def __init__(self, urm, ucm=None, stopwords=[], load_ucm=False, save_ucm=False, binary=False, verbose=True, mode='offline', datareader=None, verbose_evaluation=True):
assert(mode in ('offline', 'online'))
if binary: urm.data=np.ones(urm.data.shape[0])
# best: norm, wor, split, skipw, porter2, lanca2
norm = True
work = True
split = True
skip_words = True
date = False
porter = False
porter2 = True
lanca = False
lanca2 = True
data1 = False
self.ucm=ucm
if self.ucm is None and not load_ucm:
nlp = NLP(datareader, stopwords=stopwords, norm=norm, work=work, split=split, date=date, skip_words=skip_words,
porter=porter, porter2=porter2, lanca=lanca, lanca2=lanca2)
self.ucm = nlp.get_UCM(data1=data1)
elif self.ucm is None and load_ucm:
self.load_ucm('ucm_nlp.npz')
if save_ucm:
self.save_ucm('ucm_nlp.npz')
self.m_uc = pre.bm25_row(self.ucm.copy()).tocsr()
self.m_cu = pre.bm25_row(self.ucm.copy()).T.tocsr()
self.urm = urm
self.binary = binary
self.verbose = verbose
self.verbose_ev = verbose_evaluation
self.dr = datareader
self.mode = mode
if mode == 'offline':
self.ev = Evaluator(self.dr)
def __init__(self,
urm,
pop=None,
binary=False,
verbose=True,
mode='offline',
datareader=None,
verbose_evaluation=True):
assert (mode in ('offline', 'online'))
if binary: urm.data = np.ones(urm.data.shape[0])
if pop is None: self.pop = urm.sum(axis=0).A1
else: self.pop = pop
self.urm = urm
self.m_ui = pre.bm25_row(urm.copy()).tocsr()
self.m_iu = pre.bm25_row(urm.T.copy()).tocsr()
self.binary = binary
self.verbose = verbose
self.verbose_ev = verbose_evaluation
self.dr = datareader
self.mode = mode
if mode == 'offline':
self.ev = Evaluator(self.dr)
def __init__(self,
urm,
pop=None,
binary=False,
K1=1.2,
B=0.75,
verbose=True,
mode='offline',
datareader=None,
verbose_evaluation=True,
mode_t=False,
trick=False):
assert (mode in ('offline', 'online'))
if binary: urm.data = np.ones(urm.data.shape[0])
if pop is None: self.pop = urm.sum(axis=0).A1
else: self.pop = pop
self.dr = datareader
self.urm = urm
urm_aux = urm.copy()
ut.inplace_set_rows_zero(X=urm_aux,
target_rows=self.dr.get_test_pids()
) #don't learn from challange set
urm_aux.eliminate_zeros()
if mode_t: self.m_ui = urm_aux.copy().tocsr()
else: self.m_ui = pre.bm25_row(urm_aux.copy(), K1=K1, B=B).tocsr()
if mode_t: self.m_iu = urm_aux.T.copy().tocsr()
else: self.m_iu = pre.bm25_row(urm_aux.T.copy(), K1=K1, B=B).tocsr()
self.binary = binary
self.verbose = verbose
self.verbose_ev = verbose_evaluation
self.mode = mode
self.mode_t = mode_t
if trick:
self.urm = pre.bm25_row(
urm).tocsr() #high click, high ndcg, better no use
if mode == 'offline':
self.ev = Evaluator(self.dr)
if data1: nome+="data1_"
nlp = NLP2(dr, stopwords=[], norm=norm,work=work,split=split,date=date, skip_words=skip_words,
porter=porter,porter2=porter2,lanca=lanca,lanca2=lanca2)
# new_titles, occ_full, occ_single = nlp.fit( verbose=False, workout=True, normalize=True, date=True, lancaster=False,
# porter=False, underscore=True, double_fit=False)
ucm = nlp.get_UCM(data1=data1)
urm = dr.get_urm()
test_playlists = dr.get_test_pids()
print('ucm', ucm.shape)
print('Computing similarity...')
start = time.time()
# Compute similarity
ucm= bm25_row(ucm)
similarity = tversky_similarity(ucm, binary=False, shrink=1, alpha=0.1, beta=1)
similarity = similarity.tocsr()
print(time.time() - start)
print('Computing eurm...')
start = time.time()
# Compute eurm
eurm = dot_product(similarity, urm, k=500)
eurm = eurm.tocsr()
eurm = eurm[test_playlists, :]
print('eurm', eurm.shape)
print(time.time() - start)
elif feature_type == 'artist':
album = False
artist = True
else:
print("invalid type")
complete_name = mode + "_" + name + "_" + feature_type + "_knn=" + str(
knn) + "_topk=" + str(topk)
if mode == "offline":
dr = Datareader(verbose=False, mode=mode, only_load=True)
urm = dr.get_urm()
icm = dr.get_icm(arid=artist, alid=album)
pid = dr.get_test_pids()
icm_bm25 = pre.bm25_row(icm)
cbfi = Knn_content_item()
cbfi.fit(urm, icm_bm25, pid)
cbfi.compute_model(top_k=knn,
sm_type=TVERSKY,
shrink=100,
alpha=0.1,
binary=False,
verbose=True)
cbfi.compute_rating(top_k=topk, verbose=True, small=True)
sps.save_npz(complete_name + ".npz", cbfi.eurm)
ev = Evaluator(dr)
ev.evaluate(recommendation_list=eurm_to_recommendation_list(cbfi.eurm),
import recommenders.similarity.p3alpha_rp3beta as p3r3
import numpy as np
from utils import ensembler
import scipy.sparse as sps
import gc
from sklearn.preprocessing import normalize
import sys
from utils.pre_processing import bm25_col, bm25_row
dr = Datareader(verbose=False, mode='offline', only_load=True)
ev = Evaluator(dr)
#Getting for the recommender algorithm
urm = dr.get_urm()
#urm.data = np.ones(len(urm.data))
p_ui = bm25_row(urm.copy())
p_iu = bm25_row(urm.T.copy())
pop = urm.sum(axis=0).A1
pids = dr.get_test_pids()
t_urm = sps.csr_matrix(p_ui.copy()[pids])
def recsys(alpha, beta):
alpha = alpha
beta = beta
k = 200
shrink = 100
config = ('alpha=%.2f beta=%.2f k=%d shrink=%d binary=False' %
(alpha, beta, k, shrink))
sim = p3r3.p3alpha_rp3beta_similarity(p_iu,
p_ui,
else:
print("invalid type")
complete_name = mode + "_" + name + "_" + feature_type + "_knn=" + str(
knn) + "_topk=" + str(topk)
if mode == "offline":
dr = Datareader(verbose=False, mode=mode, only_load=True)
urm = dr.get_urm()
icm = dr.get_icm(arid=artist, alid=album)
pid = dr.get_test_pids()
clustered_icm, cluster_allocation = clusterize_icm(icm,
n_clusters=1000)
icm_bm25 = pre.bm25_row(clustered_icm)
cbfi = Knn_content_item()
cbfi.fit(urm, icm_bm25, pid)
cbfi.compute_model(top_k=knn,
sm_type=TVERSKY,
shrink=100,
alpha=0.1,
binary=False,
verbose=True)
cbfi.compute_rating(top_k=topk, verbose=True, small=True)
sps.save_npz(complete_name + ".npz", cbfi.eurm)
ev = Evaluator(dr)
ev.evaluate(recommendation_list=eurm_to_recommendation_list(cbfi.eurm),