Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Andy McDonald
Retail customers are shifting from experience to participation and ownership
The days of the passive retail consumer is over. Today, they’re seeking a much deeper involvement in their purchasing journey – and the brands who can give them this are the ones with whom they will choose to shop. The retail industry has just experienced a watershed couple of years, defined by unprecedented changes and brought on in part by the pandemic – high inflation, rising energy prices, the cost-of-living crisis and ongoing geopolitical uncertainty.
The modern retail customer wants more than just an experience
Consumer attitudes and behaviours are changing. People are seeking value from their shopping, and while price will be the ultimate purchase driver, there is a reluctance to compromise on convenience and values. Expectations of service, retail technology and sustainability are rising. The future of retail is one where the shopper will be much more deeply involved.
Random Forest Regression for Continuous Well Log Prediction
MACHINE LEARNING | PETROPHYSICS An overview of a popular machine learning algorithm applied to petrophysics Random Forest is a very popular and relatively easy to understand machine learning algorithm. In my previous article on Random Forest we attempted to predict categorical data (lithology) from a series of well log measurements. Within this article we are going to focus on the prediction of continuous measurements.
Random Forest for Lithology Classification From Well Log Data
Machine Learning | Petrophysics Classifying the Subsurface With Machine Learning Random Forest is a very popular machine learning algorithm that can be used for both classification, where we are trying to predict a category or class, and regression, where we are trying to predict a continuous variable.
Seaborn Heatmap for Visualising Data Correlations
Data Visualisation | Seaborn Visualise how well features correlate with each other with a simple heatmap Heatmaps are a great tool for creating beautiful figures and can provide us with insights on trends and allow us to easily identify potential outliers within a dataset. Within this tutorial, we are going to look at one of the uses for a heatmap — the correlation matrix heatmap.
7 Tips To Get You Off To A Great Start When Learning Python
Lessons learned from 5 years of developing Python skills Have you heard about Python from a friend or on the internet and wanted to try it out but don’t know where to start? If so, then this article is for you. About 5–6 years ago I was in a very similar position. As part of my job, I needed to write a custom script for a number of equations within a software package. This script was a bit more complex than simple equations and I needed to include proper logic within it.
Seaborn Pairplot — Enhance your Data Understanding With a Single Plot
A short guide on using Seaborn’s Pairplot in Python The Seaborn Pairplot allows us to plot pairwise relationships between variables within a dataset. This creates a nice visualisation and helps us understand the data by summarising a large amount of data in a single figure. This is essential when we are exploring our dataset and trying to become familiar with it. As the saying goes, a picture paints a thousand words.
6 Machine Learning Algorithms to Know About When Learning Data Science
Short Explanations of 6 Popular Machine Learning Algorithms Machine Learning has become very popular over the past decade or so with many industries adopting new algorithms to automate processes and increase productivity. Machine Learning is a branch of Artificial Intelligence (AI) and involves machines/computers learning from data and generating results without being explicitly programmed to do so. In traditional programming we provide the input data and the rules to generate an output.
5 Essential Tips to Improve the Readability of Your Python Code
Improving your Python Code Through Documentation, Type Hinting and Proper Variable Names Do you often look back at some code you wrote 6 months ago and scratch your head and wonder what this mess is? Or have you been passed a project that has been worked on by someone else and struggle to know where to start? If so you are not alone.
Use Seaborn FacetGrid to Quickly Create Figures With Subplots
Enhance your Exploratory Data Analysis Process by Using Seaborn’s FacetGrid — An Example Using Earthquake Data Data visualization is an essential part of any data analysis or machine learning workflow. It allows us to gain insights about our data, and as the famous saying suggests, ‘a picture is worth a thousand words’. When working with data visualizations in Python, we may want to split the data up by categories or different groups. This is achieved using Seaborn’s FacetGrid function.
Creating Boxplots with the Seaborn Python Library
A Quick Getting Started Guide for Seaborn Boxplots Boxplots are a great statistical tool for visualising data and are commonly used during the Exploratory Data Analysis (EDA) phase of data science projects. They provide us with a quick statistical summary of the data, help us understand how data is distributed and help identify anomalous data points (outliers). Within this short tutorial we are going to see how to generate boxplots using the popular Seaborn Python library.
Creating True Multi-Page Streamlit Apps - The New Way (2022)
The Latest Way to Make Streamlit Apps Multi-page Streamlit is an open source python based framework for developing and deploying interactive data science dashboards and machine learning models. In my previous Streamlit article, I discussed how to get started building a simple Earthquake data explorer. This was a simple single page web app, that allowed you to view data and generate some plots.
Seaborn Relplot in Python: Visualising Relationships in Data
Visualising Well Log Data Using Seaborn’s relplot The Seaborn Relational Plot (relplot) allows us to visualise how variables within a dataset relate to each other. Data visualisation is an essential part of any data analysis or machine learning workflow. It allows to gain insights about our data. As the famous saying suggests, ‘a picture is worth a thousand words’.
