How to accelerate and compress neural networks with quantization

Going from floats to integers Neural networks are very resource intensive algorithms. They not only incur significant computational costs, they also consume a lot of memory in addition. Even though the commercially available computational resources increase day by day, optimizing the training and inference of deep neural networks is extremely important. If we run our … Read more

Factorization Machines for Item Recommendation with Implicit Feedback Data

Model Evaluation Now that all the theory is out of the way, let’s see how these components come together to produce high-quality recommendations on a well-known real-world data set. We’ll train an implicit feedback FM model using the author’s new RankFM package which implements the techniques described above and compare its performance to the popular … Read more

Five reasons to view this Azure Synapse Analytics virtual event

The virtual event Azure Synapse Analytics: How It Works is now available on demand. In demos and technical discussions, Microsoft customers explain how they’re using the newest Azure Synapse Analytics capabilities to deliver insights faster, bring together an entire analytics ecosystem in a central location, reduce costs, and transform decision-making. This post outlines five key … Read more

Advancing Azure service quality with artificial intelligence: AIOps

“In the era of big data, insights collected from cloud services running at the scale of Azure quickly exceed the attention span of humans. It’s critical to identify the right steps to maintain the highest possible quality of service based on the large volume of data collected. In applying this to Azure, we envision infusing … Read more

Azure Digital Twins: Powering the next generation of IoT connected solutions

Last month at Microsoft Build 2020, we announced the new features for Azure Digital Twins, the IoT platform that enables the creation of next-generation IoT connected solutions that model the real world. Today, we are announcing that these updated capabilities are now available in preview. Using the power of IoT, businesses have gained unprecedented insights … Read more

Product Placement, Pricing and Promotion Strategies with Association Rule Learning

Using the Apriori algorithm to offer product recommendation, product placement, pricing and bundling strategies Imagine if we could understand what our customers’ next purchase could be! Imagine if we could find patterns in purchase behaviour and use it to our advantage! The key to the future is in history! Market Basket Analysis helps retailers identify … Read more

Coloring an Image using Crayola Colors (Python)

Creating an array of colors. Firstly, I picked the corresponding RGB values for a 120 crayons Crayola box and copied them into a list. colorsFile = open(“colors.txt”,”r”)colors = []for line in colorsFile.readlines():colorset = line.strip().split(” “)rgbFormat = [int(x) for x in colorset[2].split(“,”)]colors.append(rgbFormat) Secondly, I started by picking an image and resizing it to a smaller size. … Read more

Machine Learning for Neonatal Intensive Care

The neonatal intensive care unit (NICU) is an environment in which life-changing decisions are made. Neonatologists use information from a variety of sources to build up a picture of a newborn’s condition to ensure they are receiving the right medical care. These highly trained specialists use their judgement in tandem with a constant stream of … Read more

Simple Face Detection in Python

In this post, I will show you how to build a simple face detector using Python. Building a program that detects faces is a very nice project to get started with computer vision. In a previous post, I showed how to recognize text in an image, it is a great way to practice python in … Read more

What Python package is best for getting data from Twitter? Comparing Tweepy and Twint.

What does that all mean? Practically, if the only thing that you are looking to do is collect a large number tweets, Twint is probably a better tool, whereas Tweepy is better suited for collecting a richer set of metadata, allows for flexibility and potentially scalability as well for those using the official API. That’s … Read more

6 Key Areas of Business Intelligence in the New Era

Image by Qimono from Pixabay (CC0) Back in 1958, Han Peter Luhn, a researcher at IBM, initiated the concept of Business Intelligence (BI), using the definition from Webster’s Dictionary: to apprehend the interrelationships of presented facts in such a way as to guide action towards a desired goal. Given its definition, Business Intelligence is indeed … Read more

State-of-the-art python project setup

An opinionated setup guide for your next python project Python is one of the fastest growing programming languages. It’s tooling is evolving fast to catch up. I have been writing python for over 10 years now and sometimes it’s hard to keep up with all the new tooling out there. Recently, I had an opportunity … Read more

Introducing Modeltime: Tidy Time Series Forecasting using Tidymodels

[This article was first published on business-science.io, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t. I’m beyond excited to introduce modeltime, a new time series forecasting package designed … Read more

Categories R Tags ExcerptFavorite

The Three Stages of a Data Scientist

In this article, we’ll explore the differences between data scientists as Decision Support, Advisor and Integrated Partner One of the best and worst parts of being a data scientist is the ambiguity that the role can often entail. Since data science is a relatively new function, the mandate and objectives aren’t always clear. This often … Read more

The Riddler – June 26th

This weeks express deals with an erratic driver: In Riddler City, the city streets follow a grid layout, running north-south and east-west. You’re driving north when you decide to play a little game. Every time you reach an intersection, you randomly turn left or right, each with a 50 percent chance. After driving through 10 … Read more

Categories R Tags ExcerptFavorite

Jean Alfonso-Decena: Leading Innovation in Conversational AI and Disrupting the Philippine FinTech…

