Tarek Amr | Publications

Hands-On Machine Learning with Scikit-Learn and Scientific Python Toolkits

Author: Tarek Amr - ISBN-13: 978-1838826048 - Packt Publishing (c) July 24, 2020

📚 This book is your practical guide to bootstrap your data science career, and to start buildning hands-on machine learning solutions with scikit-learn and its related ecosystem. 📬 Order it from the following links.

Practical D3.js: Master the use of D3.js in the real world

📚 This book is your guide to Data Visualisation using D3.js & JavaScript. 📝 I co-authored this book with Rayna Stamboliyska. 📬 Order it from the following links.

Python Data Visualization Cookbook

📚 Over 70 recipes to get you started with popular Python libraries based on the principal concepts of data visualization

Konfliktkulturen

📚 Texte zu Politik, Gesellschaft, Alltag und Kunst. 🇩🇪 I wrote one chapter, among many other authors.

URL-Based Web Page Classification using Language Models

🎓 The goal of this research is to be able to classify web pages using their URLs only.

🕷 Springer

URL-Based Web Page Classification using Language Models

🎓 The goal of this research is to be able to classify web pages using their URLs only.

🕷 Dissertation

A Survey on Feature Selection Techniques

🥢 Feature selection plays an important role in the data mining process. 🔎 In this review, we discuss the different feature selection approaches, and the relation between them and the various machine learning algorithms.

A Survey on Time-Series Data Classification

⏰ Time-series (or sequential) data are every where. They are important in stock market analysis, economics, sales forecasting, and the study of natural phenomena such as temperature and wind speed. 🔎 In this report, I focus on time-series data classiﬁcation by shedding the light on the researches done in this area.

🕷 Self Published

Language Identification: Do You Speak London?

🌍 Do You Speak London (dysl) is a command line tool and python library for natural language identification, also known as LangID, using character-based n-Gram Language Model. Currently pre-packaged with training data for 4 languages; English, Arabic, Spanish and Portuguese. However, you can simply re-train it on your own dataset. 🤖 This paper explains the basic architecture of the library as well as its theoretical background.

Human-Computer Interaction

🗂 Misc school reports on Usability and Human-Computer Interaction

Linux-Based DiffServ Router

💻 We built a GUI software on top of the Linux TC (Traffic Control), to apply QoS to the network traffic. 🚀 A DSCP mark is applied to each class. Then the traffic is shaped and prioritized according to those classes.

🕷 Slide Share

Pie and Donut Charts using D3.js

🌀 D3.js is a JavaScript library that is widely used in data visualisation and animation. The power of d3.js and its flexibility, comes at the expense of its steep learning curve. There are some libraries built on top of it that provide numerous off-the-shelf charts in order to make the users’ life easier, however, learning to work with d3.js is essential sometimes, especially when you need to create sophisticated and custom visualisations.

🕷 School of Data

How to build an Interactive Dictionary using ElasticSearch

🌊 ElasticSearch is a search server based on Lucene. 💬 It provides a distributed, multitenant-capable full-text search engine with a RESTful web interface and schema-free JSON documents. Nevertheless, there are endless uses of Elasticsearch beyond that, and here is one of them.

🕷 Medium (Meedan Labs)

Predict the Future with Regression Analysis using Scikit-Learn and a little bit of Python

⛅ Introduction to regression analysis and the very basics of machine learning using Scikit-Learn and a little bit of Python.

🕷 Medium (Self)

How we built a Recommendation System at TicketSwap

♪ TicketSwap is second-hand tickets marketplace. ♬ To make sure we recommend the best events for our fans, we had to build a recommendation engine that can predict their taste. ♫ In this post, I explain our Neural Embedding approach, and the steps we took from data enrichment to model evaluation and deployment. We used libraries such as Gendsim and Flask. ♩ So feel free to contact me about any further technical details.

🕷 Medium (TicketSwap)

A gentle introduction to Confidence Intervals

🤖 While interviewing applicants for a data analyst position at my employer, I was shocked to find out that many of the applicants do not fully grasp basic statistical concepts, such as standard error and confidence intervals. These aren’t obscure statistical concepts, but essential ones for the job, thus, I wanted to spend some time here explaining them in more details.

