Python version 3.10
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ model_file: model.pkl
|
|
| 14 |
|
| 15 |
Suicide Detection text classification model.
|
| 16 |
|
| 17 |
-
PYTHON 3.
|
| 18 |
|
| 19 |
|
| 20 |
## Training Procedure
|
|
@@ -32,73 +32,73 @@ See main.py for further details.
|
|
| 32 |
<details>
|
| 33 |
<summary> Click to expand </summary>
|
| 34 |
|
| 35 |
-
| Hyperparameter | Value
|
| 36 |
-
|
| 37 |
-
| memory |
|
| 38 |
-
| steps | [('tfidf', TfidfVectorizer(min_df=100, ngram_range=(1, 3),<br /> preprocessor=<function preprocessor at
|
| 39 |
-
| verbose | True
|
| 40 |
-
| tfidf | TfidfVectorizer(min_df=100, ngram_range=(1, 3),<br /> preprocessor=<function preprocessor at
|
| 41 |
-
| classifier | XGBClassifier(base_score=None, booster=None, callbacks=None,<br /> colsample_bylevel=None, colsample_bynode=None,<br /> colsample_bytree=None, device=None, early_stopping_rounds=None,<br /> enable_categorical=False, eval_metric=None, feature_types=None,<br /> gamma=None, grow_policy=None, importance_type=None,<br /> interaction_constraints=None, learning_rate=None, max_bin=None,<br /> max_cat_threshold=None, max_cat_to_onehot=None,<br /> max_delta_step=None, max_depth=None, max_leaves=None,<br /> min_child_weight=None, missing=nan, monotone_constraints=None,<br /> multi_strategy=None, n_estimators=None, n_jobs=None,<br /> num_parallel_tree=None, random_state=None, ...)
|
| 42 |
-
| tfidf__analyzer | word
|
| 43 |
-
| tfidf__binary | False
|
| 44 |
-
| tfidf__decode_error | strict
|
| 45 |
-
| tfidf__dtype | <class 'numpy.float64'>
|
| 46 |
-
| tfidf__encoding | utf-8
|
| 47 |
-
| tfidf__input | content
|
| 48 |
-
| tfidf__lowercase | True
|
| 49 |
-
| tfidf__max_df | 1.0
|
| 50 |
-
| tfidf__max_features |
|
| 51 |
-
| tfidf__min_df | 100
|
| 52 |
-
| tfidf__ngram_range | (1, 3)
|
| 53 |
-
| tfidf__norm | l2
|
| 54 |
-
| tfidf__preprocessor | <function preprocessor at
|
| 55 |
-
| tfidf__smooth_idf | True
|
| 56 |
-
| tfidf__stop_words |
|
| 57 |
-
| tfidf__strip_accents |
|
| 58 |
-
| tfidf__sublinear_tf | False
|
| 59 |
-
| tfidf__token_pattern | (?u)\b\w\w+\b
|
| 60 |
-
| tfidf__tokenizer |
|
| 61 |
-
| tfidf__use_idf | True
|
| 62 |
-
| tfidf__vocabulary |
|
| 63 |
-
| classifier__objective | binary:logistic
|
| 64 |
-
| classifier__base_score |
|
| 65 |
-
| classifier__booster |
|
| 66 |
-
| classifier__callbacks |
|
| 67 |
-
| classifier__colsample_bylevel |
|
| 68 |
-
| classifier__colsample_bynode |
|
| 69 |
-
| classifier__colsample_bytree |
|
| 70 |
-
| classifier__device |
|
| 71 |
-
| classifier__early_stopping_rounds |
|
| 72 |
-
| classifier__enable_categorical | False
|
| 73 |
-
| classifier__eval_metric |
|
| 74 |
-
| classifier__feature_types |
|
| 75 |
-
| classifier__gamma |
|
| 76 |
-
| classifier__grow_policy |
|
| 77 |
-
| classifier__importance_type |
|
| 78 |
-
| classifier__interaction_constraints |
|
| 79 |
-
| classifier__learning_rate |
|
| 80 |
-
| classifier__max_bin |
|
| 81 |
-
| classifier__max_cat_threshold |
|
| 82 |
-
| classifier__max_cat_to_onehot |
|
| 83 |
-
| classifier__max_delta_step |
|
| 84 |
-
| classifier__max_depth |
|
| 85 |
-
| classifier__max_leaves |
|
| 86 |
-
| classifier__min_child_weight |
|
| 87 |
-
| classifier__missing | nan
|
| 88 |
-
| classifier__monotone_constraints |
|
| 89 |
-
| classifier__multi_strategy |
|
| 90 |
-
| classifier__n_estimators |
|
| 91 |
-
| classifier__n_jobs |
|
| 92 |
-
| classifier__num_parallel_tree |
|
| 93 |
-
| classifier__random_state |
|
| 94 |
-
| classifier__reg_alpha |
|
| 95 |
-
| classifier__reg_lambda |
|
| 96 |
-
| classifier__sampling_method |
|
| 97 |
-
| classifier__scale_pos_weight |
|
| 98 |
-
| classifier__subsample |
|
| 99 |
-
| classifier__tree_method |
|
| 100 |
-
| classifier__validate_parameters |
|
| 101 |
-
| classifier__verbosity |
|
| 102 |
|
| 103 |
</details>
|
| 104 |
|
|
@@ -180,7 +180,7 @@ div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,
|
|
| 180 |
#sk-container-id-1 a.estimator_doc_link:hover {/* unfitted */background-color: var(--sklearn-color-unfitted-level-3);color: var(--sklearn-color-background);text-decoration: none;
|
| 181 |
}#sk-container-id-1 a.estimator_doc_link.fitted:hover {/* fitted */background-color: var(--sklearn-color-fitted-level-3);
|
| 182 |
}
|
| 183 |
-
</style><div id="sk-container-id-1" class="sk-top-container" style="overflow: auto;"><div class="sk-text-repr-fallback"><pre>Pipeline(steps=[('tfidf',TfidfVectorizer(min_df=100, ngram_range=(1, 3),preprocessor=<function preprocessor at
|
| 184 |
|
| 185 |
## Evaluation Results
|
| 186 |
|
|
|
|
| 14 |
|
| 15 |
Suicide Detection text classification model.
|
| 16 |
|
| 17 |
+
PYTHON 3.10 ONLY
|
| 18 |
|
| 19 |
|
| 20 |
## Training Procedure
|
|
|
|
| 32 |
<details>
|
| 33 |
<summary> Click to expand </summary>
|
| 34 |
|
| 35 |
+
| Hyperparameter | Value |
|
| 36 |
+
|-------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 37 |
+
| memory | |
|
| 38 |
+
| steps | [('tfidf', TfidfVectorizer(min_df=100, ngram_range=(1, 3),<br /> preprocessor=<function preprocessor at 0x7f8d443a30a0>)), ('classifier', XGBClassifier(base_score=None, booster=None, callbacks=None,<br /> colsample_bylevel=None, colsample_bynode=None,<br /> colsample_bytree=None, device=None, early_stopping_rounds=None,<br /> enable_categorical=False, eval_metric=None, feature_types=None,<br /> gamma=None, grow_policy=None, importance_type=None,<br /> interaction_constraints=None, learning_rate=None, max_bin=None,<br /> max_cat_threshold=None, max_cat_to_onehot=None,<br /> max_delta_step=None, max_depth=None, max_leaves=None,<br /> min_child_weight=None, missing=nan, monotone_constraints=None,<br /> multi_strategy=None, n_estimators=None, n_jobs=None,<br /> num_parallel_tree=None, random_state=None, ...))] |
|
| 39 |
+
| verbose | True |
|
| 40 |
+
| tfidf | TfidfVectorizer(min_df=100, ngram_range=(1, 3),<br /> preprocessor=<function preprocessor at 0x7f8d443a30a0>) |
|
| 41 |
+
| classifier | XGBClassifier(base_score=None, booster=None, callbacks=None,<br /> colsample_bylevel=None, colsample_bynode=None,<br /> colsample_bytree=None, device=None, early_stopping_rounds=None,<br /> enable_categorical=False, eval_metric=None, feature_types=None,<br /> gamma=None, grow_policy=None, importance_type=None,<br /> interaction_constraints=None, learning_rate=None, max_bin=None,<br /> max_cat_threshold=None, max_cat_to_onehot=None,<br /> max_delta_step=None, max_depth=None, max_leaves=None,<br /> min_child_weight=None, missing=nan, monotone_constraints=None,<br /> multi_strategy=None, n_estimators=None, n_jobs=None,<br /> num_parallel_tree=None, random_state=None, ...) |
|
| 42 |
+
| tfidf__analyzer | word |
|
| 43 |
+
| tfidf__binary | False |
|
| 44 |
+
| tfidf__decode_error | strict |
|
| 45 |
+
| tfidf__dtype | <class 'numpy.float64'> |
|
| 46 |
+
| tfidf__encoding | utf-8 |
|
| 47 |
+
| tfidf__input | content |
|
| 48 |
+
| tfidf__lowercase | True |
|
| 49 |
+
| tfidf__max_df | 1.0 |
|
| 50 |
+
| tfidf__max_features | |
|
| 51 |
+
| tfidf__min_df | 100 |
|
