Fernando's repositories
Text-Classification-LSTMs-PyTorch
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.
Stacking-Blending-Voting-Ensembles
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.
Text-Classification-CNN-PyTorch
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.
Text-Generation-BiLSTM-PyTorch
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.
Kubeflow_Pipelines
This repository aims to develop a step-by-step tutorial on how to build a Kubeflow Pipeline from scratch in your local machine.
SKORCH-PyTorch-Wrapper
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.
VGAE-PyTorch
This repository shows an implementation of the VGAE based model with PyTorch.
SHAP-Classification-example
This repository contains an example of how to implement the shap library to interpret a machine learning model.
SpeechRecognition
This repository contains the implementation of an Automatic Speech Recognition system in python, using a client-server architecture with Web Sockets.
Tracking-ML-model-MLflow
This repository shows the use of MLflow to track parameters, metrics and artifacts of a pipeline on a machine learning model.
FeatureSelection_-_RandomForest
# 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
ONNX-PyTorch-TF-Caffe2
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.
PolynomialCurveFitting
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.
TPOT-Optimal-Pipeline-Searching
This repository contains an implementation of TPOT for obtaining optimal pipelines with the use of genetic algorithms.
AuthorVerificiation
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.
PyTorch-Lightning
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
Analysis_Taxi_behavior_NY
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.
Data-Visualization-Cancer-DataSet
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.
FernandoLpz
Config files for my GitHub profile.
GeneralizedOptimalSparseDecisionTrees
Generalized Optimal Sparse Decision Trees
House_Prices_Regression_Techniques
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.
Machine_Learning_for_Disaster
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.
Regressors_for_taxi_fare_prediction
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.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Weather-in-Australia--Classification-and-Visualization
The notebook break down a problem of classification based on a weather in australia's data set. The idea of this work is to show different aproaches in how to visualize a data set, besides the idea is to develop different kind of Machine Learning Algorithms as Random Forest, SVM and Neural Networks.