BC ALL
Saved by @nandanarunesh

All the @madewithml machine learning fundamentals & MLOps lessons are released!

- 🛠 Project-based
- 💻 Intuition & application (code)
- 🏆 26K+ GitHub ⭐️
- ❤️ 30K+ community
- ✅ 47 lessons, 100% open-source

https://t.co/XIhD3wl1DA

🧵 Thread on details & lesson highlights 👇

 Who is this course for?

- 💻 Software engineers / Data scientists looking to learn how to responsibly create ML systems.
- 🎓 College grads looking to learn the practical skills they'll need for the industry.
- 🚀 Product Managers who want to develop a technical foundation.
We start with lessons on the fundamentals of ML through intuitive explanations, clean code and visualizations.

📚 Foundations
- Python (variables, functions, classes, decorators)
- NumPy (numerical analysis)
- Pandas (data analysis)
- PyTorch (operations, gradients)
Then we dive into implementing basic ML algorithms 1⃣ from scratch then 2⃣ in PyTorch. Starting from simple models → complex models.

📈 Modeling
- Linear Regression
- Logistic Regression
- Neural Networks
- Data Quality (⚠️ very important)
- Utilities (for loading and training)
We wrap up the fundamentals by implementing deep learning algorithms in PyTorch.

🤖 Deep Learning
- CNNs
- Embeddings
- RNNs
- Transformers

💡 We motivate the need for specific architectures and additional complexity as we implement each method.
The first MLOps lessons are on the Product development and iteration cycle.

📦 Product
- Identify the core objective.
- Design a solution with constraints.
- Evaluation strategies that avoid bias.
- Iterate via feedback and motivate adding complexity.
Next we dive into exploring and transforming our data.

🔢 Data
- Labeling (data worth modeling, active learning)
- Preprocessing (prepare + transform)
- Exploration (answering questions)
- Splitting (multi-label classification)
- Augmentation (nlpaug, transformation functions)
📈 Modeling
- Baselines (simple → complex)
- Evaluation (overall, slices, generated)
- Experiment tracking (tracking, viewing and loading)
- Optimization (sampling + pruning)

💡 These aren't just tutorial code snippets. We implement everything with clean and tested code.
Next, we move our work from notebooks to scripts.

📝 Scripting
- Organization
- Packaging (setup + virtualenv)
- Documentation (auto)
- Logging (logger, handler, formatter)
- Styling (black, isort, flake8)
- Makefile

💻 All of this makes for a very calm developing experience.
Now we're ready to wrap our application via various interfaces.

📦 Interfaces
- Command-line (CLI)
- RESTful API with FastAPI (design, schemas, validation)

💡 These interfaces allow us to quickly execute both internal (training, testing, etc.) and external (inference) tasks.
Throughout development, we've been testing not only our code but also our data and models.

✅ Testing
- Test types, coverage, best practices
- Pytest fixtures, markers, parametrize
- Test data w/ Great Expectations
- Test models via slicing functions
- Behavioral tests
We want to ensure that our work is entirely reproducible by anyone.

♻️ Reproducibility
- Git basics via workflows (dev, inspect, merge, etc.)
- Pre-commit hooks (+ custom local)
- Versioning code + config + data = models via DVC
- Containerization via Docker
Next, we want to be able to showcase our work and enable interaction via @streamlit.

📊 Dashboard:
- Data: annotation, EDA, preprocessing
- Performance: overall, slices, regressions
- Inference: intermediate & final outputs
- Inspection: labeling (FP), weaknesses (FN)
Then, we wrap all of the CI/CD workflows we’ve created with @GitHub Actions:

🔄 CI/CD workflows
- Workflow components (events, runners, jobs)
- Testing Actions locally using Act
- Best practices (ex. caching)
- ML Actions (Great Expectations checkpoints, DVC CML)
Next, we explore the infra needed to deploy & serve ML applications.

🛠️ Infrastructure:
- Serving (batch, real-time)
- Processing (batch, stream)
- Learning (offline, online)
- Testing (AB, canary, shadow)
- Optimization (prune, quantize, distill)
- Methods (K8s, serverless)
We ensure the health of our ML system with appropriate monitoring.

🔍 Monitoring:
- identifying drift (data, target, concept)
- measuring drift on uni/multivariate data via
- reducers (PCA, UAE)
- detectors (chi^2, KS, MMD)
- solutions (not always retraining)
Finally, we connect our DataOps & MLOps workflows in our ML systems.

▶️ Workflow orchestration w/ @ApacheAirflow
- DAGs
- Scheduler
- Tasks
- Operators
- Runs

🏪 Feature stores w/ @feast_dev
- data ingestion
- feature definitions
- historical/online features
Over the past 7 years, I've worked on ML and product at @Apple, health tech startups and ran my own venture in the rideshare space. I've worked with brilliant developers and managers and learned how to responsibly develop and iterate on ML systems across various industries.
I currently work closely with early-stage & mid-sized companies in helping them deliver value with ML while diving into the best & bespoke practices of this rapidly evolving space. I want to share that knowledge with the rest of the world so we can accelerate overall progress.
ML is not a separate industry, instead, it's a powerful way of thinking about data. The foundations we've laid out will continue to hold but the methods and avenues of application will evolve. So these lessons are by no means "complete" and we'll continue to keep them up-to-date.
Even more exciting content coming later this year, so stay tuned!

- 🏆 Among top MLOps repos on GitHub: https://t.co/gsYawqTq6U
- 🛠️ A highly recommended resource used by industry: https://t.co/pcMd8jZfo5
- ❤️ 30K+ community members: https://t.co/CswgmDZhCq

More from All

Aditya Todmal
Aditya Todmal
@AdityaTodmal
Master Thread of all my threads!

Hello!! 👋

• I have curated some of the best tweets from the best traders we know of.

• Making one master thread and will keep posting all my threads under this.

• Go through this for super learning/value totally free of cost! 😃

1. 7 FREE OPTION TRADING COURSES FOR


2. THE ABSOLUTE BEST 15 SCANNERS EXPERTS ARE USING

Got these scanners from the following accounts:

1. @Pathik_Trader
2. @sanjufunda
3. @sanstocktrader
4. @SouravSenguptaI
5. @Rishikesh_ADX


3. 12 TRADING SETUPS which experts are using.

These setups I found from the following 4 accounts:

1. @Pathik_Trader
2. @sourabhsiso19
3. @ITRADE191
4.


4. Curated tweets on HOW TO SELL STRADDLES.

Everything covered in this thread.
1. Management
2. How to initiate
3. When to exit straddles
4. Examples
5. Videos on
OPTION SELLING , OPTIONSTRATEGIES , CATEGORY
Naval
Naval
@naval
How to Get Rich (without getting lucky):

Seek wealth, not money or status. Wealth is having assets that earn while you sleep. Money is how we transfer time and wealth. Status is your place in the social hierarchy.

Understand that ethical wealth creation is possible. If you secretly despise wealth, it will elude you.

Ignore people playing status games. They gain status by attacking people playing wealth creation games.

You’re not going to get rich renting out your time. You must own equity - a piece of a business - to gain your financial freedom.
LIFE , STARTUPS , NAVAL1
Advertisement
itrade(DJ)
itrade(DJ)
@ITRADE191
Here is the detailed information of about strategy,

Entry time : 9.30 - 10
Exit : Upto you

Strategy :
Sell weekly ATM CE & PE at almost equal price
For ex : Sell Nifty 17250 CE at 50 and Nifty 17250 PE at 48 so it will become short straddle

Buy monthly ATM or near ATM CE & PE at matching price (5-10 points diff should be fine) as hedge
For ex : Buy Nifty 17250 CE at 150 and Nifty 17300 PE at 155 so it will become long straddle.

Weekly Short straddle + Monthly Long straddle

Adjustment:

• If you feel slightly bullish/bearish then no adjustment needed
• If Nifty moves 50 up or down and sustain then just simply roll up or down half of qnty and keep rest of the quantity. If market goes up or down further then roll up or down rest.

