Simple samples of functions to depersonalize data

depersonalize.cs

async void Main()
{
	// baby first names https://github.com/hadley/data-baby-names
	var fnames = ReadFileAsync(@"C:\temp\depersonal\bfnames.csv");
	// surnames https://github.com/fivethirtyeight/data/blob/master/most-common-name/surnames.csv
	var lnames = ReadFileAsync(@"C:\temp\depersonal\surnamesClean.csv");
	var testNames = ReadFileAsync(@"c:\temp\depersonal\nbaPlayers.csv");
	var r = new Random();
	int Max = 3;
	var result = new int[Max];
	for(int i = 0; i< Max;i++){
		result[i] = r.Next();
	}
	result.Dump();
	(await testNames).TakeLast(10)
		.Select(async re =>
		{
			var (first, last) = GenerateName(re, await fnames, await lnames);
			return new { Original = re, DeFirst = first, DeLast = last };
		})
		.Dump();
	
}

// You can define other methods, fields, classes and namespaces here

public static (string,string) GenerateName(string original, List<string> fnames, List<string> lnames, bool deterministic = false)
{
	List<string> names = new List<string>();
	//should be from hash
	Random random = deterministic ? new Random(BitConverter.ToInt32(CalculateMD5Hash(original))) : Random.Shared ;
	string firstName = fnames[random.Next(0,fnames.Count)];
	string lastName = lnames[random.Next(0,lnames.Count)];
	
	return (firstName,lastName);
}

async Task<List<string>> ReadFileAsync(string fname)
{
	var records = new List<string>();
	using (var reader = new StreamReader(fname))
	{
		while (!reader.EndOfStream)
		{
			records.Add(await reader.ReadLineAsync());
		}
		return records;
	}
}

public static byte[] CalculateMD5Hash(string input)
{
	using (var md5 = MD5.Create())
	{
		var bytes = Encoding.UTF8.GetBytes(input);
		return md5.ComputeHash(bytes);
	}
}

List<T> ReadCSV<T>(string fname)
{
	using (var reader = new StreamReader(fname))
	using (var csv = new CsvReader(reader, CultureInfo.InvariantCulture))
	{
		var records = csv.GetRecords<T>();
		return new List<T>(records);
	}
}