🎛┊applied-ml

[honest niche]

Has anyone tried spaCy's "curated transformers"? https://github.com/explosion/curated-transformers https://twitter.com/spacy_io/status/1687103018628722688?s=20

spaCy (@spacy_io)

Out now: version 1.0.0 of Curated Transformers 🎉 State-of-the-art Transformers, brick by brick. With support for Llama 2, torch.compile, ALiBi, TorchScript tracing, and many other improvements ✨

https://t.co/C4w6moAbD8

Twitter · Aug 3, 2023, 2:07 PM

This event from Weights & Biases on LLM evaluation might be of interest to folks: https://www.eventbrite.com/e/deep-dive-into-llm-evaluation-with-weights-biases-tickets-689536541357?aff=WBS

[copper acorn]

Recommender Systems in the Era of LLM . Awesome-LLM4RS-Papers:
https://github.com/nancheng58/Awesome-LLM4RS-Papers

[honest niche]

Hi everyone. I'm pleased to share we've scheduled our first #1130788094753394719 event with Sayak Paul from Hugging Face talking about diffusion models & Diffusers! Hope you'll be able to attend. 🙂 https://discord.gg/kaggle?event=1138491012562554900

If you have suggestions for other speakers / events in applied ML or research areas, let me know!

[honest niche]

Follow-up from the Discord event @graceful temple just held -- @fresh bluff if you or anyone at H20 would like to give a talk about H20 or your team's involvement in competitions or anything, hit me up 🙂

[fresh bluff]

Sure thing, Meg! Thanks for the opportunity!

[honest niche]

Just send me an email: [e-mail] and we could coordinate there

[honest niche]

Has anyone played around with Jupyter AI? https://github.com/jupyterlab/jupyter-ai

[honest niche]

A reading list for practical applications of LLMs from the inestimable Vicki Boykis https://gist.github.com/veekaybee/be375ab33085102f9027853128dc5f0e

[lunar ether]

Vicki is amazing! Such a down-to-Earth practitioner. I read as much of her work as I can.

That reminds me - speaking of Vicki - her "What Are Embeddings" guide is astounding.

[queen fern]

Hi, I am currently taking the machine learning course on Google skills. I am a bit confused on the training, testing and validation set. After training set, do we use test or validation set?

[frigid yoke]

You are training your model using the train set, and then you evaluate its performance using the validation set. You use the performance metrics coming from the validation set to improve your training. Then, in order to ensure that you haven't accidentally overfitted the values in the validation set (it can happen), you use your test set to ensure that the results in your metrics are indeed good

[queen fern]

Thank you.

[fleet palm]

Here's a visual:

[noble fable]

Hey, my team is working on real estate project and I am new to ml, I want to make recommendation model for this project can you please suggest me what to do?

Or model should be trained or developed when project get deployed?

I want to implement my learning

[deft pecan]

is your dataset similar to the boston house price dataset? Is it a regression problem? my suggestion would be that you should start with visualization and think about what kind of data preprocessing should you do to your data before you input all of these data into some model. if it is a small dataset, I recommend you to start with simple model such as linear regression or SVM and do K fold cross validation.

[mild ice]

Guys, please help me find resources for: Analysis of News Articles and videos for regional languages

I want to make a Media News Monitoring and Feedback System that can handle multiple regional languages, categorize news stories, and notify me about negative coverage of news in the media.
You may suggest some good resources related to sentiment analysis from news articles and video transcripts

[noble fable]

Thank,
I already made a KNN model but I don't know how I would go ahead.
I mean how the recommendation model works on a big company's website.
I just implemented my learning as creating an API for knn algo by making features matric of some important attributes.
What should I do next...

[velvet lotus]

Check out how you can use the ChatGPT API to solve various Natural Language Processing tasks in a very short amount of time with minimum coding experience in my latest video!

If you know how to work with python lists, dictionaries, for loops, if statements, while loops and functions, you can now easily solve NLP tasks such as text summarization, sentiment analysis, topic modeling, text transformations (like translation, grammar correction, style adjustments), chatbot development, and so much more!

On a personal note, it was a lot of fun to design the thumbnail for this one! 😁

https://youtu.be/e8z886SP-fU

[finite moth]

Hi everyone 👋 I new to object detection and tracking domain and I currently working on a project. I want to tune yolo-nas model for my dataset. Current I have 4-6 videos with annotation. I have extracted annotations into separate frame-wise text file for each video.
Text format is: class-number x_center_normalized y_center_normalized width_normalized height_normalized
Eg: sample_1.txt ->

5 0.102 0.32 0.63 0.21

sample2_txt:

5 0.102 0.32 0.63 0.21
2 0.402 0.82 0.33 0.11

How do I fine tune yolo-nas? I initially had videos and 1 annotation file containing details about the bounding box and object class. Now how do I proceed? I tried following: https://colab.research.google.com/drive/1q0RmeVRzLwRXW-h9dPFSOchwJkThUy6d
But I don't know which dataloaders to use and how to format my dataset?

[velvet lotus]

If you want to learn more about Generative AI and how you can use it in your life and at work, check out my latest video! 🙂

https://youtu.be/uki2DndUfZE

[mild ice]

https://youtu.be/_g3d9_rblLI

[shy spade]

Hello everyone! I am new to machine learning and have been working on leveraging XGBoost via Python in a Jupyter Notebook to try and create an algorithm that can predict customer churn for a saas company using a data set with various features from the customer's usage over the last 6 months prior to their churn.

My dataset has 85 rows and is heavily unbalanced as - there are roughly 70 customers that did not churn and 15 that did churn.

Does anyone have any suggestions on how I can alter my model to better understand the minority class? Thanks!!

[tepid flame]

before starting on any modelling I suggest you gather more data. 85 rows is nowhere near enough to build any ML model that would perform well in the real world

[shy spade]

Hi @tepid flame - Thank you so much for the advice 🙏

Quick follow up question - Is there a general guideline to the minimum amount of data I should have to gather any meaningful insight?

I figured it was a low amount of data but wasn't sure how much would be enough (or not enough).

Thank you again Wendy!

[surreal needle]

There is no general answer to that question - it is data-dependent. Maybe there is a single feature that explains a given outcome, in which case a relatively small amount of data may be enough. In real life for most outcomes there are multiple contributing factors, which is why more data points are needed. This is especially the case for imbalanced datasets, even though 70:15 ratio is not too bad. As to meaningful insights, people have different definitions. You may be able to get 85% accuracy from your dataset as it is right now because >82% of data is in the dominant class. That would still mean that you probably wouldn't be able to predict the low-abundance class with high accuracy.

[fossil patrol]

Idk how complicated model you have been planning, but a simple experiment could be dropping features at random and checking accuracies.

If you follow a greedy approach it will be way complicated task, with around 2^85 - 1 models which is computational inefficient, but if you have any feature information you can try this way out.

Btw recommended to use standard things like correlation coefficient and stuffs to eliminate redundant features

[fossil patrol]

Here's why we make use of Balanced Accuracy or F1 scores to evaluate the model.

[bright tendon]

Hi, has anyone ever used GANs before to generate synthetic data to train financial models? I have seen articles about the use of GANs in fraud for imbalanced models, I want to try it but am not sure exactly how I would apply a GAN in theory and any potential risks I should be aware of when building a model off the synthetic data it generates.

[sudden hearth]

Hi! When putting a forecasting model in production, what metrics/kpi do you guys suggest are good indicators that the model is doing good/bad? Besides mape

[velvet lotus]

You should monitor the same evaluation metric you used in cross-validation and to calculate the test score (the generalization error) during model development. If the metric during deployment starts to deviate from the test score, it might be time to retrain the model.

[south spoke]

For model with small datasets Naive Bayes have decent results: https://scikit-learn.org/stable/modules/naive_bayes.html

[south spoke]

Hi guys, I need somebody with decent #reinforcement-learning experience to review my attempt at #✖┊connect-x competition to train an agent able to beat provided negamax agent. Tonight, I will reach 10+ mil. training steps and results are still disappointing (at least only 1 illegal move in the last iteration, but still not able to beat negamax and win only 2 out of 3 games against the dumb random agent). I have published my cry for help in Kaggle discussions: https://www.kaggle.com/discussions/questions-and-answers/480250, but no reaction so far. So, maybe discord will be better?

[sage apex]

Hi, guys
we can combine stt, chatgpt and tts to make voice chatbot
if we use streaming mode for stt and chatgpt, users can get response within 2 seconds and it can be useful.
I have developed AI call center by using Twilio and a voice chatbot.
I think it can take a role of human callers.

[dark hatch]

Hey All! Would you like to quantize an LLM to run quickly on your laptop or tiny devices? Quantization is the answer. Here is a code walkthrough for using llama.cpp for GGUF quantization in 10 mins. Hope its useful: https://youtu.be/j7ahltwlFH0?si=Waa35po2YwqrQC3_

[visual wharf]

I am running a notebook for RF and is taking over 16 hours with a sample size of 95,000 but using BayesSearchCV with x50 iterations, the same data took KNN 2 hours, DT, LR 40 mins. Do you think there is a issue with the code or is it just taking this long?

[quartz wind]

I can understand that is the algorithm itself. Do you know the differences between KNN and Bayes Search? It is a good starting point 😃

[grand ether]

Are there any Machine Learning alternative for the course we follow for learning Python provided by the University of Helsinki? This course is very helpful, concise, and comprehensive. It would be great if we had a similar alternative for Machine Learning.

[molten sand]

What do you mean? Kaggle has many courses on Machine Learning

[mild ice]

Hello, How can I finetune llama3 for MultiLabel classfication. Do I need to follow the same prompt format for each row as mentioned https://www.kaggle.com/code/danielhanchen/kaggle-llama-3-8b-unsloth-notebook/notebookhere.
Or is there any other method like we do for BERT?

[prime bolt]

How to get room direction in indoor photo/image.

[quiet shore]

Hellooo, hi everyone. Can you recommend book or something else for learning neruralprophet?

[leaden dew]

Hi, everybody. I have a question.
I want to make a method to architecture the neural network for given real problem.
Is this possible?
So, I mean can we make the certain arhictecture of network based on neuro science?
Please help me overview of this and methods.
Where I can find the proper references?

[distant violet]

Hi All,

I am working with a client who is expecting me to do a commodity price forecasting on monthly basis. But they will be able to provide us with only monthly data for past 5 years. (60 data points)

I have tried Holt’s winter model, ARIMA, SARIMAX, LSTM, LR, Prophet. But the accuracy is not up to the mark.

What is the minimum data points requirement to do the monthly forecasting?

Can I please have help with the correct approach here?

[split canyon]

Halloooo, What architecture do you mean? the current MLP is based on Neuro. Try to search for this ✨. Kan is new and kinda hyped. I haven't tested KAN before but will do it in my studies.

[leaden dew]

Thanks, @split canyon

[split canyon]

Anytime 🫶

[split canyon]

Try to augment if possible or generate new features like windowing. If it overtfits just do regularization techniques. The thing is , it's sometimes not the models problem. Sometimes it's the data problem. DM me if you want to know more about time series forecasting 👋

[ripe gulch]

Which ML framework should I learn as a beginner so that I can find job quickly??? I mean tf or pytorch

[tawdry tusk]

Tensorflow imo

[vague panther]

its quite debatable pytorch or tf learn both it will be more helpful

[neat acorn]

If you're more interested in industry side then go through pytorch if academia then go through tensor flow

[naive wadi]

I have a question for the folks using ml at an enterprise level. Has a kaggle helped you with skill building and have you brought any kaggle ideas into production?

[merry nymph]

If anyone is publishing papers either in LLM's or Computer vision please do include me iam too much interested to work due to lack of network iam unable to do things that what I want to do
Please please do include me if anyone is publishing papers 🙏🙏🙏🙏

[fading garden]

I see a lot of enterprise level kagglers on BlueSky

[naive wadi]

Oh yeah? Any one I should follow? Or recs?

[leaden dew]

Hi, everybody.
I'm looking for ar related to project where that can detect palne and argument the objects on that.
If there is anybody who knows, please tell me.
Thanks.

[leaden dew]

Hi, everybody.
We're building news analysis models and need to collect news data of 20 years.
Is there anybody who knows news data service well?
Please tell me.

[fathom olive]

did anyone try creating a text translation model, like from english to some unique language!
Let's say we want to create a model that translate English to LangX.
Any ideas?

[scarlet pewter]

I think this is indirectly implemented by LLM enthusiasts

That they convert English text to vector embeddings that is understood by the model; except in this case we are assigning LangX words to the vector embeddings.

The idea seems cool, you can try that way.

Oops, I meant query embeddings* or whatever an appropriate term be

[mild orchid]

Hey everyone! 👋 I wanted to share that I'm organizing the Data & AI Blogathon. What’s it all about? You’ll be writing blog posts on topics like Data Science, AI, Machine Learning, and more. We’ll have a variety of categories, including topics like Data Science and Data Engineering, as well as different formats like case studies, tutorials, how-to guides, and more. With over 7 categories to choose from, you’ll have plenty of chances to get noticed and win!

What’s in it for you?

• Get featured in big newsletters
• Mentorship from experts in the field
• Connect with top mentors, ambassadors and other AI professionals.
• Get your work shared with over 500,000 followers

If you’re looking to grow your network, get advice, and get your work noticed, this is for you! 👉 Register here: https://forms.gle/FD9FfKJMYp6QCYEE7
Feel free to connect with me on Linkedin as well! https://www.linkedin.com/in/ginacostag/

[forest moth]

Hey, i need help

We have long conveyor like 5 kms long
In which there are idlers around 4 to 5k
We divided conveyor section with imaginary line let's say every 20m , in that there are around 10-12 idlers of same dimensions.

We have normal data that is after replacement of idlers, and have abnormal data that is before replacement , we have dataset in the form of real positive fft that is each row contains list with 5k integers

If i train 1dcnn based auto encoder or vae it works section wise, like I can see higher reconstruction error in abnormal data. But it is impossible to create model for every section it will be computationally very expensive. I want single model that will work entire conveyor, but when I combine all data and train then it won't generalise well.

Also I tried extracting statistical features like kurtosis , skewness etc and trained dense vae but no luck what can I do ?

Note: i can see abnormality in normal data too. Even after cleaning it becomes more sensitive to normal data as well tell me better approach if you have any experience related to similer problem

[wind cliff]

https://myhistory.co.ke ..i need you to atest this website give reviews i will be happy 😁. Guys i need your reviews

[marsh matrix]

hello everyone, i am beginner - intermediate in ML

i learnt all the basic algorithms and neural network

built some models too

i am wondering what should i do now ?

what options do i have to explore ?

[high token]

This is interesting, Blogathon..this is first time I heard. So. do you have a site or something

[grave hornet]

job maybe!!

[desert silo]

What are the names of companies that are specially for aiml specialisation freshers?? List in India!

[clever cove]

😂

[small sandal]

hi can any one help me in learning ml

[vague panther]

-# ¯⁠\⁠_⁠(⁠ツ⁠)⁠_⁠/⁠¯

[small sandal]

thank you

[winged crypt]

Hi, I have a dataset of floor plans (general floor plans not only architecural) trained and labeled and am using yolov11 instance segmentation to get the rooms, doors and windows information. However, the result is not very accurate especially some rooms are identified as weird polygons. Any advice on how to prepare high quality data or better machine learning / AI method to recognize the rooms information? Thank s in advance.

[rich anvil]

🚀 Looking for Teammates – Join AgriIntel! 🌱

Hi Everyone,

I’m putting together a high-impact AI project — AgriIntel — a Smart Farming Assistant built to solve real problems faced by small-scale farmers like my own family.

👉 This isn’t just a side project or a college assignment.
AgriIntel is being developed as a serious portfolio product to help each team member showcase real-world impact, demonstrate ML/Data Science skills, and land strong remote roles.

---

🧠 What We're Building:

• 🌾 Crop Recommendation Engine — based on soil, pH, rainfall, etc.
• 📈 Crop Price Forecasting — using Time Series (Prophet/LSTM)
• 🍂 Leaf Disease Detection — with Computer Vision (YOLOv5 / MobileNet)
• 🗣️ Hindi Voice Assistant — powered by Whisper + gTTS
• 📊 Insightful Dashboard — Streamlit or React

---

✅ Why You Should Join:

• 📌 Build something recruiters will ask about
• 💼 Boost your GitHub + Resume with real-world work
• 🧩 Collaborate in a sprint-style, outcome-driven team
• 🌍 Contribute to a product that impacts real lives

---

🔗 Full Pitch + Roadmap:
👉 Click to View

📩 Interested in joining? DM me directly or connect on LinkedIn:
💼 LinkedIn – Dinesh Kumar

Let’s build AgriIntel together — and create something that truly matters! 🌾💡

—
Dinesh Kumar

[fleet pilot]

Try no code visualization tool like Orange 3.x. You can consolidate various concepts easily.

[grave aurora]

Hi! Wondering if anyone has experience on ML applied to People Analytics? I’m researching the topic but can’t find realistic value adding project ideas

[manic trench]

What is the best way to self learn ML?

[fleet pilot]

If you are just a beginner, the you tube videos by Statquest Josh Starmmer and videos by Louis Serrano can provide you a head start. Simple visualization and short videos for understanding the subject in the shortest possible time in my opinion. If you require a ,"no code" visualization flow tools to experiment with data and various models then you can use open-source Orange 3.8x version along with various addons provided. Very easy to learn with a number of videos tutorials. Other open source tools I have experimented with are Weka, Knime.

[manic trench]

Thank you so much i will look into it

[viral torrent]

my friends, does anybody have an idea for my graduation project? it should be AI related of course, should be innovative, no one has ever made it and it should solve a real world problem

appreciate it anyways

[white yew]

man, that's up to you. Scroll through the kaggle, look into datasets, read, watch youtube videos you like and come back to datasets again. Works with me, sooner or later i'll find a problem i want to solve for myself.
I think it's like open source contributions - you do it for yourself, coz you're interested in it, you want to know the answer, and so you have the greatest motivation of achieving it

[manic steeple]

Hey guys,
Its been long since i processed datasets to be implemented for ML projects. Does anyone here provide me with some sort of guide that could potentially help me with developing projects and stuff??

[cyan elbow]

Hey Guys,I am seeeking recommendations for an impactful AI/ML project that would strongly appeal to product based companies when they are hiring. The goal is to maximize my chances of securing a job.
Please do suggest me asap : )

[gaunt jackal]

I know lead generation seems to be all the rage lately

[sour light]

I want to participate in kaggle competition , I am new so I want to join a team for first hand experience

[humble delta]

Let's go i am also new.

[cinder lagoon]

👋 I just built a free tool that turns any PDF, image, or Word doc into a clean dataset using just a prompt — kinda like ChatGPT but for messy files.

Want to give it a quick try and tell me what’s broken or missing? Takes 2 mins. Would love your feedback 🙏
👉 https://pdf2dataset.streamlit.app

[trim stream]

It doesn’t work when I click on the link

[loud siren]

any advise on how I should get started learning ML and in a proper structure?

[earnest gorge]

I build via LLM collaboration. I work with different AI models to run research, hone my understanding, and apply to see what works. Just shoot for the dream and then refit to MVP version and iterate. You'll get it, or get something at least haha You need to understand ML fundamentals but you could just let AI teach you about AI essentially--edit not a replacement from coding yourself, but if the learning curve is too steep just have fun! Whatever works!

[fleet pilot]

Can you place your background directly or indirectly relevant to the subject matter?

[craggy oracle]

https://www.historyofdatascience.com/dartmouth-summer-research-project-the-birth-of-artificial-intelligence/

[prime bolt]

Let's goooo

[acoustic basalt]

You can consider me too 😅

[left hull]

hi all

[acoustic basalt]

Hello

[stark vigil]

Hi, @everybody
I have one question, I'm training ml models for the prediction, which is classification problem of 3 classes, where the number of samples are similar but the predition is skewed.
First class and second class is predicted with low precision tough, third class is never predicted. What's the reason? I can' t find the reason.
Before, when I applyed reinforcement learning, where the three classes were assigned to three actions and one action is never selected, too.
Actually, that is the preeiction model of forex eur/usd.

[void wraith]

hello guys i am doing a small project on texture classification. can anyone help me with understanding what is wavelet technique?

[stark vigil]

Hi, @everyone
Is there anyone who joins radical ai founders' masterclass?
I didn't have an opportunity to apply for that.
Please give me the meeting urls for them.

[red jacinth]

did you take stratified training data, ie equal proportions of all classes in train and test data

[stark vigil]

Yes, same

[drowsy raptor]

Hi everyone, im doing the intro to ML course and im a bit confused on step 3 of the lesson 4 exercise (https://www.kaggle.com/learn/intro-to-machine-learning)

question: Inspect your predictions and actual values from validation data.
code:

print(val_predictions[:5])
# print the top few actual prices from validation data
print(y.head())```
the bit i am a bit tripped up on is: 
 ```# print the top few validation predictions --> this bit of the question confuses me
print(val_predictions.head())```

i was wondering what the correct way to do what the question is asking is. i done 
```print(val_predictions[:5])```
 but im not sure if thats what the exercise was asking

[slim yew]

if it is just for inspection then i think both of them is correct. But I preffer y.head() method. But if you want to check accuracy or precision you can go for precision_score or accuracy_score and there are many more like f2_score,f1_score etc. Just my opinion i could be wrong.

[warm bough]

Scam

[neat acorn]

Hello all, I'm Muhammad Yousif, BS IT student with focus on data science and ai. I'm here looking for possible collaboration in research or work. If you're eager to collaborate just dm me with your ideas

[hasty pilot]

HI guys I'm in everything programming ML and agents looking to team up ASAP

[glass pagoda]

Hi everyone, I'm predicting the next F1 race winners, if you're interested you can check out the dataset and the notebooks here: https://www.kaggle.com/datasets/rockyt07/formula-1-championships-1950-2025. Feel free to tinker with it.

[regal bronze]

🎥 New Video Released: Epistemic World Model vs Baseline – Full Generalization Test
I’m thrilled to share the full demo of my Epistemic World Model in action:
https://www.youtube.com/watch?v=Sw57PKee__w

In this video, I walk through the architecture, training curve, and generalization results in a high-entropy combinatorial environment ( Brazilian Lotto history). While the baseline model remains stuck at ~10% hit-rate for ≥1/6 events, my model climbs to 81.6% across 100 epochs.

✔ Core highlights:

Structured “Q1 (aleatoric) / Q2 (epistemic)” gating for belief management

Stable pyramidal state vector: Memory / Pain / Choice / Exploration

Continuous online learning & domain adaptation

Full comparison between baseline world model and epistêmic variant

Thought-provoking implications for future cognitive-agent architectures

Whether you’re working in ML, world models, reinforcement learning, or cognitive systems — this architecture might spark ideas for new directions in generalization.

Would love to hear your feedback, questions or ideas for collaboration.

#MachineLearning #WorldModels #EpistemicAI #1101210830688751626ization #KaggleCommunity #AIResearch

[fleet palm]

Same here @hasty pilot and @neat acorn maybe we can help one another by working together and learning alongside

[neat acorn]

Dm me

[hasty pilot]

what are we working on

[neat acorn]

that's seems like black box we should have to discuss in dm

[hasty pilot]

cool, any hackathon on?

[neat acorn]

Maybe, actually I'm actively participating in multiple things hackathons, competitions, research and projects etc. so I can discuss things around these

For further dm me

[trim pebble]

heyy! anyone with some experience in AI x cognitive science/computational neuroscience here? please hmu if so :)

[sinful ermine]

Hi @everyone
📘 Python Loops & Strings – Kaggle Notebook 🐍
This notebook explains Python loops (for, while) and strings in a detailed and easy-to-understand way, with clear examples.
It’s especially helpful for beginners 🚀

Please check it out and leave a vote ⭐ and a comment 💬 — your feedback is highly appreciated! 🙌
https://www.kaggle.com/code/dastgeerjutt/3-loops-and-strings-detailed

[acoustic prawn]

I'm training an MtG AI player. Here are my assets:

I have a functional rules engine, and a complete graph based world model. This world model is completely accurate and encodes relationships of arbitrary distance. I can easily implement a spider or walker to do traversal. GNNs or an RNNs which walks the graph could be applied here.

I have access to human-played game logs which, presumably, could be translated to resimulations of those games for observation. I can have a flagship LLM play against itself and have the AI observe. And, once the AI is halfway competent, I have self play.

And I have a clear goal. Given the state of the game world, multiple objectives, and a set of possible actions, how do I select the best possible action(s) when they're presented?

[rustic dune]

🚗⚡ Just dropped a 🔥 Kaggle Masterpiece: Analyzed 271K Washington State EVs with INTERACTIVE MAPS, XGBoost Ensembles, & 2027 Forecasts!

Key Insights:
✅ Tesla dominates 60% – but Chevy Bolt crushes on range/price
✅ Urban Heatmaps reveal Seattle hotspots (download HTML map!)
✅ ML Beast: R²=0.95 predicting range, 94% CAFV eligibility
✅ Forecast: +50K new EVs by 2027 – infrastructure crisis ahead?

Built with GeoPandas, Folium, StackingRegressor (XGB+LGBM+RF). Perfect for policy makers & energy pros!

🔗 Dive in & upvote: [https://www.kaggle.com/code/hammadansari7/electric-vehicle-population-analysis]

What’s YOUR take on EV adoption? Rural lag or tech hype?

#DataScience #Kaggle #MachineLearning #GeospatialAnalysis #ElectricVehicles #EV #Forecasting #XGBoost #Sustainability #AI

@Kaggle @Tesla @robikscube @towardsdatascience @everyone

[worldly jewel]

Just a reminder that our server rules prohibit requesting upvotes and tagging in a broad group of users - although we love seeing the projects folks are working on.

[crisp nimbus]

Hello everyone! 👋

If you want to upgrade your IT skills and learn more about the Microsoft ecosystem (Azure, AI, Cloud, etc.), come join the Microsoft Elevate Training Center! 🚀

This program is great for those who want to prepare for official certifications or simply stay updated with the latest technologies together with Dicoding.

Register for free through this link: https://www.dicoding.com/elevate/registration?referrer_id=5510036

Let’s go while the opportunity is still there!

[versed hemlock]

Anyone can provide the best dataset download link for deepfake detection videos with good qualities videos and of various diiferent varities ?? It will be great help to me.