numpy-ml
Ever wish you had an inefficient but somewhat legible collection of machine
learning algorithms implemented exclusively in NumPy? No?
Installation
For rapid experimentation
To use this code as a starting point for ML prototyping / experimentation, just clone the repository, create a new virtualenv, and start hacking:
$ git clone https://github.com/ddbourgin/numpy-ml.git
$ cd numpy-ml && virtualenv npml && source npml/bin/activate
$ pip3 install -r requirements-dev.txt
As a package
If you don't plan to modify the source, you can also install numpy-ml as a
Python package: pip3 install -u numpy_ml.
The reinforcement learning agents train on environments defined in the OpenAI
gym. To install these alongside numpy-ml, you
can use pip3 install -u 'numpy_ml[rl]'.
Documentation
For more details on the available models, see the project documentation.
Available models
-
Gaussian mixture model
- EM training
-
Hidden Markov model
- Viterbi decoding
- Likelihood computation
- MLE parameter estimation via Baum-Welch/forward-backward algorithm
-
Latent Dirichlet allocation (topic model)
- Standard model with MLE parameter estimation via variational EM
- Smoothed model with MAP parameter estimation via MCMC
-
Neural networks
- Layers / Layer-wise ops
- Add
- Flatten
- Multiply
- Softmax
- Fully-connected/Dense
- Sparse evolutionary connections
- LSTM
- Elman-style RNN
- Max + average pooling
- Dot-product attention
- Embedding layer
- Restricted Boltzmann machine (w. CD-n training)
- 2D deconvolution (w. padding and stride)
- 2D convolution (w. padding, dilation, and stride)
- 1D convolution (w. padding, dilation, stride, and causality)
- Modules
- Bidirectional LSTM
- ResNet-style residual blocks (identity and convolution)
- WaveNet-style residual blocks with dilated causal convolutions
- Transformer-style multi-headed scaled dot product attention
- Regularizers
- Dropout
- Normalization
- Batch normalization (spatial and temporal)
- Layer normalization (spatial and temporal)
- Optimizers
- SGD w/ momentum
- AdaGrad
- RMSProp
- Adam
- Learning Rate Schedulers
- Constant
- Exponential
- Noam/Transformer
- Dlib scheduler
- Weight Initializers
- Glorot/Xavier uniform and normal
- He/Kaiming uniform and normal
- Standard and truncated normal
- Losses
- Cross entropy
- Squared error
- Bernoulli VAE loss
- Wasserstein loss with gradient penalty
- Noise contrastive estimation loss
- Activations
- ReLU
- Tanh
- Affine
- Sigmoid
- Leaky ReLU
- ELU
- SELU
- GELU
- Exponential
- Hard Sigmoid
- Softplus
- Models
- Bernoulli variational autoencoder
- Wasserstein GAN with gradient penalty
- word2vec encoder with skip-gram and CBOW architectures
- Utilities
col2im(MATLAB port)im2col(MATLAB port)conv1Dconv2Ddeconv2Dminibatch
- Layers / Layer-wise ops
-
Tree-based models
- Decision trees (CART)
- [Bagging] Random forests
- [Boosting] Gradient-boosted decision trees
-
Linear models
- Ridge regression
- Logistic regression
- Ordinary least squares
- Weighted linear regression
- Generalized linear model (log, logit, and identity link)
- Gaussian naive Bayes classifier
- Bayesian linear regression w/ conjugate priors
- Unknown mean, known variance (Gaussian prior)
- Unknown mean, unknown variance (Normal-Gamma / Normal-Inverse-Wishart prior)
-
n-Gram sequence models
- Maximum likelihood scores
- Additive/Lidstone smoothing
- Simple Good-Turing smoothing
-
Multi-armed bandit models
- UCB1
- LinUCB
- Epsilon-greedy
- Thompson sampling w/ conjugate priors
- Beta-Bernoulli sampler
- LinUCB
-
Reinforcement learning models
- Cross-entropy method agent
- First visit on-policy Monte Carlo agent
- Weighted incremental importance sampling Monte Carlo agent
- Expected SARSA agent
- TD-0 Q-learning agent
- Dyna-Q / Dyna-Q+ with prioritized sweeping
-
Nonparameteric models
- Nadaraya-Watson kernel regression
- k-Nearest neighbors classification and regression
- Gaussian process regression
-
Matrix factorization
- Regularized alternating least-squares
- Non-negative matrix factorization
-
Preprocessing
- Discrete Fourier transform (1D signals)
- Discrete cosine transform (type-II) (1D signals)
- Bilinear interpolation (2D signals)
- Nearest neighbor interpolation (1D and 2D signals)
- Autocorrelation (1D signals)
- Signal windowing
- Text tokenization
- Feature hashing
- Feature standardization
- One-hot encoding / decoding
- Huffman coding / decoding
- Byte pair encoding / decoding
- Term frequency-inverse document frequency (TF-IDF) encoding
- MFCC encoding
-
Utilities
- Similarity kernels
- Distance metrics
- Priority queue
- Ball tree
- Discrete sampler
- Graph processing and generators
Contributing
Am I missing your favorite model? Is there something that could be cleaner /
less confusing? Did I mess something up? Submit a PR! The only requirement is
that your models are written with just the Python standard
library and NumPy. The
SciPy library is also permitted under special
circumstances ;)
See full contributing guidelines here.