machine-learning-notes
Collection of useful machine learning codes and snippets (originally intended for my personal use)
File Explorer
Download Latest Version (.zip)- rule-based-text-classifier_vader.ipynb
- pandas2-pyarrow.ipynb
- results.png
- __init__.py
- dataset.py
- model.py
- main.py
- README.md
- requirements.txt
- setup.py
- 1080ti.txt
- 2080ti.txt
- 3090.txt
- intel-cpu.txt
- m1-cpu.txt
- m1-gpu.txt
- m1pro-cpu.txt
- m1pro-gpu.txt
- m1-cpu-mlp.txt
- m1-gpu-mlp.txt
- mlp-1080ti.txt
- mlp-2080ti.txt
- mlp-3090.txt
- mlp-intel-cpu.txt
- mlp-m1max-gpu_torch1.13.0.dev20220522.txt
- mlp-m1pro-cpu_torch1.12.0.dev20220518.txt
- mlp-m1pro-cpu_torch1.13.0.dev20220522.txt
- mlp-m1pro-gpu_torch1.12.0.dev20220518.txt
- mlp-m1pro-gpu_torch1.13.0.dev20220522.txt
- 1080ti.txt
- 2080ti.txt
- 3090.txt
- intel-cpu.txt
- m1-plain-gpu_torch 1.12.0.dev20220518.txt
- m1-plain-gpu_torch-1.13.0.dev20220522.txt
- m1max-gpu_torch-1.12.0.dev20220518.txt
- m1max-gpu_torch-1.13.0.dev20220522.txt
- m1pro-cpu_torch 1.12.0.dev20220518.txt
- m1pro-cpu_torch1.13.0.dev20220522.txt
- m1pro-gpu_torch 1.12.0.dev20220518.txt
- m1pro-gpu_torch1.13.0.dev20220522.txt
- m1ultra-cpu_torch-1.13.0.dev20220522.txt
- m1ultra-gpu_torch-1.13.0.dev20220522.txt
- titanv-cpu.txt
- titanv.txt
- lenet-mnist.py
- mlp-mnist.py
- README.md
- vgg16-cifar10.py
- iris_mod.csv
- gradient-boosting-with-categorical-feat.ipynb
- sklearn-categorical-numerical-mix.ipynb
- sklearn-onehot-encoding-mixedtype-df.ipynb
- sklearn-ordinal-encoding-mixedtype-df.ipynb
- sklearn-permutation-importance.ipynb
- my_xgboost_classifier.py
- README.md
- xgboost-cloud-gpu.py
- cat.jpeg
- basic-pytorch-cnn-for-3-ele-pytorch-video.ipynb
- imagenet_int_to_label.py
- torchvision-efficientnet-v2.ipynb
- 1_normal_approx.py
- 2.1_bootstrap_t.py
- 2.2_bootstrap_percentile.py
- 2.3_bootstrap_632.py
- 3_bootstrap_test.py
- get_dataset.py
- ci-simulation-repeated.ipynb
- ci-simulation.ipynb
- confidence-intervals-for-ml.ipynb
- notebook.ipynb
- shared_utilities.py
- orion-recommendations.png
- mlp_cli2.py
- README.md
- shared_utilities.py
- sweeper.py
- 01.1-gridsearch-decisiontree-example.ipynb
- 01.2-gridsearch-stacking-example.ipynb
- 02.1-randomsearch-decisiontree-example.ipynb
- 02.2-randomsearch-stacking-example.ipynb
- 03.1-hyperopt-decisiontree-example.ipynb
- 03.2-hyperopt-xgboost-example.ipynb
- 04.1-optuna-decisiontree-example.ipynb
- 04.2-optuna-xgboost-example.ipynb
- 04.3-optuna-lightgbm-example.ipynb
- 05.1-successive-halving-decisiontree.ipynb
- 05.2-successive-halving-stacking.ipynb
- 06.1-genetic-opt.ipynb
- 07.1-orion_wip.ipynb
- sklearn-parameter-sampler.ipynb
- 1-baseline.ipynb
- 2-step-decay.ipynb
- 3-cosine-restarts.ipynb
- 4-cosine-epoch-decay.ipynb
- 5-cosine-batch-decay.ipynb
- 6-cosine-batch-decay-warmstart.ipynb
- overview.png
- shared_utilities.py
- dataset.py
- model.py
- vgg16-bceloss.ipynb
- vgg16-bcewithlogitsloss.ipynb
- binary-cross-entropy-in-pytorch.ipynb
- Four-matrix-multiplications.ipynb
- pytorch-regression-model.ipynb
- mlp_cli2.py
- README.md
- shared_utilities.py
- mlp_cli.py
- README.md
- shared_utilities.py
- epoch=8-step=4050.ckpt
- last.ckpt
- hparams.yaml
- metrics.csv
- checkpointing.ipynb
- shared_utilities.py
- __init__.py
- dataset.py
- model.py
- plotting.py
- 4_inspecting-the-dataset.ipynb
- 6_evaluating-the-results.ipynb
- main.py
- README.md
- requirements.txt
- setup.py
- .gitignore
- LICENSE
- README.md
# Installation Guide
1. Get the code
git clone https://github.com/rasbt/machine-learning-notes
Downloads the entire project code from GitHub to your computer.
cd machine-learning-notes
Moves into the project folder you just downloaded.
2. Python
Easy RecommendedPrerequisites
β οΈ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.
pip install -r benchmark/pytorch-lightning-m1-gpu/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.
// repository documentation
Was this content helpful?
(0 ratings)