Customer-Purchase-Prediction-ML-System
A turnkey MLOps pipeline demonstrating how to go from raw events to real-time predictions at scale.
File Explorer
Download Latest Version (.zip)- airflow-dags.jpg
- data-grip-offline-store.jpg
- data-pipeline-dag.jpg
- feature-retrieval-swagger-ui.jpg
- grafana.jpg
- kafka-connectors.jpg
- kafka-message.jpg
- kafka-to-feast-online-store-job-log.jpg
- kafka-topic-cdc.jpg
- kafka-topic-schema-validation.jpg
- kafka-topic.jpg
- minio-buckets.jpg
- minio-record.jpg
- mlflow-models.jpg
- mlflow-ui.jpg
- nginx-proxy-manager-1.jpg
- nginx-proxy-manager-2.jpg
- ray-dashboard.jpg
- ray-task-details.jpg
- schema-validation-job-log.jpg
- serving-pipeline-swagger-ui.jpg
- signoz-1.jpg
- signoz-2.jpg
- spark-streaming-job.jpg
- training-pipeline-dag.jpg
- training-pipeline-tasks.jpg
- validated-events-to-features-job.jpg
- pipeline.png
- eda.ipynb
- inference.py
- model.ubj
- serving.ipynb
- train.ipynb
- postgresql-cdc.json
- .env.example
- __init__.py
- create_table.py
- Dockerfile
- insert_data.py
- models.py
- postgresql_client.py
- requirements.txt
- run.sh
- start.sh
- validated_events.sql
- .feastignore
- __init__.py
- api.py
- data_sources.py
- Dockerfile
- entities.py
- feature_store.docker.yaml
- feature_store.yaml
- features_view.py
- ingest_stream.py
- offline_write_batch.py
- requirements.txt
- run.sh
- .env.example
- Dockerfile
- dashboards.yaml
- datasources.yaml
- prometheus.yml
- histogramQuantile
- histogramQuantile.go
- alertmanager.yml
- alerts.yml
- clickhouse-cluster.xml
- clickhouse-config.xml
- clickhouse-storage.xml
- clickhouse-users.xml
- custom-function.xml
- docker-compose-core.yaml
- docker-compose-local.yaml
- docker-compose.testing.yaml
- docker-compose.yaml
- keeper_config.xml
- otel-collector-config.yaml
- otel-collector-opamp-config.yaml
- prometheus.yml
- test-app-docker-compose.yaml
- locustfile.py
- nginx-config.conf
- ingest_raw_data.py
- validate_raw_data.py
- load_to_dwh.py
- transform_data.py
- __init__.py
- __init__.py
- data_loader.py
- hyperparameter_tuning.py
- model_trainer.py
- results_saver.py
- data_pipeline.py
- training_pipeline.py
- db_utils.py
- dim_schemas.py
- event_schema.py
- fact_schemas.py
- monitoring.py
- sql_utils.py
- __init__.py
- data_pipeline_config.py
- tune_config.py
- chk.yml
- .ge_store_backend_id
- gold_layer_suite.json
- raw_data_suite.json
- data_docs_custom_styles.css
- .gitignore
- great_expectations.yml
- load_training_data.sql
- analytical_views.sql
- ray_setup.py
- __init__.py
- .env.example
- .gitignore
- docker-compose.orchestration.yaml
- Dockerfile
- requirements.txt
- ecommerce_events.avsc
- sample.parquet
- .env.example
- Dockerfile
- generate_schemas.py
- produce.py
- run.sh
- Dockerfile
- ray_test.py
- requirements.txt
- .dockerignore
- __init__.py
- Dockerfile
- main.py
- online_feature_service.py
- prediction_service.py
- requirements.txt
- avro-1.11.1.jar
- flink-avro-1.17.1.jar
- flink-avro-confluent-registry-1.17.1.jar
- flink-connector-kafka-1.17.1.jar
- flink-table-api-java-1.17.1.jar
- jackson-annotations-2.14.2.jar
- jackson-core-2.14.2.jar
- jackson-databind-2.14.2.jar
- kafka-clients-3.4.0.jar
- kafka-connect-jdbc-10.6.4.jar
- kafka-connect-json-schema-converter-7.5.0.jar
- kafka-schema-registry-7.5.0.jar
- kafka-schema-registry-client-7.5.0.jar
- postgresql-42.4.3.jar
- minio-sink-connector.json
- s3-sink-connector.json
- kafka_sink.py
- kafka_source.py
- check_s3_bucket.py
- deploy_s3_connector.py
- __init___.py
- alert_invalid_events_job.py
- base.py
- schema_validation_job.py
- metrics.py
- .env.example
- main.py
- .dockerignore
- .env.example
- .gitattributes
- .gitignore
- .pre-commit-config.yaml
- .python-version
- docker-compose.cdc.yaml
- docker-compose.data-lake.yaml
- docker-compose.dwh.yaml
- docker-compose.grafana.yaml
- docker-compose.kafka.yaml
- docker-compose.model-registry.yaml
- docker-compose.nginx.yaml
- docker-compose.observability.yaml
- docker-compose.online-store.yaml
- docker-compose.ray.yaml
- docker-compose.serving.yaml
- docker-compose.superset.yaml
- LICENSE
- Makefile
- pyproject.toml
- README.md
- uv.lock
# Installation Guide
1. Get the code
git clone https://github.com/bmd1905/Customer-Purchase-Prediction-ML-System
Downloads the entire project code from GitHub to your computer.
cd Customer-Purchase-Prediction-ML-System
Moves into the project folder you just downloaded.
2. Docker
Easy RecommendedPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker compose -f docker-compose.cdc.yaml up -d --build
Runs the command against the services defined in the compose file.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
3. Python
EasyPrerequisites
pip install -r src/cdc/requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
jupyter notebook
Launches Jupyter in your browser so you can open and run the notebook (.ipynb) files.
If it runs without errors and prints output in the terminal, it worked.
4. Make
MediumPrerequisites
- Git Needed to download the project code from GitHub.
- Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).
make up-network
Compiles the code based on the generated build configuration to produce an executable.
make up-kafka
Compiles the code based on the generated build configuration to produce an executable.
make up-cdc
Compiles the code based on the generated build configuration to produce an executable.
make schema_validation
Compiles the code based on the generated build configuration to produce an executable.
make alert_invalid_events
Compiles the code based on the generated build configuration to produce an executable.
If it finishes without errors, it worked. Try running the generated executable directly.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)