This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def individual_tweet_vectorizer(corpus, tweet, index=0, author=''): | |
""" | |
Formats a single tweet as a vector | |
:param corpus: list of all words in tweets | |
:param tweet: tweet to be vectorized | |
:param index: index of tweet in main list of tweets | |
:param author: Trump or general | |
:return: Single tweet in vector form | |
""" | |
individual_tweet_vector = np.zeros((1, len(corpus) + 2), dtype=int) | |
for word in range(len(corpus)): | |
if corpus[word] in tweet: | |
individual_tweet_vector[0][word] = 1 | |
if author != '': # If author is specified, set the last value of the tweet vector to 1 | |
individual_tweet_vector[0][-1] = 1 | |
individual_tweet_vector[0][-2] = index # Keep track of index of tweet for interpretation | |
return individual_tweet_vector |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment