├── requirements.txt ├── bank_model.skops ├── README.md ├── deployment.py ├── .prefectignore ├── ml_workflow-deployment.yaml ├── main.py ├── .gitignore └── LICENSE /requirements.txt: -------------------------------------------------------------------------------- 1 | pandas 2 | scikit-learn 3 | numpy 4 | matplotlib 5 | skops 6 | prefect -------------------------------------------------------------------------------- /bank_model.skops: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kingabzpro/ML-Workflow-Orchestration-With-Prefect/HEAD/bank_model.skops -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # ML-Workflow-Orchestration-With-Prefect 2 | An introductory project to streamline the machine learning pipeline using Prefect and Discord Notifications, from data ingestion to model saving 3 | -------------------------------------------------------------------------------- /deployment.py: -------------------------------------------------------------------------------- 1 | from prefect import flow 2 | 3 | if __name__ == "__main__": 4 | flow.from_source( 5 | source="https://github.com/kingabzpro/ML-Workflow-Orchestration-With-Prefect.git", 6 | entrypoint="main.py:ml_workflow", 7 | ).deploy( 8 | name="first-prefect-deployment", 9 | work_pool_name="DC-work-pool", 10 | cron="*/5 * * * *", 11 | ) 12 | -------------------------------------------------------------------------------- /.prefectignore: -------------------------------------------------------------------------------- 1 | # prefect artifacts 2 | .prefectignore 3 | 4 | # python artifacts 5 | __pycache__/ 6 | *.py[cod] 7 | *$py.class 8 | *.egg-info/ 9 | *.egg 10 | 11 | # Type checking artifacts 12 | .mypy_cache/ 13 | .dmypy.json 14 | dmypy.json 15 | .pyre/ 16 | 17 | # IPython 18 | profile_default/ 19 | ipython_config.py 20 | *.ipynb_checkpoints/* 21 | 22 | # Environments 23 | .python-version 24 | .env 25 | .venv 26 | env/ 27 | venv/ 28 | 29 | # MacOS 30 | .DS_Store 31 | 32 | # Dask 33 | dask-worker-space/ 34 | 35 | # Editors 36 | .idea/ 37 | .vscode/ 38 | 39 | # VCS 40 | .git/ 41 | .hg/ 42 | -------------------------------------------------------------------------------- /ml_workflow-deployment.yaml: -------------------------------------------------------------------------------- 1 | ### 2 | ### A complete description of a Prefect Deployment for flow 'ml-workflow' 3 | ### 4 | name: ml_workflow_bank_churn 5 | description: null 6 | version: 5ab76bc07471372eb60aa1469844a895 7 | # The work queue that will handle this deployment's runs 8 | work_queue_name: default 9 | work_pool_name: DC-work-pool 10 | tags: 11 | - dev 12 | parameters: {} 13 | schedule: null 14 | schedules: [] 15 | is_schedule_active: null 16 | infra_overrides: {} 17 | 18 | ### 19 | ### DO NOT EDIT BELOW THIS LINE 20 | ### 21 | flow_name: ml-workflow 22 | manifest_path: null 23 | infrastructure: 24 | type: process 25 | env: {} 26 | labels: {} 27 | name: null 28 | command: null 29 | stream_output: true 30 | working_dir: null 31 | _block_document_id: 32f51283-7f99-4bec-9f78-aad042c9fa40 32 | _block_document_name: anonymous-3cfa57d3-84df-4e96-8339-f596c8b315f2 33 | _is_anonymous: true 34 | block_type_slug: process 35 | _block_type_slug: process 36 | storage: null 37 | path: C:\Repository\GitHub\ML-Workflow-Orchestration-With-Prefect 38 | entrypoint: main.py:ml_workflow 39 | parameter_openapi_schema: 40 | title: Parameters 41 | type: object 42 | properties: 43 | filename: 44 | title: filename 45 | default: train.csv 46 | position: 0 47 | type: string 48 | required: null 49 | definitions: null 50 | timestamp: '2024-03-14T17:32:23.266177+00:00' 51 | triggers: [] 52 | enforce_parameter_schema: null 53 | -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import skops.io as sio 3 | from prefect import flow, task 4 | from sklearn.feature_selection import SelectKBest, chi2 5 | from sklearn.impute import SimpleImputer 6 | from sklearn.linear_model import LogisticRegression 7 | from sklearn.metrics import accuracy_score, f1_score 8 | from sklearn.model_selection import train_test_split 9 | from sklearn.preprocessing import MinMaxScaler, OrdinalEncoder 10 | 11 | 12 | @task 13 | def load_data(filename: str): 14 | bank_df = pd.read_csv(filename, index_col="id", nrows=1000) 15 | bank_df = bank_df.drop(["CustomerId", "Surname"], axis=1) 16 | bank_df = bank_df.sample(frac=1) 17 | return bank_df 18 | 19 | 20 | @task 21 | def preprocessing(bank_df: pd.DataFrame): 22 | cat_col = [1, 2] 23 | num_col = [0, 3, 4, 5, 6, 7, 8, 9] 24 | 25 | # Filling missing categorical values 26 | cat_impute = SimpleImputer(strategy="most_frequent") 27 | bank_df.iloc[:, cat_col] = cat_impute.fit_transform(bank_df.iloc[:, cat_col]) 28 | 29 | # Filling missing numerical values 30 | num_impute = SimpleImputer(strategy="median") 31 | bank_df.iloc[:, num_col] = num_impute.fit_transform(bank_df.iloc[:, num_col]) 32 | 33 | # Encode categorical features as an integer array. 