Python for Stock Market Trading

Image for post
Image for post
Photo by Aziz Acharki on Unsplash

We all like python programming language because it is easy to understand, and also it is the most appropriate programming language for data science. Python is easy because we don’t need to focus on the error solving part but build a robust product. Today, we will see how we can utilize python programming to find the most volatile stock in the share market with a few lines of python code.

Before starting with the code part, we need to find a source that can provide us the stock price data. Many sources like Quandl, Quantopian, and Yahoo Finance can offer us the live share market data using their API. …

Custom Style Transfer for Snapchat Lenses

Image for post
Image for post
Photo by Amanda Vick on Unsplash

SnapML provides a way to utilize machine learning to build more immersive Snapchat AR Lenses. Style transfer is a computer vision technology that allows creators and developers to transfer any design from one source image to any targeted image.

Once our style transfer model is ready, we’ll upload and configure the converted ONNX/PB model file in Lens Studio, and from there, upload the resulting to our personal Snapchat app. And, then we can make it public so that others can use our lens.

As this is a deep learning approach, we’ll need a large amount of data. We’ll utilize the COCO dataset to train our model. And for model training, we’ll use Google Colab because it provides us a high-quality free GPU and ML code processing. …

Language Translation on your Mobile Device

Image for post
Image for post
Photo by Meghan Schiereck on Unsplash

Running machine learning models on your Jupyter Notebook is fine, but have you ever thought about how these models can run on your mobile device, which has limited space and processing power? If we use models directly in our mobile application, it will increase the size of the mobile app too much — so how do we manage this on a mobile device? I am going to go through the answers to these questions in this article.

So, when the data become complicated in machine learning, we need to use some complex models to deal with complex datasets. But when we use a complex model, like in the case of deep learning, the number of layers and neurons gets an increase and this leads to an increase in model size. TensorFlow allows us an approach to reduce the model size to make it suitable for mobile devices and we can achieve this using TensorFlow Lite. …

GANs for Mobile Devices

Image for post
Image for post
Photo by 🇸🇮 Janko Ferlič on Unsplash

Generative adversarial networks (GANs) are among the more significant advancements in deep learning in recent years. Previously, we used machine learning and deep learning techniques with a considerable amount of data to build a model to understand data by classifying them. But now, with GANs, we use an algorithm that generates data for us.

Two of the most commonly used and efficient generative models are Variational Autoencoders (VAE) and Generative Adversarial Networks (GAN).

A VAE learns a given distribution comparing its input to its output; this is good for learning hidden representations of data but is pretty bad for generating new data. …

Python for Text Analytics

Image for post
Image for post
Photo by João Ferrão on Unsplash

Extracting text data is the initial step to do further analysis of the data. We have a considerable amount of data present over social media. However, we need a system that can help us extract useful information from the bundle of text data. Some famous applications that use text extraction are Resume Parsing and Invoice Reading. In this article, We will see some latest free to use python libraries to extract text data and how to use them.

1. Pdf Plumber

PDF Plumber library is written in python. This library can solve different purposes while extracting text. …

Haste Makes Waste Story

Image for post
Image for post
Photo by Hybrid on Unsplash

Like we say, “Writing is an art,” and we all should respect the Art. While writing an article, your story must give some value to the reader. The purpose of the reader, why he/she select your article to read should meet. Your reader can come from any background, so you also need to make sure that you keep the story neat and straightforward.

Like in Art, we make sure to focus on the edges in any drawing. Similarly, here, We should focus on the edge part of our article. …

Make Your Article Trend with Zero Investment

Image for post
Image for post
Author’s Medium Stats with 80% Views from Google Search

People spend a tremendous amount of money on marketing strategies to make their product on top of Google Search and just for a limited amount of time. What if I tell you that my article is trending on Google continuously for three months and without even paying a single dollar to any party.

When I successfully make my article trend on Google Search, I thought that this might not last long as some other writer will write the story, and after some time, my story will come down in ranking. …

A Set of Curated Images From Unsplash

Disclaimer: I am not writing it for any promotional purpose or any money; I found it useful for writers, so I thought of sharing it.

Image for post
Image for post
Source: Unsplash Curated

Images are necessary to emit boringness in an article, and if we use the right image that can adequately describe the theme, it gives an excellent idea to a reader about the article content. …

AI can now help in solving Partial differential equations.

You might have wondered in your college times why we learn these partial differential equations, what is the practical use of these equations because they are hard to solve and time-consuming. At some point, they are impossible to solve due to their complexity.

Image for post
Image for post
Photo by Science in HD on Unsplash

Artificial Intelligence can Now Solve a Mathematical Problem that can Make Researchers’ Life Easier. The researchers discovered that these partial differential equations PDEs can help us understand how nature works. Most of the differential equations are impossible to solve due to their complexity, but once they got solved, we can get more exciting things from it.

There are many research areas like how the population grows, how any fluid moves, how magnetic radio waves work, the weight updation in deep learning, electric circuits, and even if we talk about the forces the differential equations help us describe the motion. And, these are just a glimpse of the practical use of partial differential equations. …

Excel for Data Science Journey

Image for post
Image for post
Photo by Lukas Blazek on Unsplash

A Data Scientist spends plenty of time with the data. And, When we talk about the data, excel come in handy all the time. Excel has many useful functions like addition, subtraction, multiplication, but those are useful for calculation. In the data science field, we need a massive amount of data to train our machine learning models. The data can come from different sources, but finally, we need it organized. And, in most of the case, we convert our data in tabular format.

Once we convert the data in the tabular format, we need to plot different graphs and charts to visualize the data features and get the relation in other data columns. Before plotting the data, we need to make many changes and perform many operations in our data. …


Pranjal Saxena

Data Scientist with 2500+ relevant connections on LinkedIn. Get to know about me here

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store