added model
Browse files- README.md +11 -11
- config.json +3 -3
- model.joblib +2 -2
README.md
CHANGED
|
@@ -9,9 +9,9 @@ model_file: model.joblib
|
|
| 9 |
widget:
|
| 10 |
structuredData:
|
| 11 |
LegalName:
|
| 12 |
-
-
|
| 13 |
-
-
|
| 14 |
-
-
|
| 15 |
---
|
| 16 |
|
| 17 |
# Model description
|
|
@@ -34,20 +34,20 @@ The model is trained with below hyperparameters.
|
|
| 34 |
| Hyperparameter | Value |
|
| 35 |
|------------------------------------------------------|----------------------------------------------------------------|
|
| 36 |
| memory | |
|
| 37 |
-
| steps | [('feature_extraction', ColumnTransformer(transformers=[('abbreviations',<br /> <__main__.ELFAbbreviationTransformer object at
|
| 38 |
| verbose | False |
|
| 39 |
-
| feature_extraction | ColumnTransformer(transformers=[('abbreviations',<br /> <__main__.ELFAbbreviationTransformer object at
|
| 40 |
| classifier | ComplementNB() |
|
| 41 |
| feature_extraction__n_jobs | |
|
| 42 |
| feature_extraction__remainder | drop |
|
| 43 |
| feature_extraction__sparse_threshold | 0.3 |
|
| 44 |
| feature_extraction__transformer_weights | |
|
| 45 |
-
| feature_extraction__transformers | [('abbreviations', <__main__.ELFAbbreviationTransformer object at
|
| 46 |
| feature_extraction__verbose | False |
|
| 47 |
| feature_extraction__verbose_feature_names_out | True |
|
| 48 |
-
| feature_extraction__abbreviations | <__main__.ELFAbbreviationTransformer object at
|
| 49 |
-
| feature_extraction__tokenizer | CountVectorizer(binary=True, lowercase=False,<br /> tokenizer=<
|
| 50 |
-
| feature_extraction__abbreviations__elf_abbreviations | <__main__.ELFAbbreviations object at
|
| 51 |
| feature_extraction__abbreviations__jurisdiction | PL |
|
| 52 |
| feature_extraction__abbreviations__use_endswith | True |
|
| 53 |
| feature_extraction__abbreviations__use_lowercasing | True |
|
|
@@ -66,7 +66,7 @@ The model is trained with below hyperparameters.
|
|
| 66 |
| feature_extraction__tokenizer__stop_words | |
|
| 67 |
| feature_extraction__tokenizer__strip_accents | |
|
| 68 |
| feature_extraction__tokenizer__token_pattern | (?u)\b\w\w+\b |
|
| 69 |
-
| feature_extraction__tokenizer__tokenizer | <
|
| 70 |
| feature_extraction__tokenizer__vocabulary | |
|
| 71 |
| classifier__alpha | 1.0 |
|
| 72 |
| classifier__class_prior | |
|
|
@@ -79,7 +79,7 @@ The model is trained with below hyperparameters.
|
|
| 79 |
|
| 80 |
The model plot is below.
|
| 81 |
|
| 82 |
-
<style>#sk-
|
| 83 |
|
| 84 |
## Evaluation Results
|
| 85 |
|
|
|
|
| 9 |
widget:
|
| 10 |
structuredData:
|
| 11 |
LegalName:
|
| 12 |
+
- Miejskie Przedsiębiorstwo Energetyki Cieplnej Spółka z ograniczoną odpowiedzialnością
|
| 13 |
+
- Przedsiębiorstwo Produkcyjno Usługowe Mimal Krystyna Fludra
|
| 14 |
+
- NGS OIL & GAS S.A.
