Helper function to generate dictionary map to rename columns in one pandas dataframe to match those in another dataframe

fuzzy_column_name_match.py

def fuzzy_column_name_match(list1, list2):
    from fuzzywuzzy import process
    threshold = 60
    response = {}
    for name_to_find in list1:
        resp_match =  process.extractOne(name_to_find ,list2)
        if resp_match[1] > threshold:
            response[name_to_find] = resp_match[0]
    return response
  
  
# Example Useage

fuzzy_map(source.columns, target.columns)

# {'LINK_NO': 'Link_No',
# 'Route_No': 'ROAD_NO',
# 'State Link name': 'ST',
# 'Road Name ': 'ROAD_NAME',
# 'Road No': 'ROAD_NO',
# 'LINK_SUB_CATEGORY': 'Link Category',
# 'SLK Start': 'ST',
# 'SLK End': 'end_SLK',
# 'Region': 'section',
# 'Func_ Class': 'MR_Class',
# 'Func_ Class.1': 'MR_Class',
# 'AADT Max': 'AADT',
# 'AADT  Min': 'AADT',
# 'Select AADT to Use': 'AADT',
# 'Site No of selected AADT': 'AADT',
# 'SLK of Selected AADT': 'AADT',
# 'Date of Selected AADT': 'AADT',
# 'Unnamed: 24': 'Unnamed: 11'}

# as you can see in the example output, it kinda sucks, but it is still easier to keep valid rows than to type from scratch