training data without x features

models/catboost_model.py

@@ -11,7 +11,15 @@ from tqdm import tqdm
 
 
 class CAT_BOOST:
-    def __init__(self, data_frame, params={}, n_split_kfold=5, test_size=0.15, seed=42):
+    def __init__(
+        self,
+        data_frame,
+        params={},
+        n_split_kfold=5,
+        test_size=0.15,
+        seed=42,
+        output_file_tuning="cat_boost_tuning_results.csv",
+    ):
         self.data_frame = data_frame
         self.params = params
         self.n_split_kfold = n_split_kfold
@@ -35,6 +43,8 @@ class CAT_BOOST:
         self.kmeans_estimator = self.params.get("kmeans_estimator", 5)
         self.tuning_results = None
 
+        self.output_file_tuning = output_file_tuning
+
     def preprocess(self):
         self.scaling_method = self.params.get("scaling_method", None)
 
@@ -208,6 +218,6 @@ class CAT_BOOST:
         df_tuning = pandas.concat(
             [df_tuning.drop(columns=["metrics"]), metrics_df], axis=1
         )
-        df_tuning.to_csv("cat_boost_tuning_results.csv", index=False)
+        df_tuning.to_csv(self.output_file_tuning, index=False)
 
         return

models/compare_models.py

@@ -2,9 +2,9 @@ import pandas
 from catboost_model import CAT_BOOST
 from lightgbm_model import LIGHT_GBM
 
-data_frame = pandas.read_csv("./data/Ketamine_icp_no_missing.csv")
+data_frame = pandas.read_csv("../data/Ketamine_icp_no_missing.csv")
 
-cat_boost_results = pandas.read_csv("./cat_boost_tuning_results.csv")
+cat_boost_results = pandas.read_csv("./cat_boost_tuning_results_no_x.csv")
 lgbm_results = pandas.read_csv("./lightgbm_tuning_results.csv")
 
 
@@ -44,12 +44,12 @@ lgbm_test_metrics_clean = clean_metrics(lgbm_test_metrics)
 
 comparison_df = pd.DataFrame(
     [
-        {"model": "catboost", **cat_test_metrics_clean},
+        {"model": "lightgbm_no_x", **cat_test_metrics_clean},
         {"model": "lightgbm", **lgbm_test_metrics_clean},
     ]
 )
 
-comparison_filename = "comparison_catboost_lightgbm.csv"
+comparison_filename = "comparison_lightgbm_no_x_vs_lightgbm.csv"
 comparison_df.to_csv(comparison_filename, index=False)
 
 print(f"Comparison saved to: {comparison_filename}")

models/lightgbm_model.py

@@ -11,7 +11,15 @@ from tqdm import tqdm
 
 
 class LIGHT_GBM:
-    def __init__(self, data_frame, params={}, n_split_kfold=5, test_size=0.15, seed=42):
+    def __init__(
+        self,
+        data_frame,
+        params={},
+        n_split_kfold=5,
+        test_size=0.15,
+        seed=42,
+        output_file_tuning="lightgbm_tuning_results.csv",
+    ):
         self.data_frame = data_frame
         self.params = params
         self.n_split_kfold = n_split_kfold
@@ -37,6 +45,8 @@ class LIGHT_GBM:
         self.kmeans_estimator = self.params.get("kmeans_estimator", 5)
         self.tuning_results = None
 
+        self.output_file_tuning = output_file_tuning
+
     def preprocess(self):
         self.scaling_method = self.params.get("scaling_method", None)
         if self.scaling_method:
@@ -232,6 +242,6 @@ class LIGHT_GBM:
         df_tuning = pandas.concat(
             [df_tuning.drop(columns=["metrics"]), metrics_df], axis=1
         )
-        df_tuning.to_csv("lightgbm_tuning_results.csv", index=False)
+        df_tuning.to_csv(self.output_file_tuning, index=False)
 
         return