imsciences 0.6.1.5__tar.gz → 0.6.1.6__tar.gz

{imsciences-0.6.1.5 → imsciences-0.6.1.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.6.1.5
+Version: 0.6.1.6
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.6.1.5 → imsciences-0.6.1.6}/imsciences/datafunctions.py

@@ -209,8 +209,8 @@ class dataprocessing:
 
         print("\n37. Replace substrings in column of strings")
         print("   - Description: Replace substrings in column of strings based off dictionary, can also change column to lower")
-        print("   - Usage: replace_substrings(df, column, replacements, to_lower=False)")
-        print("   - Example: replace_substrings(df, 'Influencer Handle', replacement_dict, to_lower=True)") 
+        print("   - Usage: replace_substrings(df, column, replacements, to_lower=False, new_column=None)")
+        print("   - Example: replace_substrings(df, 'Influencer Handle', replacement_dict, to_lower=True, new_column='Short Version')") 
 
         print("\n38. Add totals column")
         print("   - Description: Sums all columns with the option to exclude an date column to create a total column")
@@ -1371,29 +1371,39 @@ class dataprocessing:
 
         return df
 
-    def replace_substrings(self, df, column, replacements, to_lower=False):
-        """
-        Replaces substrings in a column of a DataFrame based on a dictionary of replacements. 
-        Optionally converts the column values to lowercase.
-
-        Args:
-        df (pd.DataFrame): The DataFrame containing the column to modify.
-        column (str): The column name where the replacements will be made.
-        replacements (dict): A dictionary where keys are substrings to replace and values are the replacement strings.
-        to_lower (bool, optional): If True, the column values will be converted to lowercase before applying replacements. Default is False.
-
-        Returns:
-        pd.DataFrame: The DataFrame with the specified replacements made, and optionally with lowercase strings.
-        """
-        
-        # Apply substring replacements
-        for old, new in replacements.items():
-            df[column] = df[column].str.replace(old, new, regex=False)
+        def replace_substrings(self, df, column, replacements, to_lower=False, new_column=None):
+            """
+            Replaces substrings in a column of a DataFrame based on a dictionary of replacements. 
+            Optionally converts the column values to lowercase and allows creating a new column or modifying the existing one.
+
+            Args:
+            df (pd.DataFrame): The DataFrame containing the column to modify.
+            column (str): The column name where the replacements will be made.
+            replacements (dict): A dictionary where keys are substrings to replace and values are the replacement strings.
+            to_lower (bool, optional): If True, the column values will be converted to lowercase before applying replacements. Default is False.
+            new_column (str, optional): If provided, the replacements will be applied to this new column. If None, the existing column will be modified. Default is None.
+
+            Returns:
+            pd.DataFrame: The DataFrame with the specified replacements made, and optionally with lowercase strings.
+            """
             
-        # Optionally convert to lowercase
-        if to_lower:
-            df[column] = df[column].str.lower()
-        return df
+            if new_column is not None:
+                # Create a new column for replacements
+                df[new_column] = df[column]
+                temp_column = new_column
+            else:
+                # Modify the existing column
+                temp_column = column
+            
+            # Apply substring replacements
+            for old, new in replacements.items():
+                df[temp_column] = df[temp_column].str.replace(old, new, regex=False)
+            
+            # Optionally convert to lowercase
+            if to_lower:
+                df[temp_column] = df[temp_column].str.lower()
+            
+            return df
 
     def add_total_column(self, df, exclude_col=None, total_col_name='Total'):
         """

{imsciences-0.6.1.5 → imsciences-0.6.1.6}/imsciences.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.6.1.5
+Version: 0.6.1.6
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.6.1.5 → imsciences-0.6.1.6}/setup.py

@@ -8,7 +8,7 @@ def read_md(file_name):
             return f.read()
     return ''
 
-VERSION = '0.6.1.5'
+VERSION = '0.6.1.6'
 DESCRIPTION = 'IMS Data Processing Package'
 LONG_DESCRIPTION = read_md('README.md')  # Reading from README.md