🕷 Medium (Code X)

Generalized Linear Models (GLM)

🖋 As its name suggests, the Generalized Linear Model is an extension to our ultimate favorite Linear Regression algorithm. I am sure y’all know the theory behind the linear regressors quite well, so I will limit the next section to just the details needed for understand the GLMs.

🕷 Medium (Code X)

Pytest’s assert is not what you think it is

🌳 What is Abstract Syntax Trees, or AST for short? And how pytest hacks it to give you a better UX?

🕷 Medium (Code X)

Discovery, Recommendation and Curation: How are we connecting talent with fans

♬ Since we are born we are in an exploration mode, we always want to know what’s new, what’s trend, discover the news related to our interests. In the post-covid era even more, connection is what people want. Being connected among each other and being connected to what we like. Discovery platforms' goal is to serve this purpose; through these platforms consumers can find what’s interesting for them, publishers can increase engagement with their content while monetising on ads space, paid by advertisers to show their products/services to the right target audiences.

🕷 YouTube (Discovery, Recommendation and Curation)

SWE & MLE: Path-dependent Processes

🌊 The term “Path dependence” is used in the history of economics. When there are two groups, each go through different historic events, and consequently take different actions, the two groups end up having two different economies, no matter how small and insignificant the actions they took. In this talk, I argued that software engineers (SWE's) and machine learning engineers (MLE's) also went through path dependent processes and ended up having different cultures

Machine learning & Data Analysis [Ar]

🌊 Eslam Mahmoud had a chat with me about my role as Lead Machine Learning Engineer at TicketSwap. The discussion went to the differences between Machine Learning and Data Analysis, we jumped from topic to topic, till we ended up talking for almost 2 hours.

🕷 YouTube (Machine learning & Data Analysis) [Ar]

Data Driven Marketplaces [Ar]

🗂 Tarek Amr will talk about the role of data science in building online platforms for eCommerce marketplaces. Online marketplaces are great business models with plenty of peculiar problems to deal with. As Tarek has spent most of his career as a data scientist in marketplaces platforms, he would shed the light on some of the problems and how the data-driven approach is used to solve them.

🕷 YouTube (Data Driven Marketplaces) [Ar]

The war on endomorphs has to end

🍩 Why “eat less and exercise more” isn’t the answer? Tips for losing weight and getting in shape according to your body (somato)type.

🕷 Medium

Multicultural Robots and Racist Machines

🤖 Is it possible for computers to become racist and act upon stereotypes? Maybe it is better to understand computers, robots and machine learning to understand their limitations and possibilities.

🕷 Deutsche Welle (DW.com)

Mwazna: New Transparency Platform Aims to Make Egyptian Politics More Objective

💰 Mwazna is the Arabic for “state budget”, and it’s the name of a new platform which lets citizens monitor the income and spending of the Egyptian government.

🕷 Huff Post

Egypt’s revolution will get a shot in the arm with data to show how the government spends its money

💰 Mwazna (budget in Arabic) the brainchild of a data scientist, Tarek Amr, and a web developer and hacker, Amr Sobhy, aims to inform Egyptians on how their money is being spent through an easy to use site.

🕷 QZ

Egypt: The Unspoken Languages of the Streets

🔊 We as humans have a unique ability to communicate via spoken languages. 🔇 However, in a crowded and loud city like Cairo, we sometimes need more than a spoken language to communicate.

🕷 Global Voices

Story Curation

🍲 Using social media updates to build a news story. 🍒 In this slides I summarize how we curate stories in Global Voices from social media updates, after adding context to them.

🕷 Slide Share

Networked Revolts

👑 My presentation in Networked Revolts session held in Athens, Greece, May 2011. The session was discussing the uprisings spreading across North Africa and the Middle East and its relation to Social Media.

🕷 Slide Share

Failed Startups - Lessons Learned

Author: Tarek Amr - GeekFest Cairo (c) 29 May 2010

🎖 A presentation about my failed startup and the lessons I learned from its failure.

🕷 Slide Share