Getting Started With Streamlit Web Based Applications
A gentle introduction to creating Streamlit web apps Streamlit is an open source python based framework for developing and deploying interactive data science dashboards and machine learning models. This means that you do not have to rely on a team of front end developers or spend large amounts of time learning web design languages such as HTML, CSS or Javascript in order to deploy your dashboard or model.
Pandas Profiling - Easy Exploratory Data Analysis in Python
Fast and effective EDA with the Pandas Profiling Library Exploratory Data Analysis (EDA) is an important and essential part of the data science and machine learning workflow. It allows us to become familiar with our data by exploring it, from multiple angles, through statistics, data visualisations, and data summaries. This helps discover patterns in the data, spot outliers, and gain a solid understanding of the data we are working with.
Convert CSV Files to LAS Files with Python
Quick and simple conversion process to create a LAS file from scratch using LASIO and CSV Data Well log data can be delivered in a variety of formats (DLIS, LAS, CSV, ASC etc.). If you have a CSV file containing well log data, and you want to convert it to LAS format, you can use the LASIO library LAS files are a simple format. They are simple text files that contain meta data about the well, parameter information, and log data measurements.
Public Datasets for Machine Learning in Geoscience
The best open source geoscience datasets for applying data science, machine learning and petrophysical techniques Photo by imgix on Unsplash For many years well logging and petrophysics datasets have remained locked up in oil and gas company servers or government servers and has only been accessible to those people who have the right access privileges.
6 Python Libraries You Should Know About for Well Log Data & Petrophysics
Discover 6 great python libraries that you can start using today with well log data Photo by Hitesh Choudhary on Unsplash One of the great things about Python is the vast number of open source libraries that have been developed to improve the way we work with data and make sense of it. Within the petrophysics and geoscience domains there are a number of helpful libraries that can make things easier when working with well log data.
Enhance Your Plotly Express Scatter Plot With Marginal Plots
Plotly Express Scatter Plot of well log data illustrating marginal plots on both axes. Image by the author. Scatter plots are a commonly used data visualisation tool within data science. They allow us to plot two numerical variables, as points, on a two dimensional graph. From these plots, we can understand if there is a relationship between the two variables, and what the strength of that relationship is.
Visualising Well Paths With the Welly Python Library
3D Line Plot showing the position of a well path generated from the Welly Python Library. Image by the author. There are multiple depth references used within well logging to denote a position along the wellbore. These include measured depth (MD), true vertical depth (TVD), true vertical depth subsea (TVDSS) etc. All of which are critical measurements for the successful development and completion of a well. Illustration showing the differences between MD, TVD, and TVDSS.
Well Log Data Outlier Detection With Machine Learning and Python
Photo by Will Myers on Unsplash Outliers are anomalous points within a dataset. They are points that don’t fit within the normal or expected statistical distribution of the dataset and can occur for a variety of reasons such as sensor and measurement errors, poor data sampling techniques, and unexpected events.
Identification and Handling of Missing Well Log Data Prior to Petrophysical Machine Learning
Photo by Markus Spiske on Unsplash Machine learning and Artificial Intelligence are becoming popular within the geoscience and petrophysics domains. Especially over the past decade. Machine learning is a subdivision of Artificial Intelligence and is the process by which computers can learn and make predictions from data without being explicitly programmed to do so.
Exploring Well Log Data Using Pandas, Matplotlib and Seaborn
Photo by Markus Spiske on Unsplash Machine learning and Artificial Intelligence are becoming popular within the geoscience and petrophysics domains. Especially over the past decade. Machine learning is a subdivision of Artificial Intelligence and is the process by which computers can learn and make predictions from data without being explicitly programmed to do so.
Creating Boxplots of Well Log Data Using Matplotlib in Python
Boxplots are a great tool for data visualisation, they can be used to understand the distribution of your data, whether it is skewed or not, and whether any outliers are present. In this article, we will look at what boxplots are and how we can display them using pandas and matplotlib. To accompany this article, I have made the following YouTube Video. What are Boxplots?
Using Line Plots from Matplotlib to Create Simple Log Plots of Well Log Data
Well log plot created using the matplotlib Python library. Image by author. Well log plots are a common visualization tool within geoscience and petrophysics. They allow easy visualization of data (for example, Gamma Ray, Neutron Porosity, Bulk Density, etc) that have been acquired along the length (depth) of a wellbore. On these plots, we display our logging measurements on the x-axis and measured depth or true vertical depth on the y-axis.
