πŸ”₯ Matt Dancho (Business Science) πŸ”₯ Profile picture
Aug 13 β€’ 8 tweets β€’ 3 min read β€’ Read on X
🚨 BREAKING: IBM launches a free Python library that converts ANY document to data

Introducing Docling. Here's what you need to know: 🧡 Image
1. What is Docling?

Docling is a Python library that simplifies document processing, parsing diverse formats β€” including advanced PDF understanding β€” and providing seamless integrations with the gen AI ecosystem. Image
2. Document Conversion Architecture

For each document format, the document converter knows which format-specific backend to employ for parsing the document and which pipeline to use for orchestrating the execution, along with any relevant options. Image
3. PDF Conversion to Markdown

Here is an example of the DocLayNet paper from arXiv, converted into Markdown format by Docling. Image
4. Core Technology:

Docling includes:

- PDF Backends for parsing
- Layout Analysis Model
- Vision-Based Table Formatter
- OCR for Text Image
5. Every data analyst, data scientist, and data engineer needs to learn Generative AI

99% of them are overlooking AI. This is a massive opportunity for you.

I'd like to help.
On Wednesday, August 20th, I'm sharing one of my best AI/ML Projects for FREE:

How I built an AI Customer Segmentation Agent with Python:

Register here (1,821 registered): learn.business-science.io/ai-registerImage
That's a wrap! Over the next 24 days, I'm sharing the 24 concepts that helped me become an AI data scientist.

If you enjoyed this thread:

1. Follow me @mdancho84 for more of these
2. RT the tweet below to share this thread with your audience

β€’ β€’ β€’

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

Keep Current with πŸ”₯ Matt Dancho (Business Science) πŸ”₯

πŸ”₯ Matt Dancho (Business Science) πŸ”₯ Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

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

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @mdancho84

Aug 12
Type 1 and Type 2 errors are confusing. In 3 minutes, I'll demolish your confusion. Let's dive in. 🧡 Image
1. Type 1 Error (False Positive):

This occurs when the pregnancy test tells Tom, the man, that he is pregnant. Obviously, Tom cannot be pregnant, so this result is a false alarm. In statistical terms, it's detecting an effect (in this case, pregnancy) when it actually doesn't exist.
2. Type 2 Error (False Negative):

This happens when Lisa, who is actually pregnant, takes the test, and it tells her that she's not pregnant. The test failed to detect the real condition of pregnancy. In statistical terms, it's failing to detect a real effect (pregnancy) that is there.
Read 12 tweets
Aug 9
Stop doing Customer Segmentation with plain vanilla Scikit Learn.

Add these 7 Python libraries to your RFM, clustering, and
customer segmentation projects: Image
1. Data preparation

- load data withβ€―pandas
- impute/mask withβ€―Feature-engine

Website: feature-engine.trainindata.com/en/latest/inde…Image
2. Feature creation:

- derive recency/frequency/monetary features
- Use rfm or Lifetimes

Github: github.com/sonwanesuresh9…Image
Read 9 tweets
Aug 9
RIP Data Scientists.

The Generative AI Data Scientist is NOW what companies want.

This is actually good news. Let me explain: Image
Companies are sitting on mountains of unstructured data.

PDF
Word docs
Meeting notes
Emails
Videos
Audio Transcripts

This is useful data. But it's unusable in its existing form. Image
The AI data scientist builds the systems to analyze information, gain business insights, and automates the process.

- Models the system
- Use AI to extract insights
- Drives predictive business insights Image
Read 6 tweets
Aug 8
RIP Tableau and PowerBI.

Enter Julius AI.

This is what Julius can do: Image
1. The $10 Billion problem with Tableau and PowerBI?

Dashboards are static.

But businesses are dynamic.

That's why I'm so excited about this new tool: Julius AI Image
2. Julius AI is for Data Analytics

Julius AI is built to analyze any database, PDF, or spreadsheet, and combine results into summarized business intelligence in seconds. Image
Read 11 tweets
Aug 8
Boxplots are one of the most useful tools in my Data Science arsenal.

In 6 minutes, I'll eviscerate your confusion.

Let's dive in. Image
1. What is a boxplot?

A boxplot is a standardized way of displaying the distribution of data based on a five-number summary: minimum, first quartile (Q1), median, third quartile (Q3), and maximum. Image
2. Invention:

The boxplot was invented in 1969 by John Tukey, as part of his pioneering work in data visualization. Tukey's EDA emphasized the importance of using simple graphical and numerical methods to start understanding the data before making any assumptions about its underlying distribution or applying complex statistical models. The boxplot emerged from this philosophy. Tukey's boxplot was designed to be a quick and easy way to visualize the distribution of data.
Read 12 tweets
Aug 7
The 3 types of machine learning (that every data scientist should know).

In 3 minutes I'll eviscerate your confusion. Let's go: 🧡 Image
1. The 3 Fundamental Types of Machine Learning:

- Supervised Learning
- Unsupervised Learning
- Reinforcement Learning.

Let's break them down:
2. Supervised Learning:

Supervised Learning maps a set of inputs (features) to an output (target). There are 2 types: Classification and Regression.
Read 11 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(