Alexey Grigorev
@Al_Grigor
Followers
23,258
Following
478
Media
521
Statuses
5,592
👷♂️ Building @DataTalksClub community 🎤 Event and podcast host 📚 Book author and course instructor 🌍 Berlin, Germany
Want to talk about data? Join:
Joined January 2020
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
BLEACH
• 167020 Tweets
Saka
• 126035 Tweets
#SixTONESANN
• 73559 Tweets
#らんまアニメ
• 58259 Tweets
DARLING DARLING ITS HANNI DAY
• 50863 Tweets
Southampton
• 46461 Tweets
Havertz
• 34137 Tweets
Fulham
• 29811 Tweets
Sterling
• 23303 Tweets
ジェシー
• 22001 Tweets
Brentford
• 19345 Tweets
Martinelli
• 16502 Tweets
レインボーブリッジ封鎖
• 12805 Tweets
#オールスター後夜祭
• 11625 Tweets
Ahtisa
• 11147 Tweets
Kovacic
• 10575 Tweets
Pinned Tweet
We plan a free course about LLM and AI engineering to cover:
🔸 LLMs and RAG
🔸 Vector databases
🔸 Orchestration
🔸 Monitoring
We will launch the course if there's enough interest.
Fill in this form if you're interested:
9
42
227
Learning path to mastering Data Science:
🔸 Python
🔸 Git
🔸 SQL
🔸 NumPy
🔸 Pandas
🔸 Scikit-Learn
🔸 Flask
🔸 Docker
🔸 AWS
🔸 TensorFlow
🔸 Linear Algebra
🔸 Machine Learning basics
What else?
171
665
3K
When learning machine learning, focus on these algorithms first:
🔸 Linear regression
🔸 Logistic regression
🔸 Decision trees
🔸 Random forest
🔸 Gradient boosting
🔸 Neural networks (also CNN)
In this order
Knowing them will cover 95% of applied ML cases
29
431
2K
Tools that cover 90% of data science use cases
🔸 Git
🔸 Bash
🔸 SQL
🔸 NumPy
🔸 Pandas
🔸 Scikit-Learn
🔸 Flask
🔸 Docker
Focus on them first
35
345
2K
Roadmap for learning ML Engineering:
🔸 Linear regression
🔸 Logistic regression
🔸 Evaluation metrics
🔸 Docker, web services, cloud
🔸 Model deployment
🔸 Tree-based models
🔸 Neural networks
🔸 Kubernetes
Learn it in this order and you'll be ready for an ML engineering job
23
337
2K
200+ Data Science interview questions
🔸 Supervised machine learning (linear models, trees, neural nets)
🔸 Feature selection, parameter tuning
🔸 Unsupervised learning (clustering, dim reduction)
🔸 Recommenders and search
🔸 SQL
🔸 Coding (Python), algorithms
With answers 👇
36
431
2K
My onsite interview for ML engineering with a FAANG company:
🔸 Behavioral
🔸 Coding round 1 (two problems)
🔸 Coding round 2 (two problems)
🔸 System design
🔸 ML case study
Here are the questions I got👇
40
235
1K
Registration to Machine Learning Zoomcamp 2022 is open!
Learn ML Engineering in 4 months in a free online course:
- Linear and logistic regression
- Tree-based models
- Neural networks
- Deployment with AWS, Serverless, Kubernetes
👉
41
477
1K
I just started a Data Engineering community here on Twitter
Since the communities on Twitter is a new thing, it's invite-only currently
Reply if you need an invite
561
160
1K
The most useful online courses I took when learning machine learning
🔸 Machine Learning (coursera)
🔸 Statistical Learning (edx)
🔸 Analytics Edge (edx)
🔸 Learning from Data (caltech)
I took a lot of courses. But these four were the best
23
187
1K
Most candidates cannot solve this interview problem:
🔸 Input: "aaaabbbcca"
🔸 Output: [("a", 4), ("b", 3), ("c", 2), ("a", 1)]
Write a function that converts the input to the output
I ask it in the screening interview and give it 25 minutes
How would you solve it?
480
115
1K
Learning paths to mastering:
🔸 Data science
🔸 Data engineering
🔸 Machine learning engineering
🔸 MLOps
All in one mega-thread! 👇
(Make sure to check the replies!)
3
187
819
Want to get into Machine Learning?
