├── .gitignore ├── README.md ├── app.py └── requirements.txt /.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 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/#use-with-ide 110 | .pdm.toml 111 | 112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 113 | __pypackages__/ 114 | 115 | # Celery stuff 116 | celerybeat-schedule 117 | celerybeat.pid 118 | 119 | # SageMath parsed files 120 | *.sage.py 121 | 122 | # Environments 123 | .env 124 | .venv 125 | myenv/ 126 | env/ 127 | venv/ 128 | ENV/ 129 | env.bak/ 130 | venv.bak/ 131 | 132 | # Spyder project settings 133 | .spyderproject 134 | .spyproject 135 | 136 | # Rope project settings 137 | .ropeproject 138 | 139 | # mkdocs documentation 140 | /site 141 | 142 | # mypy 143 | .mypy_cache/ 144 | .dmypy.json 145 | dmypy.json 146 | 147 | # Pyre type checker 148 | .pyre/ 149 | 150 | # pytype static type analyzer 151 | .pytype/ 152 | 153 | # Cython debug symbols 154 | cython_debug/ 155 | 156 | # PyCharm 157 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 158 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 159 | # and can be added to the global gitignore or merged into this file. For a more nuclear 160 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 161 | #.idea/ -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ## ML FLow experiements 2 | 3 | MLFLOW_TRACKING_URI=https://dagshub.com/krishnaik06/mlflowexperiments.mlflow \ 4 | MLFLOW_TRACKING_USERNAME=krishnaik06 \ 5 | MLFLOW_TRACKING_PASSWORD=7104284f1bb44ece21e0e2adb4e36a250ae3251f \ 6 | python script.py 7 | 8 | -------------------------------------------------------------------------------- /app.py: -------------------------------------------------------------------------------- 1 | # The data set used in this example is from http://archive.ics.uci.edu/ml/datasets/Wine+Quality 2 | # P. Cortez, A. Cerdeira, F. Almeida, T. Matos and J. Reis. 3 | # Modeling wine preferences by data mining from physicochemical properties. In Decision Support Systems, Elsevier, 47(4):547-553, 2009. 4 | 5 | import os 6 | import warnings 7 | import sys 8 | 9 | import pandas as pd 10 | import numpy as np 11 | from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score 12 | from sklearn.model_selection import train_test_split 13 | from sklearn.linear_model import ElasticNet 14 | from urllib.parse import urlparse 15 | import mlflow 16 | from mlflow.models import infer_signature 17 | import mlflow.sklearn 18 | 19 | import logging 20 | 21 | logging.basicConfig(level=logging.WARN) 22 | logger = logging.getLogger(__name__) 23 | 24 | 25 | def eval_metrics(actual, pred): 26 | rmse = np.sqrt(mean_squared_error(actual, pred)) 27 | mae = mean_absolute_error(actual, pred) 28 | r2 = r2_score(actual, pred) 29 | return rmse, mae, r2 30 | 31 | 32 | if __name__ == "__main__": 33 | warnings.filterwarnings("ignore") 34 | np.random.seed(40) 35 | 36 | # Read the wine-quality csv file from the URL 37 | csv_url = ( 38 | "https://raw.githubusercontent.com/mlflow/mlflow/master/tests/datasets/winequality-red.csv" 39 | ) 40 | try: 41 | data = pd.read_csv(csv_url, sep=";") 42 | except Exception as e: 43 | logger.exception( 44 | "Unable to download training & test CSV, check your internet connection. Error: %s", e 45 | ) 46 | 47 | # Split the data into training and test sets. (0.75, 0.25) split. 48 | train, test = train_test_split(data) 49 | 50 | # The predicted column is "quality" which is a scalar from [3, 9] 51 | train_x = train.drop(["quality"], axis=1) 52 | test_x = test.drop(["quality"], axis=1) 53 | train_y = train[["quality"]] 54 | test_y = test[["quality"]] 55 | 56 | alpha = float(sys.argv[1]) if len(sys.argv) > 1 else 0.5 57 | l1_ratio = float(sys.argv[2]) if len(sys.argv) > 2 else 0.5 58 | 59 | with mlflow.start_run(): 60 | lr = ElasticNet(alpha=alpha, l1_ratio=l1_ratio, random_state=42) 61 | lr.fit(train_x, train_y) 62 | 63 | predicted_qualities = lr.predict(test_x) 64 | 65 | (rmse, mae, r2) = eval_metrics(test_y, predicted_qualities) 66 | 67 | print("Elasticnet model (alpha={:f}, l1_ratio={:f}):".format(alpha, l1_ratio)) 68 | print(" RMSE: %s" % rmse) 69 | print(" MAE: %s" % mae) 70 | print(" R2: %s" % r2) 71 | 72 | mlflow.log_param("alpha", alpha) 73 | mlflow.log_param("l1_ratio", l1_ratio) 74 | mlflow.log_metric("rmse", rmse) 75 | mlflow.log_metric("r2", r2) 76 | mlflow.log_metric("mae", mae) 77 | 78 | #predictions = lr.predict(train_x) 79 | #signature = infer_signature(train_x, predictions) 80 | 81 | ## For Remote server only(DAGShub) 82 | 83 | remote_server_uri="https://dagshub.com/krishnaik06/mlflowexperiments.mlflow" 84 | mlflow.set_tracking_uri(remote_server_uri) 85 | 86 | tracking_url_type_store = urlparse(mlflow.get_tracking_uri()).scheme 87 | 88 | # Model registry does not work with file store 89 | if tracking_url_type_store != "file": 90 | # Register the model 91 | # There are other ways to use the Model Registry, which depends on the use case, 92 | # please refer to the doc for more information: 93 | # https://mlflow.org/docs/latest/model-registry.html#api-workflow 94 | mlflow.sklearn.log_model( 95 | lr, "model", registered_model_name="ElasticnetWineModel" 96 | ) 97 | else: 98 | mlflow.sklearn.log_model(lr, "model") 99 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | mlflow==2.5.0 --------------------------------------------------------------------------------