imsciences 0.9.6.9__tar.gz → 0.9.7.0__tar.gz

{imsciences-0.9.6.9 → imsciences-0.9.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.9.6.9
+Version: 0.9.7.0
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.9.6.9 → imsciences-0.9.7.0}/imsciences/mmm.py

@@ -583,37 +583,32 @@ class dataprocessing:
 
         return pivoted_df
 
-    def apply_lookup_table_for_columns(self, df, col_names, to_find_dict, if_not_in_dict="Other", new_column_name="Mapping"):
+    def apply_lookup_table_for_columns(df, col_names, to_find_dict, if_not_in_dict="Other", new_column_name="Mapping"):
         """
-        Creates a new DataFrame column based on a look up table, possibly with multiple columns to look up on (dictionary of substrings to class mappings).
+        Creates a new DataFrame column based on a look up table, using exact matches.
 
         Parameters:
         df (pandas.DataFrame): The DataFrame containing the data.
-        col_names (list of str): these are the columns which are used for the lookup. One column or several columns can be inputted as a list, provided there is a merged column to lookup on. If there are multiple columns to look up on then a merged column must be inputted as the key of the dictionary of format e.g. col1|col2|col3
-        to_find_dict (dict): your look up table, where keys are the values being looked up, and the values are the resulting mappings. 
-        if_not_in_dict (str, optional): default value if no substring matches are found in the look up table dictionary. Defaults to "Other".
-        new_column_name (str, optional): name of new column. Defaults to "Mapping".
+        col_names (list of str): List of column names to use for lookup. If more than one, values are merged with '|'.
+        to_find_dict (dict): Lookup dictionary with exact keys to match.
+        if_not_in_dict (str, optional): Value used if no match is found. Defaults to "Other".
+        new_column_name (str, optional): Name of new output column. Defaults to "Mapping".
 
         Returns:
-        pandas.DataFrame: DataFrame with a new column containing the look up table results.
+        pandas.DataFrame: DataFrame with a new column containing lookup results.
         """
 
-        # Create regex pattern with word boundaries from the dictionary
-        regex_pattern = "|".join(r'\b' + re.escape(key) + r'\b' for key in to_find_dict.keys())
-        
         # Preprocess DataFrame if multiple columns
         if len(col_names) > 1:
-            df["Merged"] = df[col_names].astype(str).apply('|'.join, axis=1)
+            df["Merged"] = df[col_names].astype(str).agg('|'.join, axis=1)
             col_to_use = "Merged"
         else:
             col_to_use = col_names[0]
 
-        # Extract the first match using the regex pattern
-        matches = df[col_to_use].str.extract(f'({regex_pattern})', expand=False, flags=re.IGNORECASE)
-        
-        # Map the matches to the corresponding values in the dictionary
-        df[new_column_name] = matches.str.lower().map({k.lower(): v for k, v in to_find_dict.items()}).fillna(if_not_in_dict)
-        
+        # Normalize case for matching
+        lookup = {k.lower(): v for k, v in to_find_dict.items()}
+        df[new_column_name] = df[col_to_use].str.lower().map(lookup).fillna(if_not_in_dict)
+
         # Drop intermediate column if created
         if len(col_names) > 1:
             df.drop(columns=["Merged"], inplace=True)

{imsciences-0.9.6.9 → imsciences-0.9.7.0}/imsciences.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.9.6.9
+Version: 0.9.7.0
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.9.6.9 → imsciences-0.9.7.0}/setup.py

@@ -8,7 +8,7 @@ def read_md(file_name):
             return f.read()
     return ''
 
-VERSION = '0.9.6.9'
+VERSION = '0.9.7.0'
 DESCRIPTION = 'IMS Data Processing Package'
 LONG_DESCRIPTION = read_md('README.md')