def hybrid_rec(user_ratings, user, icm_m, sim_skr=20, w_cbf=0.82, w_cf=0.18):
"""
hybrid recommendations for a user
Parameters
----------
user_ratings: the rating of the user to be recommended
user: the user to be recommenended
icm_m: the ICM matrix
sim_skr: the shrink sim for CBF
w_cbf: the weight for CBF
w_cf: the weight for CF
Returns
-------
List of 5 movies recommended
"""
totals_cbf = {} # {item : sum (rating * similarity)}
totals_cf = {} # {item : sum (rating * similarity)}
rankings = {} # {item : (sim_cbf * w_cbf) + (sim_cf * w_cf)}
avg_rec = [(5.0, 33173), (5.0, 33475), (5.0, 1076), (5.0, 35300), (5.0, 15743)]
# generiamo il ranking di cbf
for other_movie in icm_m: # scandisco tutti i movie non recensiti dall'user e li confronto con quelli recensiti
if other_movie not in user_ratings:
for movie in user_ratings:
if movie != other_movie:
# per ogni movie non recensito dall'user calcolo la similarity con quelli recensiti
similarity = item_sim(icm_m, movie, other_movie, skr=sim_skr)
if similarity != 0:
totals_cbf.setdefault(other_movie, 0.0)
totals_cbf[other_movie] += user_ratings[movie] * similarity
# generiamo il ranking di cf
for other in urm:
# don't compare me to myself
if other == user:
continue
similarity_urm = adj_cosine_sim(urm, user, other, 6)
# ignore scores of zero or lower
if similarity_urm <= 0:
continue
for item in urm[other]:
# only score movies I haven't seen yet
if item not in urm[user] or urm[user][item] == 0:
# Similarity * Score
totals_cf.setdefault(item, 0)
totals_cf[item] += urm[other][item] * similarity_urm
# mergiamo i ranking di cbf e cf pesando i valori
for movie in totals_cbf:
rankings[movie] = totals_cbf[movie] * w_cbf
if movie in totals_cf:
rankings[movie] += totals_cf[movie] * w_cf
for movie in totals_cf:
if movie not in rankings:
rankings[movie] = totals_cf[movie] * w_cf
# togliamo da ranking i movie troppo popolari
"""
# se il film meno popolare votato dall'user ha meno di 10 voti metto una soglia nel range dove eliminare
if user_min_pop[user] < 10:
for i in range(0, 500):
if sort_popularity[i][0]in rankings:
del rankings[sort_popularity[i][0]]
# altrimenti eliminiamo i film piu' popolari del meno popolare votato dall'utente senza nessuna soglia
else:
for i in range(0,index_pop[user_min_pop[user]]):
if sort_popularity[i][0]in rankings:
del rankings[sort_popularity[i][0]]
"""
for i in range(0, index_pop[user_min_pop[user]]):
if sort_popularity[i][0] in rankings:
del rankings[sort_popularity[i][0]]
# compute the ranking for every movie, but the due to the shrink term the value are not prediction
rankings_final = [(total, item) for item, total in rankings.items()]
sort_rankings = sorted(rankings_final, key=lambda x: -x[0])[0:5]
# This should happen when there are less than five similar movie for the movies
if len(sort_rankings) < 5:
for elem in avg_rec:
sort_rankings.append(elem)
sort_rankings = sort_rankings[0:5]
string_s = ""
for rate in range(0, len(sort_rankings)):
string_s = string_s + " " + str(sort_rankings[rate][1])
return string_s
def cbf_recommendations(user_ratings,user, icm_m, sim_skr=20, shrink=10):
"""
* WARNING:
# This function is very resources and time consuming if it is done in large batch (e.g in a for loop over
the whole movies)
This function computes the recommendations using a CBF (Content Based Filtering) technique.
