Relaxed XGBBoost to reduce training time in later scripts

model_selection/hyperparam_tuning.py

@@ -106,9 +106,10 @@ if __name__ == "__main__":
                     'warm_start': [True, False]},
         "AB": {'n_estimators': randint(50, 150), 
             'learning_rate': uniform(0.8, 1.2)},
-        "XGB": {'n_estimators': randint(100, 1000), 
-                'max_depth': randint(3, 10), 
-                'learning_rate': uniform(0.01, 0.3)},
+        "XGB": {'n_estimators': randint(100, 500), 
+                'max_depth': randint(3, 6), 
+                'learning_rate': uniform(0.05, 0.15),
+                'tree_method': ['hist']},
         "LR": {'penalty': ['l1', 'l2', 'elasticnet', None], 
             'solver': ['lbfgs', 'sag', 'saga']},
         "SVM": {'C': uniform(0.8, 1.2), 
@@ -146,6 +147,8 @@ if __name__ == "__main__":
             hyperparam_df = pd.DataFrame(index=list(models.keys()), columns=['Best Parameters'])
             for model_name, model in models.items():
                 print(f"{group}-{method_names[j]}-{model_name}")
+                if model_name != 'XGB':
+                    continue
                 # Find optimal hyperparams for curr model
                 params = hyperparameters[model_name]
                 search = RandomizedSearchCV(model, param_distributions=params, cv=cv, n_jobs=10, scoring='precision')