34 | cat_encode = OrdinalEncoder() 35 | bank_df.iloc[:, cat_col] = cat_encode.fit_transform(bank_df.iloc[:, cat_col]) 36 | 37 | # Scaling numerical values. 38 | scaler = MinMaxScaler() 39 | bank_df.iloc[:, num_col] = scaler.fit_transform(bank_df.iloc[:, num_col]) 40 | return bank_df 41 | 42 | 43 | @task 44 | def data_split(bank_df: pd.DataFrame): 45 | # Splitting data into training and testing sets 46 | X = bank_df.drop(["Exited"], axis=1) 47 | y = bank_df.Exited 48 | 49 | X_train, X_test, y_train, y_test = train_test_split( 50 | X, y, test_size=0.3, random_state=125 51 | ) 52 | return X_train, X_test, y_train, y_test 53 | # Identify numerical and categorical columns 54 | 55 | 56 | @task 57 | def train_model(X_train, X_test, y_train): 58 | # Selecting the best features 59 | KBest = SelectKBest(chi2, k="all") 60 | X_train = KBest.fit_transform(X_train, y_train) 61 | X_test = KBest.transform(X_test) 62 | 63 | # Train the model 64 | model = LogisticRegression(max_iter=1000, random_state=125) 65 | model.fit(X_train, y_train) 66 | 67 | return model 68 | 69 | 70 | @task 71 | def get_prediction(X_test, model: LogisticRegression): 72 | return model.predict(X_test) 73 | 74 | 75 | @task 76 | def evaluate_model(y_test, prediction: pd.DataFrame): 77 | accuracy = accuracy_score(y_test, prediction) 78 | f1 = f1_score(y_test, prediction, average="macro") 79 | 80 | print("Accuracy:", str(round(accuracy, 2) * 100) + "%", "F1:", round(f1, 2)) 81 | 82 | 83 | @task 84 | def save_model(model: LogisticRegression): 85 | sio.dump(model, "bank_model.skops") 86 | 87 | 88 | @flow(log_prints=True) 89 | def ml_workflow(filename: str = "train.csv"): 90 | data = load_data(filename) 91 | prep_data = preprocessing(data) 92 | X_train, X_test, y_train, y_test = data_split(prep_data) 93 | model = train_model(X_train, X_test, y_train) 94 | predictions = get_prediction(X_test, model) 95 | evaluate_model(y_test, predictions) 96 | save_model(model) 97 | 98 | 99 | if __name__ == "__main__": 100 | ml_workflow() 101 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | #folders 2 | mlruns 3 | 4 | # Byte-compiled / optimized / DLL files 5 | __pycache__/ 6 | *.py[cod] 7 | *$py.class 8 | 9 | # C extensions 10 | *.so 11 | 12 | # Distribution / packaging 13 | .Python 14 | build/ 15 | develop-eggs/ 16 | dist/ 17 | downloads/ 18 | eggs/ 19 | .eggs/ 20 | lib/ 21 | lib64/ 22 | parts/ 23 | sdist/ 24 | var/ 25 | wheels/ 26 | share/python-wheels/ 27 | *.egg-info/ 28 | .installed.cfg 29 | *.egg 30 | MANIFEST 31 | 32 | # PyInstaller 33 | # Usually these files are written by a python script from a template 34 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 35 | *.manifest 36 | *.spec 37 | 38 | # Installer logs 39 | pip-log.txt 40 | pip-delete-this-directory.txt 41 | 42 | # Unit test / coverage reports 43 | htmlcov/ 44 | .tox/ 45 | .nox/ 46 | .coverage 47 | .coverage.* 48 | .cache 49 | nosetests.xml 50 | coverage.xml 51 | *.cover 52 | *.py,cover 53 | .hypothesis/ 54 | .pytest_cache/ 55 | cover/ 56 | 57 | # Translations 58 | *.mo 59 | *.pot 60 | 61 | # Django stuff: 62 | *.log 63 | local_settings.py 64 | db.sqlite3 65 | db.sqlite3-journal 66 | 67 | # Flask stuff: 68 | instance/ 69 | .webassets-cache 70 | 71 | # Scrapy stuff: 72 | .scrapy 73 | 74 | # Sphinx documentation 75 | docs/_build/ 76 | 77 | # PyBuilder 78 | .pybuilder/ 79 | target/ 80 | 81 | # Jupyter Notebook 82 | .ipynb_checkpoints 83 | 84 | # IPython 85 | profile_default/ 86 | ipython_config.py 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 | -------------------------------------------------------------------------------- /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 [yyyy] [name of copyright owner] 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 | --------------------------------------------------------------------------------