analyzeTweets.py 文件源码

def translateHinglishTweets(tweets_text):
    counter = 0
    tweets_text_translated = []
    n = len(tweets_text)

    open_file = open("dictionary.pickle", "rb")
    dictionary = pickle.load(open_file)
    open_file.close()

    english_stopwords_set = set(stopwords.words('english'))

    for i in range(n):
        text = tweets_text[i]
        translated_text = ""
        tokens = wordpunct_tokenize(text)
        words = [word.lower() for word in tokens]
        for word in words:
            if word in english_stopwords_set:
                translated_text = translated_text + " " + word
            elif (word in dictionary):
                #print word + "-" + dictionary[word]
                translated_text = translated_text + " " + dictionary[word]
                counter = counter + 1
            else:
                translated_text = translated_text + " " + word
        tweets_text_translated.append(translated_text)

    #print counter
    return tweets_text_translated