add Dockerfile

Dockerfile

@@ -1,7 +1,45 @@
-FROM python:3.9-alpine
+# Build from a LINUX lightweight version of Anaconda
+FROM continuumio/miniconda3
 
-COPY . /app/
+# Update packages and install nano unzip and curl
+RUN apt-get update
+RUN apt-get install nano unzip curl -y
 
-RUN echo "Cookies and cheesecakes are my favorites" > favorites_cakes.txt
+# Install AWS cli - Necessary since we are going to interact with S3 
+RUN curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip"
+RUN unzip awscliv2.zip
+RUN ./aws/install
 
-CMD python /app/app.py
+# THIS IS SPECIFIC TO HUGGINFACE
+# We create a new user named "user" with ID of 1000
+RUN useradd -m -u 1000 user
+# We switch from "root" (default user when creating an image) to "user" 
+USER user
+# We set two environmnet variables 
+# so that we can give ownership to all files in there afterwards
+# we also add /home/user/.local/bin in the $PATH environment variable 
+# PATH environment variable sets paths to look for installed binaries
+# We update it so that Linux knows where to look for binaries if we were to install them with "user".
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+# We set working directory to $HOME/app (<=> /home/user/app)
+WORKDIR $HOME/app
+
+# Copy all local files to /home/user/app with "user" as owner of these files
+# Always use --chown=user when using HUGGINGFACE to avoid permission errors
+COPY --chown=user . $HOME/app
+
+# Copy and install dependencies 
+COPY requirements.txt /requirements.txt
+RUN pip install -r /requirements.txt
+
+# Launch mlflow server 
+# Here we chose to have $PORT as environment variable but you could have hard coded 7860 
+# If you are sure to push into production 
+# Advantage to use an env variable is that your code is more portable if you were to deploy to another 
+# type of server
+CMD mlflow server -p $PORT \
+    --host 0.0.0.0 \
+    --backend-store-uri $BACKEND_STORE_URI \
+    --default-artifact-root $ARTIFACT_STORE_URI

requirements.txt

@@ -1,73 +1,10 @@
-alembic==1.16.4
-annotated-types==0.7.0
-anyio==4.9.0
-blinker==1.9.0
-cachetools==5.5.2
-certifi==2025.7.14
-charset-normalizer==3.4.2
-click==8.2.1
-cloudpickle==3.1.1
-contourpy==1.3.2
-cycler==0.12.1
-databricks-sdk==0.58.0
-docker==7.1.0
-fastapi==0.116.1
-Flask==3.1.1
-fonttools==4.58.5
-gitdb==4.0.12
-GitPython==3.1.44
-google-auth==2.40.3
-graphene==3.4.3
-graphql-core==3.2.6
-graphql-relay==3.2.0
-greenlet==3.2.3
-gunicorn==23.0.0
-h11==0.16.0
-idna==3.10
-importlib_metadata==8.7.0
-itsdangerous==2.2.0
-Jinja2==3.1.6
-joblib==1.5.1
-kiwisolver==1.4.8
-Mako==1.3.10
-MarkupSafe==3.0.2
-matplotlib==3.10.3
-mlflow==3.1.1
-mlflow-skinny==3.1.1
-narwhals==1.47.0
-numpy==2.3.1
-opentelemetry-api==1.35.0
-opentelemetry-sdk==1.35.0
-opentelemetry-semantic-conventions==0.56b0
-packaging==25.0
-pandas==2.3.1
-pillow==11.3.0
-plotly==6.2.0
-protobuf==6.31.1
-pyarrow==20.0.0
-pyasn1==0.6.1
-pyasn1_modules==0.4.2
-pydantic==2.11.7
-pydantic_core==2.33.2
-pyparsing==3.2.3
-python-dateutil==2.9.0.post0
-pytz==2025.2
-PyYAML==6.0.2
-requests==2.32.4
-rsa==4.9.1
-scikit-learn==1.7.0
-scipy==1.16.0
-six==1.17.0
-smmap==5.0.2
-sniffio==1.3.1
-SQLAlchemy==2.0.41
-sqlparse==0.5.3
-starlette==0.47.1
-threadpoolctl==3.6.0
-typing-inspection==0.4.1
-typing_extensions==4.14.1
-tzdata==2025.2
-urllib3==2.5.0
-uvicorn==0.35.0
-Werkzeug==3.1.3
-zipp==3.23.0
+boto3
+pandas 
+gunicorn 
+streamlit 
+scikit-learn 
+matplotlib 
+seaborn 
+plotly
+mlflow
+psycopg2-binary