def main():
mongo = Mongo()
db_imdb = mongo.client["imdb"]
db_imdb["movies"].create_index([("keywords", pymongo.ASCENDING)])
print("[keywordsCombine] Created index for keywords in movies")
collect_from_keywords(mongo.client) # 34 seconds
collect_from_tags(mongo.client) # 5 minutes
combine(mongo.client) # 8 seconds
db_integration = mongo.client["integration"]
db_integration["integrated_tag"].create_index([("tag", pymongo.ASCENDING)])
print("[keywordsCombine] Created index for tag in integrated_tag")
# not used due to inaccurate
# # fix_popularity(mongo.client) # 3 seconds
imdbPeopleIndex.build(mongo) # 3 minutes
store_people_name_only(mongo.client) # 36 seconds
reconstruct_tags(mongo.client) # 6 seconds
db_integration = mongo.client["integration"]
db_integration["normalized_tags"].create_index([("tag", pymongo.ASCENDING)
])
print("[keywordsCombine] Created index for tag in normalized_tags")
count_movies_with_tags(mongo.client) # 3 seconds
copy_movies(mongo.client) # 15 seconds
db_integration = mongo.client["integration"]
db_integration["copy_movies"].create_index([("imdbtitle",
pymongo.ASCENDING)])
print("[keywordsCombine] Created index for imdbtitle in copy_movies")
def main():
recommender = MovieRecommend(Mongo("movieRecommend"))
# # -----------------------------------------------------------------
# # unit test, input: User ID = 4
# print("[MovieRecommend] ***** Unit test for recommend_movies_for_user() *****")
# user_id = 4
# recommends = recommender.recommend_movies_for_user(user_id)
# recommender.print_recommend(recommends)
# # -----------------------------------------------------------------
# # unit test, input tags:
# # [28, 387, 599, 704, 794]
# # ["adventure", "feel-good", "life", "new york city", "police"]
# print("[MovieRecommend] ***** Unit test for recommend_movies_based_on_tags() *****")
# tags = [28, 387, 599, 704, 794]
# recommends = recommender.recommend_movies_based_on_tags(tags)
# recommender.print_recommend(recommends)
# print("[MovieRecommend] ***** Unit test for recommend_movies_based_on_tags() with tag contents input *****")
# tags = ["adventure", "feel-good", "life", "new york city", "police"]
# recommends = recommender.recommend_movies_based_on_tags(tags, tagid=False)
# recommender.print_recommend(recommends)
# # -----------------------------------------------------------------
# # unit test, input: Movie ID = 1 "Toy Story (1995)"
# print("[MovieRecommend] ***** Unit test for recommend_movies_for_movie() *****")
# movie_id = 1
# recommends = recommender.recommend_movies_for_movie(movie_id)
# recommender.print_recommend(recommends)
# # -----------------------------------------------------------------
# print("[MovieRecommend] ***** Unit test for recommend_movies_for_twitter() *****")
# user_screen_name = "BrunoMars"
# # user_screen_name = "LeoDiCaprio"
# # user_screen_name = "BarackObama"
# # user_screen_name = "sundarpichai"
# # user_screen_name = "BillGates"
# # user_screen_name = "jhsdfjak"
# recommends = recommender.recommend_movies_for_twitter(user_screen_name)
# # recommender.print_recommend(recommends)
# print(recommender.get_titles_by_mids(recommends))
# # -----------------------------------------------------------------
# print("[MovieRecommend] ***** Unit test for recommend_movies_for_twitter_integrated() *****")
# user_screen_name = "BrunoMars"
# # user_screen_name = "LeoDiCaprio"
# # user_screen_name = "BarackObama"
# # user_screen_name = "sundarpichai"
# # user_screen_name = "BillGates"
# # user_screen_name = "jhsdfjak"
# recommends = recommender.recommend_movies_for_twitter_integrated(user_screen_name)
# for recommend in recommends:
# print(recommend.encode("utf8"))
# # -----------------------------------------------------------------
# # unit test, input tags:
# # ["adventure", "feel good", "life", "new york city", "police"]
# print("[MovieRecommend] ***** Unit test for recommend_movies_based_on_tags_integrated() with tag contents input *****")
# tags = ["adventure", "feel good", "life", "new york city", "police"]
# recommends = recommender.recommend_movies_based_on_tags_integrated(tags)
# for recommend in recommends:
# print(recommend.encode("utf8"))
# # -----------------------------------------------------------------
# unit test for recommend_movies_based_on_history()
print(
"[MovieRecommend] ***** Unit test for recommend_movies_based_on_history() *****"
)
user_history = []
user_history.append("Toy Story (1995)")
user_history.append("Big Hero 6 (2014)")
user_history.append("X-Men: Days of Future Past (2014)")
user_history.append("The Lego Movie (2014)")
user_history.append("The Secret Life of Walter Mitty (2013)")
user_history.append("Death Note: Desu nto (2006)")
user_history.append("Zombieland (2009)")
user_history.append("Fifty Shades of Grey (2015)")
user_history.append("The Maze Runner (2014)")
recommends = recommender.recommend_movies_based_on_history(user_history)
recommends = recommender.get_titles_by_mids(recommends)
for recommend in recommends:
print(recommend.encode("utf8"))
def main():
mongo = Mongo("movieRecommend")
parse(mongo)
def main():
# Add ANEW all list into database.
# runtime: (0.05s)
mongo = Mongo("movieRecommend")
parse(mongo)
def main():
mongo = Mongo("movieRecommend")
retrieve(mongo)
def main():
mongo = Mongo("imdb")
build(mongo)
def main():
twitter = Tweepy(Mongo("movieRecommend"))
# twitter.get_rate_limit()
# twitter.extract_profile("LeoDiCaprio")
# twitter.extract_profile("BrunoMars")
twitter.extract_profile("jhsdfjak")
