from skopt.space import Real, Integer, Categorical
from Utils.Evaluator import EvaluatorHoldout
from Utils.DataSplitter import DataSplitter
from Utils.DataReader import DataReader
import os
# Model to be tuned
from hybrid import Hybrid
################################# READ DATA #################################
reader = DataReader()
splitter = DataSplitter()
urm = reader.load_urm()
ICM = reader.load_icm()
URM_train, URM_val, URM_test = splitter.split(urm, validation=0.2, testing=0.1)
################################ EVALUATORS ##################################
evaluator_validation = EvaluatorHoldout(URM_val, [10])
evaluator_test = EvaluatorHoldout(URM_test, [10])
############################### OPTIMIZER SETUP ###############################
recommender_class = Hybrid
parameterSearch = SearchBayesianSkopt(
recommender_class,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test)
hyperparameters_range_dictionary = {}
def fit(self,
topK=50,
shrink=100,
similarity='cosine',
normalization="none",
feature_weighting="none",
**similarity_args):
self.topK = topK
self.shrink = shrink
reader = DataReader()
icm = reader.load_icm()
if normalization == "bm25":
self.URM_train = similaripy.normalization.bm25(self.URM_train,
axis=1)
if normalization == "tfidf":
self.URM_train = similaripy.normalization.tfidf(self.URM_train,
axis=1)
if normalization == "bm25plus":
self.URM_train = similaripy.normalization.bm25plus(self.URM_train,
axis=1)
if feature_weighting == "bm25":
icm = similaripy.normalization.bm25(icm, axis=1)
if feature_weighting == "tfidf":
icm = similaripy.normalization.tfidf(icm, axis=1)
if feature_weighting == "bm25plus":
icm = similaripy.normalization.bm25plus(icm, axis=1)
matrix = sps.hstack((self.URM_train.transpose().tocsr(), icm))
if similarity == "cosine":
similarity_matrix = similaripy.cosine(matrix,
k=self.topK,
shrink=self.shrink,
binary=False,
threshold=0)
if similarity == "dice":
similarity_matrix = similaripy.dice(matrix,
k=self.topK,
shrink=self.shrink,
binary=False,
threshold=0)
if similarity == "jaccard":
similarity_matrix = similaripy.jaccard(matrix,
k=self.topK,
shrink=self.shrink,
binary=False,
threshold=0)
if similarity == "asym":
similarity_matrix = similaripy.asymmetric_cosine(
matrix,
k=self.topK,
shrink=self.shrink,
binary=False,
threshold=0)
if similarity == "rp3beta":
similarity_matrix = similaripy.rp3beta(matrix,
k=self.topK,
shrink=self.shrink,
binary=False,
threshold=0,
alpha=0.3,
beta=0.61)
self.W_sparse = similarity_matrix
self.W_sparse = check_matrix(self.W_sparse, format='csr')