🔸 If you want to learn — learn mathematics
🔸 if you want to earn — learn Scikit-Learn
28
106
825
Learning path to mastering MLOps:
🔸 Linux
🔸 Python
🔸 Docker
🔸 AWS
🔸 Terraform
🔸 Kubernetes
🔸 Prometheus
🔸 Grafana
🔸 Kubeflow
What else?
30
124
775
Want to learn Data Engineering?
Join Data Engineering Zoomcamp!
📅17 Jan 22
💰 Free
Plan:
🔸️ Data warehousing (BigQuery)
🔸️ Batch processing (Airflow, Spark)
🔸️ Analytics engineering (DBT)
🔸️ Stream processing (Kafka)
👉
16
221
769
Our free ML Engineering course starts soon
🔸 Regression & classification
🔸 Evaluation metrics
🔸 Tree-based models
🔸 Deep learning
🔸 AWS, Serverless, Kubernetes
👉
Retweet it and I'll send you a notion doc with student notes from previous cohort
31
511
733
Want to become a Data Engineer in 2023?
Join
@DataTalksClub
's free course and learn
🔸Docker, Terraform
🔸Workflow orchestration (Prefect)
🔸Data warehousing (BigQuery)
🔸Analytics engineering (dbt)
🔸Batch processing (Spark)
🔸Stream processing (Kafka)
8
191
726
🤖 Learning machine learning?
Focus on mastering these algorithms:
🔸 Linear regression
🔸 Logistic regression
🔸 Decision trees
🔸 Random forest
🔸 Gradient boosting
🔸 Neural networks + CNN
Don't know how?
Here's a detailed mega-thread 👇
(check the replies as well!)
15
171
701
Machine Learning at university:
🔸 Eigenvalues, eigenvectors
🔸 Lagrange multipliers
🔸 KKT conditions
🔸 Optimization in function spaces
Machine Learning at work:
from sklearn.linear_model import LogisticRegression
19
101
699
ML Zoomcamp is back!
We're starting a new cohort of the free course for ML engineers! Want to join?
You can read more about the course and register 👇🏼
7
178
666
More than 5,500 people already signed up to our data engineering course!
Do you also want to learn data engineering for free?
We cover topics ranging from batch and stream processing to analytics engineering
👉
We start on 17 Jan!
7
171
650
Our Data Engineering Course starts now!
Join here:
(or watch later in recording!)
Have fun!
1
121
645
ML Zoomcamp - learn ML engineering in 4 months in a free online course
🔸 Regression
🔸 Classification
🔸 Evaluation metrics
🔸 Model deployment
🔸 Decision trees and ensembles
🔸 Neural networks
🔸 Serverless deep learning
🔸 Kubernetes and Kubeflow
👉
19
181
623
They say:
"Kaggle doesn't teach you how to translate a business problem into machine learning terms"
This is NOT true
You CAN learn a great deal from
@kaggle
Let me tell you how you can do it in 4 simple steps. None of them requires taking part in a competition
Thread 👇
15
123
598
If your machine learning model is 99% correct, something is wrong
Possible reasons:
🔸 Wrong evaluation metric
🔸 Bad validation set
🔸 Overfitting
🔸 Leakage
What else?
60
78
583
Things you don't need to be a great ML engineer
🔸 Mathematics
🔸 Statistics
🔸 In-depth ML knowledge
Instead focus on this
🔸 Intuitive understanding of ML algorithms
🔸 Good engineering practices
🔸 Cloud
🔸 Model deployment
16
87
560
Our Data Engineering course is over and we're preparing a new one
MLOps Zoomcamp:
🔸 Processes
🔸 Training (experiment tracking, ML pipelines)
🔸 Serving (online, batch, streaming)
🔸 Monitoring
🔸 Best practices
Register here, it's free
7
127
549
A new cohort of Data Engineering Zoompcamp starts soon!
That's why we prepared an introductory article so you can learn more about it.
You can read it at
10
94
538
In less than a week we're starting Data Engineering Zoomcamp
It's a free 10-week course about Data Engineering fundamentals
Join us and 18,000 more students!
👉
4
137
495
Our free MLOps course already has 3.8k+ registrations and 1k+ stars on GitHub!