WOMEN IN TECHNOLOGY SERIES An Interview with the Head of Operations & Partnerships at Starbutter AI Over the past few years, tech companies and researchers all over the world have been competing to advance the frontiers of artificial intelligence. With the broadening and fast-paced developments in the space of technology, it is clear that utilizing … Read more

Modules and Packages in Python: Fundamentals for Data Scientists

Understand the basics with a concrete example! Photo by Matthew Fournier on Unsplash When your Python code grows in size, most probably it becomes unorganised over time. Keeping your code in the same file as it grows makes your code difficult to maintain. At this point, Python modules and packages help you to organize and … Read more

Build The World’s Simplest ETL (Extract, Transform, Load) Pipeline in Ruby With Kiba

We’re going to bundle this up in a tiny ruby project. Create our directory $ mkdir kiba-etl && cd kiba-etl/ Add the source CSV Create a CSV file with touch phone.csv and paste in the following. id,number1,123.456.78912,2223,303-030-30304,444-444-44445,900-000-000016,#10000000007,#98989898988,800-000-000009,999.999.999910,1.1.1.1.1.1.1.1.1.111,(112)233-445512,(121)212-0000 In a real situation, you might use a service like Twilio to detect if they’re real phone numbers. … Read more

Introduction to Factors in R

Factors play a crucial role in data analysis. Learn how to create, subset, and compare them. A factor refers to a statistical data type used to store categorical variables. Categorical variables belong to a limited number of categories. Continuous variables, on the other hand, can correspond to an infinite number of values. It is important … Read more

Cocalc vs. Colab — Which Is Better for a Hands-On Workshop?

photo by author I recently had the opportunity to deliver a hands-on workshop on training a Keras deep learning model. This workshop was a follow-on for a session I had done for a local meetup that reviewed the content in my upcoming book for Manning Publications, Deep Learning with Structured Data. After the introductory session … Read more

Visualizing Principle Components for Images

[This article was first published on R – Hi! I am Nagdev, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t. Principle Component Analysis (PCA) is a great tool … Read more

Categories R Tags ExcerptFavorite

Introduction to Trend Filtering with Applications in Python

Recently, I’ve been working on a project that involves some time-series modelling for quantitative investment strategies. Specifically, a key component of the strategy involves developing a differentiated investment approach for different regimes. Such an identification is useful because when the underlying dynamics of the financial market shift, the strategies that work well in one regime … Read more

Netflix Recommender System — A Big Data Case Study

The story behind Netflix’s famous Recommendation System Image by Thibault Penin on Unsplash What is Netflix and what do they do? Netflix is a media service provider that is based out of America. It provides movie streaming through a subscription model. It includes television shows and in-house produced content along with movies. Initially, Netflix used … Read more

Single Line of Code to Interchange Between Python Objects and JSON

Python Programming Tips The easiest way to serialise/deserialise between Python objects and JSON — Attr and Cattr In one of my previous article, I have introduced probably the best practice of Object-Oriented Programming (OOP) in Python, which is using the library “Attrs”. Probably the Best Practice of Object-Oriented Python — Attr Makes Python Object-Oriented Programming … Read more

Introducing GooglyPlusPlus!!!

“We can lift ourselves out of ignorance, we can find ourselves as creatures of excellence and intelligence and skill.”“Heaven is not a place, and it is not a time. Heaven is being perfect.”“Your whole body, from wingtip to wingtip, is nothing more than your thought itself, in a form you can see. Break the chains … Read more

Categories R Tags ExcerptFavorite

Setup Vue.js Hello World In Visual Studio Code

Go to this link to download: Node.js. I selected the “Recommended For Most Users” option and then used all the default settings in the Node.js setup. Checkpoint: Once it has finished installing, type into your command line: node -v && npm -v And it should look like this (your versions may be more recent than … Read more

Pneumonia Detection using Deep Learning

With the recent outbreak of COVID-19 also known as the coronavirus, it does seem like history is repeating itself and we are going back in time to the 1900s during the spanish influenza. The coronavirus is a deadly virus that has claimed hundreds of thousands of lives in countries around the world. Older adults and … Read more

The forgotten legacy of Traditional Medicine in the age of coronavirus

In the midst of all our plant medicinals studying, one very stressful pressure always comes up: It’s tough to get clinical trials of any promising candidate compound initiated anywhere in the world. But the class of compounds we study aren’t typical pharma drugs formulated straight from a laboratory drawing board; these are plant medicinals. So … Read more

Build Intuition for the Fourier Transform

A Magical Algorithm for Convolution and Signal Processing The Fourier Transform and its cousins (the Fourier Series, the Discrete Fourier Transform, and the Spherical Harmonics) are powerful tools that we use in computing and to understand the world around us. The Discrete Fourier Transform (DFT) is used in the convolution operation underlying computer vision and … Read more

