python DataCamp：使用Python导入数据（第2部分）https://www.datacamp.com/courses/importing-data-in-python-part-2

Posted 2021-05-09

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()