| 52 |
+
| tfidf__ngram_range | (1, 3) |
|
| 53 |
+
| tfidf__norm | l2 |
|
| 54 |
+
| tfidf__preprocessor | <function preprocessor at 0x7f8d443a30a0> |
|
| 55 |
+
| tfidf__smooth_idf | True |
|
| 56 |
+
| tfidf__stop_words | |
|
| 57 |
+
| tfidf__strip_accents | |
|
| 58 |
+
| tfidf__sublinear_tf | False |
|
| 59 |
+
| tfidf__token_pattern | (?u)\b\w\w+\b |
|
| 60 |
+
| tfidf__tokenizer | |
|
| 61 |
+
| tfidf__use_idf | True |
|
| 62 |
+
| tfidf__vocabulary | |
|
| 63 |
+
| classifier__objective | binary:logistic |
|
| 64 |
+
| classifier__base_score | |
|
| 65 |
+
| classifier__booster | |
|
| 66 |
+
| classifier__callbacks | |
|
| 67 |
+
| classifier__colsample_bylevel | |
|
| 68 |
+
| classifier__colsample_bynode | |
|
| 69 |
+
| classifier__colsample_bytree | |
|
| 70 |
+
| classifier__device | |
|
| 71 |
+
| classifier__early_stopping_rounds | |
|
| 72 |
+
| classifier__enable_categorical | False |
|
| 73 |
+
| classifier__eval_metric | |
|
| 74 |
+
| classifier__feature_types | |
|
| 75 |
+
| classifier__gamma | |
|
| 76 |
+
| classifier__grow_policy | |
|
| 77 |
+
| classifier__importance_type | |
|
| 78 |
+
| classifier__interaction_constraints | |
|
| 79 |
+
| classifier__learning_rate | |
|
| 80 |
+
| classifier__max_bin | |
|
| 81 |
+
| classifier__max_cat_threshold | |
|
| 82 |
+
| classifier__max_cat_to_onehot | |
|
| 83 |
+
| classifier__max_delta_step | |
|
| 84 |
+
| classifier__max_depth | |
|
| 85 |
+
| classifier__max_leaves | |
|
| 86 |
+
| classifier__min_child_weight | |
|
| 87 |
+
| classifier__missing | nan |
|
| 88 |
+
| classifier__monotone_constraints | |
|
| 89 |
+
| classifier__multi_strategy | |
|
| 90 |
+
| classifier__n_estimators | |
|
| 91 |
+
| classifier__n_jobs | |
|
| 92 |
+
| classifier__num_parallel_tree | |
|
| 93 |
+
| classifier__random_state | |
|
| 94 |
+
| classifier__reg_alpha | |
|
| 95 |
+
| classifier__reg_lambda | |
|
| 96 |
+
| classifier__sampling_method | |
|
| 97 |
+
| classifier__scale_pos_weight | |
|
| 98 |
+
| classifier__subsample | |
|
| 99 |
+
| classifier__tree_method | |
|
| 100 |
+
| classifier__validate_parameters | |
|
| 101 |
+
| classifier__verbosity | |
|
| 102 |
|
| 103 |
</details>
|
| 104 |
|
|
|
|
| 180 |
#sk-container-id-1 a.estimator_doc_link:hover {/* unfitted */background-color: var(--sklearn-color-unfitted-level-3);color: var(--sklearn-color-background);text-decoration: none;
|
| 181 |
}#sk-container-id-1 a.estimator_doc_link.fitted:hover {/* fitted */background-color: var(--sklearn-color-fitted-level-3);
|
| 182 |
}
|
| 183 |
+
</style><div id="sk-container-id-1" class="sk-top-container" style="overflow: auto;"><div class="sk-text-repr-fallback"><pre>Pipeline(steps=[('tfidf',TfidfVectorizer(min_df=100, ngram_range=(1, 3),preprocessor=<function preprocessor at 0x7f8d443a30a0>)),('classifier',XGBClassifier(base_score=None, booster=None, callbacks=None,colsample_bylevel=None, colsample_bynode=None,colsample_bytree=None, device=None,early_stopping_rounds=None,enable_categorical=False, eval_metric=None,featur...importance_type=None,interaction_constraints=None, learning_rate=None,max_bin=None, max_cat_threshold=None,max_cat_to_onehot=None, max_delta_step=None,max_depth=None, max_leaves=None,min_child_weight=None, missing=nan,monotone_constraints=None, multi_strategy=None,n_estimators=None, n_jobs=None,num_parallel_tree=None, random_state=None, ...))],verbose=True)</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 fitted sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-1" type="checkbox" ><label for="sk-estimator-id-1" class="sk-toggleable__label fitted sk-toggleable__label-arrow fitted"> Pipeline<a class="sk-estimator-doc-link fitted" rel="noreferrer" target="_blank" href="https://scikit-learn.org/1.4/modules/generated/sklearn.pipeline.Pipeline.html">?