web_scraping_stars_analysis.py

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# convert stars' dictionary to pandas dataframe
frame = pd.DataFrame(star_table)

# format stars' dataframe
frame.credits = frame.credits.astype('int')
frame.year_born = frame.year_born.astype('int')
frame.year_first_movie = frame.year_first_movie.astype('int')

# calculate age at first movie
frame['age_at_first_movie'] = frame['year_first_movie'] - frame['year_born']

# find former child actors
print('{} performers started as child actors'.format(frame[frame.age_at_first_movie <= 12].shape[(0)]))

# plot stars' age distribution
frame.year_born.hist()

# plot credits vs. gender
sns.catplot(
    data=frame, kind="bar",
    x="gender", y="credits",
    ci="sd", palette="dark", alpha=.6, height=6
)

# plot count of female vs male actors
sns.countplot(x="gender", data=frame)