This course teaches the basics of productionizing ML:
🔸 Tracking experiments
🔸 Building training pipelines
🔸 Model deployment
🔸 Model monitoring
🔸 Best practices
👉
6
114
488
The most useful part of math for applied machine learning is Linear Algebra
🔸 Vector multiplication
🔸 Vector norm
🔸 Matrix multiplication
🔸 Matrix inverse
Focus on learning that and you'll know enough for 95% of practical cases
18
99
467
Books I used when learning machine learning
🔸 Pattern Classification
🔸 Pattern Recognition and Machine Learning
🔸 Machine Learning: A Probabilistic Perspective
🔸 Elements of Statistical Learning
🔸 Deep Learning
There were others as well. But these were most useful
14
78
463
The toughest data science interview I ever had
I got bombarded for 45 minutes with theoretical questions:
🔸 Entropy
🔸 KL divergence, other divergences
🔸 Kolmogorov complexity
🔸 Jacobian and Hessian
🔸 Linear independence
🔸 Determinant
Continued 👇
20
66
471
Interview process for ML Engineers and Data Scientists:
1️⃣ Screening
2️⃣ Machine Learning
3️⃣ Coding
4️⃣ Case studies
5️⃣ System design
6️⃣ Behavioral
Here's what you can expect at each step (Thread) 👇
7
107
460
Learning path to mastering data engineering:
🔸 SQL
🔸 Git
🔸 Bash
🔸 PostgreSQL
🔸 Java, Scala
🔸 Python
🔸 Docker
🔸 AWS
🔸 Airflow
🔸 Kafka
🔸 Spark
🔸 Kubernetes
What else? (if this list is not long enough)
39
94
458
Our free MLOps course starts tomorrow
Hurry up, register now!
We'll cover:
🔸️ Processes
🔸️ Experiment tracking
🔸️ Creating ML pipelines
🔸️ Model deployment
🔸️ Model monitoring
🔸️ Best engineering practices
👉
6
114
452
I'm a citizen of Russian Federation and I'm very ashamed of what my government is doing
This is shocking and I still cannot believe this is happening
People of Ukraine, I love you all and I hope that your families and friends are safe
7
27
434
I have 5 copies of Machine Learning Bookcamp
To win one:
🔸 Follow me
🔸 Retweet this tweet
Winners selected randomly. Results announced on Wednesday
ML Bookcamp - Learn machine learning by doing projects
🔗
@ManningBooks
24
478
381
Good data engineering is a pre-requisite for data science
15
35
358
Many machine learning models boil down to matrix multiplication
🔸 Linear regression
🔸 Logistic regression
🔸 Neural networks
Matrix multiplication is the cornerstone of machine learning
Learning machine learning? Learn to think in matrix operations
9
66
356
I found an old collection of my tweets put together in a notion doc
Topics:
🔸 Processes
🔸 ML Engineering
🔸 MLOps
🔸 Data science
🔸 Data engineering
🔸 Tools
🔸 Math
🔸 Learning ML
And other things
100+ tweets in total
Retweet and I'll DM it to you
59
408
312
Are you curious about MLOps?
How can you apply it in a real-world project?
Here is a summary of my article about it 🧵
5
67
332
Hey
@YouTube
can you please unblock our free Data Engineering course? It's certainly not a deceptive practice - and I believe not spam and scam either
Well, at least thanks for not blocking the entire channel!
The "appeal" button is of course not working
@YouTubeCreators
17
59
323
Mastering linear regression
🔸 Take a dataset
🔸 Train a model with Scikit-Learn
🔸 Understand the coefficients
🔸 Experiment with regularization
🔸 Experiment with feature transformations
🔸 Implement it using normal equation
🔸 Implement it using SGD
Something else?
18
55
316
2,500+ students have signed up for our free ML engineering course!
Join us too and learn
🔸 Linear & logistic regression
🔸 Virtual environments, Docker
🔸 Model deployment with AWS
🔸 Tree-based models
🔸 Neural networks
🔸 Kubernetes
🔸 KServe
👉
11
72
322
It's week 6 of Machine Learning Zoomcamp and we cover tree-based models:
🔸 Credit risk scoring project
🔸 Decision trees
🔸 Parameter tuning
🔸 Random forest
🔸 Gradient boosting
🔸 Tuning XGBoost
👉
0
67
305
Data Engineering Zoomcamp starts now!
We're covering topics ranging from batch and stream processing to analytics engineering
Do you want to learn data engineering for free?
Join us live to learn more about the course:
2
61
294
I have 5 copies of Machine Learning Bookcamp
To win one:
🔸 Follow me
🔸 Retweet this tweet
Winners selected randomly. Results announced on Wednesday
ML Bookcamp - Learn machine learning by doing projects
🔗
@ManningBooks
25
432
288
Registration to Data Engineering Zoomcamp is open!
