tweet

print tweet

tweet = "We have some delightful new food in the cafeteria. Awesome!!!"
tweet

tweet = Does anyone call New Haven "NeHa"?

tweet = '''Does anyone call New Haven "NeHa"?'''

print tweet

tweet = 'Does anyone call New Haven "NeHa"?'

print tweet

['everything','in','brackets','separated','by','commas.']

positive_words = ['awesome', 'good', 'nice', 'super', 'fun']

print positive_words

print positive_words

new_word_to_add = 'like'
positive_words.append(new_word_to_add)

print positive_words

negative_words = ['awful','lame','horrible','bad']
print negative_words

tweet = 'We have some delightful new food in the cafeteria. Awesome!!!'
words = tweet.split()
print words

print tweet 
len(tweet)

#sets
set([3,4,5,5])

#Dictionary

article_1 = {'title': 'Cat in the Hat', 'author': 'Dr. Seuss', 'Year': 1957}

#And a list of dictionaries is awfully close to a JSON.
article_2 = {'title': 'Go Do Go!', 'author': 'PD Eastman', 'Year': 1961}

articles = [article_1, article_2]

articles

for word in words:
print word

tweet_2 = "Food is lame today. I don't like it at all."
words_2 = tweet_2.split()

for word in words_2:
    if word in positive_words:
        print '+'
        

tweet_2 = "Food is lame today. I don't like it at all."
tweet_2 = tweet_2.replace("n't"," not")
tweet_2 = tweet_2.replace("not "," not_")

print tweet_2

words_2 = tweet_2.split()

for word in words_2:
    if word in positive_words:
        print '+'
    if word in negative_words:
        print '-'

print 3 + ' is a number.'

print ['puppies','dogs'] + 'are pets.'

for some_number in [1,2,4,9]:
    sentence = str(some_number) + ' is a number.'
    print sentence

print tweet.lower()

print words.lower()

print 'awesome!!!'.strip('!')

from string import punctuation

punctuation

'awesome!!!!'.strip(punctuation)

'awesome!!!! party'.strip(punctuation)

print 'awesome!!! party'
print 'awesome!!! party'.replace('!','')

word = 'awesome!!!'
word_processed = word.strip('!').lower()
print word_processed

postive_counter = 0

for word in words:
    word_processed = word.lower()
    word_processed = word_processed.strip(punctuation)
    if word_processed in positive_words:
        postive_counter = postive_counter + 1
print postive_counter

negative_file[:50]

negative_list = negative_file.splitlines()

negative_list[:5]

print negative_list[0:1]

print negative_list[-5:]

obama_tweets = open('obama_tweets.txt', 'r').read()
obama_tweets = obama_tweets.splitlines()

def open_list(filename):
    list_file = open(filename, 'r').read()
    list_file = list_file.splitlines()
    return list_file

obama_tweets = open_list('obama_tweets.txt')

#loop, but don't go through everything yet
for tweet in obama_tweets[:5]:
    print tweet
    positive_counter = 0
    #Lower case everything
    tweet_processed = tweet.lower()
    
    #split by ' ' into a list of words
    words = tweet_processed.split()
    
    #Loop through each word in the tweet
    for word in words:
        
        clean_word = word.strip(punctuation)
        
        if clean_word in postive_list:
            print clean_word
            positive_counter = positive_counter+1
    
    print positive_counter,len(words)

#loop, but don't go through everything yet
for tweet in obama_tweets[:5]:


    positive_counter = 0
    negative_counter = 0
    
    #Lower case everything
    tweet_processed = tweet.lower()
    
    #split by ' ' into a list of words
    words = tweet_processed.split()
    
    #Loop through each word in the tweet
    for word in words:
        clean_word = word.strip(punctuation)
        
        if clean_word in postive_list:
            positive_counter = positive_counter + 1
        if clean_word in negative_list:
            negative_counter = negative_counter + 1
    
    print positive_counter, negative_counter, len(words)

csv_file = open('tweet_sentiment.csv','w')
csv_writer = csv.writer( csv_file )

def clean_split(tweet):
    ''' Take sentence and return cleaned list of words '''
    return [word.strip(punctuation) for word in tweet.lower().split()]

#turn the lists into sets so we can do intersections
postive_set  = set(postive_list)
negative_set = set(negative_list)


sentiment = []
for tweet in obama_tweets:
    words = clean_split(tweet)
    postive_counter =  len( postive_set.intersection(words) )
    negative_counter = len( negative_set.intersection(words) )
    sentiment.append ( [ postive_counter , negative_counter, len(words)] )

with  open('tweet_sentiment_2.csv','w') as csv_file:
    csv_writer = csv.writer( csv_file )
    csv_writer.writerows(sentiment)