Fernando's Projects
In this notebook I show you an analysis of taxis behavior in September, 2015 NY. The idea of this work is to find and show you insights as well as some visualizations to understand in a better way the analysis.
This project shows up the algorithm k-means implemented to cluster documents from the contest PAN CLEF 2O16 where the topics of the documentes are reviews and novels.
This repository shows up a siamese arquitectue proposed to solve the problem of author verification particularly the problem about given a pair of documents decide if both are from the same author or not based on their writting style. The siamese arquitecture is composed by an assemble of two convolutional layers and a LSTM recurrent neurnal net followed by a euclidean distance.
The purpose of this notebook is to show a deep analysis of the behavior of crimes happended in CDMX, MΓ©xico in years from 2014 to 2016.
The idea of this notebook is to show you one way to visualize a data set for a classification task. The data set is about diagnosis of cancer based on a series of features. As mentioned above the goal is to classify if the pacient has cancer or not. However in this notebook we only focus in the visualization part.
# Feature Selection & Random Forest-based Model In this kernel I will develop a solution by first, selecting the most relevant features and then applying a random forest to solve the classification problem
Config files for my GitHub profile.
Generalized Optimal Sparse Decision Trees
In this work I will show you a deep analysis, data visualization and the regression aproach based on the dataset "House Prices" provided for kaggle in: https://www.kaggle.com/c/house-prices-advanced-regression-techniques/data.
This repository aims to develop a step-by-step tutorial on how to build a Kubeflow Pipeline from scratch in your local machine.
In this challenge, we ask you to complete the analysis of what sorts of people were likely to survive. In particular, we ask you to apply the tools of machine learning to predict which passengers survived the tragedy.
This repository shows the implementation of a multilayer perceptron making use of tensorflow in python in a toy dataset to detect fertility issue. Tensorflow Python The dataset was downloaded from https://archive.ics.uci.edu/ml/datasets/Fertility#
This repository shows an example of how to use the ONNX standard to interoperate between different frameworks. In this example, we train a model with PyTorch and make predictions with Tensorflow, ONNX Runtime, and Caffe2.
This code shows the implementation of polynomial curve fitting and the regularization over the parameters. In this example we are trying to fit the curve generate by the function sin(2pix), where "x" is a vector of values generated randomly under a normal distribution.
This repository shows a couple of examples to start using PyTorch Lightning right away. PyTorch Lightning provides several functionalities that allow to organize in a flexible, clean and understandable way each component of the training phase of a PyTorch model
The idea of this notebook is to show you an approach making use of different regressors which are: XGBoosting Random Forest Gradient Boosting Tree Ada Boost Regressor In this notebook we compare the performance of each regressor making a variation in the number of estimator for each regressor.
This repository contains an example of how to implement the shap library to interpret a machine learning model.
This repository shows an example of the usability of SKORCH to train a PyTorch model making use of different capabilities of the scikit-learn framework.
This repository contains the implementation of an Automatic Speech Recognition system in python, using a client-server architecture with Web Sockets.
This repository contains an example of each of the Ensemble Learning methods: Stacking, Blending, and Voting. The examples for Stacking and Blending were made from scratch, the example for Voting was using the scikit-learn utility.
TensorFlow Tutorial and Examples for Beginners with Latest APIs
The aim of this repository is to show a baseline model for text classification through convolutional neural networks in the PyTorch framework. The architecture implemented in this model was inspired by the one proposed in the paper: Convolutional Neural Networks for Sentence Classification.
The aim of this repository is to show a baseline model for text classification by implementing a LSTM-based model coded in PyTorch. In order to provide a better understanding of the model, it will be used a Tweets dataset provided by Kaggle.
In this repository you will find an end-to-end model for text generation by implementing a Bi-LSTM-LSTM based model with PyTorch's LSTMCells.
This repository contains an implementation of TPOT for obtaining optimal pipelines with the use of genetic algorithms.
This repository shows the use of MLflow to track parameters, metrics and artifacts of a pipeline on a machine learning model.
π€ Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.