initial commit

Author: Kurdzik

.github/workflows/build_push.yaml

@@ -0,0 +1,59 @@
+name: Build and push ml endpoint
+
+env:
+  TAG: $(echo ${GITHUB_SHA::8}-$(date +'%Y-%m-%d'))
+  REPO_NAME: portfolio
+  APP_NAME: ml-api
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+    types:
+      - closed
+
+jobs:
+  build:
+    runs-on: self-hosted
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+
+      - name: Login to DockerHub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.DOCKERHUB_LOGIN  }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+          registry: srv17.mikr.us:40073
+
+      - name: build and push
+        run: |
+          docker build \
+          -t srv17.mikr.us:40073/${{ env.REPO_NAME }}/${{ env.APP_NAME}}:${{ env.TAG }} \
+          -f Dockerfile .
+
+          docker push srv17.mikr.us:40073/${{ env.REPO_NAME }}/${{ env.APP_NAME}}:${{ env.TAG }}
+          
+          docker build \
+          -t srv17.mikr.us:40073/${{ env.REPO_NAME }}/${{ env.APP_NAME}}:latest \
+          -f Dockerfile .
+          
+          docker push srv17.mikr.us:40073/${{ env.REPO_NAME }}/${{ env.APP_NAME}}:latest
+  redeploy:
+    runs-on: self-hosted
+    needs: build
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+
+      - name: Deploy
+        run: |
+          cd kubernetes && sh create_secrets_and_deploy.sh \
+          ${{ secrets.DOCKERHUB_LOGIN  }} \
+          ${{ secrets.DOCKERHUB_TOKEN }}

.gitignore copy

@@ -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/#use-with-ide
+.pdm.toml
+
+# 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/
+demo.ipynb
+kubernetes/secret.yaml

.pre-commit-config.yaml

@@ -0,0 +1,32 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.3.0
+    hooks:
+    -   id: check-builtin-literals
+        args: ['--no-allow-dict-kwargs']
+    -   id: check-docstring-first
+    -   id: debug-statements
+    -   id: double-quote-string-fixer
+    -   id: end-of-file-fixer
+        exclude: '.*\.txt$'
+    -   id: name-tests-test
+    -   id: flake8
+        args: ['--max-line-length', '120']
+    -   id: trailing-whitespace
+-   repo: https://github.com/asottile/reorder_python_imports
+    rev: v1.6.1
+    hooks:
+    -   id: reorder-python-imports
+        language_version: python3
+-   repo: https://github.com/asottile/add-trailing-comma
+    rev: v1.4.1
+    hooks:
+        - id: add-trailing-comma
+-   repo: https://github.com/Yelp/detect-secrets.git
+    rev: v1.4.0
+    hooks:
+    -   id: detect-secrets
+        name: Detect secrets
+        language: python
+        entry: detect-secrets-hook
+        args: ['scan']

Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.10-slim-buster
+
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y libgomp1
+
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+ENV GIT_PYTHON_REFRESH=quiet
+
+EXPOSE 8000
+COPY . .
+
+ENTRYPOINT ["uvicorn", "api:app", "--host", "0.0.0.0", "--port", "8000"]

api.py

@@ -0,0 +1,58 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+import pandas as pd
+from otomoto.preprocessing import Preprocessing
+from otomoto.model_training import ModelTrainer
+from otomoto.utils import get_unique_values
+from otomoto.model_predictions import Predictor
+from otomoto.input_models import OtomotoInputData
+from fastapi import Body
+from fastapi import HTTPException
+
+app = FastAPI()
+
+
+@app.post("/api/v1/otomoto/train_model",tags=['model_training'])
+async def train_model():
+    try:
+        data_processor = Preprocessing()
+        data_processor.preprocess_data()
+
+        input_data = data_processor.get_data()
+
+        model_trainer = ModelTrainer(input_data, target_column='price')
+        model_trainer.preprocess()
+        model_trainer.train_models()
+
+    except Exception as error:
+        raise HTTPException(status_code=500, detail=f"Error occurred: {error}")
+
+    return {"message": "Models trained and registered successfully"}
+
+
+@app.post("/api/v1/otomoto/get_dropdown_values",tags=['dropdown_values'])
+async def get_dropdown_values():
+    try:
+        unique_values = get_unique_values()
+    except Exception as error:
+        raise HTTPException(status_code=500, detail=f"Error occurred: {error}")
+
+    return unique_values
+
+
+@app.post("/api/v1/otomoto/predict",tags=['model_predictions'])
+async def predict(data: OtomotoInputData = Body(...)):
+    json_data = data.model_dump()
+    model_name = json_data['model_name']
+    transformer_name = 'otomoto_data_encoder'
+    features = {k: v for k, v in json_data.items() if k != 'model_name'}    
+    try:
+        predictor = Predictor(model_name, transformer_name)
+        pred = predictor.predict(features)
+    
+    except Exception as error:
+        raise HTTPException(status_code=500, detail=f"Error occurred: {error}")
+    
+    return {"message": pred}
+    
+