Created
July 25, 2018 23:20
-
-
Save akrisanov/199e16900c876b65582d42e05e4ca9c8 to your computer and use it in GitHub Desktop.
DataCamp: Importing Data in Python (Part 2) https://www.datacamp.com/courses/importing-data-in-python-part-2
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 re | |
import matplotlib.pyplot as plt | |
import seaborn as sns | |
def word_in_text(word, text): | |
word = word.lower() | |
text = tweet.lower() | |
match = re.search(word, text) | |
if match: | |
return True | |
return False | |
# Initialize list to store tweet counts | |
[clinton, trump, sanders, cruz] = [0, 0, 0, 0] | |
# Iterate through df, counting the number of tweets in which | |
# each candidate is mentioned | |
for index, row in df.iterrows(): | |
clinton += word_in_text('clinton', row['text']) | |
trump += word_in_text('trump', row['text']) | |
sanders += word_in_text('sanders', row['text']) | |
cruz += word_in_text('cruz', row['text']) | |
# Set seaborn style | |
sns.set(color_codes=True) | |
# Create a list of labels:cd | |
cd = ['clinton', 'trump', 'sanders', 'cruz'] | |
# Plot histogram | |
ax = sns.barplot(cd, [clinton, trump, sanders, cruz]) | |
ax.set(ylabel="count") | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment