improved some code references

ml/src/analysis/test_ats_resolution.py

@@ -43,7 +43,7 @@ def main():
                     "scale_pos_weight": scale_pos_weight,
                     "use_label_encoder": False,
                     "learning_rate": 0.07,
-                    "seed": 0
+                    "random_state": 0
             }
             
             model = xgb.XGBClassifier(**params)

ml/src/analysis/test_model_features.py

@@ -5,7 +5,6 @@ from tools import file_writer, data_loader
 from sklearn.model_selection import StratifiedKFold
 import xgboost as xgb
 from sklearn.metrics import accuracy_score
-import xgboost as xgb
 import pandas as pd
 from utility.metrics import gini_xgb
 import shap
@@ -72,8 +71,7 @@ def get_best_shap_features(X: np.ndarray, y: np.ndarray,
                               eval_metric='logloss',
                               use_label_encoder=False,
                               n_jobs=-1,
-                              random_state=0,
-                              seed=seed)
+                              random_state=seed)
     
     acc_score_list = list()
     for i, (train_index, test_index) in enumerate(kf.split(X, y)):

ml/src/model/train_xgboost_model.py

@@ -55,7 +55,7 @@ def main(dataset_version : str = 'emb'):
                 "use_label_encoder": False,
                 "learning_rate": 0.07,
                 "eval_metric": "logloss",
-                "seed": 0
+                "random_state": 0
         }
                 
         model = xgb.XGBClassifier(**params)

ml/src/tools/classifiers.py

@@ -61,7 +61,7 @@ class XgbClassifier(BaseClassifer):
                   "max_depth": 4,
                   "scale_pos_weight": scale_pos_weight,
                   "objective": "binary:logistic",
-                  "seed": 0,
+                  "random_state": 0,
                   "use_label_encoder": False,
                   "eval_metric": 'logloss'}
         return xgb.XGBClassifier(**params)

ml/src/tuning/tune_random_forest_gs.py

 import numpy as np
-import pandas as pd
 import paths as pt
 from sklearn.model_selection import GridSearchCV
-from xgboost import XGBClassifier
-from tools import data_loader, file_writer
+from tools import data_loader
 from sklearn.model_selection import StratifiedKFold
 from sklearn.ensemble import RandomForestClassifier
-from sklearn.metrics import roc_auc_score, accuracy_score
-from sklearn.model_selection import cross_validate, cross_val_score
+from sklearn.model_selection import cross_val_score
 import matplotlib.pyplot as plt
 from pathlib import Path
 import paths as pt

ml/src/tuning/tune_random_forest_gs_os.py

 import numpy as np
-import pandas as pd
 import paths as pt
 from sklearn.model_selection import GridSearchCV
-from xgboost import XGBClassifier
-from tools import data_loader, file_writer
+from tools import data_loader
 from sklearn.model_selection import StratifiedKFold
 from sklearn.ensemble import RandomForestClassifier
-from sklearn.metrics import roc_auc_score, accuracy_score
-from imblearn.pipeline import make_pipeline, Pipeline
+from imblearn.pipeline import Pipeline
 from imblearn.over_sampling import ADASYN
 import matplotlib.pyplot as plt
 from pathlib import Path

ml/src/tuning/tune_xgboost_gs.py

 import numpy as np
-import pandas as pd
 import paths as pt
+import xgboost as xgb
 from sklearn.model_selection import GridSearchCV
-from tools import data_loader, file_writer
+from tools import data_loader
 from sklearn.model_selection import StratifiedKFold
-from sklearn.ensemble import RandomForestClassifier
-from sklearn.metrics import roc_auc_score, accuracy_score
-from sklearn.model_selection import cross_validate, cross_val_score
+from sklearn.model_selection import cross_val_score
 import matplotlib.pyplot as plt
 from pathlib import Path
 import paths as pt
 import yaml
-import xgboost as xgb
 
 def main():
     with open(Path.joinpath(pt.CONFIGS_DIR, "settings.yaml"), 'r') as stream: