Post

How to get URL link on X (Twitter) App

On the Twitter thread, click on or icon on the bottom
Click again on or Share Via icon
Click on Copy Link to Tweet
Paste it above and click "Unroll Thread"!
More info at Twitter Help

🔥 Matt Dancho (Business Science) 🔥

@mdancho84

May 20, 2023 • 10 tweets • 5 min read • Read on X

Scrolly

BIG ANNOUNCEMENT: I'm beyond excited to announce that in 5 days, I'm launching my brand new course- The #Python for Machine Learning & API's Course.

This course will transform your #career.

Here's what's inside... 🧵

#datascience #course

This launch marks the culmination of 2 years of research...

It covers The 6 Top #Python libraries for machine learning and production:

1. #Pycaret: Low-code machine learning

2. #ScikitLearn: The premier ML toolkit in Python

3. #H2O: Blazing speed + AutoML

4. #MLFlow: Easy model lifecycle management

5. #FastAPI: Incredibly fast + easy APIs in python

6. #Streamlit: Simplified data science web apps

Ready to learn more AND advance your career with Python?

Then you can't miss this event.

$400 in giveaways that everyone gets for attending live!

What's the next step?

Just join my course waitlist + live launch event here.

I'm super excited!! 😀

👉Register Here: learn.business-science.io/python-ml-apis…

• • •

Missing some Tweet in this thread? You can try to force a refresh

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @mdancho84

🔥 Matt Dancho (Business Science) 🔥

@mdancho84

Jan 16

The price of the Python AI/ML Stack I've been using for 12 months:

Langchain $0
Langgraph $0
Scikit Learn $0
H2O $0
Torch $0
Pandas $0
Numpy $0
Plotly $0
Statsmodels $0
Ollama $0
OpenAI (<$1.00 per month)

Becoming a Generative AI Data Scientist cost me $12: 🧵

1. Environment:

- VSCode
- Conda
- Jupyter VSCode Integration

Start here: code.visualstudio.com/docs/datascien…

2. Data Analysis and Visualization:

- Pandas
- Plotly
- Numpy
- Statsmodels
- Scipy

Start here: pandas.pydata.org/docs/getting_s…

Read 9 tweets

🔥 Matt Dancho (Business Science) 🔥

@mdancho84

Jan 15

Here's a wild time series package in Python:

Let me introduce you to Stumpy:

Stumpy is a very unique library.

It computes a "matrix profile"

That's the secret sauce that allows you to do all these tasks:

Why a Matrix Profile? (because you can do this):

1. pattern/motif (approximately repeated subsequences within a longer time series) discovery

2. anomaly/novelty (discord) discovery

3. shapelet discovery

4. semantic segmentation

Read 6 tweets

🔥 Matt Dancho (Business Science) 🔥

@mdancho84

Jan 13

Can AI do Time Series Forecasting?

This is what I found out.

Over the past 2 years, I've been studying AI. Why?

Because there are 1,000s of ways we can combine AI with Data Science.

Time series is one of them.

Most people have bad results with AI. And Time Series is no different.

Time Series is niche.
It's nuanced.
Practitioners have a set of steps that they follow.
These steps can differ from person to person.

Read 7 tweets

🔥 Matt Dancho (Business Science) 🔥

@mdancho84

Jan 12

Introducing my SQL Data Analyst Agent.

I'm excited to announce an addition to my AI Data Science Team in Python.

This is what it does:

The AI Data Science team is a free GitHub repo that helps you perform common data science tasks 10X faster.

This is the first multi-agent in my arsenal: The SQL Data Analyst.

It combines:
- SQL Code Writing
- Database Execution (run SQL queries, get data)
- Data Visualization (produce plots or tables)

Get my AI Data Science Team and learn more at my GitHub: github.com/business-scien…

Read 5 tweets

🔥 Matt Dancho (Business Science) 🔥

@mdancho84

Jan 10

Python has powerful time series libraries.

Case in point: skforecast

Let me explain:

Skforecast is a Python library for time series forecasting using machine learning models.

Skforecast works with any regressor compatible with the scikit-learn API, including popular options like LightGBM, XGBoost, CatBoost, Keras, and many others.

skforecast shines with probabilistic forecasting.

When trying to anticipate future values, most forecasting models try to predict what will be the most likely value.

This is called point forecasting.

Read 7 tweets