Pretty recently I found a paper with the title “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. The topic of interpretability is very important in the times of complex machine learning models and it’s also related to my PhD topic (reliability of machine learning models). Therefore I wanted to play around with … Continue reading Exploring lime on the house prices dataset
Some time ago I published a blog post with the title Know your data structures!. In this previous post I explained how I improved the running time of a genetic algorithm. I promised to go more into detail about other noteworthy things in the code in a separate article since not everything was straightforward when … Continue reading Learning Club 16: Genetic Algorithms
Just a few days ago I stated the following on Twitter: Just reduced the runtime of an algorithm from 9 hours to 3 min. by using a different data structure… Know you data structures 🙂 #rstats — Verena Haunschmid (@ExpectAPatronum) May 1, 2017 Since my tweet has been liked and shared a lot, I thought … Continue reading Know your data structures!
Problem Usually when developing SSIS packages, you want the project to run on different servers, e.g. development, test and production server. If you have many environment variables creating all of them is tedious and unnecessary work. I’ll show you how you can copy environment variables between SSIS catalogues that are located on different servers. Solution … Continue reading Copy environment variables between SSIS catalogues on different servers
Some weeks ago I had a presentation at my work place about “R for data science” that I’d like to share with you. I’ve written the slides in R and rmarkdown and uploaded them to rpubs.com. I chose to use rmarkdown for my slides although we have great company PowerPoint templates, because I wanted to … Continue reading Presentation “R for Data Science”
Recently I have been starting to use dplyr for handling my data in R. It makes everything a lot smoother! My previous workflow – running an SQL query, storing the results as CSV, loading it in RStudio – is now history. With dplyr you can directly query data from many different databases in a very … Continue reading Accessing MSSQL Server with R (RSQLServer with dplyr)
Since I am a data junkie and bought my Fitbit Charge HR mainly because I wanted to collect and analyse data about myself, I was looking for ways to download the data to your computer. For most people the great stats overview in the app and in the online dashboard will be sufficient but some … Continue reading Accessing your Fitbit data
I remember when I had an R course at university I was really not a fan of rmarkdown and knitr. But since I participate in a Learning Club, where people are encouraged to document and present their code, data and results, I started to love it. Prior to that I’ve always documented my assignments at the university either … Continue reading Learning Club 05-07: Starting to love rmarkdown (Naive Bayes, Clustering, Linear Regression)
Almost 2 weeks ago the Becoming a Data Scientist podcast had 4 special interviews – each of them with members of the Learning Club, including me! I was super excited when Renee asked me some weeks ago if I wanted to participate and I was a little bit nervous during the interview. But I think … Continue reading I was guest at the Becoming a Data Scientist Podcast!
This is the third post in my dataset series. The first part gave a more general overview on where to get data. In the second post I listed sources for sports, movies, music and books data. This section will give you information on how to get weather, public/governmental data and how to find GIS data. … Continue reading Finding data sets PART 3: Weather, geographical and government data