Right now the implementation supports only a a fast similarity called item_sim (Doc in similarity.py)
* NOTE:
# this does not contain any optimization, it is just a simple and raw computation
* TODO:
# support for cosine
# some optimization are needed
Parameters
----------
user_ratings: ratings of the user, it contains all the rated movie by an user
icm_m: item content matrix
sim_skr: shrink term f the similarity
shrink: shrink of the function itself
Returns
-------
A pre-formatted string containing the 5 best recommendations (NOTE: this has been done to be less time consuming)
"""
totals = {} # dizionario {item: sum (rating * similarity)}
sim_sums = {} # dizionario {item: sum (similarity)}
avg_rec = [(5.0, 33173), (5.0, 33475), (5.0, 1076), (5.0, 35300), (5.0, 15743)]
for other_movie in icm_m: # scandisco tutti i movie non recensiti dall'user e li confronto con quelli recensiti
if other_movie not in user_ratings:
for movie in user_ratings:
if movie != other_movie:
# per ogni movie non recensito dall'user calcolo la similarity con quelli recensiti
similarity = item_sim(icm_m, movie, other_movie, skr=sim_skr)
if similarity != 0:
totals.setdefault(other_movie, 0)
totals[other_movie] += user_ratings[movie]*similarity
sim_sums.setdefault(other_movie, 0)
sim_sums[other_movie] += similarity
#togliamo da totals i film troppo popolari
for i in range(0, 1000):
if sort_popularity[i][0]in totals:
del totals[sort_popularity[i][0]]
# compute the ranking for every movie, but the due to the shrink term the value are not prediction
rankings = [(total/(sim_sums[item] + shrink), item) for item, total in totals.items()]
sort_rankings = sorted(rankings, key=lambda x: -x[0])[0:5]
# This should happen when there are less than five similar movie for the movies
if len(sort_rankings) < 5:
for elem in avg_rec:
sort_rankings.append(elem)
sort_rankings = sort_rankings[0:5]
string_s = ""
for rate in range(0, len(sort_rankings)):
string_s = string_s + " " + str(sort_rankings[rate][1])
return string_s
def cbf_recommendations(user_ratings, user, icm_m, knn, urm, sim_skr=20, shrink=10, w_cbf=0.9, w_knn=0.1):
"""
* WARNING:
# This function is very resources and time consuming if it is done in large batch (e.g in a for loop over
the whole movies)
This function computes the recommendations using a CBF (Content Based Filtering) technique.
Right now the implementation supports only a a fast similarity called item_sim (Doc in similarity.py)
* NOTE:
# this does not contain any optimization, it is just a simple and raw computation
* TODO:
# support for cosine
# some optimization are needed
Parameters
----------
user_ratings: ratings of the user, it contains all the rated movie by an user
icm_m: item content matrix
sim_skr: shrink term f the similarity
shrink: shrink of the function itself
knn: it is a
Returns
-------
A pre-formatted string containing the 5 best recommendations (NOTE: this has been done to be less time consuming)
"""
totals_cbf = {} # dizionario {item: sum (rating * similarity)}
sim_sums_cbf = {} # dizionario {item: sum (similarity)}
avg_rec = [(5.0, 33173), (5.0, 33475), (5.0, 1076), (5.0, 35300), (5.0, 15743)]
totals_knn = {}
sim_sums_knn = {}
# this is the cbf part of the code
for other_movie in icm_m: # scandisco tutti i movie non recensiti dall'user e li confronto con quelli recensiti
if other_movie not in user_ratings:
for movie in user_ratings:
if movie != other_movie:
# per ogni movie non recensito dall'user calcolo la similarity con quelli recensiti
similarity = item_sim(icm_m, movie, other_movie, skr=sim_skr)
if similarity != 0:
totals_cbf.setdefault(other_movie, 0.0)
totals_cbf[other_movie] += user_ratings[movie]*similarity
sim_sums_cbf.setdefault(other_movie, 0.0)
sim_sums_cbf[other_movie] += similarity
# this one should be the knn on users
if user in knn:
for other_user in knn[user]:
for movie in urm[other_user]:
if movie not in urm[user]:
totals_knn.setdefault(movie, 0.0)
totals_knn[movie] += urm[other_user][movie] * knn[user][other_user]
rankings = {}
"""
scores_cbf = {}
scores_knn = {}
for movie in totals_cbf:
scores_cbf[movie] = totals_cbf[movie]/sim_sums_cbf[movie]
for movie in totals_knn:
scores_knn[movie] = totals_knn[movie]/sim_sums_knn[movie]
"""
# this part is supposed to build up the totoal recommendations
for movie in totals_cbf:
rankings[movie] = totals_cbf[movie]*w_cbf
if movie in totals_knn:
rankings[movie] += totals_knn[movie]*w_knn
for movie in totals_knn:
if movie not in rankings:
rankings[movie] = totals_knn[movie]*w_knn
# this one are non normalized rankings
"""
rankings = [(total, item) for item, total in rankings.items()]"""
"""
if you wanna normalized rankings
rankings = [(round(total/(sim_sums[item]), 3), item) for item, total in rankings.items()]
"""
# compute the ranking for every movie, but the due to the shrink term the value are not prediction
rankings_final = [(total, item) for item, total in rankings.items()]
sort_rankings = sorted(rankings_final, key=lambda x: -x[0])[0:5]
# This should happen when there are less than five similar movie for the movies
if len(sort_rankings) < 5:
for elem in avg_rec:
sort_rankings.append(elem)
sort_rankings = sort_rankings[0:5]
string_s = ""
for rate in range(0, len(sort_rankings)):
string_s = string_s + " " + str(sort_rankings[rate][1])
return string_s
