pushing model RF with camember base embeddings
Browse files- README.md +130 -0
- config.json +19 -0
- confusion_matrix.png +0 -0
- skops-ngrzbpwh.pkl +3 -0
README.md
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: sklearn
|
| 4 |
+
tags:
|
| 5 |
+
- sklearn
|
| 6 |
+
- skops
|
| 7 |
+
- text-classification
|
| 8 |
+
model_format: pickle
|
| 9 |
+
model_file: skops-ngrzbpwh.pkl
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model description
|
| 13 |
+
|
| 14 |
+
This is a `Support Vector Classifier` model trained on JeVeuxAider dataset. As input, the model takes text embeddings encoded with camembert-base (768 tokens)
|
| 15 |
+
|
| 16 |
+
## Intended uses & limitations
|
| 17 |
+
|
| 18 |
+
This model is not ready to be used in production.
|
| 19 |
+
|
| 20 |
+
## Training Procedure
|
| 21 |
+
|
| 22 |
+
[More Information Needed]
|
| 23 |
+
|
| 24 |
+
### Hyperparameters
|
| 25 |
+
|
| 26 |
+
<details>
|
| 27 |
+
<summary> Click to expand </summary>
|
| 28 |
+
|
| 29 |
+
| Hyperparameter | Value |
|
| 30 |
+
|---------------------------------------------------------|---------------------------------------------------------------------------------------------------------------|
|
| 31 |
+
| memory | |
|
| 32 |
+
| steps | [('columntransformer', ColumnTransformer(transformers=[('num',<br /> Pipeline(steps=[('imputer',<br /> SimpleImputer(strategy='median')),<br /> ('scaler', StandardScaler()),<br /> ('pca',<br /> PCA(n_components=689))]),<br /> Index(['avg_1', 'avg_2', 'avg_3', 'avg_4', 'avg_5', 'avg_6', 'avg_7', 'avg_8',<br /> 'avg_9', 'avg_10',<br /> ...<br /> 'max_759', 'max_760', 'max_761', 'max_762', 'max_763', 'max_764',<br /> 'max_765', 'max_766', 'max_767', 'max_768'],<br /> dtype='object', length=2304))],<br /> verbose_feature_names_out=False)), ('randomforestclassifier', RandomForestClassifier(max_depth=15, max_features=20, min_samples_split=10,<br /> random_state=42))] |
|
| 33 |
+
| verbose | False |
|
| 34 |
+
| columntransformer | ColumnTransformer(transformers=[('num',<br /> Pipeline(steps=[('imputer',<br /> SimpleImputer(strategy='median')),<br /> ('scaler', StandardScaler()),<br /> ('pca',<br /> PCA(n_components=689))]),<br /> Index(['avg_1', 'avg_2', 'avg_3', 'avg_4', 'avg_5', 'avg_6', 'avg_7', 'avg_8',<br /> 'avg_9', 'avg_10',<br /> ...<br /> 'max_759', 'max_760', 'max_761', 'max_762', 'max_763', 'max_764',<br /> 'max_765', 'max_766', 'max_767', 'max_768'],<br /> dtype='object', length=2304))],<br /> verbose_feature_names_out=False) |
|
| 35 |
+
| randomforestclassifier | RandomForestClassifier(max_depth=15, max_features=20, min_samples_split=10,<br /> random_state=42) |
|
| 36 |
+
| columntransformer__n_jobs | |
|
| 37 |
+
| columntransformer__remainder | drop |
|
| 38 |
+
| columntransformer__sparse_threshold | 0.3 |
|
| 39 |
+
| columntransformer__transformer_weights | |
|
| 40 |
+
| columntransformer__transformers | [('num', Pipeline(steps=[('imputer', SimpleImputer(strategy='median')),<br /> ('scaler', StandardScaler()), ('pca', PCA(n_components=689))]), Index(['avg_1', 'avg_2', 'avg_3', 'avg_4', 'avg_5', 'avg_6', 'avg_7', 'avg_8',<br /> 'avg_9', 'avg_10',<br /> ...<br /> 'max_759', 'max_760', 'max_761', 'max_762', 'max_763', 'max_764',<br /> 'max_765', 'max_766', 'max_767', 'max_768'],<br /> dtype='object', length=2304))] |
|
| 41 |
+
| columntransformer__verbose | False |
|
| 42 |
+
| columntransformer__verbose_feature_names_out | False |
|
| 43 |
+
| columntransformer__num | Pipeline(steps=[('imputer', SimpleImputer(strategy='median')),<br /> ('scaler', StandardScaler()), ('pca', PCA(n_components=689))]) |
|
| 44 |
+
| columntransformer__num__memory | |
|
| 45 |
+
| columntransformer__num__steps | [('imputer', SimpleImputer(strategy='median')), ('scaler', StandardScaler()), ('pca', PCA(n_components=689))] |
|
| 46 |
+
| columntransformer__num__verbose | False |
|
| 47 |
+
| columntransformer__num__imputer | SimpleImputer(strategy='median') |
|
| 48 |
+
| columntransformer__num__scaler | StandardScaler() |
|
| 49 |
+
| columntransformer__num__pca | PCA(n_components=689) |
|
| 50 |
+
| columntransformer__num__imputer__add_indicator | False |
|
| 51 |
+
| columntransformer__num__imputer__copy | True |
|
| 52 |
+
| columntransformer__num__imputer__fill_value | |
|
| 53 |
+
