The feature-extraction and sequence-construction code

1- user_id (account id for bot ) 2- created_at (post timestamps) 3- action (Retweeting , Tweeting or Repleying) 4- is_url (Yes or No) 5- is_media (Photo , Video, No_Media) 6- is_emoji (Yes or No) 7- is_hash (Yes or No) 8- Text (Duplicated , Not-Duplicated or Empty) 9- Sentiment (Positive , Negative or Neutral ) 10- G (First Generation, Second First Generation or Third First Generation) 11- letter_sequence ( group of 7 letters reprents the the encoded values of these features for one post of the bot ) The values of each features encoded into letter based on the following: action = ("Tweeting" = "T", "Replying" = "Y", "Retweeting" = "R"), is_url = ("YES" = "U", "NO" = "X"), Sentiment = ("Positive" = "P", "Negative" = "N", "Neutral" = "L"), is_media = ("Photo" = "I", "Video" = "V", "No_Media" = "M"), Text = ("Duplicated" = "D", "Not-Duplicated" = "Q", "Empty" = "E"), is_hash = ("YES" = "H", "NO" = "Z"), is_emoji = ("YES" = "J", "NO" = "K")