imsciences 0.6.1.8__tar.gz → 0.6.2.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: imsciences
3
- Version: 0.6.1.8
3
+ Version: 0.6.2.0
4
4
  Summary: IMS Data Processing Package
5
5
  Author: IMS
6
6
  Author-email: cam@im-sciences.com
@@ -1431,11 +1431,11 @@ class dataprocessing:
1431
1431
 
1432
1432
  return df
1433
1433
 
1434
- def apply_lookup_table_based_on_substring(df, column_name, category_dict, new_col_name='Category', other_label='Other'):
1434
+ def apply_lookup_table_based_on_substring(self, df, column_name, category_dict, new_col_name='Category', other_label='Other'):
1435
1435
  """
1436
1436
  Categorizes text in a specified DataFrame column by applying a lookup table based on substrings.
1437
1437
 
1438
- Parameters:
1438
+ Args:
1439
1439
  - df (pd.DataFrame): The DataFrame containing the column to categorize.
1440
1440
  - column_name (str): The name of the column in the DataFrame that contains the text data to categorize.
1441
1441
  - category_dict (dict): A dictionary where keys are substrings to search for in the text and values are
@@ -1447,11 +1447,11 @@ class dataprocessing:
1447
1447
  - pd.DataFrame: The original DataFrame with an additional column containing the assigned categories.
1448
1448
  """
1449
1449
 
1450
- def categorize_text(text, category_dict):
1450
+ def categorize_text(text):
1451
1451
  """
1452
1452
  Assigns a category to a single text string based on the presence of substrings from a dictionary.
1453
1453
 
1454
- Parameters:
1454
+ Args:
1455
1455
  - text (str): The text string to categorize.
1456
1456
  - category_dict (dict): A dictionary where keys are substrings to search for in the text and
1457
1457
  values are the categories to assign if a substring is found.
@@ -1464,9 +1464,9 @@ class dataprocessing:
1464
1464
  if key.lower() in text.lower(): # Check if the substring is in the text (case-insensitive)
1465
1465
  return category
1466
1466
  return other_label # Default category if no match is found
1467
-
1467
+
1468
1468
  # Apply the categorize_text function to each element in the specified column
1469
- df[new_col_name] = df[column_name].apply(categorize_text, category_dict=category_dict)
1469
+ df[new_col_name] = df[column_name].apply(categorize_text)
1470
1470
  return df
1471
1471
 
1472
1472
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: imsciences
3
- Version: 0.6.1.8
3
+ Version: 0.6.2.0
4
4
  Summary: IMS Data Processing Package
5
5
  Author: IMS
6
6
  Author-email: cam@im-sciences.com
@@ -8,7 +8,7 @@ def read_md(file_name):
8
8
  return f.read()
9
9
  return ''
10
10
 
11
- VERSION = '0.6.1.8'
11
+ VERSION = '0.6.2.0'
12
12
  DESCRIPTION = 'IMS Data Processing Package'
13
13
  LONG_DESCRIPTION = read_md('README.md') # Reading from README.md
14
14
 
File without changes
File without changes