• If Nifty moves one side or about to breach BEP then add equal amount of lot. This can balance tested side. For ex: If I bought 17300 CE 4 lot as hedge then add 4 lot so you will have only one side risk . Note: Remember to keep SL at cost price (only for additional lot bought)

Capital requirement:
2.2 L for 4 lot
Adjustment requires additional capital upto 1L

Note : High risk high reward strategy, please don’t execute until you fully understand. Kindly do paper trading or backtest.
RR : 1:1
POP : 45-55%
OPTIONSLEARNINGS , ALL
Sohaib Albadawee
Sohaib Albadawee
@albadawee
In the past couple of months, 50,000,000 people read my Tweets.

That's more than the population of Canada.

My Secret?

I use the same 7 templates every time (Grab them for free) ↓

📑 Listicles

If you're starting out this one is perfect for you.

Curate lists of:

- Tools to use.
- Books to read.
- Creators to follow.
- Podcasts to listen to.

Add a question & you got a banger.

Grab this template ↓

X life-changing [books, podcasts, courses,etc..)

1. ______________
2. _____________
3. ____________
4. ___________
5. __________
6. _________
7. ________

→ What did I miss?/What else?

🔖 How to do X

This one will get you authority and fans.

Break down something you did in steps.

List them down & encourage people to go for it.

Grab the template ↓

An easy X-step process to [desired outcome]:

1. ______________
2. _____________
3. ____________
4. ___________
5. __________

6. Thank me later
ALL
Angela Jamison
Angela Jamison
@AnJamison
@MiMagaWatch @buzz\_chronicles @buzz\\\_chronicles @buzz_chronicles save as category @pdfmakerapp grab @pdfmakerapp grab this @readwiseio save @readwiseio save thread @threader compile summarize @Threadreaderapp unroll please @ttttreads unroll @unrollthread.com @SaveToBookmarks
ALL

You May Also Like

Andrew Chen
Andrew Chen
@andrewchen
👇Thread.

Published a new essay: The red flags and magic numbers that investors look for in your startup’s metrics – 80 slide deck included!


This was a deck that I created on my (longish) interview process with @a16z. It was a long path, starting with meeting folks at the firm 10 years ago. But the purpose of the deck was to explain how I would use my superpower in an investing context

Here's what I explain in the deck. As investors (whether angel or VC) we're often confronted with an up-and-to-the-right graph. Is it going to go up? Or down?


One solution to forecast these growth curves is the Growth Accounting Framework, where you add up New+Reactivated and subtract churned users. In each time period that gives you the difference in monthly actives.


The problem with this is that it's a lagging metric, not a leading one. We need to go one level deeper and look at the underlying loops that drive these numbers, to understand the quality.
STARTUPS
Vibhu Vashisth
Vibhu Vashisth
@VIBHU_Tweet
Surkanda devi mandir is a famous shrine of Hindus located near Kaddukhal distt of Uttarakhand, 11 Km from the town of Dhanaulti and 35 Km from Mussoorie.
The Temple is one of the 51 Shakti Peethas spread all over Indian Subcontinent and is dedicated to Goddess Surkanda.


Nestled on a Hill at an Altitude of 2700 m approx, the place offers a splendid view of the snow capped mountains, the picturesque scenic beauty that offers an experience of the lifetime.
The Temple build in the traditional Garhwal style exuberates the Architectural splendour.


The origins of the Surkanda Mata Mandir is attributed to Goddess Sati, consort of Bhagwan Shiv who in a rage immolated herself in her arrogant Father Daksha's Yajna Kund bcoz he didn't invite Bhagwan Shiv in the Yajna.


Devastated by the death of Sati Shiva wandered all over the cosmos performing Tandava-The Dance of Cosmic Destruction.Fearing the total annihilation of cosmos, Gods requested Bhagwan Vishnu to pacify Shiva.Bhagwan Vishnu then used his discuss to destroy the burning corps of Sati.