Join us and learn
🔸 Docker
🔸 Orchestration
🔸 Data warehousing
🔸 Analytics engineering
🔸 Batch processing
🔸 Streaming
Start date: 16 January 2023
👉
8
75
299
8 free copies of Machine Learning Bookcamp!
To get one:
- Follow me
- Retweet this tweet
ML Bookcamp: learn
#MachineLearning
by doing projects
Results on Wednesday
@ManningBooks
#100DaysOfCode
#100DaysOfMLCode
23
364
283
The most useful online courses I took when learning machine learning
🔸 Machine Learning (coursera)
🔸 Statistical Learning (edx)
🔸 Analytics Edge (edx)
🔸 Learning from Data (caltech)
I took a lot of courses. But these four were the best
9
48
294
XGBoost vs Logistic Regression:
➕ Outperforms in 95% of cases
➖ More complex
➖ More difficult to tune
➖ More difficult to serve
Want to win a
@kaggle
competition? Use XGBoost
Want to solve a business problem? Start with LogReg
18
41
296
AUC stands for "Area Under the Curve"
Usually, when we say "AUC" we mean "AUC ROC" - the area under the ROC curve
It's a way of evaluating the quality of a binary classification model based on a ROC curve
Let's see what it is 🧵
6
46
294
You want to start working with ML
Two options:
1️⃣ Learn Python, NumPy, and Scikit-Learn. Use them to solve problems
2️⃣ Spend 2 years at university, study math, graduate and then learn everything from 1️⃣
7 years ago, I chose 2️⃣. But you can save 2 years
17
28
284
We're starting a new cohort of our free Data Engineering course on Jan 15!
🔸 Learn the most important concepts in data engineering
🔸 Get real-world hands-on experience
🔸 Build a project for your portfolio
Join us at
6
84
282
It's week 12 of Machine Learning Zoomcamp!
We cover deploying deep learning models with AWS Lambda
🔸 Introduction to Serverless
🔸 TensorFlow Lite
🔸 Preparing Lambda code
🔸 Preparing a Docker image
🔸 Creating the lambda function
🔸 API Gateway
👉
7
41
278
Our Data Engineering Zoomcamp is trending on GitHub!
And we just started a new cohort of this free online course. Join us!
Register:
Star the repo:
4
58
279
Machine Learning Zoomcamp starts in a few hours!
The first lesson is already available:
🔸 Introduction to ML
🔸 CRISP-DM
🔸 Model Selection
🔸 NumPy
🔸 Linear Algebra Refresher
🔸 Pandas
Course repo 👇 Don't forget to ⭐️!
2
62
272
You want to start with ML
Two options:
1️⃣ Learn Python, NumPy, Scikit-Learn
Use them to solve business problems
2️⃣ Spend 2 years at university, study math
Graduate and learn everything from 1️⃣
8 years ago, I chose 2️⃣. But you can save 2 years
7
40
269
Earning with machine learning 💰
Invest in these skills:
🔸 Communication
🔸 Problem identification
🔸 Prioritization
🔸 Rapid prototyping
🔸 Building data pipelines
🔸 Model deployment
Did you notice math in the list? Yep, not there.
10
47
254
Do you want to bring your NumPy skills to the next level?
Implement K-Nearest Neighbors from scratch with NumPy
No loops
11
19
253
More than 1,800 people already signed up for Machine Learning Zoomcamp!
Every time somebody registers, I get an email in my Gmail. It's a great feeling - keep them coming =)
The course starts in September - hurry up!
Register here:
14
50
253
Most important things in applied machine learning:
🔸 Cross-validation
🔸 Exploratory data analysis
🔸 Data cleaning and preparation
🔸 Feature engineering
🔸 Scikit-Learn's fit() and predict()
Focus on them first
6
40
236
Machine Learning at university:
🔸 Eigenvalues, eigenvectors
🔸 Lagrange multipliers
🔸 KKT conditions
🔸 Optimization in function spaces
Machine Learning at work:
from sklearn.linear_model import LogisticRegression
3
37
239
You trained a model in a notebook
What's next?
