umarhussain88 · November 3, 2020 14:26
diff --git a/generate_keys.py b/generate_keys.py
 def generate_new_keys(*args,key='Carid',name='Carname'):
    """
    Takes in a number of dataframes and returns any duplicates with a new unique id. 
    groupby columns fixed to CarID and CarName.
    """
    # adds dictionaries into a single list.
    dicts_ = [arg.groupby(key)[name].first().to_dict() for arg in args]
    
    #merges dicts on unique key, this will exclude duplicates.
    merged_dicts = dict(ChainMap(*dicts_))
    #get the duplicate and pass the name into a list.
    delta = [v for each_dict in dicts_ for k,v in each_dict.items() if v not in merged_dict.values()]
    # get the max sequence key
    start_key =  max(merged_dict.keys()) + 1
    # create a new sequence
    sequence = range(start_key, start_key + len(delta) + 1)
    # return a dictionary.
    return {name : number for name,number in zip(delta,sequence)}
	def generate_new_keys(*args,key='Carid',name='Carname'):
	"""
	Takes in a number of dataframes and returns any duplicates with a new unique id.
	groupby columns fixed to CarID and CarName.
	"""
	# adds dictionaries into a single list.
	dicts_ = [arg.groupby(key)[name].first().to_dict() for arg in args]

	#merges dicts on unique key, this will exclude duplicates.
	merged_dicts = dict(ChainMap(*dicts_))
	#get the duplicate and pass the name into a list.
	delta = [v for each_dict in dicts_ for k,v in each_dict.items() if v not in merged_dict.values()]
	# get the max sequence key
	start_key = max(merged_dict.keys()) + 1
	# create a new sequence
	sequence = range(start_key, start_key + len(delta) + 1)
	# return a dictionary.
	return {name : number for name,number in zip(delta,sequence)}