├── .gitignore ├── Airflow_DIP ├── .gitignore ├── README.md ├── bin │ └── create_dag_from_template.py ├── dags │ ├── __init__.py │ ├── embedding_dag.py │ ├── embedding_dag_extended.py │ ├── lib │ │ ├── __init__.py │ │ └── create_graph.py │ └── test_pipeline.py ├── requirements.txt ├── scripts │ ├── __init__.py │ ├── basic_example │ │ ├── __init__.py │ │ ├── copy_file.py │ │ ├── create_file.py │ │ └── run_config.json │ └── embedding_example │ │ ├── __init__.py │ │ ├── compare_models.py │ │ ├── config.py │ │ ├── evaluate_embedding.py │ │ ├── get_informative_terms.py │ │ ├── load_data.py │ │ ├── run_config.json │ │ ├── run_config_extended.json │ │ ├── train_embedding.py │ │ └── util.py └── templates │ └── template_pipeline.py ├── Cross_Validation_Imbalanced_Datasets ├── Breast_cancer_data_processing.ipynb ├── README.md ├── cross-validation.ipynb ├── data │ ├── breast-cancer-wisconsin.data.txt │ └── data_updated.csv ├── feature_distributions.png └── requirements.txt ├── Individual_Model_Optimization ├── Individual_Model_Blog_Code.ipynb ├── README.md └── requirements.txt └── README.md /.gitignore: -------------------------------------------------------------------------------- 1 | .idea 2 | **/__pycache__ 3 | */Airflow_DIP/venv/ -------------------------------------------------------------------------------- /Airflow_DIP/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/.gitignore -------------------------------------------------------------------------------- /Airflow_DIP/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/README.md -------------------------------------------------------------------------------- /Airflow_DIP/bin/create_dag_from_template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/bin/create_dag_from_template.py -------------------------------------------------------------------------------- /Airflow_DIP/dags/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Airflow_DIP/dags/embedding_dag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/dags/embedding_dag.py -------------------------------------------------------------------------------- /Airflow_DIP/dags/embedding_dag_extended.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/dags/embedding_dag_extended.py -------------------------------------------------------------------------------- /Airflow_DIP/dags/lib/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/dags/lib/__init__.py -------------------------------------------------------------------------------- /Airflow_DIP/dags/lib/create_graph.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/dags/lib/create_graph.py -------------------------------------------------------------------------------- /Airflow_DIP/dags/test_pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/dags/test_pipeline.py -------------------------------------------------------------------------------- /Airflow_DIP/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/requirements.txt -------------------------------------------------------------------------------- /Airflow_DIP/scripts/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Airflow_DIP/scripts/basic_example/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Airflow_DIP/scripts/basic_example/copy_file.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/scripts/basic_example/copy_file.py -------------------------------------------------------------------------------- /Airflow_DIP/scripts/basic_example/create_file.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/scripts/basic_example/create_file.py -------------------------------------------------------------------------------- /Airflow_DIP/scripts/basic_example/run_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/scripts/basic_example/run_config.json -------------------------------------------------------------------------------- /Airflow_DIP/scripts/embedding_example/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Airflow_DIP/scripts/embedding_example/compare_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/scripts/embedding_example/compare_models.py -------------------------------------------------------------------------------- /Airflow_DIP/scripts/embedding_example/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/scripts/embedding_example/config.py -------------------------------------------------------------------------------- /Airflow_DIP/scripts/embedding_example/evaluate_embedding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/scripts/embedding_example/evaluate_embedding.py -------------------------------------------------------------------------------- /Airflow_DIP/scripts/embedding_example/get_informative_terms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/scripts/embedding_example/get_informative_terms.py -------------------------------------------------------------------------------- /Airflow_DIP/scripts/embedding_example/load_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/scripts/embedding_example/load_data.py -------------------------------------------------------------------------------- /Airflow_DIP/scripts/embedding_example/run_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/scripts/embedding_example/run_config.json -------------------------------------------------------------------------------- /Airflow_DIP/scripts/embedding_example/run_config_extended.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/scripts/embedding_example/run_config_extended.json -------------------------------------------------------------------------------- /Airflow_DIP/scripts/embedding_example/train_embedding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/scripts/embedding_example/train_embedding.py -------------------------------------------------------------------------------- /Airflow_DIP/scripts/embedding_example/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/scripts/embedding_example/util.py -------------------------------------------------------------------------------- /Airflow_DIP/templates/template_pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Airflow_DIP/templates/template_pipeline.py -------------------------------------------------------------------------------- /Cross_Validation_Imbalanced_Datasets/Breast_cancer_data_processing.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Cross_Validation_Imbalanced_Datasets/Breast_cancer_data_processing.ipynb -------------------------------------------------------------------------------- /Cross_Validation_Imbalanced_Datasets/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Cross_Validation_Imbalanced_Datasets/README.md -------------------------------------------------------------------------------- /Cross_Validation_Imbalanced_Datasets/cross-validation.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Cross_Validation_Imbalanced_Datasets/cross-validation.ipynb -------------------------------------------------------------------------------- /Cross_Validation_Imbalanced_Datasets/data/breast-cancer-wisconsin.data.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Cross_Validation_Imbalanced_Datasets/data/breast-cancer-wisconsin.data.txt -------------------------------------------------------------------------------- /Cross_Validation_Imbalanced_Datasets/data/data_updated.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Cross_Validation_Imbalanced_Datasets/data/data_updated.csv -------------------------------------------------------------------------------- /Cross_Validation_Imbalanced_Datasets/feature_distributions.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Cross_Validation_Imbalanced_Datasets/feature_distributions.png -------------------------------------------------------------------------------- /Cross_Validation_Imbalanced_Datasets/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Cross_Validation_Imbalanced_Datasets/requirements.txt -------------------------------------------------------------------------------- /Individual_Model_Optimization/Individual_Model_Blog_Code.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Individual_Model_Optimization/Individual_Model_Blog_Code.ipynb -------------------------------------------------------------------------------- /Individual_Model_Optimization/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/Individual_Model_Optimization/README.md -------------------------------------------------------------------------------- /Individual_Model_Optimization/requirements.txt: -------------------------------------------------------------------------------- 1 | numpy==1.16.1 2 | matplotlib==3.0.2 -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lumiata/tech_blog/HEAD/README.md --------------------------------------------------------------------------------