pplonski86

True, that was the purpose of this Django+React boilerplate. Provide minimal and easy to follow template. Additionally, every code added is documented in the series of articles so you can learn how it was done.

There is a docker-compose provided to set up and run this boilerplate application on single server machine. It can be easily adjusted to your needs.

Looks very slick! What stack are you using?

I get MLP implementation from scikit-learn and compared it with TensorFlow implementation. I used the same hyperparameters and the same optimizer (Adam). I've compared implementations on 114 datasets from Penn ML Benchmarks - they represent binary classification, multiclass classification, and regression. In comparison, I was using the CPU only. The TF was only 59 times out of 114 better than sklearn. I was surprised. The differences in performance weren't huge. What is more, the sklearn implementation seems to be about 2 times faster (I was using CPU only).

The conclusion is, that if you are already using Sckit-learn and need classic MLP then there is no need to get TensorFlow.

Isn't it available currently? or you are talking about much more extreme temperatures > 60 Celsius?

I would also be interested in history of space travel but I would rather bet that in physics book there will be information what kind of engines space crafts are using (based on which findings).

There is a Polish joke video about Russian vaccine https://youtu.be/vN2eQ_CKZT8

Thank you! Any good resources for writing good commit messages?

Could you write the name of the tools that add emoji? Is your repo public, so I can see how it looks like?

For example in fastAPI repo I see emojis in the commits https://github.com/tiangolo/fastapi

Agree, data labeling app in Django will be interesting. It will require a front-end with a lot of features to make it usable.

The website is down. Is it open-source? Do you know any open-source alternatives?

Nice!

1. Is it open-source?

2. Can I add models with REST API?

3. How do you handle large models? Are they working in the background or you just use larger severs?

In this tutorial I've used SQLite. I use PostgreSQL for production services. I don't remember now why I used such type.

You are right! I like Django admin panel, without coding you get UI and I'm comfortable with Django + DRF.

In Flask you need to add many things to make it usable.

If you check the code of the tutorial you will see that it differs from the most of the ML-to-REST-API tutorials. It's not only setting the endpoint. You can have many algorithms with many versions and stages (testing, production). There is A/B testing example. Of course you can do all in Flask but I prefer Django because many things are there already.

It really depends. For sure there are models which should be processed in the background. It is a very basic tutorial that shows how simple ML models can be used as REST API. In the tutorial I was using Random Forest trained on UCI Adult Income data set. The final model was small, and computing predictions was fast.

I would love to add more advanced part of the tutorial with background processing for large models.

is it similar to monkeylearn.com

Scheduling periodic tasks can be useful for creating ETLs or to create alarms (every 1h hour check data for new values if condition is meet then send the email alert)

Congratulations! I remember your earlier project: grid studio. Do you support scheduling periodic tasks? Do you support execution triggered with webhook? or some way to expose notebook as REST API?

What are use cases for such models?

@arikfr I've learned a lot from redash. Firstly, after knowing redash, I decided to go open-source with my service. I learned a lot from reading redash source-code/repository. Your project is amazing and was inspiration for me! Thank you!

The README.md is created for every model created by AutoML package that I'm working on.

More examples:

https://github.com/mljar/mljar-examples/tree/master/Income_c...

https://github.com/mljar/mljar-examples/tree/master/House_pr...

The link to hello robot github https://github.com/hello-robot

Is there any reason that you select 50 requests per second? Anyway, I'm also interested in performance metrics.

Amazing! Thank you

Off-topic. I'm thinking about building a game where players are controlling real robots. The players compete for resources which are randomly distributed in the land. In the first version of the game it will be on the Earth. This game can be later used to help colonize Moon and Mars.

Do you know any robots which can be used in such game?

The title could be: Researchers and Founders and Mothers. I think mothers have a lot in common with successful researchers and founders. They are laser focused on tasks (can do many in paralell) and have long term vision (a family). Although mothers dont get attention and press. They are very underrated

The mljar-supervised is an AutoML tool that works with tabular data. It can handle binary classification, multiclass classification, and regression problems. What's good in it: - it can produce markdown reports which you can commit to the repository, example: https://github.com/mljar/mljar-examples/tree/master/House_pr...

- it computes the Baseline, so you can check if you need ML or not

- this package is training simple Decision Trees with max_depth <= 5, so you can easily visualize them with amazing dtreeviz to better understand your data.

- it is using simple linear regression and include its coefficients in the summary report,

- it has a vast set of algorithms: Random Forest, Extra Trees, LightGBM, Xgboost, CatBoost (Neural Networks will be added soon).

- it can do features preprocessing, like: missing values imputation and converting categoricals. What is more, it can also handle target values preprocessing (You won't believe how often it is needed!). For example, converting categorical target into numeric.

- it tunes hyper-parameters with not-so-random-search algorithm (random-search over a defined set of values) and hill-climbing to fine-tune final models.

- it cares about the explainability of models: for every algorithm, the feature importance is computed based on permutation. Additionally, for every algorithm, the SHAP explanations are computed: feature importance, dependence plots, and decision plots (explanations can be switched off with explain_level parameter).

I'm working on open-source automated machine learning python package https://github.com/mljar/mljar-supervised that can produce markdown reports and produce ML explanations

The mljar-supervised is an AutoML tool that works with tabular data. It can handle binary classification, multiclass classification, and regression problems. What's good in it:

- it can produce markdown reports which you can commit to repository, example: https://github.com/mljar/mljar-examples/tree/master/House_pr....

- it computes the Baseline, so you can check if you need ML or not

- this package is training simple Decision Trees with max_depth <= 5, so you can easily visualize them with amazing dtreeviz to better understand your data.

- it is using simple linear regression and include its coefficients in the summary report,

- it has a vast set of algorithms: Random Forest, Extra Trees, LightGBM, Xgboost, CatBoost (Neural Networks will be added soon).

- it can do features preprocessing, like: missing values imputation and converting categoricals. What is more, it can also handle target values preprocessing (You won't believe how often it is needed!). For example, converting categorical target into numeric.

- it tunes hyper-parameters with not-so-random-search algorithm (random-search over a defined set of values) and hill-climbing to fine-tune final models.

- it cares about the explainability of models: for every algorithm, the feature importance is computed based on permutation. Additionally, for every algorithm, the SHAP explanations are computed: feature importance, dependence plots, and decision plots (explanations can be switched off with explain_level parameter).

The mljar-supervised is an AutoML tool that works with tabular data. It can handle binary classification, multiclass classification and regression problems.

What's good in it:

- it can produce markdown reports which you can commit to repository, example: https://github.com/mljar/mljar-examples/tree/master/House_pr...

- it computes the Baseline, so you can check if you need ML or not

- this package is training simple Decision Trees with max_depth <= 5, so you can easily visualize them with amazing dtreeviz to better understand your data.

- it is using simple linear regression and include its coefficients in the summary report,

- it has a vast set of algorithms: Random Forest, Extra Trees, LightGBM, Xgboost, CatBoost (Neural Networks will be added soon).

- it can do features preprocessing, like: missing values imputation and converting categoricals. What is more, it can also handle target values preprocessing (You won't believe how often it is needed!). For example, converting categorical target into numeric.

- it tunes hyper-parameters with not-so-random-search algorithm (random-search over a defined set of values) and hill-climbing to fine-tune final models.

- it cares about the explainability of models: for every algorithm, the feature importance is computed based on permutation. Additionally, for every algorithm, the SHAP explanations are computed: feature importance, dependence plots, and decision plots (explanations can be switched off with explain_level parameter).