🔸 Turn the notebook into a script
🔸 Export the model
🔸 Wrap it in Flask
🔸 Create a virtual environment
🔸 Package it in Docker
🔸 Deploy to the cloud
🔸 Start using it
5
32
233
Python problems for preparing for an ML job interview:
🔸 Count characters in a string
🔸 Find / remove duplicates in list
🔸 Run-length encoding
🔸 Find top K elements in a sequence
🔸 2 sum and 3 sum
What else were you asked on your Python interviews?
8
30
233
Accuracy can be misleading
What to use instead?
👉 Precision
Among examples predicted as positive, how many are correct?
👉 Recall
How many positive examples are identified correctly?
Confused? Let me explain it with an example 🧵
7
50
230
Almost finished recording the lesson about Random Forest for Machine Learning Zoomcamp
And here's a behind the scenes picture =)
(I actually have a QWERTZ keyboard, that's why I make so many typos in the videos)
10
15
229
Data engineering:
Moving data from one place to another
Sounds easy, but it's not
14
22
225
Our free ML Engineering course starts on Monday!
Join 4600+ other zoomcampers and learn
🔸 Linear & logistic regression
🔸 Model evaluation
🔸 Model deployment
🔸 Virtual env, Docker, AWS
🔸 Tree-based models
🔸 Neural nets
🔸 Serverless, Kubernetes
👉
12
52
226
After two years of work, it finally happened!
Machine Learning Bookcamp is no longer a MEAP!
You can get it here:
10
33
213
The most important formula in Machine Learning
w = (XᵀX)⁻¹ Xᵀy
That's Normal Equation. You use that to find the weights for the linear regression model
If you understand it, you know enough math for 95% of ML
If you don't, check this video
👉
5
33
210
Cross-validation is the most important concept in machine learning
Whenever you have a question like
🔸 Is random forest better than logistic regression?
🔸 Should I remove outliers?
🔸 Which category encoding method to use?
🔸 Do I need regularization?
Use CV to find out
4
43
210
Want to learn how to build frontend for ML?
At
@DataTalksClub
we start a DIY group to learn by doing
For the first project we will
🔸 Train a model
🔸 Build
@streamlit
frontend
🔸 Dockerize it
We have a draft plan
Retweet and I'll DM it to you (feedback is welcome!)
24
215
205
Preparing for a
#MachineLearning
#DataScience
interview?
One retweet - one theoretical interview question in the thread 👇
Feel free to give your answers
Let's start!
#100DaysOfCode
#100DaysOfMLCode
6
149
198
Data Engineering Zoomcamp starts soon
You probably have a lot of questions?
I'll answer them now live (available for replay later)
1
33
199
ML Zoomcamp - learn ML engineering online for free
🔸 Regression
🔸 Classification
🔸 Model evaluation
🔸 Model deployment
🔸 Tree-based models
🔸 Neural networks
🔸 Serverless deep learning
🔸 Kubernetes & Kubeflow
The course starts in September!
👉
5
53
193
My favorite rules of machine learning:
🔸 Don't be afraid to launch without machine learning
🔸 Keep it simple and get the infrastructure right
🔸 Interpretable models make debugging easier
🔸 Launch and iterate
What are yours?
14
29
184
Just finished recording an intro lesson to Kubernetes!
Coming soon to our Machine Leaning Zoomcamp course
2
15
193
We have almost reached 5000 registrations for the free MLOps course!
We'll cover:
🔸 Introduction to MLOps
🔸 Experiment tracking and model management
🔸 Orchestration and ML Pipelines
🔸 Model Deployment
🔸 Model Monitoring
🔸 Best Practices
👉🏼
3
42
197
Some people will tell you that you must know math to get into machine learning
Don't listen to them
They are just afraid of competition
22
20
186
Things I do every time I perform EDA
🔸 df.head()
🔸 df.describe()
🔸 df[col].unique()
🔸 df[col].nunique()
🔸 df.isnull().sum()
🔸 sns.histplot()
Here's me doing EDA for the car prices dataset
👉
8
24
195
I picked up the idea of learning
#MachineLearning
by doing projects at
@Kaggle
I spent years at university studying ML and watching how equations are solved on the blackboard
But only on Kaggle I actually learned it
#100DaysOfCode
#100DaysOfMLCode
5
45
192
Skills to impress potential data science employers:
🔸 Data engineering
🔸 Model deployment
🔸 Cloud-based services
🔸 Infrastructure as code tools
🔸 Communication and storytelling
What else?
