def performComputation(data):
try:
# SELECT IMPORTANT COMPONENTS
data = data[['tweetText', 'sentiment', 'weight', 'timeCreated']]
sentiment_valcounts = data['sentiment'].value_counts(sort=False)
# PLOT SENTIMENT BAR CHART (BOKEH)
# create a new plot with a title and axis labels
p = Bar(sentiment_valcounts, title='Tweets per Sentiment', height=450,
xlabel='Sentiment', ylabel='Count')
print sentiment_valcounts
# output_file("histogram.html")
# show(p)
script_bar, div_bar = components(p)
# END OF BAR CHART
# PIE/DONUT CHART (google api)
s = sentiment_valcounts.to_frame() # Convert series to dataframe
sentiment_labels = list(s.index) # Get the index [positive or negative]
sentiment_values = [sentiment_valcounts[0], sentiment_valcounts[1]]
piedata = [(sentiment_labels[0], np.asscalar(sentiment_valcounts[0])),
# Converting from numpy Int64 to normal int
(sentiment_labels[1],
np.asscalar(sentiment_valcounts[1]))] # Converting from numpy Int64 to normal int
no_positive_tweets = np.asscalar(sentiment_valcounts[0])
no_negative_tweets = np.asscalar(sentiment_valcounts[1])
# END PIE
# WORDCLOUD
# Get Stop Words
stop = act.getStopWordList()
text = data['tweetText']
tokens = []
for txt in text.values:
tokens.extend([t.lower().strip(":,.") for t in txt.split()])
filtered_tokens = [w for w in tokens if not w in stop]
# freq_dist = FreqDist(filtered_tokens)
p = pd.Series(filtered_tokens)
# get the counts per word
freq = p.value_counts()
# How many max words do we want to give back
freq = freq.ix[0:30]
# print freq.keys()[:20]
freq_json = freq.to_json()
# response.headers.add('Access-Control-Allow-Origin', "*")
# END OF WORDCLOUD
return script_bar, div_bar, data, piedata, freq_json, no_positive_tweets, no_negative_tweets
except Exception as e:
print e
return render_template('error.html', error=e)
