Structured-Data

Exploration of machine learning and deep learning with structured datasets (usually tabular data).

Example Notebooks

• https://github.com/dcpatton/Structured-Data/blob/main/higgs_dnn.ipynb

  Binary classification of numerical data

• https://github.com/dcpatton/Structured-Data/blob/main/kdd_cup_1999.ipynb

  Classificaiton of large imbalanced dataset. Demonstrates use of TensorFlow feature_column

• https://github.com/dcpatton/Structured-Data/blob/main/diabetes_linear_regression.ipynb

  Linear regression in TensorFlow. Also calculation of resulting statistics

• https://github.com/dcpatton/Structured-Data/blob/main/target_encoding_cms_claims.ipynb

  Demonstration of Target Encoding a categorical column with high cardinality

• https://github.com/dcpatton/Structured-Data/blob/main/tf_embedding_cms_claims.ipynb

  Demonstration of Embedding a categorical column with high cardinality

• https://github.com/dcpatton/Structured-Data/blob/main/deep_solar.ipynb

  Large regression problem with lots of imputation techniques