Creating Scatter Plots (Crossplots) of Well Log Data using Matplotlib in Python
Neutron density scatter plot / crossplot created with matplotlib in python. Image by the author. Introduction Scatter plots are a commonly used data visualisation tool. They allow us to identify and determine if there is a relationship (correlation) between two variables and the strength of that relationship. Within petrophysics scatter plots, are commonly known as crossplots.
Creating Histograms of Well Log Data Using Matplotlib in Python
Photo by Marcin Jozwiak on Unsplash Introduction Histograms are a commonly used tool within exploratory data analysis and data science. They are an excellent data visualisation tool and appear similar to bar charts. However, histograms allow us to gain insights about the distribution of the values within a set of data and allow us to display a large range of data in a concise plot.
10 Applications of Machine Learning Within Petrophysics
Photo by Dan Meyers on Unsplash Several decades of hydrocarbon exploration have led to the acquisition and storage of large quantities of well related measurements, which have been used to characterise the subsurface geology and its hydrocarbon potential. The potential of these large volumes of data has been increasingly exploited over the last couple of decades as computational power and the adoption of new machine learning algorithms increase.
Using the missingno Python library to Identify and Visualise Missing Data Prior to Machine Learning
Photo by Tim Mossholder on Unsplash Data exploration and pre-processing are important steps within any data science or machine learning workflow. When working on tutorial or training datasets it can be the case that they have been engineered in a way to make it easy to work with and allow the algorithm being discussed to be run successfully. However, in the real world, data is messy! It can have erroneous values, incorrect labels and parts of it can be missing.
How to use Unsupervised Learning to Cluster Well Log Data using Python
Application of unsupervised cluster analysis on well log data to identify lithofacies (Image by Author) Understanding the subsurface lithology is an important task in geoscience and petrophysics. Using a variety of electrical measurements generated from well logging technology we are able to make inferences about the underlying geology, such as the lithology, facies, porosity, and permeability.
Loading Well Log Data From DLIS using Python
There are a number of different formats that well log and petrophysical data can be stored in. In the earlier articles and notebooks of this series, we have mainly focused on loading data from CSV files (here) and LAS files (here and here). Even though LAS files are one of the common formats, they have a flat structure with a header section containing metadata about the well and the file followed by a series of columns containing values for each logging curve.
Adding Formation Data to a Well Log Plot
Well log plots are a common visualization tool within geoscience and petrophysics. They allow easy visualization of data (for example, Gamma Ray, Neutron Porosity, Bulk Density, etc) that has been acquired along the length (depth) of a wellbore.
Porosity-Permeability Relationships Using Linear Regression in Python
A short guide on applying a linear regression in Python to semi-log data Photo by Ekaterina Novitskaya on Unsplash Core data analysis is a key component in the evaluation of a field or discovery, as it provides direct samples of the geological formations in the subsurface over the interval of interest. It is often considered the ‘ground truth’ by many and is used as a reference for calibrating well log measurements and petrophysical analysis.
Building a web scraper for geologic data using Selenium and Beautiful Soup in Python
How to iteratively search a website and extract data from it Photo by AltumCode on Unsplash For a work task, I recently found myself needing to determine how many geologic maps have been published in the state of Colorado, a task that brought me to the United States Geological Survey (USGS) publications warehouse [1]. The National Geologic Map Database (NGMDB)[2], an offshoot of the pubs warehouse, shows 4,855 published maps for the state of Colorado (Fig. 1).
Petrophysics: Gamma Ray Normalization in Python
Photo by Maxwell Nelson on Unsplash Hands-on Tutorials Normalization of well log data is a common and routine process within a petrophysical workflow and is used to correct for variations in logging curves between wells. These variations can arise due a number of different reasons such as incorrect tool calibrations, varying tool vintage and changes in borehole environmental conditions between the wells.
Channel 4 taps Simplestream for online Paralympics coverage
UK broadcaster Channel 4 has partnered with over-the-top video technology firm Simplestream for its online coverage of Parasport and the Tokyo 2020 Paralympics. London-headquartered Simplestream has built an accessible video platform and responsive website for Channel 4 that is designed to handle multiple live concurrent streams and on-demand video.
Eurofins partners with the IRT for IMF solutions
Quality assurance company, Eurofins Digital Testing, has unveiled software solutions designed to help companies adopt the Interoperable Mastering Format (IMF). Eurofins’ IMF products are based on technology provided by the German, Austrian and Swiss public service broadcasters’ joint research centre, the Institut für Rundfunktechnik (IRT), thanks to an exclusive global licensing deal.
Amobee launches data marketplace for connected TV ads
Ad-tech company Amobee has launched a data marketplace for connected TV and cross-screen advertising campaigns. Amobee has launched its CTV Data Marketplace with more than 60 data providers, including Oracle Data Cloud, the LiveRamp Data Store, IRI, Inscape, Lotame, Eyeota and Tru Optik.
