Check out the list of top 10 Python projects on GitHub given below.

1. Magenta: Explore the artist inside you with this python project. A Google Brain’s brainchild, it leverages deep learning and reinforcement learning algorithms to create drawings, music, and other similar artistic products.

2. Photon: Designing web crawlers can be fun with the Photon project. It is a fast crawler designed for open-source intelligence tools. Photon project helps you perform data crawling functions, which include extracting data from URLs, e-mails, social media accounts, XML and pdf files, and Amazon buckets.

3. Mail Pile: Want to learn some encrypting tricks? This project on GitHub can help you learn to send and receive PGP encrypted electronic mails. Powered by Bayesian classifiers, it is capable of automatic tagging and handling huge volumes of email data, all organized in a clean web interface.

4. XS Strike: XS Strike helps you design a vulnerability to check your network’s security. It is a security suite developed to detect vulnerability attacks. XSS attacks inject malicious scripts into web pages. XSS’s features include four handwritten parsers, a payload generator, a fuzzing engine, and a fast crawler.

5. Google Images Download: It is a script that looks for keywords and phrases to optionally download the image files. All you need to do is, replicate the source code of this project to get a sense of how it works in practice.

6. Pandas Project: Pandas library is a collection of data structures that can be used for flexible data analysis and data manipulation. Compared to other libraries, its flexibility, intuitiveness, and automated data manipulation processes make it a better choice for data manipulation.

7. Xonsh: Used for designing interactive applications without the need for command-line interpreters like Unix. It is a Python-powered Shell language that commands promptly. An easily scriptable application that comes with a standard library, and various types of variables and has its own virtual environment management system.

8. Manim: The Mathematical Animation Engine, Manim, can create video explainers. Using Python 3.7, it produces animated videos, with added illustrations and display graphs. Its source code is freely available on GitHub and for tutorials and installation guides, you can refer to their 3Blue1Brown YouTube channel.

9. AI Basketball Analysis: It is an artificial intelligence application that analyses basketball shots using an object detection concept. All you need to do is upload the files or submit them as a post requests to the API. Then the OpenPose library carries out the calculations to generate the results.

10. Rebound: A great project to put Python to use in building Stackoverflow content, this tool is built on the Urwid console user interface, and solves compiler errors. Using this tool, you can learn how the Beautiful Soup package scrapes StackOverflow and how subprocesses work to find compiler errors.

C language Projects ⬇️⬇️⬇️

"Here are the some Machine Learning Projects"

Algorithms-Leetcode-Javascript

Webpack questions/answers you can use to prepare for interviews or test your knowledge.

Creator: Stepan V
Stars ⭐️: 178
Forked By : 60
GitHub Repo: https://github.com/styopdev/webpack-interview-questions

Curated papers, articles, and blogs on data science & machine learning in production.
https://github.com/eugeneyan/applied-ml

Raspberry Pi IoT Projects
John C. Shovic, 2021

Managing Machine Learning Projects
Simon Thompson, 2022

Feature Scaling is one of the most useful and necessary transformations to perform on a training dataset, since with very few exceptions, ML algorithms do not fit well to datasets with attributes that have very different scales.

Let's talk about it 🧵

There are 2 very effective techniques to transform all the attributes of a dataset to the same scale, which are:
▪️ Normalization
▪️ Standardization

The 2 techniques perform the same task, but in different ways. Moreover, each one has its strengths and weaknesses.

Normalization (min-max scaling) is very simple: values are shifted and rescaled to be in the range of 0 and 1.

This is achieved by subtracting each value by the min value and dividing the result by the difference between the max and min value.

In contrast, Standardization first subtracts the mean value (so that the values always have zero mean) and then divides the result by the standard deviation (so that the resulting distribution has unit variance).

More about them:
▪️Standardization doesn't frame the data between the range 0-1, which is undesirable for some algorithms.
▪️Standardization is robust to outliers.
▪️Normalization is sensitive to outliers. A very large value may squash the other values in the range 0.0-0.2.

Both algorithms are implemented in the Scikit-learn Python library and are very easy to use. Check below Google Colab code with a toy example, where you can see how each technique works.

https://colab.research.google.com/drive/1DsvTezhnwfS7bPAeHHHHLHzcZTvjBzLc?usp=sharing

Check below spreadsheet, where you can see another example, step by step, of how to normalize and standardize your data.

https://docs.google.com/spreadsheets/d/14GsqJxrulv2CBW_XyNUGoA-f9l-6iKuZLJMcc2_5tZM/edit?usp=drivesdk

Well, the real benefit of feature scaling is when you want to train a model from a dataset with many features (e.g., m > 10) and these features have very different scales (different orders of magnitude). For NN this preprocessing is key.

Enable gradient descent to converge faster