|
| 15 |
---
|
| 16 |
|
| 17 |
# Model description
|
|
|
|
| 34 |
| Hyperparameter | Value |
|
| 35 |
|------------------------------------------------------|----------------------------------------------------------------|
|
| 36 |
| memory | |
|
| 37 |
+
| steps | [('feature_extraction', ColumnTransformer(transformers=[('abbreviations',<br /> <__main__.ELFAbbreviationTransformer object at 0x7f38e082e4f0>,<br /> 0),<br /> ('tokenizer',<br /> CountVectorizer(binary=True, lowercase=False,<br /> tokenizer=<__main__.LegalEntityTokenizer object at 0x7f38e082ee50>),<br /> 0)])), ('classifier', ComplementNB())] |
|
| 38 |
| verbose | False |
|
| 39 |
+
| feature_extraction | ColumnTransformer(transformers=[('abbreviations',<br /> <__main__.ELFAbbreviationTransformer object at 0x7f38e082e4f0>,<br /> 0),<br /> ('tokenizer',<br /> CountVectorizer(binary=True, lowercase=False,<br /> tokenizer=<__main__.LegalEntityTokenizer object at 0x7f38e082ee50>),<br /> 0)]) |
|
| 40 |
| classifier | ComplementNB() |
|
| 41 |
| feature_extraction__n_jobs | |
|
| 42 |
| feature_extraction__remainder | drop |
|
| 43 |
| feature_extraction__sparse_threshold | 0.3 |
|
| 44 |
| feature_extraction__transformer_weights | |
|
| 45 |
+
| feature_extraction__transformers | [('abbreviations', <__main__.ELFAbbreviationTransformer object at 0x7f38e082e4f0>, 0), ('tokenizer', CountVectorizer(binary=True, lowercase=False,<br /> tokenizer=<__main__.LegalEntityTokenizer object at 0x7f38e082ee50>), 0)] |
|
| 46 |
| feature_extraction__verbose | False |
|
| 47 |
| feature_extraction__verbose_feature_names_out | True |
|
| 48 |
+
| feature_extraction__abbreviations | <__main__.ELFAbbreviationTransformer object at 0x7f38e082e4f0> |
|
| 49 |
+
| feature_extraction__tokenizer | CountVectorizer(binary=True, lowercase=False,<br /> tokenizer=<__main__.LegalEntityTokenizer object at 0x7f38e082ee50>) |
|
| 50 |
+
| feature_extraction__abbreviations__elf_abbreviations | <__main__.ELFAbbreviations object at 0x7f38f438b670> |
|
| 51 |
| feature_extraction__abbreviations__jurisdiction | PL |
|
| 52 |
| feature_extraction__abbreviations__use_endswith | True |
|
| 53 |
| feature_extraction__abbreviations__use_lowercasing | True |
|
|
|
|
| 66 |
| feature_extraction__tokenizer__stop_words | |
|
| 67 |
| feature_extraction__tokenizer__strip_accents | |
|
| 68 |
| feature_extraction__tokenizer__token_pattern | (?u)\b\w\w+\b |
|
| 69 |
+
| feature_extraction__tokenizer__tokenizer | <__main__.LegalEntityTokenizer object at 0x7f38e082ee50> |
|
| 70 |
| feature_extraction__tokenizer__vocabulary | |
|
| 71 |
| classifier__alpha | 1.0 |
|
| 72 |
| classifier__class_prior | |
|
|
|
|
| 79 |
|
| 80 |
The model plot is below.
|
| 81 |
|
| 82 |
+
<style>#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 {color: black;background-color: white;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 pre{padding: 0;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-toggleable {background-color: white;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 label.sk-toggleable__label-arrow:before {content: "▸";float: left;margin-right: 0.25em;color: #696969;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: "▾";}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-parallel-item::after {content: "";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-serial::before {content: "";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-item {z-index: 1;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-parallel::before {content: "";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-parallel-item {display: flex;flex-direction: column;position: relative;background-color: white;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-parallel-item:only-child::after {width: 0;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;position: relative;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-label label {font-family: monospace;font-weight: bold;background-color: white;display: inline-block;line-height: 1.2em;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-label-container {position: relative;z-index: 2;text-align: center;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-e1208602-57d4-43f2-85c3-031517eb1aa4 div.sk-text-repr-fallback {display: none;}</style><div id="sk-e1208602-57d4-43f2-85c3-031517eb1aa4" class="sk-top-container" style="overflow: auto;"><div class="sk-text-repr-fallback"><pre>Pipeline(steps=[('feature_extraction',ColumnTransformer(transformers=[('abbreviations',<__main__.ELFAbbreviationTransformer object at 0x7f38e082e4f0>,0),('tokenizer',CountVectorizer(binary=True,lowercase=False,tokenizer=<__main__.LegalEntityTokenizer object at 0x7f38e082ee50>),0)])),('classifier', ComplementNB())])</pre><b>Please rerun this cell to show the HTML repr or trust the notebook.