| columntransformer__num__imputer__keep_empty_features | False |
|
| 54 |
+
| columntransformer__num__imputer__missing_values | nan |
|
| 55 |
+
| columntransformer__num__imputer__strategy | median |
|
| 56 |
+
| columntransformer__num__imputer__verbose | deprecated |
|
| 57 |
+
| columntransformer__num__scaler__copy | True |
|
| 58 |
+
| columntransformer__num__scaler__with_mean | True |
|
| 59 |
+
| columntransformer__num__scaler__with_std | True |
|
| 60 |
+
| columntransformer__num__pca__copy | True |
|
| 61 |
+
| columntransformer__num__pca__iterated_power | auto |
|
| 62 |
+
| columntransformer__num__pca__n_components | 689 |
|
| 63 |
+
| columntransformer__num__pca__n_oversamples | 10 |
|
| 64 |
+
| columntransformer__num__pca__power_iteration_normalizer | auto |
|
| 65 |
+
| columntransformer__num__pca__random_state | |
|
| 66 |
+
| columntransformer__num__pca__svd_solver | auto |
|
| 67 |
+
| columntransformer__num__pca__tol | 0.0 |
|
| 68 |
+
| columntransformer__num__pca__whiten | False |
|
| 69 |
+
| randomforestclassifier__bootstrap | True |
|
| 70 |
+
| randomforestclassifier__ccp_alpha | 0.0 |
|
| 71 |
+
| randomforestclassifier__class_weight | |
|
| 72 |
+
| randomforestclassifier__criterion | gini |
|
| 73 |
+
| randomforestclassifier__max_depth | 15 |
|
| 74 |
+
| randomforestclassifier__max_features | 20 |
|
| 75 |
+
| randomforestclassifier__max_leaf_nodes | |
|
| 76 |
+
| randomforestclassifier__max_samples | |
|
| 77 |
+
| randomforestclassifier__min_impurity_decrease | 0.0 |
|
| 78 |
+
| randomforestclassifier__min_samples_leaf | 1 |
|
| 79 |
+
| randomforestclassifier__min_samples_split | 10 |
|
| 80 |
+
| randomforestclassifier__min_weight_fraction_leaf | 0.0 |
|
| 81 |
+
| randomforestclassifier__n_estimators | 100 |
|
| 82 |
+
| randomforestclassifier__n_jobs | |
|
| 83 |
+
| randomforestclassifier__oob_score | False |
|
| 84 |
+
| randomforestclassifier__random_state | 42 |
|
| 85 |
+
| randomforestclassifier__verbose | 0 |
|
| 86 |
+
| randomforestclassifier__warm_start | False |
|
| 87 |
+
|
| 88 |
+
</details>
|
| 89 |
+
|
| 90 |
+
### Model Plot
|
| 91 |
+
|
| 92 |
+
<style>#sk-container-id-3 {color: black;background-color: white;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: "▸";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: "▾";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 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-container-id-3 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-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: "";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: "";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: "";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 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;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 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-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id="sk-container-id-3" class="sk-top-container" style="overflow: auto;"><div class="sk-text-repr-fallback"><pre>Pipeline(steps=[('columntransformer',ColumnTransformer(transformers=[('num',Pipeline(steps=[('imputer',SimpleImputer(strategy='median')),('scaler',StandardScaler()),('pca',PCA(n_components=689))]),Index(['avg_1', 'avg_2', 'avg_3', 'avg_4', 'avg_5', 'avg_6', 'avg_7', 'avg_8','avg_9', 'avg_10',...'max_759', 'max_760', 'max_761', 'max_762', 'max_763', 'max_764','max_765', 'max_766', 'max_767', 'max_768'],dtype='object', length=2304))],verbose_feature_names_out=False)),('randomforestclassifier',RandomForestClassifier(max_depth=15, max_features=20,min_samples_split=10,random_state=42))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</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="sk-estimator-id-11" type="checkbox" ><label for="sk-estimator-id-11" class="sk-toggleable__label sk-toggleable__label-arrow">Pipeline</label><div class="sk-toggleable__content"><pre>Pipeline(steps=[('columntransformer',ColumnTransformer(transformers=[('num',Pipeline(steps=[('imputer',SimpleImputer(strategy='median')),('scaler',StandardScaler()),('pca',PCA(n_components=689))]),Index(['avg_1', 'avg_2', 'avg_3', 'avg_4', 'avg_5', 'avg_6', 'avg_7', 'avg_8','avg_9', 'avg_10',...'max_759', 'max_760', 'max_761', 'max_762', 'max_763', 'max_764','max_765', 