<span>Documentation for Pipeline</span></a><span class="sk-estimator-doc-link fitted">i<span>Fitted</span></span></label><div class="sk-toggleable__content fitted"><pre>Pipeline(steps=[('tfidf',TfidfVectorizer(min_df=100, ngram_range=(1, 3),preprocessor=<function preprocessor at 0x7f8d443a30a0>)),('classifier',XGBClassifier(base_score=None, booster=None, callbacks=None,colsample_bylevel=None, colsample_bynode=None,colsample_bytree=None, device=None,early_stopping_rounds=None,enable_categorical=False, eval_metric=None,featur...importance_type=None,interaction_constraints=None, learning_rate=None,max_bin=None, max_cat_threshold=None,max_cat_to_onehot=None, max_delta_step=None,max_depth=None, max_leaves=None,min_child_weight=None, missing=nan,monotone_constraints=None, multi_strategy=None,n_estimators=None, n_jobs=None,num_parallel_tree=None, random_state=None, ...))],verbose=True)</pre></div> </div></div><div class="sk-serial"><div class="sk-item"><div class="sk-estimator fitted sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-2" type="checkbox" ><label for="sk-estimator-id-2" class="sk-toggleable__label fitted sk-toggleable__label-arrow fitted"> TfidfVectorizer<a class="sk-estimator-doc-link fitted" rel="noreferrer" target="_blank" href="https://scikit-learn.org/1.4/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html">?<span>Documentation for TfidfVectorizer</span></a></label><div class="sk-toggleable__content fitted"><pre>TfidfVectorizer(min_df=100, ngram_range=(1, 3),preprocessor=<function preprocessor at 0x7f8d443a30a0>)</pre></div> </div></div><div class="sk-item"><div class="sk-estimator fitted sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="sk-estimator-id-3" type="checkbox" ><label for="sk-estimator-id-3" class="sk-toggleable__label fitted sk-toggleable__label-arrow fitted">XGBClassifier</label><div class="sk-toggleable__content fitted"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,colsample_bylevel=None, colsample_bynode=None,colsample_bytree=None, device=None, early_stopping_rounds=None,enable_categorical=False, eval_metric=None, feature_types=None,gamma=None, grow_policy=None, importance_type=None,interaction_constraints=None, learning_rate=None, max_bin=None,max_cat_threshold=None, max_cat_to_onehot=None,max_delta_step=None, max_depth=None, max_leaves=None,min_child_weight=None, missing=nan, monotone_constraints=None,multi_strategy=None, n_estimators=None, n_jobs=None,num_parallel_tree=None, random_state=None, ...)</pre></div> </div></div></div></div></div></div>
|
| 184 |
|
| 185 |
## Evaluation Results
|
| 186 |
|
main.py
CHANGED
|
@@ -86,7 +86,7 @@ model_card.metadata.license = "mit"
|
|
| 86 |
model_description = """
|
| 87 |
Suicide Detection text classification model.
|
| 88 |
|
| 89 |
-
PYTHON 3.
|
| 90 |
"""
|
| 91 |
|
| 92 |
model_card.add(**{"Model description": model_description})
|
|
|
|
| 86 |
model_description = """
|
| 87 |
Suicide Detection text classification model.
|
| 88 |
|
| 89 |
+
PYTHON 3.10 ONLY
|
| 90 |
"""
|
| 91 |
|
| 92 |
model_card.add(**{"Model description": model_description})
|
model.pkl
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 sha256:9a748119b514aaefb9c9cebd919616e3266ef2e2269a5dc408d2f0d5d4b3728f
|
| 3 |
+
size 222084905
|