Exploring Data Science with .NET using Polyglot Notebooks & ML.NET

Course details

In this course, Matt Eland—an AI specialist, Microsoft MVP, and author—equips experienced .NET developers with the skills to conduct data analytics and data science experiments using Polyglot Notebooks. Dive into the core of Polyglot Notebooks, its relationship to Jupyter Notebooks, and language support for C#, F#, PowerShell, SQL, and Mermaid diagrams. Learn data ingestion, sharing between kernels, exploratory data analysis with descriptive statistics, and data visualization using libraries like Microsoft.Data.Analysis, ScottPlot, and Plotly.NET. Explore basic machine learning concepts, model training, train/test splits, evaluation, and beginner classification/regression experiments with ML.NET's AutoML capabilities. Plus, cover advanced Polyglot Notebooks integrations like Azure OpenAI, Semantic Kernel, Sequence Diagram Generation, and Azure AI Services.

Learning objectives
Analyze and apply the core concepts of Polyglot Notebooks, including its relationship with Jupyter Notebooks and support for various programming languages
Construct exploratory data analysis pipelines by ingesting data, performing descriptive statistics, and creating visualizations using appropriate libraries.
Evaluate and implement basic machine learning models for classification and regression tasks using ML.NET's AutoML capabilities, including training, testing, and assessing model performance

Concepts

0. Introduction

01 - Data science with .NET
02 - What you should know

1. Introducing Polyglot Notebooks

03 - Notebooks and kernels
04 - Installing Polyglot Notebooks
05 - Creating your first Notebook
06 - C# cells
07 - Variable sharing between cells
08 - Declaring classes and methods
09 - F# cells
10 - Sharing variables between kernels
11 - Markdown cells
12 - Mermaid diagrams
13 - Importing NuGet packages

2. Data Wrangling with DataFrames

14 - Introducing DataFrames
15 - Renaming and removing columns
16 - Replacing missing values
17 - Dropping missing values
18 - Feature engineering
19 - Merging DataFrames
20 - Grouping data
21 - Filtering data
22 - Exporting DataFrames

3. Data Analysis and Visualization with DataFrames and Plotly.NET

23 - Describing DataFrames
24 - Getting values from individual columns
25 - Histograms
26 - Box and violin plots
27 - Scatter plots

4. Machine Learning with ML.NET

28 - Intro to machine learning, ML.NET, and AutoML
29 - Loading data into train test sets
30 - Training classification models
31 - Evaluating classification models
32 - Training regression models
33 - Evaluating regression models
34 - Saving and loading models
35 - Generating predictions from models
36 - Additional ML.NET topics

5. Deploying Polyglot Notebooks

37 - Adopting Polyglot Notebooks
38 - Getting into data science and AI as a developer

Conclusion

39 - Next steps