My Cookie Mix

Large language models (LLMs) support data analysis through conversational user interfaces, as exemplified in OpenAI's ChatGPT (formally known as Advanced Data Analysis or Code Interpreter). Essentially, LLMs produce code for accomplishing diverse analysis tasks. However, presenting raw code can obscure the logic and hinder user verification. To empower users with enhanced comprehension and augmented control over analysis conducted by LLMs, we propose a novel approach to transform LLM-generated code into an interactive visual representation. In the approach, users are provided with a clear, step-by-step visualization of the LLM-generated code in real time, allowing them to understand, verify, and modify individual data operations in the analysis. Our design decisions are informed by a formative study (N=8) probing into user practice and challenges. We further developed a prototype named WaitGPT and conducted a user study (N=12) to evaluate its usability and effectiveness. The findin...

Come primo passo è opportuno  e utile un bel giro sul sito ufficiale della comunità italiana di Python ( http://python.it/ ), ricco di informazioni utili a chi si avvicina per la prima volta a questo linguaggio. Altra documentazione (ovviamente in inglese) è disponibile sul sito ufficiale di Python ( https://www.python.org/ ) Poi, in ordine di utilità decrescente: Corso di introduzione alla programmazione su Kaggle ( https://www.kaggle.com/learn/intro-to-programming ). Corso molto utile per chi non ha mai programmato, introduce in modo veloce ad alcuni temi della programmazione in generale (anche se la sintassi utilizzata è quella di Python). Consigliato " Pensare in Python " (versione italiana di Think Python di Allen Downey), ottimo libro per apprendere le basi di Python. Assolutamente consigliato, a patto che si svolgano puntualmente tutti gli esercizi indicati . Può essere scaricato gratuitamente qui:  https://github.com/AllenDowney/ThinkPythonItalian/blob/maste...

by Raj Jain, Washington University in St. Louis, and Imrich Chlamatac, Università degli Studi di Trento and other places "A heuristic algorithm is proposed for dynamic calculation of the median and other quantiles. The estimates are produced dynamically as the observations are generated. The observations are not stored; therefore, the algorithm has a very small and fixed storage requirement regardless of the number of observations. This makes it ideal for implementing in a quantile chip that can be used in industrial controllers and recorders. The algorithm is further extended to histogram plotting. The accuracy of the algorithm is analyzed. ... The advantage of the P^2 algorithm is that observations need not to be stored and no prior knowledge of the range of values is required. The storage requirement of the proposed algorithm is small and fixed, regardless of the number of observations." Download the full article (pdf):  https://cacm.acm.org/research/the-p2-algorithm-f...

Have you ever found yourself staring at a graph or slide, wondering what the creator was trying to convey? Perhaps you've sat through a presentation, only to be left scratching your head, unsure of what to do next. Don’t put your audience in this same uncomfortable position. Instead, connect the dots for them to make it clear what the point is and what action they should take. When you fail to explicitly state the purpose of your communication, you run the risk of the important insight being lost, or someone arriving at the wrong conclusion. Read more:  https://www.storytellingwithdata.com/blog/is-your-point-clear

Secondo Jensen Huang l’intelligenza artificiale generativa porterà via il posto agli sviluppatori e non servirà più studiare programmazione. Pensavamo fosse una sciocchezza, ma il primo AI Software Engineer ha fatto vacillare le nostre certezze. Leggi tutto:  https://www.dday.it/redazione/48796/devin-lai-software-engineer-che-da-ragione-al-ceo-di-nvidia-meglio-studiare-biologia-che-coding

Some people say, “The data speaks for itself.”  But the data never speaks. And it needs interpreters.  Data science and statistics go hand in hand. In data science, we collect, analyze, and visualize data. Statistics give us a lens on our data to spot patterns, trends, and connections. Statistics help us see when our analysis is off and ensure our analysis isn’t just based on intuition but grounded in fact.  Statistical thinking can help you decide whether ideas, commonly believed to be sound and intuitive, are perhaps not as rational as initially perceived. While the outcome of an analysis might seem straightforward on the surface, statistical analysis allows us to delve deeper. Leggi tutto:  https://www.knime.com/blog/statistics-for-data-science

Despite huge investments in data science initiatives, 94% of organizations face a list of challenges that prevent them from developing and implementing the data science projects that are needed to improve operational efficiency. Top of the list is a lack of skilled talent. And here’s the thing: This lack won’t be filled simply by having more data scientists coming out of universities. The degree in data science proves a baseline qualification in that specific field, but a lot of organizations aren’t only looking for “pure” data scientists. To implement more data science projects, companies also need their existing workforce to gain data science skills. That’s because these people already have valuable on-the-job experience and business understanding that enables them to recognize when something in the data looks off. Leggi tutto:  https://www.knime.com/blog/can-i-get-into-data-science-with-no-experience Ci sono almeno un paio di punti interessanti in questo post: le competenze di ...

Il presente testo ha come obiettivo principale quello di rispondere a una domanda che spesso studenti e ricercatori si trovano ad affrontare: cosa faccio con tutti questi dati? Le tecniche di data mining offrono una risposta a questo quesito soprattutto perché la maggioranza dei software statistici disponibili al giorno d’oggi incorporano delle routine che rendono l’applicazione di questi modelli molto semplice.  La breve guida proposta si rivolge a studenti che non hanno confidenza con l’analisi dei dati e che necessitano di farsi un’idea di cosa possono dire i database e soprattutto di quali sono gli strumenti più idonei per rispondere alle domande di ricerca. Il testo si compone di diversi paragrafi che attraverso definizioni ed esempi mostreranno al lettore come estrarre informazioni dai database in modo semplice e scoprire pertanto alcuni meccanismi che vengono utilizzati nel mondo della ricerca, ma non solo, per comprendere al meglio il comportamento degli attori delle r...