Last active
March 19, 2016 19:32
-
-
Save leighst/2acff73c0b4e70457333 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 | |
import nltk | |
def count_words(text, words): | |
count = -1 | |
try: | |
tokens = nltk.word_tokenize(text) | |
count = 0 | |
for t in tokens: | |
norm_t = t.lower() | |
if (norm_t in words): | |
count = count + 1 | |
except: | |
print("error") | |
return count | |
def count_swears(text): | |
return count_words(text, sw) | |
tw = pd.read_csv('/Users/lestew/Downloads/7983102_29842bf08e6351e434c2774a693cb64f8167d531/tweets.csv') | |
tw['datetime'] = pd.to_datetime(tw.timestamp) | |
tw = tw.set_index('datetime') | |
tw['day'] = tw.index.dayofweek | |
tw['swears'] = tw.text.apply(count_swears) | |
sw_days = tw[tw.swears > 0] | |
d = sw_days[sw_days.retweeted_status_id.isnull()].day | |
p = d.value_counts().sort_index().plot.bar() | |
p.set_xticklabels(["mon", "tue", "wed", "thu", "fri", "sat", "sun"]) | |
pylab.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment