Danil Zherebtsov
Danil Zherebtsov
  • 58
  • 107 966
You can't deploy ML model without these
How to properly prepare your model for serving and what are the deployment options available.
All videos in a series:
1️⃣ Business & Data understanding - ua-cam.com/video/c_CAK0tln_w/v-deo.html
2️⃣ Data Processing - ua-cam.com/video/Zkmyq-pDnmU/v-deo.html
3️⃣ Modeling Best Practices - ua-cam.com/video/EOWLqekVYp0/v-deo.html
4️⃣ Model Deployment - THIS VIDEO
Model deployment with Docker - ua-cam.com/video/vA0C0k72-b4/v-deo.html
Model deployment with UI & Streamlit - ua-cam.com/video/EEuoDuQiQYs/v-deo.html
----------------------------------------------------------------------------------
Attributes:
Deliberate Thought by Kevin MacLeod is licensed under a Creative Commons Attribution 4.0 license. creativecommons.org/licenses/by/4.0/
Source: incompetech.com/music/royalty-free/?keywords=deliberate+thought
Artist: incompetech.com/
Переглядів: 2 553

Відео

How to train an effective model and prove everyone that it works.
Переглядів 3507 місяців тому
Fundamentals of correct ML model training. From selecting the optimization/evaluation metrics to the validation strategies. All videos in a series: 1️⃣ Business & Data understanding - ua-cam.com/video/c_CAK0tln_w/v-deo.html 2️⃣ Data Processing - ua-cam.com/video/Zkmyq-pDnmU/v-deo.html 3️⃣ Modeling Best Practices - THIS VIDEO 4️⃣ Model Deployment - ua-cam.com/video/oYlNP21g2Y0/v-deo.html Attribu...
Prepare data for Machine Learning like a Pro
Переглядів 2607 місяців тому
Here we'll discuss: - What are the different data types and how to work with all of them? - How to correctly transform everything into numeric format? - What goes into feature-engineering? - How make sure all the above won't break when new data starts coming in? All videos in a series: 1️⃣ Business & Data understanding - ua-cam.com/video/c_CAK0tln_w/v-deo.html 2️⃣ Data Processing - THIS VIDEO 3...
All the steps of any DS project Spelled Out by a Data Scientist
Переглядів 2697 місяців тому
Business understanding - Data assessment - Date processing - Modeling - Deployment: a comprehensive walkthrough about how to Data Science. All videos in a series: 1️⃣ Business & Data understanding - THIS VIDEO 2️⃣ Data Processing - ua-cam.com/video/Zkmyq-pDnmU/v-deo.html 3️⃣ Modeling Best Practices - ua-cam.com/video/EOWLqekVYp0/v-deo.html 4️⃣ Model Deployment - ua-cam.com/video/oYlNP21g2Y0/v-d...
New kind of Kaggle competitions just launched! Top 50 get rewarded.
Переглядів 3457 місяців тому
Spoiler: the whole competition is hosted on Telegram! Competition Telegram Bot: t.me/SynnaxCompetitionBot Competition Discussion Channel: t.me/SynnaxLab Competition Description & Files: tinyurl.com/eu2txd6y Attributes: Deliberate Thought by Kevin MacLeod is licensed under a Creative Commons Attribution 4.0 license. creativecommons.org/licenses/by/4.0/ Source: incompetech.com/music/royalty-free/...
Getting ahead of 99% of your peers is easy. Do this.
Переглядів 3568 місяців тому
Get a better job, recognition, financial freedom doing these simple things. Deliberate Thought by Kevin MacLeod is licensed under a Creative Commons Attribution 4.0 license. creativecommons.org/licenses/by/4.0/ Source: incompetech.com/music/royalty-free/?keywords=deliberate thought Artist: incompetech.com/ Inspired by Victor Cheng's newsletter!
Quick ML model cloud deployment with UI explained
Переглядів 1,1 тис.9 місяців тому
Quickly transform your local ML model into an online app/service with user interface using nothing but streamlit. Repository with code from the video: github.com/DanilZherebtsov/deploy-model-streamlit Deliberate Thought by Kevin MacLeod is licensed under a Creative Commons Attribution 4.0 license. creativecommons.org/licenses/by/4.0/ Source: incompetech.com/music/royalty-free/?keywords=delibera...
Learn Generative AI & Data Science from scratch in 2024: Complete guide.
Переглядів 2,9 тис.11 місяців тому
From Scratch: in 2024 start and finish with a job your journey in to Data Science with incline into Generative AI. Told by a Data Scientist. Courses in sequence: Step 1️⃣ PYTHON • Python masterclass - tinyurl.com/5n78h2py • Python OOP - tinyurl.com/58wkzhn7 Step 2️⃣ GIT • Git from zero to hero - tinyurl.com/mrxtyb57 Step 3️⃣ Data Science • Traditional Data Science & ML Master Class - tinyurl.co...
Learn these pandas tricks now
Переглядів 17811 місяців тому
Simple yet non obvious pandas capabilities that I use every day. 0:00 Intro 0:14 Import broken data 0.58 Get indexes of min/max values 1:26 Subset data by values 2:07 Remove records by value 3:01 Split data 3:28 Get % data distribution 3:59 Dataframe to markdown 4:14 Open data in Chrome/Safari Code from video here: gist.github.com/DanilZherebtsov/ca88245bfa4de56521a9107b73b55079
Process 100GB data like it is 20GB, told by a Data Scientist
Переглядів 386Рік тому
How to work with 100 GB datasets on your local machine. Code here: gist.github.com/DanilZherebtsov/4a2e0692f37d8db76b02d6130f10fe3f Automated option: $pip install verstack # from verstack import PandasOptimizer optimizer = PandasOptimizer() df = optimizer.optimize_memory_usage('data.csv') #
How to science the sh!t out of a problem.
Переглядів 377Рік тому
True story. Don't try this at home...
Night in life of a Data Scientist. True story...
Переглядів 2,6 тис.Рік тому
Night in life of a Data Scientist. True story...
Deploy ML model in 10 minutes. Explained
Переглядів 39 тис.Рік тому
Level up your Data Science to Machine Learning Engineering. Docker engine download: docs.docker.com/engine/install/ Repo with code from video: github.com/DanilZherebtsov/ml-docker-flask-api Study MACHINE LEARNING DEPLOYMENT INTO PRODUCTION ENVIRONMENT Course 1 (Intro in ML in prod): imp.i384100.net/MLProduction1 Course 2 (ML&Data Lifecycle in prod): imp.i384100.net/MLProduction2 Course 3 (ML Mo...
Crazy ways porn sites use your data
Переглядів 2,1 тис.Рік тому
Crazy ways porn sites use your data
Is iPhone 15 worth it?
Переглядів 241Рік тому
Is iPhone 15 worth it?
Advanced missing values imputation technique to supercharge your training data.
Переглядів 2,2 тис.Рік тому
Advanced missing values imputation technique to supercharge your training data.
LITTLE tings that make a BIG programmer
Переглядів 392Рік тому
LITTLE tings that make a BIG programmer
Amazon interview cought on tape
Переглядів 1,3 тис.Рік тому
Amazon interview cought on tape
5 Breathtaking tech books that I will never forget
Переглядів 236Рік тому
5 Breathtaking tech books that I will never forget
Best Mac productivity apps
Переглядів 1,2 тис.Рік тому
Best Mac productivity apps
M2 Max VS M2 Air - Machine Learning. Should you buy the Air for Data Science?
Переглядів 2,8 тис.Рік тому
M2 Max VS M2 Air - Machine Learning. Should you buy the Air for Data Science?
Correct Data Science setup for Arm Macs (M1/M2)
Переглядів 1,8 тис.Рік тому
Correct Data Science setup for Arm Macs (M1/M2)
M2 Mac python installation the right way
Переглядів 4 тис.Рік тому
M2 Mac python installation the right way
Best Mac terminal mode ever
Переглядів 1,7 тис.Рік тому
Best Mac terminal mode ever
M2 MAX changed everything
Переглядів 1 тис.Рік тому
M2 MAX changed everything
How Make Money Coding Works?!
Переглядів 231Рік тому
How Make Money Coding Works?!
This is easier than it sounds
Переглядів 272Рік тому
This is easier than it sounds
Killer Resume template that will get you a job
Переглядів 775Рік тому
Killer Resume template that will get you a job
Single skill to supercharge your Data Science career
Переглядів 1,5 тис.Рік тому
Single skill to supercharge your Data Science career
Spelled out: what is ChatGPT, how is it trained, is it conscious…
Переглядів 172Рік тому
Spelled out: what is ChatGPT, how is it trained, is it conscious…

КОМЕНТАРІ

  • @satish1012
    @satish1012 3 дні тому

    Thanks a lot! Now I understand the core concepts. If I understand correctly, in Azure AI/ML, once a model is deployed, it provides a URL for inference along with a Docker image. I guess this is what the cloud provider is doing in the background - wrapping the model (e.g., the .joblib file) into a REST API (using something like Flask) and deploying it as a container in a Kubernetes (K8s) cluster. I guess something is happening with AWS Sage Maker

  • @FatemehBoobord
    @FatemehBoobord 4 дні тому

    Thank you, I really enjoy the code, but is it possible to use it when we simultaneously have missing data in features and labels(multilabel)?

  • @wtfanurag
    @wtfanurag 8 днів тому

    Thanks!

  • @sohamdutta4381
    @sohamdutta4381 11 днів тому

    I am getting an Aborted ! Error whenever i am using the docker --run command. Anyone knows whats going on ?

  • @mubashirshaikh
    @mubashirshaikh 14 днів тому

    you look like klaus mikaelson from vampire diaries lol

  • @mubashirshaikh
    @mubashirshaikh 14 днів тому

    lol i am working on creating a sort of analysis automation tool for my college project and this is exactly what i was looking for. Initially i was thinking about going with the iterativeimputer or knnimputer. Is your nanimputer is better than them? if thats the case then you are a fucking genius

  • @akshu7832
    @akshu7832 22 дні тому

    Informative

  • @mounishkm6906
    @mounishkm6906 25 днів тому

    After the setup of my terminal apple logo is turned into question mark and the folder image how to fix it can you please replay

    • @lifecrunch
      @lifecrunch 17 днів тому

      Your terminal apple logo turned into a question mark?? Can you provide some more details.

  • @sushant9047
    @sushant9047 Місяць тому

    Can we deploy for the code that is written in jypter notebook

    • @lifecrunch
      @lifecrunch Місяць тому

      Jupyter notebook is a research environment, not development. For production applications use .py files.

  • @AashishShah-h1k
    @AashishShah-h1k Місяць тому

    Hi, I faced a problem importing tenzorflow after installing tensorflow-metal. Did anyone else face this as well?

    • @lifecrunch
      @lifecrunch 17 днів тому

      Hi. Since the video release some changes happened. Try this: Step 1: Install TensorFlow dependencies from Apple Conda channel. conda install -c apple tensorflow-deps Step 2: Install base TensorFlow (Apple's fork of TensorFlow is called tensorflow-macos). python -m pip install tensorflow-macos Step 3: Install Apple's tensorflow-metal to leverage Apple Metal (Apple's GPU framework) for M1, M1 Pro, M1 Max GPU acceleration. python -m pip install tensorflow-metal

  • @taido4883
    @taido4883 2 місяці тому

    Exceptional video! Thank you Danil! I watched tons of other videos and have no idea on how to deploy my ML model. Stumble on this one and now I'm able to do it.

    • @lifecrunch
      @lifecrunch 2 місяці тому

      You're welcome! More cool videos coming soon

  • @יוסילוי-ח8ו
    @יוסילוי-ח8ו 2 місяці тому

    really well done. thank you!!

  • @anmolchhetri3033
    @anmolchhetri3033 2 місяці тому

    very helpful thanks, But is it require to do hyperparameter tuning of lightgbm models?

    • @lifecrunch
      @lifecrunch 2 місяці тому

      For the purpose of missing values imputation - not necessary. Tuning can give a subtle accuracy improvement and it’s justified for an actual prediction model, but I wouldn’t do it for a data processing step.

  • @yk_mislyn
    @yk_mislyn 2 місяці тому

    thanks for letting people know, but can the camera on our phone be usable by the ****** tracking the data, to gather info=' like ' facial recognition && voice data location and finger prints data.

    • @lifecrunch
      @lifecrunch 2 місяці тому

      All of this data is processed on your phone. That's how your FaceId works and other authentication services you use every day. But how **** use this data - no-one knows. It is claimed that this data never leaves your phone. I surely hope so...

  • @yk_mislyn
    @yk_mislyn 2 місяці тому

    You look like a pornstar

  • @prestonryan3734
    @prestonryan3734 2 місяці тому

    Absolute mad lad

  • @pranaychauhan2709
    @pranaychauhan2709 2 місяці тому

    very helpful !!!!!!!!!!!

  • @chidozieuzoegwu4056
    @chidozieuzoegwu4056 2 місяці тому

    Sharp

  • @chidozieuzoegwu4056
    @chidozieuzoegwu4056 2 місяці тому

    Subscribed immediately. What a straight to point video. Thanks, man.

    • @lifecrunch
      @lifecrunch 2 місяці тому

      Thanks! More cool videos coming soon

  • @stefangrandl8623
    @stefangrandl8623 2 місяці тому

    Thanks for the video and all the effort it took to produce it. It's easy to follow and nicely animated. 👍🏼 However, as of today I would rather use BentoML instead of FastAPI. It's even easier to set up an API and then publish a docker image.

    • @lifecrunch
      @lifecrunch 2 місяці тому

      Well, it's a matter of personal preference. I just got around Streamlit first...

  • @lorenzolupo9982
    @lorenzolupo9982 2 місяці тому

    This content is fire! I love the efficiency of information delivery, slow enough to understand every step and speedy enough not to waste time, with visual helpers to focus on the right visual information. I also love that you kept errors in the video, so that we learn the most common we might encounter and how to tackle them. Keep it up!

    • @lifecrunch
      @lifecrunch 2 місяці тому

      Thanks for the motivation!

  • @dmitriysmetanin
    @dmitriysmetanin 2 місяці тому

    Дружище, давай на русском. Больше ведь будет просмотров

    • @lifecrunch
      @lifecrunch 2 місяці тому

      Это как ты так посчитал?) Русскоязычное население 220 млн., а на английском говорят 1.4 млрд…

    • @dmitriysmetanin
      @dmitriysmetanin 2 місяці тому

      @@lifecrunch на международном английском говорят 1.4 млрд, но просмотры твои на международный уровень как-то не тянут. Не все математикой объясняется)

  • @fazilahamed1240
    @fazilahamed1240 2 місяці тому

    quick and clear... good job buddy

  • @narangfamily7668
    @narangfamily7668 2 місяці тому

    cheers mate thanks!

  • @mohamedanas8493
    @mohamedanas8493 2 місяці тому

    can i deploy my computer vision project using this method

    • @lifecrunch
      @lifecrunch 2 місяці тому

      Sure. You can deploy any model this way.

  • @TaeJoonKim-y1d
    @TaeJoonKim-y1d 2 місяці тому

    Thanks for sharing this video. This is very informative.

  • @Virat_._Kohli123
    @Virat_._Kohli123 3 місяці тому

  • @Virat_._Kohli123
    @Virat_._Kohli123 3 місяці тому

    Mark my words,one day you will going to be a super star 🎉❤

  • @shr00shr
    @shr00shr 3 місяці тому

    Thanks, Danil ! This is exactly what I was looking for. Clear and concise tutorial,🙏

    • @lifecrunch
      @lifecrunch 3 місяці тому

      Glad it was helpful!

  • @mohameddawoud8435
    @mohameddawoud8435 3 місяці тому

    How to use the libraries in VS CODE after installation ?

    • @lifecrunch
      @lifecrunch 3 місяці тому

      VSCode is just a text editor. You are installing the libraries in your Python environment. Import them at the top of your script and use them according to the documentation

  • @mkaya4677
    @mkaya4677 3 місяці тому

    Hi, First of all, your video provides very useful information, and I want to thank you for that. I have a question I would like to ask you. I am analyzing air pollution in a city in my country. For this purpose, I have created a dataset using air pollution data and meteorological data. I then organized these data into hourly intervals. However, I encountered a problem. My dataset contains null values. These null values appear consecutively in some parts of the dataset. For example, in the first 3000 rows, there are approximately 2500 null values for the NO2, NOX, and NO air pollutants, but in the remaining part of the dataset, there are very few null values. In addition, there are rows where data for all air pollutants are missing, but these rows cover a short period consecutively. I believe this might be due to workers turning off the devices after working hours on certain days. I have previously trained a few models to fill in these missing values, but I did not achieve good results. I would like to ask for your guidance. In these two cases, should I fill in the missing data or exclude them from the dataset? What would be the most accurate method to complete these missing values?

    • @lifecrunch
      @lifecrunch 3 місяці тому

      In the first place (a lot of consecutive missing values at the top) I would just drop them. As for those NaNs in the middle, since your data is a time series, I would use something like a rolling window or nearest neighbors values to fill in the blank spots.

  • @juancarlosruelas8935
    @juancarlosruelas8935 3 місяці тому

    Great video! Can you make a video seting up R with vitual environments as well?

