def obtainNgrams(tweetListPreProcessed, maxNgram):
# Join all the tweets in one language. Return one dictionary of languages
corpus, arrayLanguagesFull = concatenateLanguageTweets(tweetListPreProcessed)
# individualLanguage=true:
# Only individual languages(en,es,..)
# individualLanguage=false:
# Mixed languages(en+es,pt+gl,..)
individualLanguage = True
if individualLanguage:
corpus, arrayLanguages = separateIndividualLanguages(corpus)
# clean dictionary of double spaces from concatenation
for key in corpus.keys():
corpus[key] = preprocess.remove_multiple_spaces(corpus.get(key))
corpusNgrams = freqDistributions(corpus, maxNgram + 1)
return corpusNgrams, arrayLanguages, arrayLanguagesFull
