├── src
├── __init__.py
└── DIN.py
├── img
└── submit_v1.png
├── data
├── README.md
└── prepare_data_v1.py
├── fuxictr_version.py
├── requirements.txt
├── config
├── base_config
│ ├── dataset_config.yaml
│ └── model_config.yaml
└── DIN_ebnerd_large_x1_tuner_config_01.yaml
├── run_param_tuner.py
├── .gitignore
├── run_expid.py
├── submit.py
├── README.md
└── LICENSE
/src/__init__.py:
--------------------------------------------------------------------------------
1 | from .DIN import *
2 |
3 |
4 |
5 |
--------------------------------------------------------------------------------
/img/submit_v1.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/reczoo/RecSys2024_CTR_Challenge/HEAD/img/submit_v1.png
--------------------------------------------------------------------------------
/data/README.md:
--------------------------------------------------------------------------------
1 | # Dataset
2 |
3 | Directories:
4 | + Ebnerd: raw data
5 | + Ebnerd_large_x1: preprocessed csv data
6 | + ebnerd_large_x1_xxxxxxxx: preprocessed npz data
7 |
--------------------------------------------------------------------------------
/fuxictr_version.py:
--------------------------------------------------------------------------------
1 | """
2 | Please install fuxictr first, or directly add the package to sys.path
3 | """
4 | import fuxictr
5 | assert fuxictr.__version__ == "2.2.3"
6 |
--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | fuxictr==2.2.3
2 | keras_preprocessing
3 | PyYAML
4 | pandas
5 | scikit-learn
6 | numpy
7 | h5py
8 | tqdm
9 | pyarrow
10 | polars<1.0.0
11 |
--------------------------------------------------------------------------------
/config/base_config/dataset_config.yaml:
--------------------------------------------------------------------------------
1 | ### Tiny data for tests only
2 | tiny_seq:
3 | data_root: ../../data/
4 | data_format: npz
5 | train_data: ../../data/tiny_seq/train.npz
6 | valid_data: ../../data/tiny_seq/valid.npz
7 | test_data: ../../data/tiny_seq/test.npz
8 |
9 |
10 |
--------------------------------------------------------------------------------
/run_param_tuner.py:
--------------------------------------------------------------------------------
1 | # =========================================================================
2 | # Copyright (C) 2022. Huawei Technologies Co., Ltd. All rights reserved.
3 | #
4 | # Licensed under the Apache License, Version 2.0 (the "License");
5 | # you may not use this file except in compliance with the License.
6 | # You may obtain a copy of the License at
7 | #
8 | # http://www.apache.org/licenses/LICENSE-2.0
9 | #
10 | # Unless required by applicable law or agreed to in writing, software
11 | # distributed under the License is distributed on an "AS IS" BASIS,
12 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 | # See the License for the specific language governing permissions and
14 | # limitations under the License.
15 | # =========================================================================
16 |
17 | from datetime import datetime
18 | import gc
19 | import argparse
20 | import fuxictr_version
21 | from fuxictr import autotuner
22 |
23 | if __name__ == '__main__':
24 | parser = argparse.ArgumentParser()
25 | parser.add_argument('--config', type=str, default='../config/tuner_config.yaml',
26 | help='The config file for para tuning.')
27 | parser.add_argument('--tag', type=str, default=None, help='Use the tag to determine which expid to run (e.g. 001 for the first expid).')
28 | parser.add_argument('--gpu', nargs='+', default=[-1], help='The list of gpu indexes, -1 for cpu.')
29 | args = vars(parser.parse_args())
30 | gpu_list = args['gpu']
31 | expid_tag = args['tag']
32 |
33 | # generate parameter space combinations
34 | config_dir = autotuner.enumerate_params(args['config'])
35 | autotuner.grid_search(config_dir, gpu_list, expid_tag)
36 |
37 |
--------------------------------------------------------------------------------
/config/base_config/model_config.yaml:
--------------------------------------------------------------------------------
1 | Base:
2 | model_root: './checkpoints/'
3 | num_workers: 3
4 | verbose: 1
5 | early_stop_patience: 2
6 | pickle_feature_encoder: True
7 | save_best_only: True
8 | eval_steps: null
9 | debug_mode: False
10 | group_id: null
11 | use_features: null
12 | feature_specs: null
13 | feature_config: null
14 |
15 | DIN_test:
16 | model: DIN
17 | dataset_id: tiny_seq
18 | loss: 'binary_crossentropy'
19 | metrics: ['logloss', 'AUC']
20 | task: binary_classification
21 | optimizer: adam
22 | learning_rate: 1.0e-3
23 | embedding_regularizer: 0
24 | net_regularizer: 0
25 | batch_size: 128
26 | embedding_dim: 4
27 | dnn_hidden_units: [64, 32]
28 | dnn_activations: relu
29 | attention_hidden_units: [64]
30 | attention_hidden_activations: "Dice"
31 | attention_output_activation: null
32 | attention_dropout: 0
33 | din_target_field: adgroup_id
34 | din_sequence_field: click_sequence
35 | net_dropout: 0
36 | batch_norm: False
37 | epochs: 1
38 | shuffle: True
39 | seed: 2019
40 | monitor: 'AUC'
41 | monitor_mode: 'max'
42 |
43 | DIN_test2:
44 | model: DIN
45 | dataset_id: tiny_seq2
46 | loss: 'binary_crossentropy'
47 | metrics: ['logloss', 'AUC']
48 | task: binary_classification
49 | optimizer: adam
50 | learning_rate: 1.0e-3
51 | embedding_regularizer: 0
52 | net_regularizer: 0
53 | batch_size: 128
54 | embedding_dim: 4
55 | dnn_hidden_units: [64, 32]
56 | dnn_activations: relu
57 | attention_hidden_units: [64]
58 | attention_hidden_activations: "Dice"
59 | attention_output_activation: null
60 | attention_dropout: 0
61 | din_target_field: adgroup_id
62 | din_sequence_field: click_sequence
63 | net_dropout: 0
64 | batch_norm: False
65 | epochs: 1
66 | shuffle: True
67 | seed: 2019
68 | monitor: 'AUC'
69 | monitor_mode: 'max'
70 |
71 | DIN_default: # This is a config template
72 | model: DIN
73 | dataset_id: TBD
74 | loss: 'binary_crossentropy'
75 | metrics: ['logloss', 'AUC']
76 | task: binary_classification
77 | optimizer: adam
78 | learning_rate: 1.0e-3
79 | embedding_regularizer: 0
80 | net_regularizer: 0
81 | batch_size: 10000
82 | embedding_dim: 40
83 | dnn_hidden_units: [500, 500, 500]
84 | dnn_activations: relu
85 | attention_hidden_units: [64]
86 | attention_hidden_activations: "Dice"
87 | attention_output_activation: null
88 | attention_dropout: 0
89 | din_target_field: item_id
90 | din_sequence_field: click_history
91 | din_use_softmax: False
92 | net_dropout: 0
93 | batch_norm: False
94 | epochs: 100
95 | shuffle: True
96 | seed: 2019
97 | monitor: {'AUC': 1, 'logloss': -1}
98 | monitor_mode: 'max'
99 |
100 |
--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | # Byte-compiled / optimized / DLL files
2 | __pycache__/
3 | *.py[cod]
4 | *$py.class
5 |
6 | # C extensions
7 | *.so
8 |
9 | # Distribution / packaging
10 | .Python
11 | build/
12 | develop-eggs/
13 | dist/
14 | downloads/
15 | eggs/
16 | .eggs/
17 | lib/
18 | lib64/
19 | parts/
20 | sdist/
21 | var/
22 | wheels/
23 | share/python-wheels/
24 | *.egg-info/
25 | .installed.cfg
26 | *.egg
27 | MANIFEST
28 |
29 | # PyInstaller
30 | # Usually these files are written by a python script from a template
31 | # before PyInstaller builds the exe, so as to inject date/other infos into it.
32 | *.manifest
33 | *.spec
34 |
35 | # Installer logs
36 | pip-log.txt
37 | pip-delete-this-directory.txt
38 |
39 | # Unit test / coverage reports
40 | htmlcov/
41 | .tox/
42 | .nox/
43 | .coverage
44 | .coverage.*
45 | .cache
46 | nosetests.xml
47 | coverage.xml
48 | *.cover
49 | *.py,cover
50 | .hypothesis/
51 | .pytest_cache/
52 | cover/
53 |
54 | # Translations
55 | *.mo
56 | *.pot
57 |
58 | # Django stuff:
59 | *.log
60 | local_settings.py
61 | db.sqlite3
62 | db.sqlite3-journal
63 |
64 | # Flask stuff:
65 | instance/
66 | .webassets-cache
67 |
68 | # Scrapy stuff:
69 | .scrapy
70 |
71 | # Sphinx documentation
72 | docs/_build/
73 |
74 | # PyBuilder
75 | .pybuilder/
76 | target/
77 |
78 | # Jupyter Notebook
79 | .ipynb_checkpoints
80 |
81 | # IPython
82 | profile_default/
83 | ipython_config.py
84 |
85 | # ignore dataset
86 | Ebnerd_*
87 |
88 | # pyenv
89 | # For a library or package, you might want to ignore these files since the code is
90 | # intended to run in multiple environments; otherwise, check them in:
91 | # .python-version
92 |
93 | # pipenv
94 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
95 | # However, in case of collaboration, if having platform-specific dependencies or dependencies
96 | # having no cross-platform support, pipenv may install dependencies that don't work, or not
97 | # install all needed dependencies.
98 | #Pipfile.lock
99 |
100 | # poetry
101 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
102 | # This is especially recommended for binary packages to ensure reproducibility, and is more
103 | # commonly ignored for libraries.
104 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
105 | #poetry.lock
106 |
107 | # pdm
108 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
109 | #pdm.lock
110 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
111 | # in version control.
112 | # https://pdm.fming.dev/#use-with-ide
113 | .pdm.toml
114 |
115 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
116 | __pypackages__/
117 |
118 | # Celery stuff
119 | celerybeat-schedule
120 | celerybeat.pid
121 |
122 | # SageMath parsed files
123 | *.sage.py
124 |
125 | # Environments
126 | .env
127 | .venv
128 | env/
129 | venv/
130 | ENV/
131 | env.bak/
132 | venv.bak/
133 |
134 | # Spyder project settings
135 | .spyderproject
136 | .spyproject
137 |
138 | # Rope project settings
139 | .ropeproject
140 |
141 | # mkdocs documentation
142 | /site
143 |
144 | # mypy
145 | .mypy_cache/
146 | .dmypy.json
147 | dmypy.json
148 |
149 | # Pyre type checker
150 | .pyre/
151 |
152 | # pytype static type analyzer
153 | .pytype/
154 |
155 | # Cython debug symbols
156 | cython_debug/
157 |
158 | # PyCharm
159 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can
160 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
161 | # and can be added to the global gitignore or merged into this file. For a more nuclear
162 | # option (not recommended) you can uncomment the following to ignore the entire idea folder.
163 | #.idea/
164 |
--------------------------------------------------------------------------------
/run_expid.py:
--------------------------------------------------------------------------------
1 | # =========================================================================
2 | # Copyright (C) 2022. Huawei Technologies Co., Ltd. All rights reserved.
3 | #
4 | # Licensed under the Apache License, Version 2.0 (the "License");
5 | # you may not use this file except in compliance with the License.
6 | # You may obtain a copy of the License at
7 | #
8 | # http://www.apache.org/licenses/LICENSE-2.0
9 | #
10 | # Unless required by applicable law or agreed to in writing, software
11 | # distributed under the License is distributed on an "AS IS" BASIS,
12 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 | # See the License for the specific language governing permissions and
14 | # limitations under the License.
15 | # =========================================================================
16 |
17 |
18 | import os
19 | os.chdir(os.path.dirname(os.path.realpath(__file__)))
20 | import sys
21 | import logging
22 | import fuxictr_version
23 | from fuxictr import datasets
24 | from datetime import datetime
25 | from fuxictr.utils import load_config, set_logger, print_to_json, print_to_list
26 | from fuxictr.features import FeatureMap
27 | from fuxictr.pytorch.dataloaders import RankDataLoader
28 | from fuxictr.pytorch.torch_utils import seed_everything
29 | from fuxictr.preprocess import FeatureProcessor, build_dataset
30 | import src
31 | import gc
32 | import argparse
33 | import os
34 | from pathlib import Path
35 |
36 |
37 | if __name__ == '__main__':
38 | ''' Usage: python run_expid.py --config {config_dir} --expid {experiment_id} --gpu {gpu_device_id}
39 | '''
40 | parser = argparse.ArgumentParser()
41 | parser.add_argument('--config', type=str, default='./config/', help='The config directory.')
42 | parser.add_argument('--expid', type=str, default='DeepFM_test', help='The experiment id to run.')
43 | parser.add_argument('--gpu', type=int, default=-1, help='The gpu index, -1 for cpu')
44 | args = vars(parser.parse_args())
45 |
46 | experiment_id = args['expid']
47 | params = load_config(args['config'], experiment_id)
48 | params['gpu'] = args['gpu']
49 | set_logger(params)
50 | logging.info("Params: " + print_to_json(params))
51 | seed_everything(seed=params['seed'])
52 |
53 | data_dir = os.path.join(params['data_root'], params['dataset_id'])
54 | feature_map_json = os.path.join(data_dir, "feature_map.json")
55 | if params["data_format"] == "csv":
56 | # Build feature_map and transform data
57 | feature_encoder = FeatureProcessor(**params)
58 | params["train_data"], params["valid_data"], params["test_data"] = \
59 | build_dataset(feature_encoder, **params)
60 | feature_map = FeatureMap(params['dataset_id'], data_dir)
61 | feature_map.load(feature_map_json, params)
62 | logging.info("Feature specs: " + print_to_json(feature_map.features))
63 |
64 | model_class = getattr(src, params['model'])
65 | model = model_class(feature_map, **params)
66 | model.count_parameters() # print number of parameters used in model
67 |
68 | train_gen, valid_gen = RankDataLoader(feature_map, stage='train', **params).make_iterator()
69 | model.fit(train_gen, validation_data=valid_gen, **params)
70 |
71 | logging.info('****** Validation evaluation ******')
72 | valid_result = model.evaluate(valid_gen)
73 | del train_gen, valid_gen
74 | gc.collect()
75 |
76 | test_result = {}
77 | result_filename = Path(args['config']).name.replace(".yaml", "") + '.csv'
78 | with open(result_filename, 'a+') as fw:
79 | fw.write(' {},[command] python {},[exp_id] {},[dataset_id] {},[train] {},[val] {},[test] {}\n' \
80 | .format(datetime.now().strftime('%Y%m%d-%H%M%S'),
81 | ' '.join(sys.argv), experiment_id, params['dataset_id'],
82 | "N.A.", print_to_list(valid_result), print_to_list(test_result)))
83 |
--------------------------------------------------------------------------------
/submit.py:
--------------------------------------------------------------------------------
1 | # =========================================================================
2 | # Copyright (C) 2024. FuxiCTR Authors. All rights reserved.
3 | #
4 | # Licensed under the Apache License, Version 2.0 (the "License");
5 | # you may not use this file except in compliance with the License.
6 | # You may obtain a copy of the License at
7 | #
8 | # http://www.apache.org/licenses/LICENSE-2.0
9 | #
10 | # Unless required by applicable law or agreed to in writing, software
11 | # distributed under the License is distributed on an "AS IS" BASIS,
12 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 | # See the License for the specific language governing permissions and
14 | # limitations under the License.
15 | # =========================================================================
16 |
17 | import os
18 | os.chdir(os.path.dirname(os.path.realpath(__file__)))
19 | import sys
20 | import logging
21 | import fuxictr_version
22 | from fuxictr import datasets
23 | from datetime import datetime
24 | from fuxictr.utils import load_config, set_logger, print_to_json, print_to_list
25 | from fuxictr.features import FeatureMap
26 | from fuxictr.pytorch.dataloaders import RankDataLoader
27 | from fuxictr.pytorch.torch_utils import seed_everything
28 | from fuxictr.preprocess import FeatureProcessor, build_dataset
29 | import src
30 | import gc
31 | import argparse
32 | import os
33 | from pathlib import Path
34 | import polars as pl
35 | import shutil
36 | import multiprocessing as mp
37 | import pandas as pd
38 |
39 |
40 | def grank(x):
41 | scores = x["score"].tolist()
42 | tmp = [(i, s) for i, s in enumerate(scores)]
43 | tmp = sorted(tmp, key=lambda y: y[-1], reverse=True)
44 | rank = [(i+1, t[0]) for i, t in enumerate(tmp)]
45 | rank = [str(r[0]) for r in sorted(rank, key=lambda y: y[-1])]
46 | rank = "[" + ",".join(rank) + "]"
47 | return str(x["impression_id"].iloc[0]) + " " + rank
48 |
49 | if __name__ == '__main__':
50 | ''' Usage: python run_expid.py --config {config_dir} --expid {experiment_id} --gpu {gpu_device_id}
51 | '''
52 | parser = argparse.ArgumentParser()
53 | parser.add_argument('--config', type=str, default='./config/', help='The config directory.')
54 | parser.add_argument('--expid', type=str, default='DeepFM_test', help='The experiment id to run.')
55 | parser.add_argument('--gpu', type=int, default=-1, help='The gpu index, -1 for cpu')
56 | args = vars(parser.parse_args())
57 |
58 | experiment_id = args['expid']
59 | params = load_config(args['config'], experiment_id)
60 | params['gpu'] = args['gpu']
61 | set_logger(params)
62 | logging.info("Params: " + print_to_json(params))
63 | seed_everything(seed=params['seed'])
64 |
65 | data_dir = os.path.join(params['data_root'], params['dataset_id'])
66 | feature_map_json = os.path.join(data_dir, "feature_map.json")
67 | if params["data_format"] == "csv":
68 | # Build feature_map and transform data
69 | feature_encoder = FeatureProcessor(**params)
70 | params["train_data"], params["valid_data"], params["test_data"] = \
71 | build_dataset(feature_encoder, **params)
72 | feature_map = FeatureMap(params['dataset_id'], data_dir)
73 | feature_map.load(feature_map_json, params)
74 | logging.info("Feature specs: " + print_to_json(feature_map.features))
75 |
76 | model_class = getattr(src, params['model'])
77 | model = model_class(feature_map, **params)
78 | model.count_parameters() # print number of parameters used in model
79 | model.to(device=model.device)
80 | model.load_weights(model.checkpoint)
81 |
82 | params["batch_size"] = 16000
83 | test_gen = RankDataLoader(feature_map, stage='test', **params).make_iterator()
84 | ans = pl.scan_csv("./data/Ebnerd_large_x1/test.csv")
85 | ans = ans.select(['impression_id', 'user_id']).collect().to_pandas()
86 | logging.info("Predicting scores...")
87 | ans["score"] = model.predict(test_gen)
88 | logging.info("Ranking samples...")
89 | ans = ans.groupby(['impression_id', 'user_id'], sort=False).apply(grank).reset_index(drop=True)
90 | logging.info("Writing results...")
91 | os.makedirs("submit", exist_ok=True)
92 | with open('submit/predictions.txt', "w") as fout:
93 | fout.write("\n".join(ans.to_list()))
94 | shutil.make_archive(f'submit/{experiment_id}', 'zip', 'submit/', 'predictions.txt')
95 | logging.info("All done.")
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | ## RecSys2024_CTR_Challenge
2 |
3 | The RecSys 2024 Challenge: https://www.recsyschallenge.com/2024/
4 |
5 | The Ekstra Bladet RecSys Challenge aims to predict which article a user will click on from a list of articles that were seen during a specific impression. Utilizing the user's click history, session details (like time and device used), and personal metadata (including gender and age), along with a list of candidate news articles listed in an impression log, the challenge's objective is to rank the candidate articles based on the user's personal preferences.
6 |
7 | This baseline is built on top of [FuxiCTR](https://github.com/reczoo/FuxiCTR), a configurable, tunable, and reproducible library for CTR prediction. The library has been selected among [the list of recommended evaluation frameworks](https://github.com/ACMRecSys/recsys-evaluation-frameworks) by the ACM RecSys Conference. By using FuxiCTR, we develop a simple yet strong baseline (AUC: 0.7154) without heavy tuning. We open source the code to help beginers get familar with FuxiCTR and quickly get started on this task.