</b></div><div class="sk-container" hidden><div class="sk-item sk-dashed-wrapped"><div class="sk-label-container"><div class="sk-label sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="b22014d7-b892-49d0-a00f-77d5d3d91ace" type="checkbox" ><label for="b22014d7-b892-49d0-a00f-77d5d3d91ace" class="sk-toggleable__label sk-toggleable__label-arrow">Pipeline</label><div class="sk-toggleable__content"><pre>Pipeline(steps=[('feature_extraction',ColumnTransformer(transformers=[('abbreviations',<__main__.ELFAbbreviationTransformer object at 0x7f38e082e4f0>,0),('tokenizer',CountVectorizer(binary=True,lowercase=False,tokenizer=<__main__.LegalEntityTokenizer object at 0x7f38e082ee50>),0)])),('classifier', ComplementNB())])</pre></div></div></div><div class="sk-serial"><div class="sk-item sk-dashed-wrapped"><div class="sk-label-container"><div class="sk-label sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="be227d86-c6ce-4eff-88e2-6efe9bed489a" type="checkbox" ><label for="be227d86-c6ce-4eff-88e2-6efe9bed489a" class="sk-toggleable__label sk-toggleable__label-arrow">feature_extraction: ColumnTransformer</label><div class="sk-toggleable__content"><pre>ColumnTransformer(transformers=[('abbreviations',<__main__.ELFAbbreviationTransformer object at 0x7f38e082e4f0>,0),('tokenizer',CountVectorizer(binary=True, lowercase=False,tokenizer=<__main__.LegalEntityTokenizer object at 0x7f38e082ee50>),0)])</pre></div></div></div><div class="sk-parallel"><div class="sk-parallel-item"><div class="sk-item"><div class="sk-label-container"><div class="sk-label sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="6b957cb5-d512-4dc4-8b89-0ce196c51db5" type="checkbox" ><label for="6b957cb5-d512-4dc4-8b89-0ce196c51db5" class="sk-toggleable__label sk-toggleable__label-arrow">abbreviations</label><div class="sk-toggleable__content"><pre>0</pre></div></div></div><div class="sk-serial"><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="a5d85fa3-7e72-43b2-b560-cf0b9bdf1b6b" type="checkbox" ><label for="a5d85fa3-7e72-43b2-b560-cf0b9bdf1b6b" class="sk-toggleable__label sk-toggleable__label-arrow">ELFAbbreviationTransformer</label><div class="sk-toggleable__content"><pre><__main__.ELFAbbreviationTransformer object at 0x7f38e082e4f0></pre></div></div></div></div></div></div><div class="sk-parallel-item"><div class="sk-item"><div class="sk-label-container"><div class="sk-label sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="2748f0f3-5698-4d09-83c0-f7a236486111" type="checkbox" ><label for="2748f0f3-5698-4d09-83c0-f7a236486111" class="sk-toggleable__label sk-toggleable__label-arrow">tokenizer</label><div class="sk-toggleable__content"><pre>0</pre></div></div></div><div class="sk-serial"><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="2adc89fe-7735-42a2-8fc4-1c272b44e547" type="checkbox" ><label for="2adc89fe-7735-42a2-8fc4-1c272b44e547" class="sk-toggleable__label sk-toggleable__label-arrow">CountVectorizer</label><div class="sk-toggleable__content"><pre>CountVectorizer(binary=True, lowercase=False,tokenizer=<__main__.LegalEntityTokenizer object at 0x7f38e082ee50>)</pre></div></div></div></div></div></div></div></div><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="330d4134-5949-4a02-985a-2a27ef3ed24c" type="checkbox" ><label for="330d4134-5949-4a02-985a-2a27ef3ed24c" class="sk-toggleable__label sk-toggleable__label-arrow">ComplementNB</label><div class="sk-toggleable__content"><pre>ComplementNB()</pre></div></div></div></div></div></div></div>
|
| 83 |
|
| 84 |
## Evaluation Results
|
| 85 |
|
config.json
CHANGED
|
@@ -10,9 +10,9 @@
|
|
| 10 |
],
|
| 11 |
"example_input": {
|
| 12 |
"LegalName": [
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
]
|
| 17 |
},
|
| 18 |
"model": {
|
|
|
|
| 10 |
],
|
| 11 |
"example_input": {
|
| 12 |
"LegalName": [
|
| 13 |
+
"Miejskie Przedsi\u0119biorstwo Energetyki Cieplnej Sp\u00f3\u0142ka z ograniczon\u0105 odpowiedzialno\u015bci\u0105",
|
| 14 |
+
"Przedsi\u0119biorstwo Produkcyjno Us\u0142ugowe Mimal Krystyna Fludra",
|
| 15 |
+
"NGS OIL & GAS S.A."
|
| 16 |
]
|
| 17 |
},
|
| 18 |
"model": {
|
model.joblib
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc0b7ee23eeb0c31117fd100ee001160a898cbdab10ee5afb43d54a8c3593c84
|
| 3 |
+
size 10288365
|