Step-by-step to a Data Scientist
Introduction of basic skills for a Data Scientist
The recommended articles the author has read this week.
This letter is posted every Monday.
This week, the author introduces two practical OSS to validate the sensitivity of model prediction, e. g. how sensitive the output is to small changes in the input.
a python library to run fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAX.
a python library to implement adversarial attacks against machine learning models.
The recommended articles the author has read this week.
This letter is posted every Monday.
Jupyter Notebook is an excellent tool for developers. However, there are some differences from the scripting method, so there are things you should know. This article introduces valuable things.
The wonderful OSS, nbsnashot, is a tool for testing a Jupyter Notebook. In the script style, we make test code, however, it is difficult in the notebook style. This OSS makes it possible and easy!
The recommended articles the author has read this week.
This letter is posted every Monday.
Excellent library, developed by Microsoft, for optimization of deep learning training and inference.
XAI, Explainable AI, is one of the recent hot topics. In this article, 6 popular OSS have been introduced, i.e., SHAP, LIME, Shapash, ELI5, InterpretML, OmniXAI.
PyCaret is a useful auto ML python library because we can deploy machine learning models with low codes. We can also perform preprocessing, compare models, and tune hyperparameters, of course with low codes.
This article is a summary of the list of the PyCaret articles introduced in this blog.
We create a docker image for PyCaret from Dockerfile. This post is intended for mastering how to build a docker image from Dockerfile with docker commands.
This post is for beginners.
In this post, we will see the tutorial of PyCaret with a regression analysis against the Boston house prices dataset. This post is intended with the step-by-step guide in mind.
This post is one of the good examples of regression analysis.
The purpose is to learn the basics of regression analysis using PyCaret. Using a famous data set, we will master the basics of everything from model construction to analysis of results.
PyCaret was fully updated in version 2.3.6.
In version 2.3.6, several new features were added. In this article, You can check the major changes. These articles are also worth reading to get an idea of the latest new features in PyCaret.
The recommended articles the author has read this week.
This letter is posted every Monday.
This week, the articles are about a Machine learning project environment, e. g. MLflow, and Jupyter Notebook.
In the environment of a machine learning project, it is very important to prepare not only a data analysis environment such as Jupyter Notebook but also an MLflow environment for managing experiment records. Managing experiment records helps to improve reproducibility and project promotion efficiency.
To build the environment of a machine learning project, docker-compose is a powerful tool. By docker-compose, we can build data-analysis and experiment-management experiments separately. This article tells us how to build such a style environment.
This article shows one example of how to use the MLflow tracking server, which is a tool for managing experiment records. There are several styles to build the MLflow tracking server. This article suggests one of the helpful styles.
The recommended articles the author has read this week.
This letter is posted every Monday.
This week, the articles are about an explanative AI.
AutoML(Automated machine learning) is one of the hot topics. This article introduces the notable AutoML libraries, e.g. PyCaret, AtoKeras, and AutoGluon.
NannyML is an open-source python library, a tool for estimating post-deployment model performance. Drift is one of the hot topics in MLOps, and this library is based on an interesting algorithm.
The recommended articles the author has read this week.
This letter is posted every Monday.
This week, the articles are about an explanative AI.
A transformer is a recent novel AI model which is based on a neural network. This model can learn context among sequence data such as sentences in a language. An attention mechanism in a transformer may be one of the most valuable knowledge we should learn.
Multicollinearity is one of the annoying problems for a data scientist. In this article, we can learn how to visualize the relationships of multicollinearity between features.
Now, the web app for the 3D-scatter plot has been released.
We can v plot the CSV-format dataset as the following image.
https://caron14-streamlit-3d-plot-by-plotly-plot3d-on-streamlit-bzo7i5.streamlitapp.com/
https://github.com/caron14/streamlit_3d_plot_by_plotly
The recommended articles the author has read this week.
This letter is posted every Monday.
This week, the articles are about an explanative AI.
An informative article whose topic is an explainable AI model. It is well known that it is difficult to build an explainable AI system. In this article, the author thinks, there is a hint.
One of the powerful methods to build an explainable AI model is to use a SHAP method. However, we face a computational problem when using a tree-based ML model with a large dataset. In this article, the new SHAP-based library is introduced. The new one is so faster.
The recommended articles the author has read this week.
This letter is posted every Monday.
This week, the articles about VAE(Variational Autoencoder) are introduced.
A tutorial of VAE by Pyro, which is a universal probabilistic programming language (PPL) written in Python and supported by PyTorch on the backend.
The theoretical background of VAE is written in detail.
The author also introduces several new features in the following articles.