10
33
184
8 reasons machine learning projects fail - by
@elenasamuylova
🔸 Doing ML for wrong reasons
🔸 ML not needed
🔸 Bad data
🔸 Poor problem framing
🔸 Model ≠ product
🔸 Bad infrastructure
🔸 No trust from stakeholders
🔸 Production failures
Solution? 👉
4
34
182
Week 1 of Machine Learning Zoomcamp:
🔸 What's ML
🔸 Supervised Machine Learning
🔸 Process for ML projects
🔸 Linear algebra refresher
🔸 Numpy and Pandas
Here's a thread with tweet summaries this week
2
41
183
Linear algebra's most important operations:
1️⃣ Vector-vector multiplication
2️⃣ Matrix-vector multiplication
3️⃣ Matrix-matrix multiplication
The best way to understand them is to express 2️⃣ with 1️⃣ and 3️⃣ with 2️⃣
Let me show you how 🧵
4
28
185
8 free copies of Machine Learning Bookcamp!
To get one:
- Follow me
- Retweet this tweet
ML Bookcamp: learn
#MachineLearning
by doing projects
Results on Wednesday
@ManningBooks
#100DaysOfCode
#100DaysOfMLCode
21
271
163
My tech screening interview
1️⃣ Introduction (5 min)
2️⃣ Projects you worked on (5 min)
3️⃣ Deep dive into a project (20 min)
🔸 Role in the project
🔸 Why it started
🔸 Models used
🔸 Deployment process
4️⃣ Coding exercise (25 min)
5️⃣ Questions (5 min)
6
20
179
Most useful math for applied machine learning:
🔸 Vector multiplication
🔸 Vector norm
🔸 Matrix multiplication
🔸 Matrix inverse
Focus on learning that and you'll know enough for 95% of practical cases
1
28
179
10 free copies of Machine Learning Bookcamp!
To get one:
- Follow me
- Retweet this tweet
ML Bookcamp: learn
#MachineLearning
by doing projects
Results on Wednesday
@ManningBooks
#100DaysOfCode
#100DaysOfMLCode
15
300
175
Women in Data & ML to follow on Twitter
@aicoding_
@aiflavours
@anacoding
@andradaolteanuu
@BecomingDataSci
@beeonaposy
@chipro
@DalianaLiu
@frlazzeri
@KhuyenTran16
@lucytalksdata
@mervenoyann
@misraturp
@pandeyparul
@rctatman
@Soledad_Galli
@vboykis
@visenger
12
50
180
Thanks
@AWS
for selecting me as ML Hero. Can't be more happy!
As a hero, I get some AWS credits
I can give them to the community. Some ideas:
- ML Zoomcamp projects or project of the week (best projects get credits)
- Blogothon (best articles win credits)
What else can I do?
17
8
179
8 free copies of Machine Learning Bookcamp!
To get one:
- Follow me
- Retweet this tweet
ML Bookcamp: learn
#MachineLearning
by doing projects
Results on Wednesday
@ManningBooks
#100DaysOfCode
#100DaysOfMLCode
9
243
169
(XᵀX)⁻¹ Xᵀy
Do you understand what's going on here? You know enough math for 95% of machine learning
No? Do that and you're all set:
from sklearn.linear_model import LinearRegression
16
27
172
Repo for ML Zoomcamp & Bookcamp now has 1.1k stars!
There's code for
🔸 Predicting car price
🔸 Identifying churn
🔸 Model evaluation
🔸 Model deployment
🔸 Risk scoring
🔸 Clothes classification
🔸 Serverless deployment & Kubernetes
And more!
👉
2
37
172
8 free copies of Machine Learning Bookcamp!
To get one:
- Follow me
- Retweet this tweet
ML Bookcamp: learn
#MachineLearning
by doing projects
Results on Wednesday
@ManningBooks
#100DaysOfCode
#100DaysOfMLCode
11
283
163
For any project, follow these steps
1️⃣ Make it work
2️⃣ Make it right
3️⃣ Make it fast
In this exact order
It's important. Let me explain why
Thread 👇
4
19
172
Our Data Engineering course starts now!
Join us live to learn about:
- Syllabus
- Logistics
- Projects
- Learning in public
-
@DataTalksClub
slack
Watch here:
1
39
164
Are you ready to master MLOps in practice?
Learn about putting your ML in production in a free 6-week course!
From experiment tracking and model management to model deployment to best practices and more!
👉🏼
1
34
163