countwords.py

def check_word_in_tweet(word, data):
    """Checks if a word is in a Twitter dataset's text. 
    Checks text and extended tweet (140+ character tweets) for tweets,
    retweets and quoted tweets.
    Returns a logical pandas Series.
    """
    contains_column = data['text'].str.contains(word, case = False)
    contains_column |= data['extended_tweet-full_text'].str.contains(word, case = False)
    contains_column |= data['quoted_status-text'].str.contains(word, case = False) 
    contains_column |= data['retweeted_status-text'].str.contains(word, case = False) 
    return contains_column
  
# Find mentions of #python in all text fields
python = check_word_in_tweet('python', df_tweet)
# Find mentions of #javascript in all text fields
js = check_word_in_tweet('javascript', df_tweet)

# Print proportion of tweets mentioning #python
print("Proportion of #python tweets:", np.sum(python) / df_tweet.shape[0])

# Print proportion of tweets mentioning #rstats
print("Proportion of #javascript tweets:", np.sum(js) / df_tweet.shape[0])