drop earnings col

src/Dataset.py

@@ -25,7 +25,13 @@ class Dataset:
             pd.DataFrame: resulting preprocessed dataframe.
         """
         dataframe = raw_dataframe  # for conveneince
-        rows_to_drop = ["League", "S. No.", "Timestamp", "highestleague"]
+        rows_to_drop = [
+            "League",
+            "S. No.",
+            "Timestamp",
+            "highestleague",
+            "earnings",
+        ]
         # rows_to_drop = []
         dataframe = raw_dataframe.drop(rows_to_drop, axis="columns")
         dataframe = self.remove_nonaccepting_rows(dataframe)
@@ -34,9 +40,26 @@ class Dataset:
         dataframe["Is_narcissist"] = self.get_is_narcissist_col(dataframe)
 
         self.preprocess_whyplay(dataframe)
+        dataframe["Is_competitive"] = self.get_is_competitive_col(dataframe)
         # more preprocessing goes here
         return dataframe
 
+    def get_is_competitive_col(self, dataframe: pd.DataFrame):
+        # print(len(dataframe))
+        is_competitive_col = np.zeros(shape=len(dataframe))
+        is_competitive_col[
+            (dataframe["whyplay"] == "improving")
+            | (dataframe["whyplay"] == "winning")
+            | (dataframe["whyplay"] == "all of the above")
+        ] = True
+        is_competitive_col[
+            (dataframe["whyplay"] == "having fun")
+            | (dataframe["whyplay"] == "relaxing")
+        ] = False
+        is_competitive_col[(dataframe["whyplay"] == "other")] = None
+
+        return is_competitive_col
+
     def remove_nonaccepting_rows(self, dataframe: pd.DataFrame):
         # drop rows where users did not accept to having their data used
         dataframe = dataframe.drop(