imsciences 0.6.1.6__py3-none-any.whl → 0.6.1.8__py3-none-any.whl

imsciences/datafunctions.py

@@ -216,6 +216,11 @@ class dataprocessing:
         print("   - Description: Sums all columns with the option to exclude an date column to create a total column")
         print("   - Usage: add_total_column(df, exclude_col=None, total_col_name='Total')")
         print("   - Example: add_total_column(df, exclude_col='obs', total_col_name='total_media_spd')")   
+        
+        print("\n39. apply_lookup_table_based_on_substring")
+        print("    - Description: Equivalent of xlookup in excel, but only based on substrings. If a substring is found in a cell, than look it up in the dictionary. Otherwise use the other label")
+        print("    - Usage: apply_lookup_table_based_on_substring(df, column_name, category_dict, new_col_name='Category', other_label='Other')")
+        print("    - Example: apply_lookup_table_based_on_substring(df, 'Campaign Name', campaign_dict, new_col_name='Campaign Name Short', other_label='Full Funnel')")
                 
     def get_wd_levels(self, levels):
         """
@@ -1371,39 +1376,39 @@ class dataprocessing:
 
         return df
 
-        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.
+    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.
+        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.
-            """
-            
-            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
+        Returns:
+        pd.DataFrame: The DataFrame with the specified replacements made, and optionally with lowercase strings.
+        """
+        
+        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'):
         """
@@ -1426,7 +1431,43 @@ class dataprocessing:
         
         return df
 
+    def apply_lookup_table_based_on_substring(df, column_name, category_dict, new_col_name='Category', other_label='Other'):
+        """
+        Categorizes text in a specified DataFrame column by applying a lookup table based on substrings.
+
+        Parameters:
+        - df (pd.DataFrame): The DataFrame containing the column to categorize.
+        - column_name (str): The name of the column in the DataFrame that contains the text data to categorize.
+        - category_dict (dict): A dictionary where keys are substrings to search for in the text and values are 
+            the categories to assign when a substring is found.
+        - new_col_name (str): The name of the new column to be created in the DataFrame, which will hold the 
+            resulting categories. Default is 'Category'.
+
+        Returns:
+        - pd.DataFrame: The original DataFrame with an additional column containing the assigned categories.
+        """
+
+        def categorize_text(text, category_dict):
+            """
+            Assigns a category to a single text string based on the presence of substrings from a dictionary.
+
+            Parameters:
+            - text (str): The text string to categorize.
+            - category_dict (dict): A dictionary where keys are substrings to search for in the text and 
+            values are the categories to assign if a substring is found.
 
+            Returns:
+            - str: The category assigned based on the first matching substring found in the text. If no 
+            matching substring is found, returns 'Full Funnel'.
+            """
+            for key, category in category_dict.items():
+                if key.lower() in text.lower():  # Check if the substring is in the text (case-insensitive)
+                    return category
+            return other_label  # Default category if no match is found
+    
+        # Apply the categorize_text function to each element in the specified column
+        df[new_col_name] = df[column_name].apply(categorize_text, category_dict=category_dict)
+        return df
 
 
 ########################################################################################################################################

{imsciences-0.6.1.6.dist-info → imsciences-0.6.1.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.6.1.6
+Version: 0.6.1.8
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.6.1.6.dist-info → imsciences-0.6.1.8.dist-info}/RECORD

@@ -2,13 +2,13 @@ dataprocessing/__init__.py,sha256=quSwsLs6IuLoA5Rzi0ZD40xZaQudwDteF7_ai9JfTPk,32
 dataprocessing/data-processing-functions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
 dataprocessing/datafunctions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
 imsciences/__init__.py,sha256=GIPbLmWc06sVcOySWwNvMNUr6XGOHqPLryFIWgtpHh8,78
-imsciences/datafunctions.py,sha256=1DOieL8Xfh6I-5JZlM_XKPwIon-I_VcDjppuvXmhYhk,137236
+imsciences/datafunctions.py,sha256=kyspeS4ifoNb_Z_f4OfmWlEMHO6sUO8JjconGzq8Mz8,139793
 imsciences/datapull.py,sha256=TPY0LDgOkcKTBk8OekbD0Grg5x0SomAK2dZ7MuT6X1E,19000
 imsciencesdataprocessing/__init__.py,sha256=quSwsLs6IuLoA5Rzi0ZD40xZaQudwDteF7_ai9JfTPk,32
 imsciencesdataprocessing/datafunctions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
 imsdataprocessing/__init__.py,sha256=quSwsLs6IuLoA5Rzi0ZD40xZaQudwDteF7_ai9JfTPk,32
 imsdataprocessing/datafunctions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
-imsciences-0.6.1.6.dist-info/METADATA,sha256=SbdVxObVs6UW90bJ0eQIAbX1rd0urpG6sNmcxiB5uLw,854
-imsciences-0.6.1.6.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-imsciences-0.6.1.6.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
-imsciences-0.6.1.6.dist-info/RECORD,,
+imsciences-0.6.1.8.dist-info/METADATA,sha256=2NgdiqLw89mBc9VsqR9ZJ_GZmX7-CslnYmzS6mIvybw,854
+imsciences-0.6.1.8.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+imsciences-0.6.1.8.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
+imsciences-0.6.1.8.dist-info/RECORD,,