def fit(self, X: list, Y: list = None):
self.__instantiate_classifier()
X = transform(self.transformer, X)
pipe = make_pipeline(self.clf)
self.pipe = pipe.fit(X, Y)
def fit(self, X: list, Y: list = None):
self.__instantiate_classifier(X)
# Transform the input if there are dicts, multiple representation, etc.
X = transform(self.transformer, X)
pipe = make_pipeline(self.clf)
self.pipe = pipe.fit(X, Y)
def fit(self, X: list, Y: list = None):
# Transform the input
X = transform(self.transformer, X)
# Try fitting the Calibrated classifier for better classification
try:
self.__instantiate_classifier(calibrated=True)
pipe = make_pipeline(self.clf)
self.pipe = pipe.fit(X, Y)
# If exception instantiate a non-calibrated classifier, then fit
except ValueError:
self.__instantiate_classifier(calibrated=False)
pipe = make_pipeline(self.clf)
self.pipe = pipe.fit(X, Y)
def predict(self,
ratings: pd.DataFrame,
recs_number: int,
items_directory: str,
candidate_item_id_list: List = None) -> pd.DataFrame:
"""
After computing the centroid of the positive rated items by the user and getting the similarity scores
of said centroid compared with every unrated item, creates and returns a recommendation list of unrated
items ordered by their similarity score with the centroid. A candidate_item_id_list can be passed
which will be used instead of the unrated items.
EXAMPLE:
Creates a recommendation list of length 1 with the similarity to the centroid as score, only considering
the item tt0114319 instead of all the unrated items. (Ratings is a DataFrame containing the ratings
given by the user)
predict(ratings=ratings, recs_number=1, items_directory='.../somedir',
candidate_item_id_list=['tt0114319'])
Args:
candidate_item_id_list (list): list of the items that can be recommended, if None
all unrated items will be used
recs_number (int): how long the ranking will be
ratings (pd.DataFrame): ratings of a user
items_directory (str): name of the directory where the items are stored.
Returns:
scores (pd.DataFrame): DataFrame whose columns are the ids of the items (to_id),
and the similarities between the items and the centroid (rating)
"""
# Loads the items and extracts features from the unrated items, then
# extracts features from the positive rated items
# If exception, returns an empty score_frame
try:
rated_items, unrated_items, unrated_features_bag_list = \
super().preprocessing(items_directory, ratings, candidate_item_id_list)
positive_rated_features_bag_list = self.__calc_positive_rated_baglist(
rated_items, ratings)
except (ValueError, FileNotFoundError) as e:
logger.warning(str(e))
columns = ["to_id", "rating"]
score_frame = pd.DataFrame(columns=columns)
return score_frame
logger.info("Computing rated items centroid")
positive_rated_items_array = transform(
self.__transformer, positive_rated_features_bag_list)
centroid = np.array(positive_rated_items_array).mean(axis=0)
columns = ["to_id", "rating"]
score_frame = pd.DataFrame(columns=columns)
logger.info("Computing similarity between centroid and unrated items")
unrated_items_array = transform(self.__transformer,
unrated_features_bag_list)
similarities = [
self.__similarity.perform(centroid, item)
for item in unrated_items_array
]
for item, similarity in zip(unrated_items, similarities):
score_frame = pd.concat([
score_frame,
pd.DataFrame.from_records([(item.content_id, similarity)],
columns=columns)
],
ignore_index=True)
score_frame = score_frame.sort_values(
['rating'], ascending=False).reset_index(drop=True)
score_frame = score_frame[:recs_number]
return score_frame
def predict_proba(self, X_pred: list):
X_pred = transform(self.transformer, X_pred)
return self.pipe.predict_proba(X_pred)