Box Office Mojo Top 3 EDA Fun Facts Through Boxplots

Before starting, standard data import and cleaning.

import os
import pandas as pd
import numpy as np
import datetime as dt
import re
import matplotlib.pyplot as plt
import seaborn as sns
sns.set(style="darkgrid")
%matplotlib inline

fname = sorted([x for x in os.listdir('data')
                if re.match('box_office_mojo_pp', x)])[-1]
df = (pd.read_csv('data/%s' % fname)
      .set_index('title')
      .assign(release_date=lambda x: x.release_date.astype('datetime64'),
              log_gross=lambda x: np.log(x.domestic_total_gross),
              roi=lambda x: x.domestic_total_gross.div(x.budget) - 1))

Our data is the top 100 movies by box office gross from 2008 - 2018

Fact 1: Seasonality by Month

May, June, July, November and December are the strongest months.

ax = (df.assign(month=lambda x: x.release_date.dt.month)
      .pipe((sns.boxplot, 'data'), x='month', y='domestic_total_gross'))
ax.set_xticklabels(month_names,
                   rotation=45,
                   horizontalalignment='right')
ax.yaxis.set_major_formatter(formatter)
ax.set(title='Domestic Total Gross by Month',
       xlabel='',
       ylabel='')
plt.show()

Fact 2: Ratings

R-rated movies have the strongest ROI

ax = sns.boxplot(x='rating', y='roi', data=df, order=rating_order, showfliers=False)
ax.set(title='ROI by Rating', xlabel='', ylabel='')
ax.set_yticklabels(['{:,.0%}'.format(x) for x in ax.get_yticks()])
plt.show()

Fun Fact 3: Genres

If you want to make money in movies, make horror films.

mask = df.genre.isin(genres)
fig = plt.figure(figsize= [15, 10])
ax = fig.add_subplot(111)
data = df.loc[mask, ['genre', 'roi']]
sns.boxplot(x='genre', y='roi', data=data, showfliers=False)
ax.set_xticklabels(ax.get_xticklabels(),
                   rotation=45,
                   horizontalalignment='right',
                   fontweight='light')
ax.set_yticklabels(['{:,.0%}'.format(x) for x in ax.get_yticks()])
ax.set(title='ROI by Genre', xlabel='', ylabel='')
plt.show()