Refactor replace into its own function

Author: php1ic

src/nuclearmasses/io/ame_mass_parse.py

@@ -97,8 +97,7 @@ def read_file(self) -> pd.DataFrame:
         )
         # We use the NUBASE data to define whether or not an isotope is experimentally measured,
         # so for this data we'll just drop any and all '#' characters
-        str_cols = df.select_dtypes(include=["object", "string"]).columns
-        df[str_cols] = df[str_cols].astype(str).apply(lambda s: s.str.replace("#", "", regex=False))
+        df = self.strip_char_from_string_columns(df, "#")
 
         if self.year == 1983:
             # The column headers and units are repeated in the 1983 table

src/nuclearmasses/io/ame_reaction_1_parse.py

@@ -95,8 +95,7 @@ def read_file(self) -> pd.DataFrame:
         )
         # We use the NUBASE data to define whether or not an isotope is experimentally measured,
         # so for this data we'll just drop any and all '#' characters
-        str_cols = df.select_dtypes(include=["object", "string"]).columns
-        df[str_cols] = df[str_cols].astype(str).apply(lambda s: s.str.replace("#", "", regex=False))
+        df = self.strip_char_from_string_columns(df, "#")
 
         if self.year == 1983:
             # The column headers and units are repeated in the 1983 table

src/nuclearmasses/io/ame_reaction_2_parse.py

@@ -95,8 +95,7 @@ def read_file(self) -> pd.DataFrame:
         )
         # We use the NUBASE data to define whether or not an isotope is experimentally measured,
         # so for this data we'll just drop any and all '#' characters
-        str_cols = df.select_dtypes(include=["object", "string"]).columns
-        df[str_cols] = df[str_cols].astype(str).apply(lambda s: s.str.replace("#", "", regex=False))
+        df = self.strip_char_from_string_columns(df, "#")
 
         if self.year == 1983:
             # The column headers and units are repeated in the 1983 table

src/nuclearmasses/io/nubase_parse.py

@@ -185,8 +185,7 @@ def read_file(self) -> pd.DataFrame:
         # We use the NUBASE data to define whether or not an isotope is experimentally measured,
         df["Experimental"] = ~df["NUBASEMassExcess"].astype("string").str.contains("#", na=False)
         # Once we have used the '#' to determine if it's experimental or not, we can remove all instances of it
-        str_cols = df.select_dtypes(include=["object", "string"]).columns
-        df[str_cols] = df[str_cols].astype(str).apply(lambda s: s.str.replace("#", "", regex=False))
+        df = self.strip_char_from_string_columns(df, "#")
 
         df = self.parse_half_life(df)
         df = self.calculate_relative_error(df)

src/nuclearmasses/utils/converter.py

@@ -134,3 +134,9 @@ def read_fwf(base: DataInput, **kwargs):
 
         # Filesystem path
         return pd.read_fwf(base, **kwargs)
+
+    @staticmethod
+    def strip_char_from_string_columns(df: pd.DataFrame, char: str) -> pd.DataFrame:
+        cols = df.select_dtypes(include=["object", "string"]).columns
+        df[cols] = df[cols].apply(lambda s: s.str.replace(char, "", regex=False))
+        return df