Initial commit

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.JPG filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/

classification/classifier.py

@@ -0,0 +1,57 @@
+from sklearn.ensemble import AdaBoostClassifier
+from sklearn.datasets import load_iris
+from sklearn.model_selection import train_test_split
+import joblib
+import pandas as pd
+import os
+
+
+class Classifier:
+    def __init__(self):
+        pass
+
+    def train_and_save(self):
+        print("\nIRIS model training...")
+        iris = load_iris()
+        ada = AdaBoostClassifier(n_estimators=5)
+
+        X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.1, random_state=42)
+        model = ada.fit(X_train, y_train)
+
+        print(f"Model score: {ada.score(X_train, y_train):.3f}")
+        print(f"Test Accuracy: {ada.score(X_test, y_test):.3f}")
+
+        current_dir = os.path.dirname(os.path.abspath(__file__))
+        parent_dir = os.path.dirname(current_dir)
+        test_data_csv_path = os.path.join(parent_dir, "data", "test_data.csv")
+
+        pd.concat([pd.DataFrame(X_test), pd.DataFrame(y_test, columns=['4'])], axis=1).to_csv(test_data_csv_path,
+                                                                                              index=False)
+
+        model_path = os.path.join(parent_dir, "models", "model.pkl")
+        joblib.dump(model, model_path)
+        print(f"Model saved to {model_path}")
+
+
+    def load_and_test(self, data):
+        print("\nIRIS model prediction...")
+
+        current_dir = os.path.dirname(os.path.abspath(__file__))
+        parent_dir = os.path.dirname(current_dir)
+        model_path = os.path.join(parent_dir, "models", "model.pkl")
+        model = joblib.load(model_path)
+
+        features = data.get('features', [])
+
+        if not isinstance(features, list) or not all(isinstance(sample, list) for sample in features):
+            raise ValueError("Input data should be a list of feature vectors.")
+
+        # Predict the class
+        predictions = model.predict(features).tolist()
+        probabilities = model.predict_proba(features).tolist()
+
+        # Map predictions to class labels
+        iris_types = {0: 'setosa', 1: 'versicolor', 2: 'virginica'}
+        prediction_labels = [iris_types[pred] for pred in predictions]
+
+        return {"predictions": prediction_labels, "probabilities": probabilities}

main.py

@@ -0,0 +1,27 @@
+from classification.classifier import Classifier
+import json
+
+
+if __name__ == "__main__":
+    cls = Classifier()
+
+    # Training
+    cls.train_and_save()
+
+    # Testing
+    data = { "features": [
+        [6.5, 3.0, 5.8, 2.2],
+        [6.1, 2.8, 4.7, 1.2]
+    ]}
+    results = cls.load_and_test(data)
+    print("results:", results)
+
+    # Response similar to HTTP call
+    response = {
+        'statusCode': 200,
+        'body': json.dumps({
+            'predictions': results["predictions"],
+            'probabilities': results["probabilities"]
+        })
+    }
+    print("Example Full API response: ", response)