Created
August 9, 2016 05:32
-
-
Save tonybaloney/4c3c0fbaf8a9d9941c7345908ac85810 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
from nltk.sentiment.vader import SentimentIntensityAnalyzer | |
from matplotlib import pyplot as plt | |
import matplotlib.dates as mdates | |
import numpy | |
import pylab | |
with open('tweets.csv') as tweets: | |
df = pd.read_csv(tweets) | |
data = [] | |
sid = SentimentIntensityAnalyzer() | |
df['timestamp'] = pd.to_datetime(df['timestamp']) | |
chart = [] | |
for (sentence, id) in zip(df.text.values, df.timestamp.values): | |
ss = sid.polarity_scores(sentence) | |
chart.append({'sentiment': ss['compound'], 'date': id}) | |
df = pd.DataFrame.from_records(chart) | |
x = mdates.date2num(df.date) | |
z = numpy.polyfit(x, df.sentiment, 1) | |
p = numpy.poly1d(z) | |
pylab.plot(x, p(x), "r--") | |
plt.plot(df.date, df.sentiment) | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment