy** | `>=3.4.3,<3.5.0` |
+| **Default Pipeline** | `textcat` |
+| **Components** | `textcat` |
+| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Sources** | n/a |
+| **License** | n/a |
+| **Author** | [n/a]() |
+
+### Label Scheme
+
+<details>
+
+<summary>View label scheme (2 labels for 1 components)</summary>
+
+| Component | Labels |
+| --- | --- |
+| **`textcat`** | `Positief`, `Negatief` |
+
+</details>
+
+### Accuracy
+
+| Type | Score |
+| --- | --- |
+| `CATS_SCORE` | 96.54 |
+| `CATS_MICRO_P` | 96.77 |
+| `CATS_MICRO_R` | 96.77 |
+| `CATS_MICRO_F` | 96.77 |
+| `CATS_MACRO_P` | 95.83 |
+| `CATS_MACRO_R` | 97.50 |
+| `CATS_MACRO_F` | 96.54 |
+| `CATS_MACRO_AUC` | 98.18 |
+| `CATS_MACRO_AUC_PER_TYPE` | 0.00 |
+| `TEXTCAT_LOSS` | 8.31 |

config.cfg

@@ -0,0 +1,128 @@
+[paths]
+train = "/home/gebruiker/anaconda3/envs/corpus/train.spacy"
+dev = "/home/gebruiker/anaconda3/envs/corpus/dev.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = null
+seed = 0
+
+[nlp]
+lang = "nl"
+pipeline = ["textcat"]
+batch_size = 1000
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+
+[components]
+
+[components.textcat]
+factory = "textcat"
+scorer = {"@scorers":"spacy.textcat_scorer.v1"}
+threshold = 0.5
+
+[components.textcat.model]
+@architectures = "spacy.TextCatBOW.v2"
+exclusive_classes = true
+ngram_size = 1
+no_output_layer = false
+nO = null
+
+[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
+
+[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]
+cats_score = 1.0
+cats_score_desc = null
+cats_micro_p = null
+cats_micro_r = null
+cats_micro_f = null
+cats_macro_p = null
+cats_macro_r = null
+cats_macro_f = null
+cats_macro_auc = null
+cats_f_per_type = null
+cats_macro_auc_per_type = null
+
+[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.textcat]
+
+[initialize.components.textcat.labels]
+@readers = "spacy.read_labels.v1"
+path = "/home/gebruiker/anaconda3/envs/corpus/labels/textcat.json"
+require = false
+
+[initialize.tokenizer]

meta.json

@@ -0,0 +1,61 @@
+{
+  "lang":"nl",
+  "name":"meningen",
+  "version":"0.0.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_version":">=3.4.3,<3.5.0",
+  "spacy_git_version":"Unknown",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null
+  },
+  "labels":{
+    "textcat":[
+      "Positief",
+      "Negatief"
+    ]
+  },
+  "pipeline":[
+    "textcat"
+  ],
+  "components":[
+    "textcat"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "cats_score":0.9654403567,
+    "cats_score_desc":"macro F",
+    "cats_micro_p":0.9677419355,
+    "cats_micro_r":0.9677419355,
+    "cats_micro_f":0.9677419355,
+    "cats_macro_p":0.9583333333,
+    "cats_macro_r":0.975,
+    "cats_macro_f":0.9654403567,
+    "cats_macro_auc":0.9818181818,
+    "cats_f_per_type":{
+      "Positief":{
+        "p":1.0,
+        "r":0.95,
+        "f":0.9743589744
+      },
+      "Negatief":{
+        "p":0.9166666667,
+        "r":1.0,
+        "f":0.9565217391
+      }
+    },
+    "cats_macro_auc_per_type":0.0,
+    "textcat_loss":0.083148308
+  },
+  "requirements":[
+
+  ]
+}

textcat/cfg

@@ -0,0 +1,8 @@
+{
+  "labels":[
+    "Positief",
+    "Negatief"
+  ],
+  "threshold":0.5,
+  "positive_label":null
+}

textcat/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43bd59f069d64ac38dc33589fc5b775b6a63425e283e7ec3e10b6e55651f3186
+size 2097880

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"
+}