Neotion and SmarDTV outline key market trends in STB study
Future Pay TV growth will need to be driven by innovative products and new business models as demand for traditional pay-TV declines, according to a study by Neotion and SmarDTV. The ‘STB is dead… long live the STB’ report describes over-the-top television as both a challenge and an opportunity, with Pay TV operators responding to new TV viewing habits and increased competition by adapting their offers with broader product and service portfolios.
IBC 2019: Harmonic to demo OTT and broadcast deployments
Harmonic is due to demonstrate real-world deployments of its unified OTT and broadcast delivery solutions at IBC this year. Cloud, on-premises, and hybrid deployments will be showcased to illustrate how service providers, broadcasters and content owners originate and distribute their video channels.
IBC 2019: Synamedia takes aim at piracy with security enhancements
Video software provider, Synamedia, is set to unveil enhancements to its security portfolio at this year’s IBC show in Amsterdam. The company will showcase its Streaming Piracy Disruption service, which has a single workflow for both broadcast and IP streaming and now lets customers disrupt leaks without waiting for third-party takedowns.
IBC 2019: NAGRA sets focus on four key areas at IBC 2019
Securing content, optimising monetisation and improving consumer satisfaction across pay-TV will be some of the themes highlighted by NAGRA at IBC this year. Showcasing its latest technologies, the content security and multiscreen TV solutions provider will focus on four key areas: scalable service protection; anti-piracy services and forensic watermarking; engaging consumers in the OTT era; and ‘business performance redefined’.
IBC 2019: Vevo partners with Vewd for global smart TV distribution
Music video provider Vevo has partnered with smart TV OTT software provider Vewd, in a move that will make the Vevo platform available on Vewd-enabled devices around the world. The partnership will see Vewd offer the Vevo catalogue on a range of smart TVs and devices from manufacturers like Sony, Hisense, Philips, and TiVo, starting in late September 2019.
Inside Video Tech: What differentiates Verizon Media and drives its thinking
Ariff Sidi, Chief Product Officer, Verizon Media, Media Platform Ariff Sidi, Chief Product Officer at Verizon Media, Media Platform, answers questions from Andy McDonald, Contributing Editor Describe Verizon Media and the company’s core focus?
IMDb TV plans European expansion
Ad-supported video streaming service IMDb Freedive has rebranded to IMDb TV and announced plans to launch in Europe later this year. The Amazon-owned film and TV service also said that it will triple its content selection, bringing thousands of new titles to the free-to-view service in the coming months. New deals with studios like Warner Bros., Sony Pictures Entertainment and MGM Studios will make films like La La Land and Captain Fantastic available on IMDb TV.
Broadcasters’ share of AVOD revenue tipped to fall in the coming years
Ovum analyst Matthew Bailey Over the next five years broadcasters will lose share of ad-supported video-on-demand (AVOD) revenue as the global digital players continue to make gains, according to Ovum. Speaking at Videoscape Europe in London last week, Matthew Bailey, Senior Analyst, Media and Entertainment at the research firm, predicted that globally, excluding China, broadcasters will see their revenue share of the AVOD OTT market fall from 33% in 2018 to 26% in 2023.
Gracenote launches Video Popularity Score
Nielsen-owned Gracenote has launched Gracenote Video Popularity Score, a new data offering designed to help entertainment providers understand the TV shows and movies that viewers want to watch. Gracenote’s Video Popularity Score is calculated by looking at TV show airings, theatrical movie releases, viewership and ‘awareness signals’ from Gracenote and Nielsen, plus data from external sources.
Vewd and Innopia partner on streaming media device
Smart TV and OTT software provider Vewd has partnered with South Korean smart device manufacturer, Innopia, to launch a joint HDMI-based streaming media device. The new device will be powered by VewdOS – an operating system designed for smart TVs, set-top boxes, and smart home and IoT devices – and will be targeted at pay TV operators.
ProSiebenSat.1 and Discovery launch German streaming service Joyn
ProSiebenSat.1 and Discovery have launched their joint-venture ad-supported video streaming service, Joyn, in Germany. The free app offers 55 live TV channels, a media library of on-demand content that’s available during a 30-day catch-up window, and more than 40 formats that can be watched for seven days before they broadcast on TV. Joyn’s channel line-up includes channels from ProSiebenSat.1, Discovery, Viacom, WELT and Sport1, plus the channels provided by public broadcasters ARD and ZDF.
Liberty Global’s CEO of Eastern Europe steps down
Liberty Global has announced that the CEO of its Eastern European Group, Eric Tveter, is stepping down after ten years at the company. Liberty Global said in a statement that Tveter’s departure is timed with the sale of many of the assets he has overseen during his tenure at the company. Tveter has held senior leadership roles at Liberty Global since 2009 and most recently worked concurrently as CEO of the Eastern European Group and Chairman of UPC Switzerland.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Andy
Contact Andy, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack