get_tf_dictionary_for_secret_speech.py

#get the speech which we will try to identify
secret_speech = open('obama_speech_testing.txt', 'r').read()
secret_speech = secret_speech.replace('\n','').replace('  ',' ').lower()
list_of_phrases_secret = secret_speech.split(' ')

#get zipped group of every 3 consecutive words
secret_tups = [str(item) for item in zip(list_of_phrases_secret[:-2], list_of_phrases_secret[1:-1], list_of_phrases_secret[2:])]

#get TF dictionary for the secret speech
d_secret = get_phrase_freq_dict(secret_tups)