    • @lifecrunch
      @lifecrunch 3 місяці тому

      I gave up R almost 10 years ago. Although beautiful framework, I had to switch to Python because it gives much more freedom in terms of software engineering and integration into the production environment.

  • @juancarlosruelas8935
    @juancarlosruelas8935 3 місяці тому

    Brilliant

  • @avinasha3603
    @avinasha3603 3 місяці тому

    Thank you !

  • @Adebowale279
    @Adebowale279 4 місяці тому

    This is just wonderful and succinct. Thank you!

    • @lifecrunch
      @lifecrunch 4 місяці тому

      Thank you for watching!

  • @GabrielaSosa-n9l
    @GabrielaSosa-n9l 4 місяці тому

    Great videos

  • @sangeethag8228
    @sangeethag8228 4 місяці тому

    Thanks a lot Danil.. You saved 4hrs of time. Its working for me :)

  • @thevicky1428
    @thevicky1428 4 місяці тому

    Can I do llama 8b fine tuned with this sir ?

    • @lifecrunch
      @lifecrunch 4 місяці тому

      With what? Docker??

    • @thevicky1428
      @thevicky1428 4 місяці тому

      @@lifecrunch yeah, I fine tuned unsloth llama 8.1 how to deploy that with docker or cloud providers

    • @lifecrunch
      @lifecrunch 4 місяці тому

      @@thevicky1428 Just like any other model. Write the inference script to query the model with prompts or whatever you want to query it with, configure docker as explained in the video, save all the required llama artifacts into the corresponding directories and there you go. Basically repeat all the steps from the video only replacing the 'predict()' function with your llama inference code.

    • @thevicky1428
      @thevicky1428 4 місяці тому

      @@lifecrunch thanks sir

  • @HZN2502
    @HZN2502 4 місяці тому

    👑🙌🙌

  • @anmolkrishnan
    @anmolkrishnan 4 місяці тому

    Great tutorial ❤

  • @dataworldsolution
    @dataworldsolution 4 місяці тому

    Thanks Sir

  • @mariusholle8380
    @mariusholle8380 4 місяці тому

    Thank you very much! I have the M2 Air and love it. I am starting to work on machine learning and was wondering, if the upgrade would make any sense. Your video answered that for me. Thank you for that!

    • @lifecrunch
      @lifecrunch 4 місяці тому

      Yeah, if you're just starting - this is more than enough. By the time you get to big volumes of data, you will figure out how to run it on google colab or kaggle. Anyway an M2 MacBook Air is a great machine for your task.

  • @yungzed
    @yungzed 4 місяці тому

    thanks, im the sole SWE intern working on an AI/ML team, these vids help a lot

    • @lifecrunch
      @lifecrunch 4 місяці тому

      Glad that it helped!

  • @alejandrobisquertt
    @alejandrobisquertt 4 місяці тому

    Dude, great video. I don’t know how this video doesn’t have more views!!! Algo I use the terminal confirmation from your preview video every day is great. thanks

  • @AdamOne1
    @AdamOne1 5 місяців тому

    good video,keep going bro

  • @giftibe5268
    @giftibe5268 5 місяців тому

    Thanks alot for these videos. Does you have a machine learning/data science course?

    • @lifecrunch
      @lifecrunch 4 місяці тому

      No I don't, but maybe sometime in future I will invest time to make it. Thanks!

  • @giftibe5268
    @giftibe5268 5 місяців тому

    loved how you touched on other aspects. well rounded

  • @giftibe5268
    @giftibe5268 5 місяців тому

    hello, great video. I quit the iTerm and reopened it. how do i get back to the Download directory with the blue border-box? Tried typed the source ~/.zschrc, but didn't work.

  • @eswarkarthikk9571
    @eswarkarthikk9571 5 місяців тому

    i bild a object detection model . that was 180mb in size . how can i deploy my model

    • @lifecrunch
      @lifecrunch 5 місяців тому

      That’s an open ended question. Deploy where? I have a few videos on the subject, check them out.

  • @Sherry-g12
    @Sherry-g12 5 місяців тому

    Thanks a lot for the great video. Somehow the links for course 3 and 4 are invalid. Could you please help update the links?

    • @lifecrunch
      @lifecrunch 4 місяці тому

      Updated. The problem was that courses 3 and 4 were merged together and had a new link. I've posted the updated link.