def show_gender_genre_comparison():
plt.rcParams.update({'font.size': 28})
# This plot shows the
genres = ["Action", "Adventure", "Animation", "Children\'s", "Comedy", "Crime", "Documentary", "Drama",
"Fantasy", "Film-Noir", "Horror", "Musical", "Mystery", "Romance", "Sci-Fi", "Thriller", "War",
"Western"]
movie_genre = MD.load_movie_genre_matrix_1m()
male_genre = np.zeros(shape=(len(genres, )))
female_genre = np.zeros(shape=(len(genres, )))
user_gender_dict = MD.gender_user_dictionary_1m()
user_genre = MD.load_user_genre_matrix_1m()
for user_index, user in enumerate(user_genre):
if user_gender_dict[user_index] == "M":
male_genre += user
else:
female_genre += user
print(male_genre)
print(female_genre)
x = np.arange(len(genres))
ax = plt.subplot(111)
ax.bar(x-0.2, male_genre/750000, width=0.4, label='male')
ax.bar(x+0.2, female_genre/250000, width=0.4, label='female')
plt.xticks(x, ("Action", "Adventure", "Animation", "Children\'s", "Comedy", "Crime", "Documentary", "Drama",
"Fantasy", "Film-Noir", "Horror", "Musical", "Mystery", "Romance", "Sci-Fi", "Thriller", "War",
"Western"))
plt.legend()
plt.tight_layout()
plt.setp(ax.get_xticklabels(), rotation=40)
plt.ylabel("Normalized rating count")
plt.xlabel("Genres")
plt.show()
def show_avg_rating_gender_per_movie(movie_id=1):
gender_dict = MD.gender_user_dictionary_1m()
user_item = MD.load_user_item_matrix_1m()
ratings = user_item[:, movie_id]
male_ratings = []
female_ratings = []
for user_id, rating in enumerate(ratings):
if rating > 0:
if gender_dict[user_id] == 'M':
male_ratings.append(rating)
else:
female_ratings.append(rating)
plt.bar(["male", "female"], [np.average(male_ratings), np.average(female_ratings)])
plt.show()
def loyal_vs_diverse():
#X = MD.load_user_item_matrix_1m()
#T = MD.load_gender_vector_1m()
genres = [
"Action", "Adventure", "Animation", "Children\'s", "Comedy", "Crime",
"Documentary", "Drama", "Fantasy", "Film-Noir", "Horror", "Musical",
"Mystery", "Romance", "Sci-Fi", "Thriller", "War", "Western"
]
movie_genre = MD.load_movie_genre_matrix_1m(combine=True)
user_genre_distr = np.zeros(shape=(6040, movie_genre.shape[1]))
user_gender_dict = MD.gender_user_dictionary_1m()
print(user_genre_distr.shape)
with open("ml-1m/ratings.dat", 'r') as f:
for line in f.readlines():
user_id, movie_id, rating, _ = line.split("::")
movie_id = int(movie_id) - 1
user_id = int(user_id) - 1
user_genre_distr[user_id, :] += movie_genre[movie_id, :]
loyal_percents = [0.5, 0.6, 0.7]
for i, loyal_percent in enumerate(loyal_percents):
loyal_count = 0
for user_index, user in enumerate(user_genre_distr):
if max(user) / sum(user) > loyal_percent:
if True:
#print the user:
print(user_gender_dict[user_index])
top_5_index = user.argsort()[-5:][::-1]
for index in top_5_index:
print(genres[index], user[index])
loyal_count += 1
print("For threshold", loyal_percent, ",", loyal_count,
"users are considered loyal")
if True:
user_loyalty_male = []
user_loyalty_female = []
for user_index, user in enumerate(user_genre_distr):
loyalty = max(user) / sum(user)
if user_gender_dict[user_index] == 'M':
user_loyalty_male.append(loyalty)
plt.scatter(user_index, loyalty, c='b')
else:
user_loyalty_female.append(loyalty)
plt.scatter(user_index, loyalty, c='r')
print(np.average(user_loyalty_male))
print(np.average(user_loyalty_female))
def test_avg_rating_gender_per_movie_1m():
import MovieLensData as MD
from scipy.stats import ttest_ind, mannwhitneyu
gender_dict = MD.gender_user_dictionary_1m()
user_item = MD.load_user_item_matrix_1m()
movies = {}
with open("ml-1m/movies.dat", 'r') as f:
for line in f.readlines():
id, name, genre = line.replace("\n", "").split("::")
movies[int(id)] = name + "::" + genre
counter = 0
print(len(user_item[0]))
for movie_id in range(len(user_item[0])):
ratings = user_item[:, movie_id]
male_ratings = []
female_ratings = []
for user_id, rating in enumerate(ratings):
if rating > 0:
if gender_dict[user_id] == 'M':
male_ratings.append(rating)
else:
female_ratings.append(rating)
try:
_, p_value = mannwhitneyu(male_ratings, female_ratings)
if p_value < 0.05 / len(user_item[0]):
#print(movie_id+1, "%.2f" % np.average(male_ratings), len(male_ratings), "%.2f" % np.average(female_ratings), len(female_ratings), p_value)
counter += 1
#plt.bar(["male", "female"], [np.average(male_ratings), np.average(female_ratings)])
#plt.show()
if np.average(male_ratings) > np.average(female_ratings):
print(
str(movie_id + 1) + "::" + movies[movie_id + 1] +
"::M")
if np.average(male_ratings) < np.average(female_ratings):
print(
str(movie_id + 1) + "::" + movies[movie_id + 1] +
"::F")
except:
print("Testing failed for", movie_id)
print(str(1 + 1) + "::" + movies[1])
print(counter)