private async void button4_Click(object sender, EventArgs e)
{
var articleWordOccurenceData = await MongoDBHandler.GetArticleWordOccurenceData();
var words = await MongoDBHandler.GetWordCollection();
// exclude numbers 0-9 and article banner placeholder and some other irrelevant characters
var toExclude = new[]
{
"0", "1", "2", "3", "4", "5", "6", "7", "8", "9", "\n[ArticleBannerPlaceholder]\n", "10", "20", "\t", "\n—", "„"
};
words = words.Where(a => !toExclude.Contains(a.WordName)).ToList();
// get first 100 words by occurence (DESC) and extract articleWordOccurence data according to it
var wordsArray = words.OrderByDescending(a => a.Occurence).Take(100).Select(a => a.WordName).ToList();
var aWODExtracted = articleWordOccurenceData.Where(a => wordsArray.Contains(a.Word)).ToList();
await MongoDBHandler.InsertArticleWordOccurences100Words(aWODExtracted);
}