In my previous post, I wrote about using spectral biclustering for making product recommendations. In this post, I'll build on that marketing example and use the Apriori algorithm for analyzing product purchases This example is, again, taken from Giuseppe Bonaccorso's book Mastering Machine Learning Algorithms.
My roles in data analytics/science so far have always been focused on online marketing applications, such as analyzing the impact of ad campaigns, the engagement of users with a website, or the performance of blog posts. Machine Learning algorithms and Python libraries like scikit-learn can help marketers derive insights from user data and establish connections between their features or actions that otherwise would go unnoticed.
In my search for resources that bridge data science and marketing, I found the chapter Clustering and Unsupervised Models for Marketing, which explains how to use spectral biclustering for making product recommendations. In this post, I share with you my learnings about this algorithm and its implementation in Python, as taken from the book.
I've been interested in emotions ever since I've become aware of them. Maybe because I was unsure how to process and interpret them, in both myself and others. How do people express emotions and why do they do it so differently? Is being scared the same as fearing? Can I really understand or experience sirva vigad if the word doesn't exist in my native language?
My solution to deal with this personal struggle was to read and research about emotions. I know I know, you can't learn everything from books, especially not human feelings and interactions, but nevertheless I've discovered some fascinated learnings about emotions.
This is why in university I chose to research verbs of emotion, more specifically to investigate the semantic characteristics of Romanian verbs of emotion.
Cinephiles and lovers of glam rejoice this Sunday – it's Oscars Award Ceremony time! Due to Corona, this year's 93rd edition was postponed from February to April 25th – the latest in the history of the award. I was personally happy about the delay, because it gave me more time to analyse some data and come up with this blog post.
On this ocassion, I was curious to do some text mining on the acceptance speeches. Specifically, I analysed the speeches of the Best Directors between 1941 and 2019. I used a dataset from Kaggle and added missing data for 2017, 2018, and 2019 directly from the Academy Awards Acceptance Speech database.
On the occasion of the International Mother Language Day (21st February), I did and exploratory analysis and data visualisation of the World Language Family Map dataset with pandas and matplotlib.
At the beginning of the new year 2021, Kaggle created a new format of competitions aimed at beginners. On the 1st of each month, a month-long Playground competition is launched, where you can practice your ML skills on simple tabular datasets. Apart from competitive experience, the top 3 teams get to win some Kaggle merchandise!
Project completed in week 12 (14.12.-18.12.20) of the Data Science Bootcamp at Spiced Academy in Berlin.
I did it! I graduated from the Data Science Bootcamp! On Friday I presented my final project, which was about detecting emotions from speech with neural networks. It was one of the most challenging project I've worked on, because I had to learn something new (how to process audio data and make live voice predictions) and prepare everything nicely in only 7 days. Here's how it went...
Project completed in week 10 (30.11.-04.12.20) of the Data Science Bootcamp at Spiced Academy in Berlin.
This was a really exciting week, because we had a team project which combined the power of Machine Learning algorithms with the beauty of Web Development!
Project completed in week 9 (23.11.-27.11.20) of the Data Science Bootcamp at Spiced Academy in Berlin.
This week we dived into Deep Learning and learned about different types neural networks (NN) and their applications in various domains. The main goal of this project was to learn and understand what each hyperparameter in a NN model does and how to tune it, so this week was more theoretical and math-heavy than usual.
Project completed in week 8 (16.11.-20.11.20) of the Data Science Bootcamp at Spiced Academy in Berlin.
This week we learned to make a Markov Chain Monte Carlo (MCMC) simulation of new customers in a supermarket, based on data about customer paths from entrance to checkout through four aisles (fruit, drinks, dairy, and spices) recorded on five days from 7 am to 10 pm. This project was particularly challenging for two reasons: it involved object-oriented programming (OOP) and team work. In this post I'll give you an overview of our workflow.