8 |
9 | 🔥 If you find our code helpful in your competition, please cite the following paper:
10 |
11 | + Jieming Zhu, Jinyang Liu, Shuai Yang, Qi Zhang, Xiuqiang He. [Open Benchmarking for Click-Through Rate Prediction](https://arxiv.org/abs/2009.05794). *The 30th ACM International Conference on Information and Knowledge Management (CIKM)*, 2021.
12 |
13 |
14 | ### Data Preparation
15 |
16 | Note that the dataset is quite large. Preparing the full dataset needs about 1T disk space. Although some optimizations can be made to save space (e.g., store sequence features sperately), we leave it for future exploration.
17 |
18 | 1. Download the datasets at: https://recsys.eb.dk/#dataset
19 |
20 | 2. Unzip the data files to the following
21 |
22 | ```bash
23 | cd ~/RecSys2024_CTR_Challenge/data/Ebnerd/
24 | find -L .
25 |
26 | .
27 | ./train
28 | ./train/history.parquet
29 | ./train/articles.parquet
30 | ./train/behaviors.parquet
31 | ./validation
32 | ./validation/history.parquet
33 | ./validation/behaviors.parquet
34 | ./test
35 | ./test/history.parquet
36 | ./test/articles.parquet
37 | ./test/behaviors.parquet
38 | ./image_embeddings.parquet
39 | ./contrastive_vector.parquet
40 | ./prepare_data_v1.py
41 | ```
42 |
43 | 3. Convert the data to csv format
44 |
45 | ```bash
46 | cd ~/RecSys2024_CTR_Challenge/data/Ebnerd/
47 | python prepare_data_v1.py
48 | ```
49 |
50 | ### Environment
51 |
52 | Please set up the environment as follows. We run the experiments on a P100 GPU server with 16G GPU memory and 750G RAM.
53 |
54 | + torch==1.10.2+cu113
55 | + fuxictr==2.2.3
56 |
57 | ```
58 | conda create -n fuxictr python==3.9
59 | pip install -r requirements.txt
60 | source activate fuxictr
61 | ```
62 |
63 | ### Version 1
64 |
65 | 1. Train the model on train and validation sets:
66 |
67 | ```
68 | python run_param_tuner.py --config config/DIN_ebnerd_large_x1_tuner_config_01.yaml --gpu 0
69 | ```
70 |
71 | We get validation avgAUC: 0.7113. Note that in FuxiCTR, AUC is the global AUC, while avgAUC is averaged over impression ID groups.
72 |
73 | 2. Make predictions on the test set:
74 |
75 | Get the experiment_id from running logs or the result csv file, and then you can run prediction on the test.
76 |
77 | ```
78 | python submit.py --config config/DIN_ebnerd_large_x1_tuner_config_01 --expid DIN_ebnerd_large_x1_001_1860e41e --gpu 1
79 | ```
80 |
81 | 3. Make a submission. We get test AUC: 0.7154.
82 |
83 |
84 |

85 |
86 |
87 | ### Potential Improvements
88 |
89 | + To build the baseline, we simply reuse the DIN model, which is popular for sequential user interest modeling. We encourage to explore some other alternatives for user behavior sequence modeling.
90 | + We currently only consider the click behaviors, but leave out other important singnals of reading times and percentiles. It is desired to consider them with multi-objective modeling.
91 | + We use contrast vectors and image embeddings in a straightforward way. It is interesting to explore other embedding features.
92 | + How to bridge the user sequence modeling with large pretrained models (e.g., Bert, LLMs) is a promising direction to explore.
93 |
94 | ### Discussion
95 | We also welcome contributors to help improve the space and time efficiency of FuxiCTR for handling large-scale sequence datasets. If you have any question, please feel free to open an issue.
96 |
--------------------------------------------------------------------------------
/src/DIN.py:
--------------------------------------------------------------------------------
1 | # =========================================================================
2 | # Copyright (C) 2024. FuxiCTR Authors. All rights reserved.
3 | # Copyright (C) 2022. Huawei Technologies Co., Ltd. All rights reserved.
4 | #
5 | # Licensed under the Apache License, Version 2.0 (the "License");
6 | # you may not use this file except in compliance with the License.
7 | # You may obtain a copy of the License at
8 | #
9 | # http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | # Unless required by applicable law or agreed to in writing, software
12 | # distributed under the License is distributed on an "AS IS" BASIS,
13 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | # See the License for the specific language governing permissions and
15 | # limitations under the License.
16 | # =========================================================================
17 |
18 | import torch
19 | from torch import nn
20 | import numpy as np
21 | from pandas.core.common import flatten
22 | from fuxictr.pytorch.models import BaseModel
23 | from fuxictr.pytorch.layers import FeatureEmbeddingDict, MLP_Block, DIN_Attention, Dice
24 |
25 |
26 | class DIN(BaseModel):
27 | def __init__(self,
28 | feature_map,
29 | model_id="DIN",
30 | gpu=-1,
31 | dnn_hidden_units=[512, 128, 64],
32 | dnn_activations="ReLU",
33 | attention_hidden_units=[64],
34 | attention_hidden_activations="Dice",
35 | attention_output_activation=None,
36 | attention_dropout=0,
37 | learning_rate=1e-3,
38 | embedding_dim=10,
39 | net_dropout=0,
40 | batch_norm=False,
41 | din_target_field=[("item_id", "cate_id")],
42 | din_sequence_field=[("click_history", "cate_history")],
43 | din_use_softmax=False,
44 | embedding_regularizer=None,
45 | net_regularizer=None,
46 | **kwargs):
47 | super(DIN, self).__init__(feature_map,
48 | model_id=model_id,
49 | gpu=gpu,
50 | embedding_regularizer=embedding_regularizer,
51 | net_regularizer=net_regularizer,
52 | **kwargs)
53 | if not isinstance(din_target_field, list):
54 | din_target_field = [din_target_field]
55 | self.din_target_field = din_target_field
56 | if not isinstance(din_sequence_field, list):
57 | din_sequence_field = [din_sequence_field]
58 | self.din_sequence_field = din_sequence_field
59 | assert len(self.din_target_field) == len(self.din_sequence_field), \
60 | "len(din_target_field) != len(din_sequence_field)"
61 | if isinstance(dnn_activations, str) and dnn_activations.lower() == "dice":
62 | dnn_activations = [Dice(units) for units in dnn_hidden_units]
63 | self.feature_map = feature_map
64 | self.embedding_dim = embedding_dim
