Creating a model is easy. What’s hard is building a model with optimal hyperparameters!. You can create a neural network with a random number of hidden layers and it will probably give you results better than random. But to get optimal results, you need to get the best hyperparameters that optimize the results. This process of finding the best hyperparameters is known as Hyperparameters tuning.

This is basically a time-consuming and a computationally expensive process as we have to search a pretty wide space in order to find these. And also we as humans, can’t try each and every one of the combinations and thus can’t claim a set of hyper parameters as the best ones. Enter hyper parameters tuning libraries. These libraries search the parameters space and calculate the metrics for each one. …

In the Part 1 of this, we worked on setting up our React project, getting the API key from YouTube Data API v3 and also creating the Header and the SideBar component. In this part, we will work on creating the RecommendedVideos page which will get the most popular videos from the API and render it. Let’s get started

Below is the list of the parts in order to build this YouTube clone:

• Part 1 — Getting the API Key and Building the SideBar & Header (here)
• Part 2 — Building the Recommended Videos page (This one)
• Part 2 — Building the Search Page…

Have you ever just looked at some of the most popular websites in the world and wondered how good the developers of these websites must be? Well, you can be that developer.

In this four part series, we will build a YouTube clone from scratch that will fetch the data from YouTube and render it using React. Following are the different parts of this tutorial

• Part 1 — Getting the API Key and Building the SideBar & Header (This one)
• Part 2 — Building the Recommended Videos page (here)
• Part 2 — Building the Search Page (here)
• Part 3 — Building the Video Player Page (Coming…

Have you ever wondered the breed of your dog or any other dog you may see on the street? You probably would have to ask a specialist about that. Well, no more! In this post, I will teach you to build your own web application that will accept the image of your dog and output its breed with more than 80% accuracy!

You might be wondering how’s that possible? Well, we will be using Machine learning, specifically Deep Learning to train a model on a dataset of dog images with their breeds in order to learn the features that distinguish each breed. …

Everyone wants to learn the maximum amount of content in the minimum amount of time. But how? In this article, I will explain how I completed Udacity’s Data Scientist Nanodegree in 1 month when the Udacity’s Data Scientist home page says it takes around 4 months at 10 hrs/week.

Udacity’s Data Scientist Nanodegree is by far the best data science program in terms of relevance to industry I have taken online. It's totally worth the money and they are offering discounts due to Covid-19 too. …

Recommendation Systems are one of the most popular data science algorithms that drives much of the revenue for a company such as Netflix, Amazon and Google.

Recommendation systems are basically algorithms used to predict a rating or a preference that a user might attach to a particular item. The item can be a product, a movie, an article and so on.

There are various types of algorithms used in building such Recommendation Systems. Some of the popular ones are as follows:

1. Rank Based
2. Collaborative Filtering
3. Matrix Factorization
4. Content Based
5. Clustering
6. Knowledge Based

In this article, the first three algorithms are discussed along with their implementations using the data from IBM Watson Studio Platform. …

Using pipelines for data loading and analysis is one of the most popular way of building data science projects.

In this project, I used the data from FigureEight for building a web app that classifies messages for customers into appropriate disaster categories. This is extremely useful in responding better to different types of disasters.

Data Analysis

The data from FigureEight consists of two csv files. ‘disaster_messages.csv’ contains the actual messages from users and their corresponding ids. ‘disaster_categories.csv’ contains the messages ids and their categories in raw format.

The dataset is a multi-class, multi-label dataset as there are total of 36 categories with the possibility of each message having more than one category. …

There are a lot of different developers around the world. They use different programming languages, some have a PhD and some haven’t had a formal education their entire life.

You may have heard that Python is the most popular programming language among the developers or that you need to have a managerial position in order to earn a higher salary?

But let’s answer these questions using data from developers around the world. I used Stackoverflow’s Annual Developer Survey from years 2017 to 2019 to better look at these questions.

The data contains questions related to multiple aspects of software development and general preferences of developers from around the world. …