A Gentle Introduction to Machine Learning for Chemists: An Undergraduate Workshop Using Python Notebooks for Visualization, Data Processing, Analysis, and Modeling

Lafuente, Deborah; Cohen, Brenda; Fiorini, Guillermo; García, Agustín; Bringas, Mauro; Morzan, Ezequiel Martín; Onna, Diego

doi:10.1021/acs.jchemed.1c00142

Cited by 62 publications

(65 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 6 shows the scheme to obtain the polynomial equation from dataframe. The library allows for the treatment of large data sets in the convenient structure of dataframes and various tools for their handling; 52 this is especially useful when students manipulate large data sets.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Google Colab and Virtual Simulations: Practical e-Learning Tools to Support the Teaching of Thermodynamics and to Introduce Coding to Students

2022

View full text Add to dashboard Cite

Various studies have reported the versatility and great scope of programming tools in all areas of knowledge. Coding is generally of paramount importance to chemistry students regardless of whether they intend to work with theoretical chemistry. Google Colab notebooks can introduce students to programming concepts and could be a convenient tool to assist in the chemistry teaching process. In this article, we implemented Google Colab notebooks to aid in the teaching of thermodynamics in a physical chemistry class. We presented six notebooks, covering introductory concepts of both coding and thermodynamics as a set of learning objects that can be useful in a virtual learning environment. In addition, in some of the notebooks, we included a step-by-step guide on how to run virtual lab simulations. The Colab notebooks were created for students without previous experience in programming. All of the Colab notebooks contain exercises of the activities and the solutions of the proposed exercises. Furthermore, all of the Colab notebooks can be modified and downloaded from the Github repository. Finally, we used the Python programming language and Colab because they are free and widely used by the academic community.

show abstract

Section: Discussionmentioning

confidence: 99%

“… 43 Lafuente et al carried out an interesting study directed to Machine Learning for Chemists through Jupyter notebooks. 52 Inside the Open Chemistry Project, Hanwell et al. presented the JupyterLab for use in Quantum chemistry, and the project was developed using Open Source Initiative.…”

Section: Introductionmentioning

confidence: 99%

Google Colab and Virtual Simulations: Practical e-Learning Tools to Support the Teaching of Thermodynamics and to Introduce Coding to Students

2022

View full text Add to dashboard Cite

show abstract

“…However, we have found two recent publications from 2020 and 2021 where this approach is suggested. For chemistry students, Lafluente et al present an introductory workshop focusing on utilising Python and visualisation/ML libraries [66]. The example Jupyter notebooks 33 lead students through an introduction to 33 https://github.com/ML4chemArg/ Intro-to-Machine-Learning-in-Chemistry Python, basic statistics, exploratory data analysis, classification, and regression.…”

Section: Cs Pytorchmentioning

confidence: 99%

“…Recently there have been articles in multiple domains walking a domain expert through the best tools and techniques available to employ ML [52,75,111,66,92]. For example, Nakhle and Harfouche provide four detailed Jupyter notebooks 52 walking domain experts in phenomics (plant sciences) through four steps of a ML task [82].…”

Section: Guiding the Domain Expertmentioning

confidence: 99%

Building Domain-Specific Machine Learning Workflows: A Conceptual Framework for the State-of-the-Practice

Oakes¹,

Famelis²,

Sahraoui³

2022

Preprint

View full text Add to dashboard Cite

Domain experts are increasingly employing machine learning to solve their domain-specific problems. This article presents six key challenges that a domain expert faces in transforming their problem into a computational workflow, and then into an executable implementation. These challenges arise out of our conceptual framework which presents the "route" of options that a domain expert may choose to take while developing their solution.To ground our conceptual framework in the stateof-the-practice, this article discusses a selection of available textual and graphical workflow systems and their support for these six challenges. Case studies from the literature in various domains are also examined to highlight the tools used by the domain experts as well as a classification of the domain-specificity and machine learning usage of their problem, workflow, and implementation.The state-of-the-practice informs our discussion of the six key challenges, where we identify which challenges are not sufficiently addressed by available tools. We also suggest possible research directions for software engineering researchers to increase the automation of these tools and disseminate best-practice techniques between software engineering and various scientific domains.

show abstract

“…In Table S1 to S3, the data set explored is a collection of white and red wine from the "Vinho Verde" wine region in Portugal. [28][29][30] The data set for red wine consists of 1599 samples (Table S1) and the one for white wine consists of 4898 samples (Table S2). Each sample has 11 physicochemical variables: Fixed acidity (g(tartaric acid)/dm 3 ), Volatile acidity (g(acetic acid)/dm 3 ), Citric acid (g/dm 3 ), Residual sugar (g/dm 3 ), Chlorides (g(sodium chloride)/dm 3 ), Free sulfur dioxide (mg/dm 3 ), Total sulfur dioxide (mg/dm 3 ), Density (g/cm 3 ), pH, Sulphates (g(potassium sulphate)/dm 3 ), Alcohol (vol.%) and one qualitative variable: quality.…”

Section: Data Setmentioning

confidence: 99%

Principal Component Analysis (PCA) and Statistical Tests Using Factoshiny and R Commander.

Borges

Filgueiras

2021

Preprint

View full text Add to dashboard Cite

Spreadsheets are commonly used for data handling. However, in huge data sets, spreadsheets cannot do statistical tests, such as one-way ANOVA, boxplot, plot of means, principal component analysis (PCA). Most of the students had never worked with programming software such as MATLAB, Phyton, Octave and R project. Hence, in this lab experiment, students analyzed large data sets using R Commander and Factoshiny plugins. Commander and Factoshiny are packages which gives graphical user interface (GUI). GUI plugins allows students with no programming knowledge to run statical tests quickly and easily without having to type a single command line. The class was divided into three parts. First, students analyzed a red wine data set (1599 samples, 11 physicochemical variables, and one qualitative variable) to find correlations between wine quality (qualitative variable) and its physicochemical variables (quantitative variable). Second, they analyzed a white wine data set (4898 samples, 11 physicochemical variables, and one qualitative variable) to find correlations between white wine quality and its physicochemical variables. Third, they analyzed a red wine and white wine data set and found correlations between wine's physicochemical variables and their quality and type. Statistical tests and PCA were carried out using R Commander and Factoshiny, respectively. Due to the graphical interface and simplicity of these two plugins, the class can be concluded in 200 min.

show abstract

A Gentle Introduction to Machine Learning for Chemists: An Undergraduate Workshop Using Python Notebooks for Visualization, Data Processing, Analysis, and Modeling

Cited by 62 publications

References 28 publications

Google Colab and Virtual Simulations: Practical e-Learning Tools to Support the Teaching of Thermodynamics and to Introduce Coding to Students

Google Colab and Virtual Simulations: Practical e-Learning Tools to Support the Teaching of Thermodynamics and to Introduce Coding to Students

Building Domain-Specific Machine Learning Workflows: A Conceptual Framework for the State-of-the-Practice

Principal Component Analysis (PCA) and Statistical Tests Using Factoshiny and R Commander.

Contact Info

Product

Resources

About