def export_features():
train_data = read_libsvm(FLAGS.data_dir)
feat_ids, feat_vals, label = slice_libsvm(train_data)
fea = model.run_step(model.fea_out, feat_ids, feat_vals, label)
with open(FLAGS.feature_dir, 'w') as f:
for i in range(len(fea)):
f.write(str(label[i]) + ' ') # label
for j in range(len(fea[i])): # features
f.write(str(j + 1) + ':' + str(round(fea[i][j], 3)) + ' ')
f.write('\n')
print('export feature done, file : %s' % FLAGS.feature_dir)
exit()
tf.app.flags.DEFINE_string("loss_type", 'log_loss',
"loss type {square_loss, log_loss}")
tf.app.flags.DEFINE_integer("log_steps", 1000, "save summary every steps")
tf.app.flags.DEFINE_boolean("batch_norm", False,
"perform batch normaization (True or False)")
tf.app.flags.DEFINE_float(
"batch_norm_decay", 0.9,
"decay for the moving average(recommend trying decay=0.9)")
if FLAGS.dt_dir == "":
FLAGS.dt_dir = (date.today() + timedelta(1 - 1)).strftime('%Y%m%d')
FLAGS.model_dir = FLAGS.model_dir + FLAGS.dt_dir
if FLAGS.train:
data = read_libsvm(FLAGS.data_dir)
random.shuffle(data)
train_data = data[:(int)(len(data) * FLAGS.split_ratio)]
test_data = data[(int)(len(data) * FLAGS.split_ratio):]
print('read finish')
print('train data size:', (len(train_data), len(train_data[0][0])))
print('test data size:', (len(test_data), len(test_data[0][0])))
train_size = len(train_data)
test_size = len(test_data)
min_round = FLAGS.min_round
num_round = FLAGS.num_round
early_stop_round = FLAGS.early_stop_round
batch_size = FLAGS.batch_size
afm_params = {
'field_size': FLAGS.field_size,
tf.app.flags.DEFINE_string("dropout", '0.5,0.5,0.5', "dropout rate")
tf.app.flags.DEFINE_string("dt_dir", '', "data dt partition")
tf.app.flags.DEFINE_integer("num_round", 20000, "Number of round")
tf.app.flags.DEFINE_integer("min_round", 200, "Number of min round")
tf.app.flags.DEFINE_integer("early_stop_round", 2000, "Number of early stop round")
tf.app.flags.DEFINE_string("loss_type", 'log_loss', "loss type {square_loss, log_loss}")
tf.app.flags.DEFINE_integer("log_steps", 1000, "save summary every steps")
tf.app.flags.DEFINE_boolean("batch_norm", False, "perform batch normaization (True or False)")
tf.app.flags.DEFINE_float("batch_norm_decay", 0.9, "decay for the moving average(recommend trying decay=0.9)")
if FLAGS.dt_dir == "": FLAGS.dt_dir = (date.today() + timedelta(1 - 1)).strftime('%Y%m%d')
FLAGS.model_dir = FLAGS.model_dir + FLAGS.dt_dir
if FLAGS.train:
data = read_libsvm(FLAGS.data_dir); random.shuffle(data)
train_data = data[:(int)(len(data) * FLAGS.split_ratio)]; test_data = data[(int)(len(data) * FLAGS.split_ratio):]
print('read finish'); print('train data size:', (len(train_data), len(train_data[0][0]))); print('test data size:', (len(test_data), len(test_data[0][0])))
train_size = len(train_data); test_size = len(test_data)
min_round = FLAGS.min_round; num_round = FLAGS.num_round; early_stop_round = FLAGS.early_stop_round; batch_size = FLAGS.batch_size
nfm_params = {
'field_size': FLAGS.field_size,
'feature_size': FLAGS.feature_size,
'embedding_size': FLAGS.embedding_size,
'l2_reg': FLAGS.l2_reg,
'learning_rate': FLAGS.learning_rate,
'optimizer': FLAGS.optimizer,
'layer_sizes': FLAGS.deep_layers,
'layer_acts': FLAGS.active_function,
'drop_out': FLAGS.dropout,
tf.app.flags.DEFINE_string("loss_type", 'log_loss',
"loss type {square_loss, log_loss}")
tf.app.flags.DEFINE_integer("log_steps", 1000, "save summary every steps")
tf.app.flags.DEFINE_boolean("batch_norm", False,
"perform batch normaization (True or False)")
tf.app.flags.DEFINE_float(
"batch_norm_decay", 0.9,
"decay for the moving average(recommend trying decay=0.9)")
if FLAGS.dt_dir == "":
FLAGS.dt_dir = (date.today() + timedelta(1 - 1)).strftime('%Y%m%d')
FLAGS.model_dir = FLAGS.model_dir + FLAGS.dt_dir
if FLAGS.train:
data = read_libsvm(FLAGS.data_dir)
random.shuffle(data)
valid_data = read_libsvm(FLAGS.valid_dir)
train_data = data[:(int)(len(data) * FLAGS.split_ratio)]
test_data = data[(int)(len(data) * FLAGS.split_ratio):]
print('read finish')
print('train data size:', (len(train_data), len(train_data[0][0])))
print('test data size:', (len(test_data), len(test_data[0][0])))
train_size = len(train_data)
test_size = len(test_data)
min_round = FLAGS.min_round
num_round = FLAGS.num_round
early_stop_round = FLAGS.early_stop_round
batch_size = FLAGS.batch_size
deep_afm_params = {