65 | self.embedding_layer = FeatureEmbeddingDict(feature_map, embedding_dim)
66 | self.attention_layers = nn.ModuleList(
67 | [DIN_Attention(embedding_dim * len(target_field) if type(target_field) == tuple \
68 | else embedding_dim,
69 | attention_units=attention_hidden_units,
70 | hidden_activations=attention_hidden_activations,
71 | output_activation=attention_output_activation,
72 | dropout_rate=attention_dropout,
73 | use_softmax=din_use_softmax)
74 | for target_field in self.din_target_field])
75 | self.dnn = MLP_Block(input_dim=feature_map.sum_emb_out_dim(),
76 | output_dim=1,
77 | hidden_units=dnn_hidden_units,
78 | hidden_activations=dnn_activations,
79 | output_activation=self.output_activation,
80 | dropout_rates=net_dropout,
81 | batch_norm=batch_norm)
82 | self.compile(kwargs["optimizer"], kwargs["loss"], learning_rate)
83 | self.reset_parameters()
84 | self.model_to_device()
85 |
86 | def forward(self, inputs):
87 | X = self.get_inputs(inputs)
88 | feature_emb_dict = self.embedding_layer(X)
89 | for idx, (target_field, sequence_field) in enumerate(zip(self.din_target_field,
90 | self.din_sequence_field)):
91 | target_emb = self.get_embedding(target_field, feature_emb_dict)
92 | sequence_emb = self.get_embedding(sequence_field, feature_emb_dict)
93 | seq_field = list(flatten([sequence_field]))[0] # flatten nested list to pick the first sequence field
94 | mask = X[seq_field].long() != 0 # padding_idx = 0 required
95 | pooling_emb = self.attention_layers[idx](target_emb, sequence_emb, mask)
96 | for field, field_emb in zip(list(flatten([sequence_field])),
97 | pooling_emb.split(self.embedding_dim, dim=-1)):
98 | feature_emb_dict[field] = field_emb
99 | feature_emb = self.embedding_layer.dict2tensor(feature_emb_dict, flatten_emb=True)
100 | y_pred = self.dnn(feature_emb)
101 | return_dict = {"y_pred": y_pred}
102 | return return_dict
103 |
104 | def get_embedding(self, field, feature_emb_dict):
105 | if type(field) == tuple:
106 | emb_list = [feature_emb_dict[f] for f in field]
107 | return torch.cat(emb_list, dim=-1)
108 | else:
109 | return feature_emb_dict[field]
110 |
111 |
--------------------------------------------------------------------------------
/config/DIN_ebnerd_large_x1_tuner_config_01.yaml:
--------------------------------------------------------------------------------
1 | base_config: ./config/base_config/
2 | base_expid: DIN_default
3 | dataset_id: ebnerd_large_x1
4 |
5 | dataset_config:
6 | ebnerd_large_x1:
7 | data_root: ./data/
8 | data_format: csv
9 | train_data: ./data/Ebnerd_large_x1/train.csv
10 | valid_data: ./data/Ebnerd_large_x1/valid.csv
11 | test_data: ./data//Ebnerd_large_x1/test.csv
12 | min_categr_count: 10
13 | data_block_size: 100000
14 | streaming: True
15 | feature_cols:
16 | - {name: impression_id, active: True, dtype: int, type: meta, remap: False}
17 | - {name: user_id, active: True, dtype: str, type: categorical}
18 | - {name: article_id, active: True, dtype: str, type: categorical}
19 | - {name: trigger_id, active: True, dtype: str, type: categorical}
20 | - {name: device_type, active: True, dtype: str, type: categorical}
21 | - {name: is_sso_user, active: True, dtype: str, type: categorical}
22 | - {name: gender, active: True, dtype: str, type: categorical}
23 | - {name: postcode, active: True, dtype: str, type: categorical}
24 | - {name: age, active: True, dtype: str, type: categorical}
25 | - {name: is_subscriber, active: True, dtype: str, type: categorical}
26 | - {name: premium, active: True, dtype: str, type: categorical}
27 | - {name: article_type, active: True, dtype: str, type: categorical}
28 | - {name: ner_clusters, active: True, dtype: str, type: sequence, splitter: ^, max_len: 5, padding: pre}
29 | - {name: topics, active: True, dtype: str, type: sequence, splitter: ^, max_len: 5, padding: pre}
30 | - {name: category, active: True, dtype: str, type: categorical}
31 | - {name: subcategory, active: True, dtype: str, type: sequence, splitter: ^, max_len: 5, padding: pre}
32 | - {name: total_inviews, active: False, dtype: float, type: numeric, fill_na: 0}
33 | - {name: total_pageviews, active: False, dtype: float, type: numeric, fill_na: 0}
34 | - {name: total_read_time, active: False, dtype: float, type: numeric, fill_na: 0}
35 | - {name: sentiment_score, active: False, dtype: float, type: numeric, fill_na: 0}
36 | - {name: sentiment_label, active: True, dtype: str, type: categorical}
37 | - {name: subcat1, active: True, dtype: str, type: categorical}
38 | - {name: hist_id, active: True, dtype: str, type: sequence, splitter: ^, max_len: 50, padding: pre, share_embedding: article_id}
39 | - {name: hist_cat, active: True, dtype: str, type: sequence, splitter: ^, max_len: 50, padding: pre, share_embedding: category}
40 | - {name: hist_subcat1, active: True, dtype: str, type: sequence, splitter: ^, max_len: 50, padding: pre, share_embedding: subcat1}
41 | - {name: hist_sentiment, active: True, dtype: str, type: sequence, splitter: ^, max_len: 50, padding: pre, share_embedding: sentiment_label}
42 | - {name: hist_type, active: True, dtype: str, type: sequence, splitter: ^, max_len: 50, padding: pre, share_embedding: article_type}
43 | - {name: publish_days, active: True, dtype: str, type: categorical}
44 | - {name: publish_hours, active: True, dtype: str, type: categorical}
45 | - {name: impression_hour, active: True, dtype: str, type: categorical}
46 | - {name: impression_weekday, active: True, dtype: str, type: categorical}
47 | - {name: pulish_3day, active: True, dtype: str, type: categorical}
48 | - {name: pulish_7day, active: True, dtype: str, type: categorical}
49 | - {name: article_id_img, active: True, dtype: str, type: categorical, freeze_emb: True,
50 | preprocess: "copy_from(article_id)", pretrain_dim: 64, pretrained_emb: "./data/Ebnerd_large_x1/image_emb_dim64.npz",
51 | pretrain_usage: "init", min_categr_count: 1}
52 | - {name: article_id_text, active: True, dtype: str, type: categorical, freeze_emb: True,
53 | preprocess: "copy_from(article_id)", pretrain_dim: 64, pretrained_emb: "./data/Ebnerd_large_x1/contrast_emb_dim64.npz",
54 | pretrain_usage: "init", min_categr_count: 1}
