df_mean_ratings = df_merged.pivot_table('rating', index='title', columns='gender', aggfunc='mean')

ratings_by_title = df_merged.groupby('title').size()
active_titles = ratings_by_title.index[ratings_by_title >= 200]
df_mean_ratings = df_mean_ratings.loc[active_titles]

top_female_ratings = df_mean_ratings.sort_values(by='F', ascending=False)

top_male_ratings = df_mean_ratings.sort_values(by='M', ascending=False)

df_mean_ratings['diff'] = df_mean_ratings['M'] - df_mean_ratings['F']

sorted_by_diff = df_mean_ratings.sort_values(by='diff')

sorted_by_diff[::-1].head()

rating_std_by_title = df_merged.groupby('title')['rating'].std()
rating_std_by_title = rating_std_by_title.loc[active_titles]
rating_std_by_title.sort_values(ascending=False).head(10)

# title
# Plan 9 from Outer Space (1958)         1.455998
# Texas Chainsaw Massacre, The (1974)    1.332448
# Dumb & Dumber (1994)                   1.321333
# Blair Witch Project, The (1999)        1.316368
# Natural Born Killers (1994)            1.307198
# Idle Hands (1999)                      1.298439
# Transformers: The Movie, The (1986)    1.292917
# Very Bad Things (1998)                 1.280074
# Tank Girl (1995)                       1.277695
# Hellraiser: Bloodline (1996)           1.271939
# Name: rating, dtype: float64