🔥 Matt Dancho (Business Science) 🔥 Profile picture
On a mission to grow your business data science skills and accelerate your career | Get my free 5-day business for data scientists course 👇
7 subscribers
Oct 30 7 tweets 2 min read
R can make flow charts programmatically.

This is how. Image The R package is ggflowchart.

It makes it super easy to create flow charts programmatically in R: Image
Oct 22 4 tweets 1 min read
Have you heard of Upset Plots?

It's a new plot type designed to understand intersections between many categories. Image Get it free in R (on Github here): github.com/const-ae/ggups…
Oct 21 5 tweets 2 min read
This is mind-blowing (I only wish I knew it sooner).

Easy linear regression coefficient reports in R.

This is how: Image The function is ggstats::ggcoef_model().

It turns your Linear Regression into an easy-to-understand coefficient report.

I don't know how many times I've done this the hard way. Image
Oct 20 8 tweets 2 min read
This new R package is wild.

It's called ggalign. Here's what it can do: Image 1. Gene expression matrix: Image
Oct 13 9 tweets 2 min read
25 R packages you need to learn in 2024.

Let's dive in: Image 1. Janitor: Simplifying Data Cleaning
2. Skimr: Quick Data Summarization
3. bslib: Next-Gen UI for Shiny Apps
4. box: Modularize Your R Scripts
5. data.table & tidytable: High-Performance Data Manipulation
Oct 12 7 tweets 2 min read
How to analyze your data faster with R: Image In the fast-paced world of data science, getting quick insights into your data is crucial.

It allows you to understand your data better, make informed decisions, and expedite the modeling process.
Oct 9 16 tweets 4 min read
A/B Testing in R.

This is how: Image 1. A/B Testing Definition:

A/B testing is a statistical method for comparing 2 groups to determine if there is a statistically significant difference between the two groups.

It's often used in marketing analytics to gauge the effectiveness of marketing efforts.
Oct 8 7 tweets 2 min read
What is the most difficult part of becoming a data scientist?

3 common mistakes (and tips that worked for me): Image 1. Not solving business problems

Solving business problems is what drives revenue for your company.

But it’s tough to figure out how to convert to a data problem.

The trick is building.

When you make things, you make mistakes. And you grow.
Oct 6 13 tweets 4 min read
Stop using box plots.

Use this plot instead.

Here's why: Image I used to love Box Plots. Until I found out the harsh truth.

Boxplots fail when it comes to bimodal and multi-modal distributions. Image
Oct 5 11 tweets 3 min read
Myth: R can't be used for production

Fact: R can with Vetiver.

Let me explain: Image Vetiver is an R package that provides tooling to:

- Version
- Deploy
- Monitor

Trained ML Models. Here's how:
Sep 27 9 tweets 2 min read
It took me 5-years to feel confident in data science.

True story.🧵 Image This is coming from a person that has created two R packages that combine for 1.5 Million downloads.

Has trained elite data scientists at Apple, Walmart, Google.

And has built a career teaching students how to become data scientists.

Why did it take so long?
Sep 12 8 tweets 2 min read
Bold prediction: The Birth Of The Business Scientist.

Here's what is about to happen. Image According to Glassdoor research, we already have:

1. Data Analyst, $71,298/yr
2. Business Analyst, $83,924/yr
3. Data Scientist, $124,680/yr

But noticeably missing is the "Business Scientist".
Sep 3 5 tweets 2 min read
"You can't deploy in R."

BS...

You CAN with bslib. bslib is an R package that provides a modern UI toolkit for Shiny and R Markdown based on Bootstrap. Image
Sep 2 5 tweets 2 min read
Building a SQL Data Visualization Copilot:

I'm building my new AI Bootcamp, and here's what's coming... Image Companies are excited about AI. But 90% have no clue where to use it.

Well, I'd use AI for data analytics automation.

This is how:
Aug 31 6 tweets 2 min read
Python has some wild time series libraries.

Case in point: Bayesloop

Let's dive in: Image bayesloop is a python module that focuses on fitting time series models with time-varying parameters and model selection based on Bayesian inference.
Aug 30 6 tweets 2 min read
R is insane for data analytics...

Case in point: mapgl

Let's dive in: Image mapgl is an R package that connects to:

1. Mapbox GL JavaScript Library
2. MapLibre GL JS Library

Why is that important? (Can't I just use Leaflet?)

This is why:
Aug 27 7 tweets 2 min read
Companies are now hiring "Generative AI Data Scientists."

What does this mean? Let me explain: Image Over the last decade, Data Science and Machine Learning have changed Business Analytics. This has driven companies growth:

- Increased Revenue
- Building new products
- Reducing costs
Aug 26 4 tweets 2 min read
90% of data scientists, analysts, and traders aren't using Python for macroeconomic insights effectively.

Let's fix that: Image 90% of data scientists, analysts, and traders aren't using Python for macroeconomic insights effectively.

1. They're overlooking critical indicators.
2. They're missing out on strategic trading opportunities.
3. And it's costing them big time in market moves.
Aug 13 6 tweets 2 min read
Data Scientists: It's not how good you are at ChatGPT.

It's how good you are at combining your knowledge with ChatGPT.

Let me explain. Image A common misconception is that Data Scientists think ChatGPT will do their job for them.

In my experience, this is wrong.

Yes- ChatGPT is very helpful.

But it's not human-level intelligence.
Aug 7 7 tweets 3 min read
Can ChatGPT be used for Time Series in R?

I've had success with using Chatgpt for about 80% of my time series code.

Here's how I got my projects to 100% with chatgpt. 🧵 Image ChatGPT is a game changer for time series. No question.

But is it perfect? Hardly.

Things I've experienced (and overcame):
Aug 6 6 tweets 2 min read
Stop making R Shiny Web Apps from scratch.

Use ChatGPT instead.

This is how (Step 2 is the best). 🧵 Image R Shiny Web Apps take me days to build when I make them from scratch.

ChatGPT has been my secret weapon.

I use a special technique called Prompt Stacking, which is a simple idea.

Here's how Prompt Stacking works: