processTweets.py

words = []

for tweet in tweets:
    words.extend(prepareSentence(tweet["text"]))

distinct_words = set(words)

lower_threshold = 10
upper_threshold = 350
counts = []
final_words = []
for word in distinct_words:
    counts.append(words.count(word))
    if words.count(word) > lower_threshold and words.count(word) < upper_threshold: 
        final_words.append(word)

print(len(words))
print(len(distinct_words))
print(len(final_words))