Merge Pytorch branch into main and remove obsolete labs.

.gitignore

@@ -0,0 +1,139 @@
+# Initially taken from Github's Python gitignore file
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+docs/api/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+docs/.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+.idea/
+toy*.py
+.DS_Store
+post/
+toy*.ipynb
+data/
+*.c
+.nes_cache
+toy*.yml
+*.tmp
+
+shell/jina-wizard.sh
+/junit/
+/tests/junit/
+/docs/chapters/proto/docs.md
+
+# IntelliJ IDEA
+*.iml
+.idea
+
+# Data files to ignore
+notebooks/python/sigma_pdm.npy
+notebooks/python/*tmp

README.md

@@ -30,17 +30,17 @@ Analytics labs notebooks, supporting analytics teaching for BSc and MSc courses.
 
 ## Deep Learning
 
-11. [Introduction to Keras and Shallow ANN](notebooks/python/Lab_8_Keras_and_Shallow_Neural_Networks.ipynb): Gentle introduction to Keras and Tensorflow. Updated to Tensorflow 2.0.
+11. [Introduction to Keras, Pytorch, and Shallow ANN](notebooks/python/Lab_8_Keras_and_Shallow_Neural_Networks.ipynb): Gentle introduction to Keras and Pytorch.
 
-12. [Embeddings](notebooks/python/Lab_8_Embeddings.ipynb): How to calculate embedding layers, and how to use pre-trained embeddings. Currently uses Facebook's [fasttext library](https://fasttext.cc/). Updated to Tensorflow 2.0.
+12. [2D CNN and Gradient Backtracing](notebooks/python/Lab_2D_Convolutions.ipynb): 2D Convolutions for image classification. Use of pre-trained models (VGG16), and gradient backtracing to visualize what is being used to discriminate in Pytorch.
 
-13. [1D CNN and Keras' Model API](notebooks/python/Lab_9_ConvNets_for_Text_Analytics.ipynb): Intro to CNN, and how to use Keras' Model API. Also contains an implementation of [Kim et al. (2014)](https://arxiv.org/abs/1408.5882) CNN for text analytics. Updated to Tensorflow 2.0.
+13. [Multimodal learning](notebooks/python/Multimodal_Learning_House_Prices.ipynb): Regression example using ResNet50v2 and the Keras' Model API. Current multimodal example I use in my lectures combining categorical data and image data.
 
-14. [2D CNN and Gradient Backtracing](notebooks/python/Lab_2D_Convolutions.ipynb): 2D Convolutions for image classification. Use of pre-trained models (VGG16), and gradient backtracing to visualize what is being used to discriminate.
+14. [Recurrent Networks](notebooks/python/Lab_Recurrent_Networks): LSTM and GRU in Pytorch.
 
-15. [Multimodal learning (a)](notebooks/python/Multimodal_Learning_House_Prices.ipynb): Regression example using ResNet50v2 and the Keras' Model API. Current multimodal example I use in my lectures combining categorical data and image data.
+15. [Transformers](notebooks/python/Lab_Text_Analytics_Transformers): The Transformer applied using Huggingface's packages.
 
-16. [Multimodal Learning (b)](notebooks/python/Airlines.ipynb): Example shown at the 2019 [Machine Learning Bootcamp](http://www.fields.utoronto.ca/activities/19-20/bootcamp_ML_F) at the University of Toronto. Mixed content from all other labs applied to sentiment analysis. Shows how to use categorical embeddings, text embeddings, and traditional structured data to improve evaluations.
+16. [LLM API](notebooks/python/Lab_LLM_OpenAI): Using OpenAI's LLM libraries and examples.
 
 ## Other labs