How realworlddatascience/realworlddatascience.github.io works
This repository is the source for the Real World Data Science website, with articles and accompanying examples. The sampled Auburn case-study code implements a distinct workflow: configure a method and dataset, prepare product/retail data and embeddings, train or tune an ANN or random-forest model, then evaluate matches. The graph also preserves the site’s article-content branch. Source excerpts support the Auburn call relationships; README context supports the site’s purpose, but does not describe its rendering or publication internals.
Main entry points: main.py Configuration entry · ann.py ANN operations · evaluation_script.py Ranking evaluation · embedding.py Embedding interface
Components 18
Website content
- Articles and case studies
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/main.py - Auburn example
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code
Auburn workflow
- Configuration entry
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/main.py - Method types
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/user_types.py
Data preparation
- Data preparation
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/prep_data.py - Embedding interface
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/interface/embedding.py - GloVe embeddings
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/embedding/glove.py - BERT embeddings
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/embedding/bert.py - Data utilities
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/utils.py
Modeling and evaluation
- Random forest
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/random_forest.py - Legacy random forest
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/random_forest_old.py - ANN operations
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/ann.py - Legacy ANN
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/ann_old.py - ANN model
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/ann_model_and_datamodule/ann_model.py - ANN data module
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/ann_model_and_datamodule/ann_datamodule.py - Training callbacks
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/ann_model_and_datamodule/callbacks.py - Ranking evaluation
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/official_eval/evaluation_script.py
Other components
- Readers and contributors
Connections 19
- Readers and contributors → Articles and case studies: read and contribute
README.md - Articles and case studies → Auburn example: includes example
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/main.py - Configuration entry → Method types: uses method types
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/main.py - Configuration entry → Data preparation: prepares data
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/main.py - Configuration entry → Random forest: dispatches method
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/main.py - Configuration entry → ANN operations: dispatches method
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/main.py - Configuration entry → Data utilities: uses utilities
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/main.py - Data preparation → Embedding interface: requests embeddings
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/prep_data.py - Embedding interface → GloVe embeddings: dispatches embedding
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/interface/embedding.py - Embedding interface → BERT embeddings: dispatches embedding
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/interface/embedding.py - Random forest → GloVe embeddings: uses embeddings
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/random_forest.py - Random forest → Ranking evaluation: evaluates results
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/random_forest.py - Legacy random forest → GloVe embeddings: uses embeddings
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/random_forest_old.py - Legacy random forest → Ranking evaluation: evaluates results
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/random_forest_old.py - ANN operations → ANN data module: creates data module
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/ann.py - ANN operations → ANN model: creates model
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/ann.py - ANN operations → Training callbacks: registers callbacks
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/ann.py - ANN model → Ranking evaluation: uses metrics
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/ann_model_and_datamodule/ann_model.py - Legacy ANN → Ranking evaluation: uses metrics
applied-insights/case-studies/posts/2023/08/21/_code/auburn/Source Code/src/utilities/methods/ann_old.py