55 | - {name: hist_id_img, active: True, dtype: str, type: sequence, splitter: ^, max_len: 50, padding: pre, freeze_emb: True,
56 | preprocess: "copy_from(hist_id)", pretrain_dim: 64, pretrained_emb: "./data/Ebnerd_large_x1/image_emb_dim64.npz",
57 | pretrain_usage: "init", min_categr_count: 1, share_embedding: article_id_img}
58 | - {name: hist_id_text, active: True, dtype: str, type: sequence, splitter: ^, max_len: 50, padding: pre, freeze_emb: True,
59 | preprocess: "copy_from(hist_id)", pretrain_dim: 64, pretrained_emb: "./data/Ebnerd_large_x1/contrast_emb_dim64.npz",
60 | pretrain_usage: "init", min_categr_count: 1, share_embedding: article_id_text}
61 | label_col: {name: click, dtype: float}
62 |
63 |
64 | tuner_space:
65 | model_root: './checkpoints/'
66 | feature_specs: [[
67 | {name: hist_id, feature_encoder: null},
68 | {name: hist_cat, feature_encoder: null},
69 | {name: hist_subcat1, feature_encoder: null},
70 | {name: hist_sentiment, feature_encoder: null},
71 | {name: hist_type, feature_encoder: null},
72 | {name: hist_id_img, feature_encoder: "nn.Linear(64, 64, bias=False)"},
73 | {name: hist_id_text, feature_encoder: ["nn.Linear(64, 64, bias=False)"]},
74 | {name: article_id_img, feature_encoder: ["nn.Linear(64, 64, bias=False)"]},
75 | {name: article_id_text, feature_encoder: ["nn.Linear(64, 64, bias=False)"]}
76 | ]]
77 | embedding_dim: 64
78 | dnn_hidden_units: [[1024, 512, 256]]
79 | attention_hidden_units: [[512, 256]]
80 | attention_hidden_activations: ReLU
81 | dnn_activations: ReLU
82 | attention_output_activation: null
83 | din_sequence_field: [[!!python/tuple [hist_id, hist_cat, hist_subcat1, hist_sentiment, hist_type], !!python/tuple [hist_id_img, hist_id_text]]]
84 | din_target_field: [[!!python/tuple [article_id, category, subcat1, sentiment_label, article_type], !!python/tuple [article_id_img, article_id_text]]]
85 | din_use_softmax: False
86 | embedding_regularizer: 1.e-4
87 | attention_dropout: 0.2
88 | net_dropout: 0.1
89 | batch_norm: False
90 | learning_rate: 1.e-3
91 | batch_size: 8192
92 | seed: 20242025
93 | group_id: impression_id
94 | metrics: [[avgAUC, MRR, NDCG(k=5)]]
95 | monitor: avgAUC
--------------------------------------------------------------------------------
/data/prepare_data_v1.py:
--------------------------------------------------------------------------------
1 | # =========================================================================
2 | # Copyright (C) 2024. FuxiCTR Authors. All rights reserved.
3 | #
4 | # Licensed under the Apache License, Version 2.0 (the "License");
5 | # you may not use this file except in compliance with the License.
6 | # You may obtain a copy of the License at
7 | #
8 | # http://www.apache.org/licenses/LICENSE-2.0
9 | #
10 | # Unless required by applicable law or agreed to in writing, software
11 | # distributed under the License is distributed on an "AS IS" BASIS,
12 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 | # See the License for the specific language governing permissions and
14 | # limitations under the License.
15 | # =========================================================================
16 |
17 | import polars as pl
18 | import numpy as np
19 | import os
20 | from pandas.core.common import flatten
21 | from datetime import datetime
22 | from sklearn.decomposition import PCA
23 | import gc
24 |
25 |
26 | # Download the datasets and put them to the following folders
27 | train_path = "./train/"
28 | dev_path = "./validation/"
29 | test_path = "./test/"
30 | dataset_version = "Ebnerd_large_x1"
31 | image_emb_path = "image_embeddings.parquet"
32 | contrast_emb_path = "contrastive_vector.parquet"
33 | MAX_SEQ_LEN = 50
34 |
35 | print("Preprocess news info...")
36 | train_news_file = os.path.join(train_path, "articles.parquet")
37 | train_news = pl.scan_parquet(train_news_file)
38 | test_news_file = os.path.join(test_path, "articles.parquet")
39 | test_news = pl.scan_parquet(test_news_file)
40 | news = pl.concat([train_news, test_news])
41 | news = news.unique(subset=['article_id'])
42 | news = news.fill_null("")
43 |
44 | def map_feat_id_func(df, column, seq_feat=False):
45 | feat_set = set(flatten(df[column].to_list()))
46 | map_dict = dict(zip(list(feat_set), range(1, 1 + len(feat_set))))
47 | if seq_feat:
48 | df = df.with_columns(pl.col(column).apply(lambda x: [map_dict.get(i, 0) for i in x]))
49 | else:
50 | df = df.with_columns(pl.col(column).apply(lambda x: map_dict.get(x, 0)).cast(str))
51 | return df
52 |
53 | def tokenize_seq(df, column, map_feat_id=True, max_seq_length=5, sep="^"):
54 | df = df.with_columns(pl.col(column).apply(lambda x: x[-max_seq_length:]))
55 | if map_feat_id:
56 | df = map_feat_id_func(df, column, seq_feat=True)
57 | df = df.with_columns(pl.col(column).apply(lambda x: f"{sep}".join(str(i) for i in x)))
58 | return df
59 |
60 | news = news.select(['article_id', 'published_time', 'last_modified_time', 'premium',
61 | 'article_type', 'ner_clusters', 'topics', 'category', 'subcategory',
62 | 'total_inviews', 'total_pageviews', 'total_read_time',
63 | 'sentiment_score', 'sentiment_label'])
64 | news = (
65 | news.with_columns(subcat1=pl.col('subcategory').apply(lambda x: str(x[0]) if len(x) > 0 else ""))
66 | .collect()
67 | )
68 | news2cat = dict(zip(news["article_id"].cast(str), news["category"].cast(str)))
69 | news2subcat = dict(zip(news["article_id"].cast(str), news["subcat1"].cast(str)))
70 | news = tokenize_seq(news, 'ner_clusters', map_feat_id=True)
71 | news = tokenize_seq(news, 'topics', map_feat_id=True)
72 | news = tokenize_seq(news, 'subcategory', map_feat_id=False)
73 | news = map_feat_id_func(news, "sentiment_label")
74 | news = map_feat_id_func(news, "article_type")
75 | news2sentiment = dict(zip(news["article_id"].cast(str), news["sentiment_label"]))
76 | news2type = dict(zip(news["article_id"].cast(str), news["article_type"]))
77 | print(news.head())
78 | print("Save news info...")
79 | os.makedirs(dataset_version, exist_ok=True)
80 | with open(f"./{dataset_version}/news_info.jsonl", "w") as f:
81 | f.write(news.write_json(row_oriented=True, pretty=True))
82 |
83 | print("Preprocess behavior data...")
