Handling CSV files in Swift can be a straightforward process with the help of TabularData. This framework provides a simple and efficient way to read and write CSV files. With TabularData, you can easily load and save CSV files with fileImporter and fileExporter. Here is how I set them up.

Set up Environment

I have been used GPU accelerated TensorFlow on my MacBook Pro with AMD GPU. Now Pytorch has joined this field.

Class

Demo Dataset

import numpy as np
from sklearn import datasets
iris = datasets.load_iris()
iris.data.shape, iris.target.shape

The full jupyter notebook is here.

Demo dataset

The following data is used to set up demos for the following data exploration templates.

Generative adversarial network is an powerful tool in generation of images, style change, and voice conversion. MicroRNA (miRNA) is an single-stranded non-coding RNA with essential functions in RNA silencing and post transcriptional regulation in gene regulation. Customized miRNAs could help us to silence specific gene and be utilized in gene therapy. Here I applied GAN on generation of miRNA like structures as a personal little project to discover the potential of GAN in novel miRNA design. The full jupyter notebooks are here.

Recently Apple had provided a Mac optimized TensorFlow which is able to utilize Mac’s machine learning framework and GPUs. The link to Apple’s blog is here. Because I am using Anaconda and conda as my major python virtual environment manager, here is my note for installation and testing.

In Kaggle competition of COVID-19 case prediction, we sometimes need to combind different types of layers and branch the output. It is efficient to create a template for the next application.

Bagging is an ensamble method which would be helpful when the model is complex, easy to overfit. We can do voting or average the results from different models. It is not necessary to include all the models but just those estimators that can give you the best result. For optimization of hyper parameters, I have applied GridSearchCV. For cross validation, I used StratifiedKFold. The best estimators will be stored in a list and VotingClassifier is applied to implement the bagging process.

This is the note of the scores which is applied to evaluate the performance of machine learning models. In this study note, it includes Accuracy, Confusion Matrix, Precision, Recall, and F1-score. For visualize the performance, we can use Receiver Operating Characteristic Curve (ROC curve) and Area under curve (AUC)

This is my little note about setting latex and table format for jekyll blog.