Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

format according to pep8 #493

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

format according to pep8 #493

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7e1ae68
format according to pep8
Mtax Oct 10, 2022
5e89b80
add standard docstring for better usage.
Mtax Oct 10, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
87 changes: 64 additions & 23 deletions examples/run_dien.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,22 +1,53 @@
"""Simple example for DIEN model."""

import numpy as np
import tensorflow as tf

from deepctr.feature_column import SparseFeat, VarLenSparseFeat, DenseFeat,get_feature_names
from deepctr.feature_column import (DenseFeat, SparseFeat, VarLenSparseFeat,
get_feature_names)
from deepctr.models import DIEN


def get_xy_fd(use_neg=False, hash_flag=False):
feature_columns = [SparseFeat('user', 3, embedding_dim=10, use_hash=hash_flag),
SparseFeat('gender', 2, embedding_dim=4, use_hash=hash_flag),
SparseFeat('item_id', 3 + 1, embedding_dim=8, use_hash=hash_flag),
SparseFeat('cate_id', 2 + 1, embedding_dim=4, use_hash=hash_flag),
DenseFeat('pay_score', 1)]
"""Get features, labels, feature list.

_extended_summary_

Args:
use_neg (bool, optional): Whether se negative instance that samples
from item set except the clicked item. Defaults to False.
hash_flag (bool, optional): Whether hash the input to [0,num_buckets).
Defaults to False.

Returns:
x (dict): features.
y (np.array): label.
feature_columns (list): feature columns.
behavior_feature_list (list): Features to activate the historical behaviors.
"""
feature_columns = [
SparseFeat(
'user', 3, embedding_dim=10, use_hash=hash_flag),
SparseFeat(
'gender', 2, embedding_dim=4, use_hash=hash_flag),
SparseFeat(
'item_id', 3 + 1, embedding_dim=8,
use_hash=hash_flag),
SparseFeat(
'cate_id', 2 + 1, embedding_dim=4,
use_hash=hash_flag),
DenseFeat('pay_score', 1)]

feature_columns += [
VarLenSparseFeat(SparseFeat('hist_item_id', vocabulary_size=3 + 1, embedding_dim=8, embedding_name='item_id'),
maxlen=4, length_name="seq_length"),
VarLenSparseFeat(SparseFeat('hist_cate_id', 2 + 1, embedding_dim=4, embedding_name='cate_id'), maxlen=4,
length_name="seq_length")]
VarLenSparseFeat(
SparseFeat(
'hist_item_id', vocabulary_size=3 + 1, embedding_dim=8,
embedding_name='item_id'),
maxlen=4, length_name="seq_length"),
VarLenSparseFeat(
SparseFeat(
'hist_cate_id', 2 + 1, embedding_dim=4,
embedding_name='cate_id'),
maxlen=4, length_name="seq_length")]

behavior_feature_list = ["item_id", "cate_id"]
uid = np.array([0, 1, 2])
Expand All @@ -30,20 +61,30 @@ def get_xy_fd(use_neg=False, hash_flag=False):

behavior_length = np.array([3, 3, 2])

feature_dict = {'user': uid, 'gender': ugender, 'item_id': iid, 'cate_id': cate_id,
'hist_item_id': hist_iid, 'hist_cate_id': hist_cate_id,
'pay_score': score, "seq_length": behavior_length}
feature_dict = {
'user': uid, 'gender': ugender, 'item_id': iid, 'cate_id': cate_id,
'hist_item_id': hist_iid, 'hist_cate_id': hist_cate_id,
'pay_score': score, "seq_length": behavior_length}

if use_neg:
feature_dict['neg_hist_item_id'] = np.array([[1, 2, 3, 0], [1, 2, 3, 0], [1, 2, 0, 0]])
feature_dict['neg_hist_cate_id'] = np.array([[1, 2, 2, 0], [1, 2, 2, 0], [1, 2, 0, 0]])
feature_dict['neg_hist_item_id'] = np.array(
[[1, 2, 3, 0], [1, 2, 3, 0], [1, 2, 0, 0]])
feature_dict['neg_hist_cate_id'] = np.array(
[[1, 2, 2, 0], [1, 2, 2, 0], [1, 2, 0, 0]])
feature_columns += [
VarLenSparseFeat(SparseFeat('neg_hist_item_id', vocabulary_size=3 + 1, embedding_dim=8, embedding_name='item_id'),
maxlen=4, length_name="seq_length"),
VarLenSparseFeat(SparseFeat('neg_hist_cate_id', 2 + 1, embedding_dim=4, embedding_name='cate_id'),
maxlen=4, length_name="seq_length")]
VarLenSparseFeat(
SparseFeat(
'neg_hist_item_id', vocabulary_size=3 + 1, embedding_dim=8,
embedding_name='item_id'),
maxlen=4, length_name="seq_length"),
VarLenSparseFeat(
SparseFeat(
'neg_hist_cate_id', 2 + 1, embedding_dim=4,
embedding_name='cate_id'),
maxlen=4, length_name="seq_length")]

x = {name: feature_dict[name] for name in get_feature_names(feature_columns)}
x = {name: feature_dict[name]
for name in get_feature_names(feature_columns)}
y = np.array([1, 0, 1])
return x, y, feature_columns, behavior_feature_list

Expand All @@ -54,8 +95,8 @@ def get_xy_fd(use_neg=False, hash_flag=False):
USE_NEG = True
x, y, feature_columns, behavior_feature_list = get_xy_fd(use_neg=USE_NEG)

model = DIEN(feature_columns, behavior_feature_list,
dnn_hidden_units=[4, 4, 4], dnn_dropout=0.6, gru_type="AUGRU", use_negsampling=USE_NEG)
model = DIEN(feature_columns, behavior_feature_list, dnn_hidden_units=[
4, 4, 4], dnn_dropout=0.6, gru_type="AUGRU", use_negsampling=USE_NEG)

model.compile('adam', 'binary_crossentropy',
metrics=['binary_crossentropy'])
Expand Down