'max_766', 'max_767', 'max_768'],dtype='object', length=2304))],verbose_feature_names_out=False)),('randomforestclassifier',RandomForestClassifier(max_depth=15, max_features=20,min_samples_split=10,random_state=42))])</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="sk-estimator-id-12" type="checkbox" ><label for="sk-estimator-id-12" class="sk-toggleable__label sk-toggleable__label-arrow">columntransformer: ColumnTransformer</label><div class="sk-toggleable__content"><pre>ColumnTransformer(transformers=[('num',Pipeline(steps=[('imputer',SimpleImputer(strategy='median')),('scaler', StandardScaler()),('pca',PCA(n_components=689))]),Index(['avg_1', 'avg_2', 'avg_3', 'avg_4', 'avg_5', 'avg_6', 'avg_7', 'avg_8','avg_9', 'avg_10',...'max_759', 'max_760', 'max_761', 'max_762', 'max_763', 'max_764','max_765', 'max_766', 'max_767', 'max_768'],dtype='object', length=2304))],verbose_feature_names_out=False)</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="sk-estimator-id-13" type="checkbox" ><label for="sk-estimator-id-13" class="sk-toggleable__label sk-toggleable__label-arrow">num</label><div class="sk-toggleable__content"><pre>Index(['avg_1', 'avg_2', 'avg_3', 'avg_4', 'avg_5', 'avg_6', 'avg_7', 'avg_8','avg_9', 'avg_10',...'max_759', 'max_760', 'max_761', 'max_762', 'max_763', 'max_764','max_765', 'max_766', 'max_767', 'max_768'],dtype='object', length=2304)</pre></div></div></div><div class="sk-serial"><div class="sk-item"><div class="sk-serial"><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-14" type="checkbox" ><label for="sk-estimator-id-14" class="sk-toggleable__label sk-toggleable__label-arrow">SimpleImputer</label><div class="sk-toggleable__content"><pre>SimpleImputer(strategy='median')</pre></div></div></div><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-15" type="checkbox" ><label for="sk-estimator-id-15" class="sk-toggleable__label sk-toggleable__label-arrow">StandardScaler</label><div class="sk-toggleable__content"><pre>StandardScaler()</pre></div></div></div><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-16" type="checkbox" ><label for="sk-estimator-id-16" class="sk-toggleable__label sk-toggleable__label-arrow">PCA</label><div class="sk-toggleable__content"><pre>PCA(n_components=689)</pre></div></div></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="sk-estimator-id-17" type="checkbox" ><label for="sk-estimator-id-17" class="sk-toggleable__label sk-toggleable__label-arrow">RandomForestClassifier</label><div class="sk-toggleable__content"><pre>RandomForestClassifier(max_depth=15, max_features=20, min_samples_split=10,random_state=42)</pre></div></div></div></div></div></div></div>
|
| 93 |
+
|
| 94 |
+
## Evaluation Results
|
| 95 |
+
|
| 96 |
+
| Metric | Value |
|
| 97 |
+
|----------|----------|
|
| 98 |
+
| accuracy | 0.964661 |
|
| 99 |
+
| f1 score | 0.964637 |
|
| 100 |
+
|
| 101 |
+
### Confusion Matrix
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
|
| 105 |
+
# How to Get Started with the Model
|
| 106 |
+
|
| 107 |
+
[More Information Needed]
|
| 108 |
+
|
| 109 |
+
# Model Card Authors
|
| 110 |
+
|
| 111 |
+
huynhdoo
|
| 112 |
+
|
| 113 |
+
# Model Card Contact
|
| 114 |
+
|
| 115 |
+
You can contact the model card authors through following channels:
|
| 116 |
+
[More Information Needed]
|
| 117 |
+
|
| 118 |
+
# Citation
|
| 119 |
+
|
| 120 |
+
**BibTeX**
|
| 121 |
+
|
| 122 |
+
```
|
| 123 |
+
@inproceedings{...,year={2023}}
|
| 124 |
+
```
|
| 125 |
+
|
| 126 |
+
# get_started_code
|
| 127 |
+
|
| 128 |
+
import pickle as pickle
|
| 129 |
+
with open(pkl_filename, 'rb') as file:
|
| 130 |
+
pipe = pickle.load(file)
|
config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"sklearn": {
|
| 3 |
+
"environment": [
|
| 4 |
+
"scikit-learn=1.2.2"
|
| 5 |
+
],
|
| 6 |
+
"example_input": {
|
| 7 |
+
"data": [
|
| 8 |
+
"",
|
| 9 |
+
""
|
| 10 |
+
]
|
| 11 |
+
},
|
| 12 |
+
"model": {
|
| 13 |
+
"file": "skops-ngrzbpwh.pkl"
|
| 14 |
+
},
|
| 15 |
+
"model_format": "pickle",
|
| 16 |
+
"task": "text-classification",
|
| 17 |
+
"use_intelex": false
|
| 18 |
+
}
|
| 19 |
+
}
|
confusion_matrix.png
ADDED
|
skops-ngrzbpwh.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d347ae8520d1883473a8e4c6742afb6c7cb3b4a80870f131baf2115f53aa1e03
|
| 3 |
+
size 11584737
|