Reshape R dataframes wide-to-long with melt — tutorial and visualization

Before we begin our melt tutorial, let’s recreate the wide dataframe above. df_wide <- data.table(student = c(“Andy”, “Bernie”, “Cindey”, “Deb”),school = c(“Z”, “Y”, “Z”, “Y”),english = c(10, 100, 1000, 10000), # eng gradesmath = c(20, 200, 2000, 20000), # math gradesphysics = c(30, 300, 3000, 30000) # physics grades)df_wide student school english math physics1: Andy … Read more

Interesting AI/ML Articles You Should Read This Week (June 28)

Adam Tabriz, MD article combines the world of Artificial intelligence and Healthcare, through the portrayal of how AI will impact the day to day roles and services delivered by various healthcare practices. The non-technical approach of the article makes this a great read for all readers. Adam starts with a deep dive of the term … Read more

Visualizing Covid-19 Over Time Using React

1 — Getting the Data A finicky part of any visualization can be handling the input data, and this was especially true in this case because the data was owned and updated by another party (Johns Hopkins). This meant that when they changed their organizational style, I had to adjust too. I chose to rely … Read more

Hands on Churn Prediction with R and comparison of Different Models for Churn Prediction

Using GLM, Decision Tree and Random Forest to predict Churn and compare the models with their accuracy and AUC values Photo by Scott Graham on Unsplash What is Churn ? Churn rate, when applied to a customer base, refers to the proportion of contractual customers or subscribers who leave a supplier during a given time … Read more

On Data Exploration and Visualisation

So you’ve got a hot dataset you want to take a look at. Nice. How you visualise it is going to depend on what kind of data it is. Is it one, two, three, or more-dimensional? Is it discrete or continuous? Do you know? Often I find myself thinking I know what the nature of … Read more

Simulating Spectroscopic Data Part 1

It is well-recognized that one of the virtues of the R language is the extensive tools it provides for working with distributions. Functions exist to generate random number draws, determine quantiles, and examine the probability density and cumulative distribution curves that describe each distribution. This toolbox gives one the ability to create simulated data sets … Read more

Categories R Tags ExcerptFavorite

R Objects, S Objects, and Lexical Scoping

[This article was first published on Data Science Depot, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t. Two key R design principles related to objects and lexical scoping … Read more

Categories R Tags ExcerptFavorite

An overview of Covid-19 in Mexico

mexico_confirmed = pd.read_csv(‘https://raw.githubusercontent.com/DiegoHurtad0/Covid-19-Dataset-Mexico/master/time_series_covid19_confirmed_Mexico.csv’)mexico_deaths = pd.read_csv(‘https://raw.githubusercontent.com/DiegoHurtad0/Covid-19-Dataset-Mexico/master/time_series_covid19_deaths_Mexico.csv’)mexico_suspects = pd.read_csv(‘https://raw.githubusercontent.com/DiegoHurtad0/Covid-19-Dataset-Mexico/master/time_series_covid19_suspects_Mexico.csv’)mexico_negative = pd.read_csv(‘https://raw.githubusercontent.com/DiegoHurtad0/Covid-19-Dataset-Mexico/master/time_series_covid19_negative.csv’)dataset_mexico = pd.read_csv(‘https://raw.githubusercontent.com/DiegoHurtad0/Covid-19-Dataset-Mexico/master/datasetCovid19Mexico.csv’) A time-series data which contains the counts on infected cases, deaths, and recoveries across countries is also given. The time-series data have individual files for each case and needs to be processed before visualization. The country co-ordinates are also provided for time series visualization … Read more

SVM’s — Jack of all trades?

An explanation of SVM’s for linear and non-linear datasets The following explanation assumes that you have a basic understanding of supervised machine learning as well as linear discriminant functions. However, if like me, you have been gifted with the memory of goldfish, let us remind ourselves the following, Supervised Machine Learning entails the creation of … Read more

Machine Learning Basics: Simple Linear Regression

Learn the basic Machine Learning Program of Simple Linear Regression. One would perhaps come across the term “Regression” during their initial days of Data Science programming. In this story, I would like explain the program code for the very basic “Simple Linear Regression” with a common example. Overview — In statistics, Linear Regression is a … Read more

How to Build an Effective Data Science Portfolio

Studying them takes us back to the very important and commonly asked question: How do I compensate for the experience factor if I am a fresher? The answer is Projects! Wait! I already knew that… Here is what you probably didn’t know, these projects can’t be your analysis over MNIST dataset or solving the titanic … Read more

Riddler: Can You Just Keep Turning?

[This article was first published on Posts | Joshua Cook, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t. FiveThirtyEight’s Riddler Express link In Riddler City, the city streets … Read more

Categories R Tags ExcerptFavorite

Sorry, But sns.distplot() Just Isn’t Good Enough. This is, Though

2 | FacetGrid Instead of plotting directly using a seaborn (or matplotlib) function like sns.barplot(), take time to invest in a FacetGrid. While it technically doesn’t plot any information, it helps organize your data and sets up a clear framework in which you will be building your plot. Let’s take a look at our data, … Read more