def rating(self):
if self._rating is None:
download_file(IMDB_RATING_URL, f"{OUTPUT_PATH}/title.ratings.tsv.gz", False)
self._rating = SFrame.read_csv(f"{OUTPUT_PATH}/title.ratings.tsv.gz", delimiter="\t", na_values=["\\N"],
verbose=self._verbose)
self._rating = self._rating.join(self.title)
return self._rating
def crew(self):
if self._crew is None:
download_file(IMDB_CREW_URL, f"{OUTPUT_PATH}/title.crew.tsv.gz", False)
self._crew = SFrame.read_csv(f"{OUTPUT_PATH}/title.crew.tsv.gz", delimiter="\t", na_values=["\\N"],
verbose=self._verbose)
self._crew["directors"] = self.crew["directors"].apply(lambda c: c.split(","))
self._crew = self._crew.stack("directors", "directors")
return self._crew
def actors_movies(self):
if self._actors_movies is None:
download_file(IMDB_PRINCIPALS_URL, f"{OUTPUT_PATH}/title.principals.tsv.gz", False)
self._actors_movies = SFrame.read_csv(f"{OUTPUT_PATH}/title.principals.tsv.gz", delimiter="\t",
na_values=["\\N"], verbose=self._verbose)
self._actors_movies = self._actors_movies.filter_by(["actor", "actress"], "category")[
"tconst", "nconst", "characters"]
self._actors_movies = self._actors_movies.join(self.title[self.title["titleType"] == "movie"])
self._actors_movies = self._actors_movies.join(self.all_actors)
return self._actors_movies
def all_actors(self):
if self._all_actors is None:
download_file(IMDB_NAMES_URL, f"{OUTPUT_PATH}/name.basics.tsv.gz", False)
self._all_actors = SFrame.read_csv(f"{OUTPUT_PATH}/name.basics.tsv.gz", delimiter="\t",
na_values=["\\N"], verbose=self._verbose)
self._all_actors["primaryProfession"] = self._all_actors["primaryProfession"].apply(lambda x: x.split(","))
self._all_actors = self._all_actors.stack("primaryProfession", "primaryProfession")
self._all_actors = self._all_actors.filter_by(["actor", "actress"], "primaryProfession")
self._all_actors["gender"] = self._all_actors.apply(lambda p: self.add_actor_gender(p))
return self._all_actors
def popular_actors(self):
if self._actors is None:
download_file(IMDB_PRINCIPALS_URL, f"{OUTPUT_PATH}/title.principals.tsv.gz", False)
self._actors = SFrame.read_csv(f"{OUTPUT_PATH}/title.principals.tsv.gz", delimiter="\t", na_values=["\\N"],
verbose=self._verbose)
self._actors = self._actors.filter_by(["actor", "actress"], "category")["tconst", "nconst"]
self._actors = self._actors.join(
self.rating[(self.rating["titleType"] == "movie") & (self.rating["numVotes"] > 1000)])
self._actors = self._actors.groupby("nconst", operations={'averageRating': agg.AVG("averageRating"),
'count': agg.COUNT()})
self._actors = self._actors.sort("averageRating", ascending=False)
names = SFrame.read_csv(f"{OUTPUT_PATH}/name.basics.tsv.gz", delimiter="\t")
self._actors = self._actors.join(names)
self._actors["gender"] = self._actors.apply(lambda p: self.add_actor_gender(p))
return self._actors
def __init__(self,
subtitle_info_dict,
use_top_k_roles=None,
ignore_roles_names=None):
"""
Construct the SubtitleAnalyzer and create the video's role time line based
:param subtitle_info_dict: dict with the video metadata created by the SubtitleFetcher class
:param use_top_k_roles: use only the top K roles when constructing the movie? (None - to use all roles)
:param ignore_roles_names: list of roles name to ignore
"""
self._roles = defaultdict(lambda: {
"role": None,
"first": 0,
"last": 0
})
self._interactions = {}
if ignore_roles_names is None:
ignore_roles_names = set()
download_file(STANFORD_NLP_JAR_URL, STANFORD_NLP_JAR, False)
download_file(STANFORD_NLP_MODEL_URL, STANFORD_NLP_MODEL, False)
if not os.path.exists(subtitle_info_dict[SUBTITLE_PATH]):
subtitle_info_dict[ROLES_PATH] = OUTPUT_PATH + subtitle_info_dict[
ROLES_PATH].split("temp")[1]
subtitle_info_dict[
SUBTITLE_PATH] = OUTPUT_PATH + subtitle_info_dict[
SUBTITLE_PATH].split("temp")[1]
imdb_id = subtitle_info_dict[IMDB_ID].strip('t')
self._video_role_analyzer = VideoRolesAnalyzer(
imdb_id, use_top_k_roles, ignore_roles_names,
subtitle_info_dict[ROLES_PATH])
subtitle_srt_path = subtitle_info_dict[SUBTITLE_PATH]
self._subs_entities_timeline_dict = self.create_video_roles_timeline(
subtitle_srt_path)
def title(self):
if self._title is None:
download_file(IMDB_TITLES_URL, f"{OUTPUT_PATH}/title.basics.tsv.gz", False)
self._title = SFrame.read_csv(f"{OUTPUT_PATH}/title.basics.tsv.gz", delimiter="\t", na_values=["\\N"],
verbose=self._verbose)
return self._title