def revenue_budget():
''' budget level with high revenue movies'''
budget_data = utils.group_creation(df['budget']);
df['budget_group'] = pd.cut(df['budget'], budget_data[1], labels=budget_data[0], include_lowest = True)
mean = df.groupby('budget_group')['revenue'].mean()
median = df.groupby('budget_group')['revenue'].median()
plt.bar(np.arange(len(mean)),mean, label='mean')
plt.ylabel('Revenue')
plt.xlabel('budget groups')
plt.title('Budget and Revenue relationships')
plt.xticks(np.arange(len(mean)), median.index)
plt.show()
return None
def popularity_traits_earnings():
'''Profit/Loss and popularity relationship'''
earning_data = utils.group_creation(df['profit_loss'])
df['pl_group'] = pd.cut(df['profit_loss'], earning_data[1], labels=earning_data[0], include_lowest = True)
mean = df.groupby('pl_group')['popularity'].mean()
median = df.groupby('pl_group')['popularity'].median()
plt.bar(np.arange(len(mean)),mean, label='mean')
plt.ylabel('popularity')
plt.xlabel('Profit/Loss groups')
plt.title('Profit/Loss and Popularity relationships')
plt.xticks(np.arange(len(mean)), median.index)
plt.show()
return None
def popularity_traits_votes():
'''Vote average and popularity relationship'''
votes_data = utils.group_creation(df['vote_average']);
df['va_group'] = pd.cut(df['vote_average'], votes_data[1], labels=votes_data[0], include_lowest = True)
mean = df.groupby('va_group')['popularity'].mean()
median = df.groupby('va_group')['popularity'].median()
plt.bar(np.arange(len(mean)),mean, label='mean')
plt.ylabel('popularity')
plt.xlabel('Votes groups')
plt.title('Votes/Loss and Popularity relationships')
plt.xticks(np.arange(len(mean)), median.index)
plt.show()
return None
def popularity_traits_runtime():
'''Runtime and popularity relationship'''
runtime_data = utils.group_creation(df['runtime'])
df['runtime_group'] = pd.cut(df['runtime'], runtime_data[1], labels=runtime_data[0], include_lowest = True)
mean = df.groupby('runtime_group')['popularity'].mean()
median = df.groupby('runtime_group')['popularity'].median()
plt.bar(np.arange(len(mean)),mean, label='mean')
plt.ylabel('popularity')
plt.xlabel('Runtime groups')
plt.title('Runtime and Popularity relationships')
plt.xticks(np.arange(len(mean)), median.index)
plt.show()
return None