The pieces of Sati Mata's body then got scattered all over the region which were later established as Shakti Peethas by Bhagwan Shiva himself.Its believed that the head of Sati fell here and it was called Sirkhanda Mata Temple before, but with passage of time it became Surkanda.
ALL
Advertisement
WORLD OF SANATAN DHARMA
WORLD OF SANATAN DHARM...
@world_sanatan
MINUTE DETAILS ABOUT THE ATTACK ON SHAISTA KHAN AT LAL MAHAL

Remarkable Commando op

A long 🧵 but worth your time

Aurangzeb sent his maternal uncle Shaista Khan with powerful army over 1,50,000 on the request of Badibegum Sahiba, Adilshahi sultanate

1/


Shaista Khan entered Deccan to kill Chhatrapati Shivaji Maharaj & to destroy his empire. Shahista Khan captured a lot of province and fort of Chakan near Pune.

2/


Till 3 years he gave lot of troubles to the subjects of Chhatrapati Shivaji Maharaj and he personally made Lal Mahal his destination to live at , which was the property of Chhatrapati Shivaji Maharaj . Lal Mahal, where Chhatrapati Shivaji Maharaj spent his childhood.

3/

1. In the April 1663 Chhatrapati Shivaji Maharaj personally made a surprise attack on Shahista Khan in the Lal Mahal Pune.

2. Chhatrapati Shivaji Maharaj attacked with 300 soldiers at the midnight while Lal Mahal had strong security of 1.5 lac soldiers for Shahista Khan.

4/

3. He entered in Pune, he made a drama of wedding ceremony to enter in Pune near Lal Mahal.

4. During the night they made big hole at the wall of Lal Mahal and entered into the palace.

5/
ALL
Vibhu Vashisth
Vibhu Vashisth
@VIBHU_Tweet
Did you know?
Ahilyabai Holkar was one of India's
greatest women rulers of all time.

Ahilyabai was Born on May 31,1725 in the village of Chondi,Jamkhed distt,Maharashtra to a man named Mankoji Shinde,who was the Patil(Chief) of a village and a member of proud Dhangar Community.


Despite the fact that girls' education was a farther dream in those days, Ahilyabai was homeschooled by her father.
Ahilya didn't belong to any royal family but in a twist of fate she is still remembered as one of the most revered Queen in the history.


While they were living their humdrum lives, one day Malhar Rao Holkar, commander of the Peshwa Bajirao & Lord of the Malwa stopped in Chondi on his way to Pune, where he couldn't help but notice a young 8yrs old Ahilyabai in the temple service feeding the poor & hungry.

He was so impressed by the sheer innocence&beauty with simplicity character of Ahilyabai dat he asked her hand in marriage for his son Khanderao Holkar.Just like that she got married to Khanderao in 1733 at a tender age of 8&became a bride of esteemed Maratha community of Holkars

But destiny had something else in store for her as her husband died in the Battle of Kumbher in 1754 leaving her widow at 29.Distressed Ahilyabai was to commit Sati when her father-in-law Malhar Rao refused to let it happen.
ALL , AHILYABAIITIHAS
Khatvaanga
Khatvaanga
@khatvaanga
Starting my 2nd thread on Sringeri Parampara. This will cover the Jagadgurus after Sri Vidyaranya to Sri Shivabhinava Nrisimha Bharati.

It is really very tough to match the brilliance and achievements of Vidyaranya. After whom came 15 - Chandrashekara Bharati [1386-1389].

The next Acharya was Nrisimha Bharati [1389-1408]. Harihara raya found a town for this Acharya - Narasimhapuram. Acharya helped the king by guiding him in political affairs. He also initiated the kind with mahamantras for spiritual development.

Subsequent Acharyas were
15-Puroshottama Bharati [1408 - 1448]
16-Shankara Bharati[1448 - 1455]
17-Chandrasekhara Bharati II [1455 - 1464]
18- Nrisimha Bharati II [1464 - 1479]
19-Puroshottama Bharati II [1479 - 1517]

20-Ramachandra Bharati [1517 - 1560]. Sadashiva Raya was emporer of Vijayanagara during this time.
21-Nrisimha Bharati III [1560 - 1573]
22-Nrisimha Bharati IV [1573 - 1576]
23-Nrisimha Bharati V [1576 - 1600]

24-Abhinava Nrisimha Bharati [1600-1623]. When he visited Malahanikareswara temple for first time he noticed there was no Vinayaka there so he took piece of turmeric and drew outline of Ganesha on a pillar and offered puja.
ALL