{"id":24101350,"url":"https://github.com/yxtay/recommender-tensorflow","last_synced_at":"2025-05-08T01:11:42.845Z","repository":{"id":82529103,"uuid":"124250860","full_name":"yxtay/recommender-tensorflow","owner":"yxtay","description":"Recommendation Models in TensorFlow","archived":false,"fork":false,"pushed_at":"2018-12-28T05:50:57.000Z","size":48,"stargazers_count":46,"open_issues_count":1,"forks_count":13,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-05-08T01:11:37.689Z","etag":null,"topics":["cloud-ml-engine","deep-learning","deepfm","factorization-machine","google-cloud-ml-engine","google-cloud-platform","movielens","recommendation-engine","recommender-system","tensorflow","tensorflow-distributed","wide-and-deep"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yxtay.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-03-07T14:51:36.000Z","updated_at":"2025-01-20T10:10:33.000Z","dependencies_parsed_at":null,"dependency_job_id":"b60569e8-515d-4cb9-93b5-66587ea0c33a","html_url":"https://github.com/yxtay/recommender-tensorflow","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yxtay%2Frecommender-tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yxtay%2Frecommender-tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yxtay%2Frecommender-tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yxtay%2Frecommender-tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yxtay","download_url":"https://codeload.github.com/yxtay/recommender-tensorflow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252978779,"owners_count":21834917,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cloud-ml-engine","deep-learning","deepfm","factorization-machine","google-cloud-ml-engine","google-cloud-platform","movielens","recommendation-engine","recommender-system","tensorflow","tensorflow-distributed","wide-and-deep"],"created_at":"2025-01-10T16:55:10.058Z","updated_at":"2025-05-08T01:11:42.836Z","avatar_url":"https://github.com/yxtay.png","language":"Python","readme":"# Recommendation Models in TensorFlow\n\nThis repository attempts to implement models for recommendation engines in TensorFlow using the Estimator API with feature columns. \n\n\nThe trainer module in this repository also allows for distributed model training and evaluation on Google Cloud Platform. Please refer to [distributed](distributed.md).\n\n## Models\n\n- Linear classifer: [`linear.py`](trainers/linear.py)\n- DNN classifier: [`deep.py`](trainers/deep.py)\n- Linear \u0026 DNN classifier: [`linear_deep.py`](trainers/linear_deep.py)\n- DeepFM: [`deep_fm.py`](trainers/deep_fm.py)\n\n### DeepFM\n\n#### Model Parameters\n\n- `categorical_columns`: categorical feature columns input\n- `numeric_columns`: numeric feature columns input\n- `use_linear`: flag to include linear structure of model (default: `True`)\n- `use_mf`: flag to include factorisation machine structure of model (default: `True`)\n- `use_dnn`: flag to include deep structure of model (default: `True`)\n- `embedding_size`: embedding size of latent factors (default: `4`)\n- `hidden_units`: layer sizes of hidden units of deep structure (default: `[16, 16]`)\n- `activation_fn`: activation function of deep structure (default: `tf.nn.relu`)\n- `dropout`: dropout rate of deep structure (default: `0`)\n- `optimizer`: learning optimiser (default: `\"Adam\"`)\n- `learning_rate`: learning rate (default: `0.001`)\n\n## Setup\n\n```bash\n# clone repo\ngit clone git@github.com:yxtay/recommender-tensorflow.git \u0026\u0026 cd recommender-tensorflow\n\n# create conda environment\nconda env create -f=environment.yml\n\n# activate environment\nsource activate dl\n```\n## Download \u0026 Process Data\n\nThe [MovieLens 100K Dataset](https://grouplens.org/datasets/movielens/100k/) is used for demonstration purpose. The following script downloads the data, processes and enriches it with a few basic features and serialises it to `csv`.\n\n```bash\n# downloads and processes movielens 100k dataset\npython -m src.data.ml_100k local\n```\n\n**Usage**\n\n```\npython -m src.data.ml_100k local -h\n\nusage: ml_100k.py local [-h] [--url URL] [--dest DEST] [--log-path LOG_PATH]\n\noptional arguments:\n  -h, --help           show this help message and exit\n  --url URL            url of MovieLens 100k data (default:\n                       http://files.grouplens.org/datasets/movielens/ml-\n                       100k.zip)\n  --dest DEST          destination directory for downloaded and extracted\n                       files (default: data)\n  --log-path LOG_PATH  path of log file (default: main.log)\n```\n\n## Train \u0026 Evaluate DeepFM\n\n**Usage**\n```\npython -m trainers.deep_fm -h\n\nusage: deep_fm.py [-h] [--train-csv TRAIN_CSV] [--test-csv TEST_CSV]\n                  [--job-dir JOB_DIR] [--restore] [--exclude-linear]\n                  [--exclude-mf] [--exclude-dnn]\n                  [--embedding-size EMBEDDING_SIZE]\n                  [--hidden-units HIDDEN_UNITS [HIDDEN_UNITS ...]]\n                  [--dropout DROPOUT] [--batch-size BATCH_SIZE]\n                  [--train-steps TRAIN_STEPS]\n\noptional arguments:\n  -h, --help            show this help message and exit\n  --train-csv TRAIN_CSV\n                        path to the training csv data (default: data/ml-\n                        100k/train.csv)\n  --test-csv TEST_CSV   path to the test csv data (default: data/ml-\n                        100k/test.csv)\n  --job-dir JOB_DIR     job directory (default: checkpoints/deep_fm)\n  --restore             whether to restore from job_dir\n  --exclude-linear      flag to exclude linear component (default: False)\n  --exclude-mf          flag to exclude mf component (default: False)\n  --exclude-dnn         flag to exclude dnn component (default: False)\n  --embedding-size EMBEDDING_SIZE\n                        embedding size (default: 4)\n  --hidden-units HIDDEN_UNITS [HIDDEN_UNITS ...]\n                        hidden layer specification (default: [16, 16])\n  --dropout DROPOUT     dropout rate (default: 0.1)\n  --batch-size BATCH_SIZE\n                        batch size (default: 32)\n  --train-steps TRAIN_STEPS\n                        number of training steps (default: 20000)\n```\n\n## Tensorboard\n\nYou may inspect model training metrics with Tensorboard.\n\n```bash\ntensorboard --logdir checkpoints/\n```\n\n## Other Models Available\n\n```bash\n# linear model\npython -m trainers.linear\n\n# deep model\npython -m trainers.deep\n\n# wide \u0026 deep model\npython -m trainers.linear_deep\n```\n\n## Distributed\n\nFor distributed model training and evaluation, please refer to [distributed](distributed.md).\n\n## References\n\n- Harper F. M., \u0026 Konstan, J. A. (2015). The MovieLens Datasets: History and Context. ACM Transactions on Interactive Intelligent Systems, 5(4), Article 19, 19 pages. DOI=http://dx.doi.org/10.1145/2827872.\n- Cheng, H. T., Koc, L., Harmsen, J., Shaked, T., Chandra, T., Aradhye, H., ... Shah, H. (2016). Wide \u0026 Deep Learning for Recommender Systems. arXiv:1606.07792 \\[cs.LG\\].\n- Guo, H., Tang, R., Ye, Y., Li, Z., \u0026 He, X. (2017). DeepFM: A Factorization-Machine based Neural Network for CTR Prediction. arXiv:1703.04247 \\[cs.IR\\].\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyxtay%2Frecommender-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyxtay%2Frecommender-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyxtay%2Frecommender-tensorflow/lists"}