April 4, 2019 · 8 minute read
...or how to avoid the It-works-on-my-computer-but-nowhere-else-problem
The excellent comic by Jeff Lofvers illustrates what you often face in software development but also in data science. You are preparing a data analysis or predictive model, but when you want to share it, then it does not work on someone else machine. It fails, because libraries are missing,… Read more
March 20, 2019 · 18 minute read
Project report for training a MobileNetV1 based convolutional neural network (CNN) with only 14,000 images with transfer learning
I. Definition Project Overview The “A picture is worth a thousand words” stresses how important images are in the modern world. The quality of images, e.g. influences our decisions in different domains. Especially in eCommerce, where we cannot touch things they are essential. They have… Read more
February 19, 2019 · 8 minute read
Valuable insights which I gained from retrieving data from many websites over the last years which I want to share with you
“Data is the new oil. It’s valuable, but if unrefined it cannot really be used. It has to be changed into gas, plastic, chemicals, etc. to create a valuable entity that drives profitable activity; so must data be broken down, analysed for it to have value.” - Clive Humby A… Read more
February 5, 2019 · 5 minute read
A short practical guide how to find and visualize missing data with ggplot2, dplyr, tidyr
Finding missing values is an important task during the Exploratory Data Analysis (EDA) . They can affect the quality of machine learning models and need to be cleaned before training models. Detecting the missing values let’s you also evaluate the quality of your data retrieval process. This… Read more
June 22, 2018 · 3 minute read
…or how to be BOD (=Business Opportunity Detective) A few days ago I was at a beach bar with a friend who is a freelancer like me. We met a young lady working at the counter who just finished university in sports psychology. She was interviewing us about our freelancership and asked us many… Read more