84 |
85 | def join_data(data_path):
86 | history_file = os.path.join(data_path, "history.parquet")
87 | history_df = pl.scan_parquet(history_file)
88 | history_df = history_df.rename({"article_id_fixed": "hist_id",
89 | "read_time_fixed": "hist_read_time",
90 | "impression_time_fixed": "hist_time",
91 | "scroll_percentage_fixed": "hist_scroll_percent"})
92 | history_df = tokenize_seq(history_df, 'hist_id', map_feat_id=False, max_seq_length=MAX_SEQ_LEN)
93 | # history_df["hist_time"] = history_df["hist_time"].map(
94 | # lambda x: [datetime.strptime(v, "%Y-%m-%dT%H:%M:%S.%f") for v in x[-MAX_SEQ_LEN:]])
95 | history_df = history_df.select(["user_id", "hist_id"])
96 | history_df = history_df.with_columns(
97 | pl.col("hist_id").apply(lambda x: "^".join([news2cat.get(i, "") for i in x.split("^")])).alias("hist_cat"),
98 | pl.col("hist_id").apply(lambda x: "^".join([news2subcat.get(i, "") for i in x.split("^")])).alias("hist_subcat1"),
99 | pl.col("hist_id").apply(lambda x: "^".join([news2sentiment.get(i, "") for i in x.split("^")])).alias("hist_sentiment"),
100 | pl.col("hist_id").apply(lambda x: "^".join([news2type.get(i, "") for i in x.split("^")])).alias("hist_type")
101 | )
102 | history_df = history_df.collect()
103 | behavior_file = os.path.join(data_path, "behaviors.parquet")
104 | sample_df = pl.scan_parquet(behavior_file)
105 | if "test/" in data_path:
106 | sample_df = (
107 | sample_df.rename({"article_ids_inview": "article_id"})
108 | .explode('article_id')
109 | )
110 | sample_df = sample_df.with_columns(
111 | pl.lit(None).alias("trigger_id"),
112 | pl.lit(0).alias("click")
113 | )
114 | else:
115 | sample_df = (
116 | sample_df.rename({"article_id": "trigger_id"})
117 | .rename({"article_ids_inview": "article_id"})
118 | .explode('article_id')
119 | .with_columns(click=pl.col("article_id").is_in(pl.col("article_ids_clicked")).cast(pl.Int8))
120 | .drop(["article_ids_clicked"])
121 | )
122 | sample_df = (
123 | sample_df.collect()
124 | .join(news, on='article_id', how="left")
125 | .join(history_df, on='user_id', how="left")
126 | .with_columns(
127 | publish_days=(pl.col('impression_time') - pl.col('published_time')).dt.days().cast(pl.Int32),
128 | publish_hours=(pl.col('impression_time') - pl.col('published_time')).dt.hours().cast(pl.Int32),
129 | impression_hour=pl.col('impression_time').dt.hour().cast(pl.Int32),
130 | impression_weekday=pl.col('impression_time').dt.weekday().cast(pl.Int32)
131 | )
132 | .with_columns(
133 | pl.col("publish_days").clip_max(3).alias("pulish_3day"),
134 | pl.col("publish_days").clip_max(7).alias("pulish_7day"),
135 | pl.col("publish_days").clip_max(30),
136 | pl.col("publish_hours").clip_max(24)
137 | )
138 | .drop(["impression_time", "published_time", "last_modified_time"])
139 | )
140 | print(sample_df.columns)
141 | return sample_df
142 |
143 | train_df = join_data(train_path)
144 | print(train_df.head())
145 | print("Train samples", train_df.shape)
146 | train_df.write_csv(f"./{dataset_version}/train.csv")
147 | del train_df
148 |
149 | valid_df = join_data(dev_path)
150 | print(valid_df.head())
151 | print("Validation samples", valid_df.shape)
152 | valid_df.write_csv(f"./{dataset_version}/valid.csv")
153 | del valid_df
154 | gc.collect()
155 |
156 | test_df = join_data(test_path)
157 | print(test_df.head())
158 | print("Test samples", test_df.shape)
159 | test_df.write_csv(f"./{dataset_version}/test.csv")
160 | del test_df
161 | gc.collect()
162 |
163 | print("Preprocess pretrained embeddings...")
164 | image_emb_df = pl.read_parquet(image_emb_path)
165 | pca = PCA(n_components=64)
166 | image_emb = pca.fit_transform(np.array(image_emb_df["image_embedding"].to_list()))
167 | print("image_embedding.shape", image_emb.shape)
168 | item_dict = {
169 | "key": image_emb_df["article_id"].cast(str),
170 | "value": image_emb
171 | }
172 | print("Save image_emb_dim64.npz...")
173 | np.savez(f"./{dataset_version}/image_emb_dim64.npz", **item_dict)
174 |
175 | contrast_emb_df = pl.read_parquet(contrast_emb_path)
176 | contrast_emb = pca.fit_transform(np.array(contrast_emb_df["contrastive_vector"].to_list()))
177 | print("contrast_emb.shape", contrast_emb.shape)
178 | item_dict = {
179 | "key": contrast_emb_df["article_id"].cast(str),
180 | "value": contrast_emb
181 | }
182 | print("Save contrast_emb_dim64.npz...")
183 | np.savez(f"./{dataset_version}/contrast_emb_dim64.npz", **item_dict)
184 |
185 | print("All done.")
186 |
--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
1 | Apache License
2 | Version 2.0, January 2004
3 | http://www.apache.org/licenses/
4 |
5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6 |
7 | 1. Definitions.
8 |
9 | "License" shall mean the terms and conditions for use, reproduction,
10 | and distribution as defined by Sections 1 through 9 of this document.
11 |
12 | "Licensor" shall mean the copyright owner or entity authorized by
13 | the copyright owner that is granting the License.
14 |
15 | "Legal Entity" shall mean the union of the acting entity and all
16 | other entities that control, are controlled by, or are under common
17 | control with that entity. For the purposes of this definition,
18 | "control" means (i) the power, direct or indirect, to cause the
19 | direction or management of such entity, whether by contract or
20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
21 | outstanding shares, or (iii) beneficial ownership of such entity.
22 |
23 | "You" (or "Your") shall mean an individual or Legal Entity
24 | exercising permissions granted by this License.
25 |
26 | "Source" form shall mean the preferred form for making modifications,
27 | including but not limited to software source code, documentation
28 | source, and configuration files.
29 |
30 | "Object" form shall mean any form resulting from mechanical
31 | transformation or translation of a Source form, including but
32 | not limited to compiled object code, generated documentation,
33 | and conversions to other media types.
34 |
35 | "Work" shall mean the work of authorship, whether in Source or
36 | Object form, made available under the License, as indicated by a
37 | copyright notice that is included in or attached to the work
38 | (an example is provided in the Appendix below).
39 |
40 | "Derivative Works" shall mean any work, whether in Source or Object
41 | form, that is based on (or derived from) the Work and for which the
42 | editorial revisions, annotations, elaborations, or other modifications
43 | represent, as a whole, an original work of authorship. For the purposes
44 | of this License, Derivative Works shall not include works that remain
45 | separable from, or merely link (or bind by name) to the interfaces of,
46 | the Work and Derivative Works thereof.
47 |
48 | "Contribution" shall mean any work of authorship, including
49 | the original version of the Work and any modifications or additions
50 | to that Work or Derivative Works thereof, that is intentionally
51 | submitted to Licensor for inclusion in the Work by the copyright owner
52 | or by an individual or Legal Entity authorized to submit on behalf of
53 | the copyright owner. For the purposes of this definition, "submitted"
54 | means any form of electronic, verbal, or written communication sent
55 | to the Licensor or its representatives, including but not limited to
56 | communication on electronic mailing lists, source code control systems,
57 | and issue tracking systems that are managed by, or on behalf of, the
58 | Licensor for the purpose of discussing and improving the Work, but
59 | excluding communication that is conspicuously marked or otherwise
60 | designated in writing by the copyright owner as "Not a Contribution."
