Initial commit

.gitignore

@@ -0,0 +1,181 @@
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor  
+#  Cursor is an AI-powered code editor.`.cursorignore` specifies files/directories to 
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.10
+
+WORKDIR /home/app
+
+RUN apt-get update -y 
+RUN apt-get install nano unzip -y
+RUN apt install curl -y
+
+RUN curl -fsSL https://get.deta.dev/cli.sh | sh
+
+COPY requirements.txt /dependencies/requirements.txt
+RUN pip install -r /dependencies/requirements.txt
+
+COPY . /home/app
+
+CMD gunicorn app:app  --bind 0.0.0.0:$PORT --worker-class uvicorn.workers.UvicornWorker 

app.py

@@ -0,0 +1,109 @@
+import os
+import uvicorn
+import pandas as pd
+from pydantic import BaseModel
+from fastapi import FastAPI
+import mlflow
+import os
+from dotenv import load_dotenv
+
+description = """
+
+# [Fraud Detection](https://github.com/Olivier-52/fraud_detection.git)
+
+Fast API backend to predict if a payment is fraud or not from : https://huggingface.co/spaces/sdacelo/real-time-fraud-detection
+
+## Machine-Learning 
+
+Where you can:
+* `/predict` : prediction for a single value
+
+Check out documentation for more information on each endpoint. 
+"""
+
+tags_metadata = [
+    {
+        "name": "Predictions",
+        "description": "Endpoints that uses our Machine Learning model",
+    },
+]
+
+load_dotenv()
+
+# Variables MLflow : URI de tracking, nom du modèle et stage
+MLFLOW_TRACKING_APP_URI = os.getenv("MLFLOW_TRACKING_APP_URI")
+MODEL_NAME = os.getenv("MODEL_NAME", "Fraud_Detection_Project")
+STAGE = os.getenv("STAGE", "production")
+
+# Variables AWS pour accéder au bucket S3 qui contient les artifacts de MLflow
+os.environ["AWS_ACCESS_KEY_ID"] = os.getenv("AWS_ACCESS_KEY_ID")
+os.environ["AWS_SECRET_ACCESS_KEY"] = os.getenv("AWS_SECRET_ACCESS_KEY")
+
+# Variables globales pour stocker le modèle
+mlflow.set_tracking_uri(MLFLOW_TRACKING_APP_URI)
+model_uri = f"models:/{MODEL_NAME}@{STAGE}"
+model = mlflow.sklearn.load_model(model_uri)
+
+app = FastAPI(
+    title="API for Fraud Detection Project",
+    description=description,
+    version="1.0",
+    contact={
+        "name": "Olivier-52",
+        "url": "https://huggingface.co/Olivier-52",
+    },
+    openapi_tags=tags_metadata,)
+
+@app.get("/")
+def index():
+    """Return a message to the user.
+
+    This endpoint does not take any parameters and returns a message
+    to the user. It is used to test the API.
+
+    Returns:
+        str: A message to the user.
+    """
+    return "Hello world! Go to /docs to try the API."
+
+class PredictionFeatures(BaseModel):
+    category : str
+    amt : float
+    merch_fraud_level :str
+    city_fraud_level : str
+    state_fraud_level : str
+    zip_fraud_level : str
+    job_fraud_level : str
+    age_fraud_level : str
+
+@app.post("/predict", tags=["Predictions"])
+def predict(features: PredictionFeatures):
+
+    """
+    Predict if a payment is fraud or not.
+
+    This endpoint takes a set of features as input and returns a prediction
+    of whether the payment is fraud or not.
+
+    Parameters:
+        features (PredictionFeatures): A set of features describing the payment
+
+    Returns:
+        dict: A dictionary containing the prediction of whether the payment is fraud or not
+    """
+    df = pd.DataFrame({
+        "category" : [features.category],
+        "amt" : [features.amt],
+        "merch_fraud_level" : [features.merch_fraud_level],
+        "city_fraud_level" : [features.city_fraud_level],
+        "state_fraud_level" : [features.state_fraud_level],
+        "zip_fraud_level" : [features.zip_fraud_level],
+        "job_fraud_level" : [features.job_fraud_level],
+        "age_fraud_level" : [features.age_fraud_level]
+    })
+    
+    prediction = model.predict(df)[0]
+    return {"prediction": float(prediction)}
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=8000)

requirements.txt

@@ -0,0 +1,13 @@
+mlflow==2.21.3
+scikit-learn==1.4.2
+requests>=2.31.0,<3
+fastapi 
+uvicorn[standard]
+pydantic 
+typing 
+pandas 
+gunicorn 
+openpyxl 
+boto3
+python-multipart
+dotenv