from dataset import LetorDataset
import numpy as np
from clickModel.LSTMv2 import LSTMv2
from utils import read_file as rf
from clickModel.DCTR import DCTR
train_path = "../datasets/ltrc_yahoo/test_set.txt"
print("loading training set.......")
train_set = LetorDataset(train_path, 700)
click_log_path = "../datasets/ltrc_yahoo/test_click_log.txt"
test_click_log_path = "../datasets/ltrc_yahoo/test_click_log_test.txt"
click_log = rf.read_click_log(click_log_path)
test_click_log = rf.read_click_log(test_click_log_path)
pc = [0.05, 0.3, 0.5, 0.7, 0.95]
ps = [0.2, 0.3, 0.5, 0.7, 0.9]
simulator = DCTR(pc)
print(click_log.shape)
print(test_click_log.shape)
#
click_model = LSTMv2(700, 1024, train_set)
click_model.train(click_log)
print(
click_model.get_MSE(
test_click_log[np.random.choice(test_click_log.shape[0], 100)],
train_set, simulator))
if __name__ == "__main__":
# %%
train_path = "../datasets/ltrc_yahoo/set1.train.txt"
test_path = "../datasets/ltrc_yahoo/set1.test.txt"
print("loading training set.......")
train_set = LetorDataset(train_path, 700)
print("loading testing set.......")
test_set = LetorDataset(test_path, 700)
# %%
# pc = [0.4, 0.6, 0.7, 0.8, 0.9]
# ps = [0.1, 0.2, 0.3, 0.4, 0.5]
pc = [0.05, 0.3, 0.5, 0.7, 0.95]
ps = [0.2, 0.3, 0.5, 0.7, 0.9]
for id in range(1, 16):
p1 = mp.Process(target=generate_dataset,
args=(train_set, test_set, DCTR(pc),
"../feature_click_datasets/DCTR/", id))
p2 = mp.Process(target=generate_dataset,
args=(train_set, test_set, CM(pc),
"../feature_click_datasets/CM/", id))
p3 = mp.Process(target=generate_dataset,
args=(train_set, test_set, SDBN(pc, ps),
"../feature_click_datasets/SDBN/", id))
p4 = mp.Process(target=generate_dataset,
args=(train_set, test_set, SDCM(pc),
"../feature_click_datasets/SDCM/", id))
p1.start()
p2.start()
p3.start()
p4.start()
# %%
if __name__ == "__main__":
# %%
train_path = "../datasets/ltrc_yahoo/set1.train.txt"
test_path = "../datasets/ltrc_yahoo/set1.test.txt"
print("loading training set.......")
train_set = LetorDataset(train_path, 700)
# %%
# print("loading testing set.......")
# test_set = LetorDataset(test_path, 700)
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()]
# %%
if __name__ == "__main__":
# %%
train_path = "../datasets/ltrc_yahoo/set1.LetorDataset.txt"
print("loading training set.......")
with open(train_path, "rb") as fp:
train_set = pickle.load(fp)
# %%
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)),
('UBM', UBM(pc)),
# ('SDBN_reverse', SDBN_reverse(pc, ps))
]
progress = 0
for dataset, simulator in datasets_simulator:
for id in range(2, 16):
click_log_path = "../click_logs/{}/train_set{}.txt".format(
dataset, id)
test_click_log_path = "../click_logs/{}/seen_set{}.txt".format(
dataset, id)
query_frequency_path = "../click_logs/{}/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)
generator = "Mixed"
click_log_path = "../feature_click_datasets/{}/train_set1.txt".format(generator)
test_click_log_path = "../feature_click_datasets/{}/seen_set1.txt".format(generator)
click_log = rf.read_click_log(click_log_path)
test_click_log = rf.read_click_log(test_click_log_path)
# #
dataset = tf.data.TFRecordDataset(filenames='../feature_click_datasets/{}/train_set1.tfrecord'.format(generator))
# # # test_dataset = tf.data.TFRecordDataset(filenames='../feature_click_datasets/SDBN/seen_set1.tfrecord')
# # #%%
pc = [0.05, 0.3, 0.5, 0.7, 0.95]
ps = [0.2, 0.3, 0.5, 0.7, 0.9]
Mixed_models = [DCTR(pc), CM(pc), SDBN(pc, ps), SDCM(pc), UBM(pc)]
simulator = Mixed(Mixed_models)
print(click_log.shape)
print(test_click_log.shape)
#
click_model = LSTMv2(700, 1024, train_set, batch_size=128, epoch=5)
print(click_model.get_MSE(test_click_log[np.random.choice(test_click_log.shape[0], 1000)], train_set, simulator))
click_model.train(dataset)
print(click_model.get_MSE(test_click_log[np.random.choice(test_click_log.shape[0], 1000)], train_set, simulator))
click_model.model.save("../click_model_results/LSTM_models/{}_train_set1.h5".format(generator))
# test model
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()
if __name__ == "__main__":
pc = [0.05, 0.3, 0.5, 0.7, 0.95]
ps = [0.2, 0.3, 0.5, 0.7, 0.9]
Mixed_models = [DCTR(pc), SDBN(pc, ps), UBM(pc)]
# simulators = [SDBN(pc, ps), Mixed(Mixed_models), DCTR(pc), UBM(pc)]
simulators = [SDBN(pc, ps), DCTR(pc), UBM(pc)]
dataset_path = "../datasets/ltrc_yahoo/set1.train.txt"
print("loading training set.......")
dataset = LetorDataset(dataset_path, 700)
for r in range(1, 2):
for simulator in simulators:
run(simulator, dataset, r)
from clickModel.RCTR import RCTR
from clickModel.Mixed import Mixed
from utils import read_file as rf
from utils import utility
from dataset import LetorDataset
# import matplotlib.pyplot as plt
import numpy as np
import multiprocessing as mp
train_path = "../datasets/ltrc_yahoo/set1.train.txt"
print("loading training set.......")
train_set = LetorDataset(train_path, 700)
pc = [0.05, 0.3, 0.5, 0.7, 0.95]
ps = [0.2, 0.3, 0.5, 0.7, 0.9]
mixed_models = [DCTR(pc), SDBN(pc, ps), UBM(pc)]
datasets_simulator = [
('SDBN', SDBN(pc, ps)),
# ('SDCM', SDCM(pc)),
# ('CM', CM(pc)),
('DCTR', DCTR(pc)),
('UBM', UBM(pc)),
('SDBN_reverse', SDBN_reverse(pc, ps))
]
click_model = RCTR()
for dataset, simulator in datasets_simulator:
for id in range(1, 16):
click_log_path = "../click_logs/{}/train_set{}.txt".format(dataset, id)
click_log = rf.read_click_log(click_log_path)
click_model.train(click_log)