def run(simulator, dataset, run):
click_model = DFBNCM(256, 1024, 10240, 700, 700, dataset,
model=load_model('../click_model_results/DFBNCM_model/{}/train_set{}.h5'.format(simulator.name, run)))
click_log_path = "../click_logs/{}/train_set{}.txt".format(simulator.name, run)
click_log = rf.read_click_log(click_log_path)
click_model.initial_representation(click_log)
# click_model.train_tfrecord('../click_logs/{}/train_set{}_DFBNCM.tfrecord'.format(simulator.name, run),
# batch_size=64,
# epoch=20,
# steps_per_epoch=1)
#
# click_model.model.save("../click_model_results/DFBNCM_model/{}/train_set{}.h5".format(simulator.name, run))
test_click_log_path = "../click_logs/{}/seen_set{}.txt".format(simulator.name, run)
query_frequency_path = "../click_logs/{}/query_frequency{}.txt".format(simulator.name, run)
test_click_log = rf.read_click_log(test_click_log_path)
query_frequency = rf.read_query_frequency(query_frequency_path)
f = open("../click_model_results/{}/seen_set{}_{}_result.txt".format(simulator.name, run, "DFBNCM")
, "w+")
test_logs = {'10': [],
'100': [],
'1000': [],
'10000': []
}
for i in range(test_click_log.shape[0]):
qid = test_click_log[i][0]
test_logs[query_frequency[qid]].append(test_click_log[i])
frequencies = ['10', '100', '1000', '10000']
# i = 0
f.write("Click Model:" + "DFBNCM" + "\n")
for freq in frequencies:
perplexities = click_model.get_perplexity(np.array(test_logs[freq]))
MSEs = click_model.get_MSE(np.array(test_logs[freq]), dataset, simulator)
perplexity_line = "Frequency " + freq + " perplexities:"
MSEs_line = "Frequency " + freq + " MSE:"
for perp in perplexities:
perplexity_line += " " + str(perp)
for MSE in MSEs:
MSEs_line += " " + str(MSE)
f.write(perplexity_line + "\n")
f.write(MSEs_line + "\n")
f.close()
pc = [0.05, 0.3, 0.5, 0.7, 0.95]
ps = [0.2, 0.3, 0.5, 0.7, 0.9]
datasets_simulator = [('SDBN', SDBN(pc, ps)), ('SDCM', SDCM(pc)),
('CM', CM(pc)), ('DCTR', DCTR(pc))]
# datasets = ['CM']
for dataset, simulator in datasets_simulator:
for id in range(1, 2):
click_log_path = "../feature_click_datasets/{}/train_set{}.txt".format(
dataset, id)
test_click_log_path = "../feature_click_datasets/{}/seen_set{}.txt".format(
dataset, id)
query_frequency_path = "../feature_click_datasets/{}/query_frequency{}.txt".format(
dataset, id)
click_log = rf.read_click_log(click_log_path)
test_click_log = rf.read_click_log(test_click_log_path)
query_frequency = rf.read_query_frequency(query_frequency_path)
click_models = [SDBN(), SDCM(), CM(), DCTR()]
processors = []
for cm in click_models:
print(dataset, cm.name, "running!")
f = open(
"../click_model_results/{}/seen_set{}_{}_result.txt".
format(dataset, id, cm.name), "w+")
p = mp.Process(target=run,
args=(click_log, test_click_log,
query_frequency, cm, train_set, simulator,
f))
p.start()
processors.append(p)