lucidmode is an open-source, low-code and lightweight Python framework for transparent and interpretable machine learning models. It has built in machine learning methods optimized for visual interpretation of some of the most relevant calculations.


  • With package manager (coming soon)

Install by using pip package manager:

pip install lucidmode

  • Cloning repository

Clone entire github project

[email protected]:lucidmode/lucidmode.git

and then install dependencies

pip install -r requirements.txt


Artificial Neural Network

Feedforward Multilayer perceptron with backpropagation.

  • fit: Fit model to data
  • predict: Prediction according to model

Initialization, Activations, Cost functions, regularization, optimization

  • Weights Initialization: With 4 types of criterias (zeros, xavier, common, he)
  • Activation Functions: sigmoid, tanh, ReLU
  • Cost Functions: Sum of Squared Error, Binary Cross-Entropy, Multi-Class Cross-Entropy
  • Regularization: L1, L2, ElasticNet for weights in cost function and in gradient updating
  • Optimization: Weights optimization with Gradient Descent (GD, SGD, Batch) with learning rate
  • Execution: Callback (metric threshold), History (Cost and metrics)
  • Hyperparameter Optimization: Random Grid Search with Memory


  • Metrics: Accuracy, Confusion Matrix (Binary and Multiclass), Confusion Tensor (Multiclass OvR)
  • Visualizations: Cost evolution
  • Public Datasets: MNIST, Fashion MNIST
  • Special Datasets: OHLCV + Symbolic Features of Cryptocurrencies (ETH, BTC)

Author/Principal Maintainer

Francisco Munnoz (IFFranciscoME) Is an associate professor of financial engineering and financial machine learning @ITESO (Western Institute of Technology and Higher Education)