def tune_alpha(self,
range_alpha=np.arange(0.5, 1.5, 0.1),
k=100,
shrink=0,
threshold=0,
verbose_tune=False,
filename='tuning_bm25_alpha',
overwrite=False,
save_mean=True,
save_full=True):
tp = TunePrint(filename=filename,
full=save_full,
mean=save_mean,
overwrite=overwrite)
self.model(
alpha=1, beta=0, k=k, shrink=shrink,
threshold=threshold) #exploit this trick to generate fastest model
save_data = self.s.data
for alpha in range_alpha:
self.s.data = save_data
self.s.data = np.power(self.s.data, alpha)
self.alpha = alpha
self.fast_recommend()
mean, df_all_values = self.fast_evaluate_eurm()
self.clear_eurm()
s_mean = 'P = %1.4f, NDCG = %1.4f, CLICK = %1.4f' % (
mean[0], mean[1], mean[2])
if verbose_tune: print(str(self) + '\n' + s_mean)
if save_mean: tp.print_mean_values(str(self), mean)
if save_full:
tp.print_full_values(description=str(self),
dict_val={'alpha': alpha},
dataframe=df_all_values)
tp.make_pdf_full()
def tune_shrink(self,
range_shrink=np.arange(25, 300, 25),
alpha=1,
beta=0,
k=200,
threshold=0,
verbose_tune=True,
filename='tuning_bm25_shrink',
overwrite=False,
save_mean=True,
save_full=True):
tp = TunePrint(filename=filename,
full=save_full,
mean=save_mean,
overwrite=overwrite)
for shrink in range_shrink:
self.model(alpha=alpha,
beta=beta,
k=k,
shrink=shrink,
threshold=threshold)
self.fast_recommend()
self.clear_similarity()
mean, df_all_values = self.fast_evaluate_eurm()
self.clear_eurm()
s_mean = 'P = %1.4f, NDCG = %1.4f, CLICK = %1.4f' % (
mean[0], mean[1], mean[2])
if verbose_tune: print(str(self) + '\n' + s_mean)
# save values
if save_mean: tp.print_mean_values(str(self), mean)
if save_full:
tp.print_full_values(description=str(self),
dict_val={'shrink': shrink},
dataframe=df_all_values)
tp.make_pdf_full()
def tune_alpha_beta(self,
range_alpha=np.arange(0, 1.1, 0.1),
range_beta=np.arange(0, 1.1, 0.1),
k=200,
shrink=0,
threshold=0,
verbose_tune=True,
filename='tuning_bm25_alpha_beta',
overwrite=False,
save_mean=True,
save_full=True):
tp = TunePrint(filename=filename,
full=save_full,
mean=save_mean,
overwrite=overwrite)
for alpha in range_alpha:
for beta in range_beta:
self.model(alpha=alpha,
beta=beta,
k=k,
shrink=shrink,
threshold=threshold)
self.fast_recommend()
self.clear_similarity()
mean, df_all_values = self.fast_evaluate_eurm()
self.clear_eurm()
s_mean = 'P = %1.4f, NDCG = %1.4f, CLICK = %1.4f' % (
mean[0], mean[1], mean[2])
if verbose_tune: print(str(self) + '\n' + s_mean)
# save values
if save_mean: tp.print_mean_values(str(self), mean)
if save_full: tp.print_full_values(str(self), df_all_values)