finition streamlit nlp

Tarandro · Mar 12, 2021 · 13fccc9 · 13fccc9
1 parent 2b0804b
commit 13fccc9
Show file tree

Hide file tree

Showing 39 changed files with 26,621 additions and 2,208 deletions.
diff --git a/__pycache__/binaryML.cpython-38.pyc b/__pycache__/binaryML.cpython-38.pyc
diff --git a/__pycache__/class_gridsearch.cpython-38.pyc b/__pycache__/class_gridsearch.cpython-38.pyc
diff --git a/__pycache__/class_models.cpython-38.pyc b/__pycache__/class_models.cpython-38.pyc
diff --git a/__pycache__/eda_utils.cpython-38.pyc b/__pycache__/eda_utils.cpython-38.pyc
diff --git a/__pycache__/extraction_words.cpython-38.pyc b/__pycache__/extraction_words.cpython-38.pyc
diff --git a/__pycache__/feature_importance.cpython-38.pyc b/__pycache__/feature_importance.cpython-38.pyc
diff --git a/__pycache__/prediction.cpython-38.pyc b/__pycache__/prediction.cpython-38.pyc
diff --git a/__pycache__/utils.cpython-38.pyc b/__pycache__/utils.cpython-38.pyc
diff --git a/__pycache__/validation.cpython-38.pyc b/__pycache__/validation.cpython-38.pyc
diff --git a/main_nlp.py b/main_nlp.py
@@ -13,7 +13,7 @@
 
 frac = 0.8  # train_test_split fraction                 (data is split in train/test with frac = % for training dataset)
 
-max_run_time_per_model = 30  # (limit gridsearch time for each model)
+max_run_time_per_model = 300  # (limit gridsearch time for each model)
 
 scoring = 'f1'  # ['accuracy','f1','recall','precision','roc_auc']  # metric to optimize during gridsearch
 sort_leaderboard = 'f1'  # ['accuracy','f1','recall','precision','roc_auc']  # sort dataframe leaderboard by a metric

diff --git a/models_nlp/__pycache__/camembert.cpython-38.pyc b/models_nlp/__pycache__/camembert.cpython-38.pyc
diff --git a/models_nlp/__pycache__/fastText.cpython-38.pyc b/models_nlp/__pycache__/fastText.cpython-38.pyc
diff --git a/models_nlp/__pycache__/tfidf_Logistic_Regression.cpython-38.pyc b/models_nlp/__pycache__/tfidf_Logistic_Regression.cpython-38.pyc
diff --git a/models_nlp/__pycache__/tfidf_SGDclassifier.cpython-38.pyc b/models_nlp/__pycache__/tfidf_SGDclassifier.cpython-38.pyc
diff --git a/models_nlp/__pycache__/tfidf_naive_bayes.cpython-38.pyc b/models_nlp/__pycache__/tfidf_naive_bayes.cpython-38.pyc
diff --git a/models_tabular/__pycache__/blend_models.cpython-38.pyc b/models_tabular/__pycache__/blend_models.cpython-38.pyc
diff --git a/models_tabular/__pycache__/catBoost.cpython-38.pyc b/models_tabular/__pycache__/catBoost.cpython-38.pyc
diff --git a/models_tabular/__pycache__/lightGBM.cpython-38.pyc b/models_tabular/__pycache__/lightGBM.cpython-38.pyc
diff --git a/models_tabular/__pycache__/randomForest.cpython-38.pyc b/models_tabular/__pycache__/randomForest.cpython-38.pyc
diff --git a/models_tabular/__pycache__/regression_logistique.cpython-38.pyc b/models_tabular/__pycache__/regression_logistique.cpython-38.pyc
diff --git a/models_tabular/__pycache__/simpleNeuralNetwork.cpython-38.pyc b/models_tabular/__pycache__/simpleNeuralNetwork.cpython-38.pyc
diff --git a/models_tabular/__pycache__/stacking.cpython-38.pyc b/models_tabular/__pycache__/stacking.cpython-38.pyc
diff --git a/models_tabular/__pycache__/xgboost.cpython-38.pyc b/models_tabular/__pycache__/xgboost.cpython-38.pyc
diff --git a/preprocessing_data/__pycache__/preprocessing_nlp.cpython-38.pyc b/preprocessing_data/__pycache__/preprocessing_nlp.cpython-38.pyc
diff --git a/preprocessing_data/__pycache__/preprocessing_tabular.cpython-38.pyc b/preprocessing_data/__pycache__/preprocessing_tabular.cpython-38.pyc
diff --git a/results/results_nlp/X_test.csv b/results/results_nlp/X_test.csv
diff --git a/results/results_nlp/X_train.csv b/results/results_nlp/X_train.csv