drop columns

src/Dataset.py

@@ -29,7 +29,7 @@ class Dataset:
             raw_dataframe
         )  # for conveneince
         dataframe = self.remove_nonaccepting_rows(dataframe)
-        dataframe = self.treat_outliers(dataframe, 'Hours')
+        dataframe = self.treat_outliers(dataframe, "Hours")
 
         dataframe["Anxiety_score"] = self.get_combined_anxiety_score(dataframe)
         dataframe["Is_narcissist"] = self.get_is_narcissist_col(dataframe)
@@ -64,13 +64,21 @@ class Dataset:
         Returns:
             pd.DataFrame: the dataframe.
         """
-        rows_to_drop = [
-            "League",
-            "S. No.",
-            "Timestamp",
-            "highestleague",
-            "earnings",
-        ]
+        rows_to_drop = (
+            [
+                "League",
+                "S. No.",
+                "Timestamp",
+                "highestleague",
+                "earnings",
+                "Birthplace",
+                "Birthplace_ISO3",
+            ]
+            + [f"GAD{i}" for i in range(1, 8)]
+            + ["GADE"]
+            + [f"SWL{i}" for i in range(1, 6)]
+            + [f"SPIN{i}" for i in range(1, 18)]
+        )
         return dataframe.drop(rows_to_drop, axis="columns")
 
     def remove_nonaccepting_rows(
@@ -113,7 +121,7 @@ class Dataset:
         ] = "other"
         is_competitive_col = self.get_is_competitive_col(dataframe)
         return is_competitive_col
-    
+
     def treat_outliers(self, df, colname):
         q = df[colname].quantile(0.99)
         return df[df[colname] < q]