61 |
62 | "Contributor" shall mean Licensor and any individual or Legal Entity
63 | on behalf of whom a Contribution has been received by Licensor and
64 | subsequently incorporated within the Work.
65 |
66 | 2. Grant of Copyright License. Subject to the terms and conditions of
67 | this License, each Contributor hereby grants to You a perpetual,
68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69 | copyright license to reproduce, prepare Derivative Works of,
70 | publicly display, publicly perform, sublicense, and distribute the
71 | Work and such Derivative Works in Source or Object form.
72 |
73 | 3. Grant of Patent License. Subject to the terms and conditions of
74 | this License, each Contributor hereby grants to You a perpetual,
75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76 | (except as stated in this section) patent license to make, have made,
77 | use, offer to sell, sell, import, and otherwise transfer the Work,
78 | where such license applies only to those patent claims licensable
79 | by such Contributor that are necessarily infringed by their
80 | Contribution(s) alone or by combination of their Contribution(s)
81 | with the Work to which such Contribution(s) was submitted. If You
82 | institute patent litigation against any entity (including a
83 | cross-claim or counterclaim in a lawsuit) alleging that the Work
84 | or a Contribution incorporated within the Work constitutes direct
85 | or contributory patent infringement, then any patent licenses
86 | granted to You under this License for that Work shall terminate
87 | as of the date such litigation is filed.
88 |
89 | 4. Redistribution. You may reproduce and distribute copies of the
90 | Work or Derivative Works thereof in any medium, with or without
91 | modifications, and in Source or Object form, provided that You
92 | meet the following conditions:
93 |
94 | (a) You must give any other recipients of the Work or
95 | Derivative Works a copy of this License; and
96 |
97 | (b) You must cause any modified files to carry prominent notices
98 | stating that You changed the files; and
99 |
100 | (c) You must retain, in the Source form of any Derivative Works
101 | that You distribute, all copyright, patent, trademark, and
102 | attribution notices from the Source form of the Work,
103 | excluding those notices that do not pertain to any part of
104 | the Derivative Works; and
105 |
106 | (d) If the Work includes a "NOTICE" text file as part of its
107 | distribution, then any Derivative Works that You distribute must
108 | include a readable copy of the attribution notices contained
109 | within such NOTICE file, excluding those notices that do not
110 | pertain to any part of the Derivative Works, in at least one
111 | of the following places: within a NOTICE text file distributed
112 | as part of the Derivative Works; within the Source form or
113 | documentation, if provided along with the Derivative Works; or,
114 | within a display generated by the Derivative Works, if and
115 | wherever such third-party notices normally appear. The contents
116 | of the NOTICE file are for informational purposes only and
117 | do not modify the License. You may add Your own attribution
118 | notices within Derivative Works that You distribute, alongside
119 | or as an addendum to the NOTICE text from the Work, provided
120 | that such additional attribution notices cannot be construed
121 | as modifying the License.
122 |
123 | You may add Your own copyright statement to Your modifications and
124 | may provide additional or different license terms and conditions
125 | for use, reproduction, or distribution of Your modifications, or
126 | for any such Derivative Works as a whole, provided Your use,
127 | reproduction, and distribution of the Work otherwise complies with
128 | the conditions stated in this License.
129 |
130 | 5. Submission of Contributions. Unless You explicitly state otherwise,
131 | any Contribution intentionally submitted for inclusion in the Work
132 | by You to the Licensor shall be under the terms and conditions of
133 | this License, without any additional terms or conditions.
134 | Notwithstanding the above, nothing herein shall supersede or modify
135 | the terms of any separate license agreement you may have executed
136 | with Licensor regarding such Contributions.
137 |
138 | 6. Trademarks. This License does not grant permission to use the trade
139 | names, trademarks, service marks, or product names of the Licensor,
140 | except as required for reasonable and customary use in describing the
141 | origin of the Work and reproducing the content of the NOTICE file.
142 |
143 | 7. Disclaimer of Warranty. Unless required by applicable law or
144 | agreed to in writing, Licensor provides the Work (and each
145 | Contributor provides its Contributions) on an "AS IS" BASIS,
146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 | implied, including, without limitation, any warranties or conditions
148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 | PARTICULAR PURPOSE. You are solely responsible for determining the
150 | appropriateness of using or redistributing the Work and assume any
151 | risks associated with Your exercise of permissions under this License.
152 |
153 | 8. Limitation of Liability. In no event and under no legal theory,
154 | whether in tort (including negligence), contract, or otherwise,
155 | unless required by applicable law (such as deliberate and grossly
156 | negligent acts) or agreed to in writing, shall any Contributor be
157 | liable to You for damages, including any direct, indirect, special,
158 | incidental, or consequential damages of any character arising as a
159 | result of this License or out of the use or inability to use the
160 | Work (including but not limited to damages for loss of goodwill,
161 | work stoppage, computer failure or malfunction, or any and all
162 | other commercial damages or losses), even if such Contributor
163 | has been advised of the possibility of such damages.
164 |
165 | 9. Accepting Warranty or Additional Liability. While redistributing
166 | the Work or Derivative Works thereof, You may choose to offer,
167 | and charge a fee for, acceptance of support, warranty, indemnity,
168 | or other liability obligations and/or rights consistent with this
169 | License. However, in accepting such obligations, You may act only
170 | on Your own behalf and on Your sole responsibility, not on behalf
171 | of any other Contributor, and only if You agree to indemnify,
172 | defend, and hold each Contributor harmless for any liability
173 | incurred by, or claims asserted against, such Contributor by reason
174 | of your accepting any such warranty or additional liability.
175 |
176 | END OF TERMS AND CONDITIONS
177 |
178 | APPENDIX: How to apply the Apache License to your work.
179 |
180 | To apply the Apache License to your work, attach the following
181 | boilerplate notice, with the fields enclosed by brackets "[]"
182 | replaced with your own identifying information. (Don't include
183 | the brackets!) The text should be enclosed in the appropriate
184 | comment syntax for the file format. We also recommend that a
185 | file or class name and description of purpose be included on the
186 | same "printed page" as the copyright notice for easier
187 | identification within third-party archives.
188 |
189 | Copyright [2024] FuxiCTR Team
190 |
191 | Licensed under the Apache License, Version 2.0 (the "License");
192 | you may not use this file except in compliance with the License.
193 | You may obtain a copy of the License at
194 |
195 | http://www.apache.org/licenses/LICENSE-2.0
196 |
197 | Unless required by applicable law or agreed to in writing, software
198 | distributed under the License is distributed on an "AS IS" BASIS,
199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 | See the License for the specific language governing permissions and
201 | limitations under the License.
202 |
--------------------------------------------------------------------------------