Análisis de tendencias musicales globales: extracción y visualización de datos de Spotify con AWS y Power BI
Bibliographic record
Abstract
El trabajo consiste en el desarrollo de un sistema automatizado el cual se encarga de recopilar, almacenar, transformar y mostrar datos musicales sobre las diez canciones más escuchadas de Spotify de diez países elegidos (España, Italia, Alemania, Francia, Reino Unido, Estados Unidos, Canadá, Argentina, Brasil y México). El objetivo principal es presentar estos datos de manera accesible y significativa al usuario. Primeramente, para seleccionar los países a estudiar se han tenido en cuenta diversos criterios como la zona geográfica, población, cultura y actividad musical en Spotify. Así, los datos utilizados proporcionarán informes más representativos y completos al usuario. Los datos recopilados se obtienen de la plataforma Spotify® utilizando su API web oficial (Application Programming Interface). Estos datos se almacenan en la nube de Amazon Web Services® (AWS), concretamente en una base de datos Amazon DynamoDB. Para realizar este proceso de extracción, almacenamiento y transformación de datos se utiliza el servicio AWS Lambda, que permitie ejecutar código en la nube sin necesidad de un servidor, y Amazon S3 (Simple Storage Services) que proporciona servicio de almacenamiento en la nube. La presentación de los datos se realiza a través Power BI, una herramienta de Microsoft® que permite representar gráficamente la información almacenada, lo que facilita la interpretación de los datos al usuario. En resumen, el proyecto busca crear un sistema automatizado que integre tecnologías actuales como los servicios en la nube de AWS, la API web de Spotify y Power BI con el fin de permitir a los usuarios visualizar los datos de manera intuitiva y utilizarlos según sus necesidades. ABSTRACT The job involves developing an automated system that is responsible for collecting, storing, transforming, and displaying musical data about the top ten most played songs on Spotify in ten selected countries (Spain, Italy, Germany, France, the United Kingdom, the United States, Canada, Argentina, Brazil, and Mexico). The main goal is to present this data in an accessible and meaningful way to the user. Firstly, in order to select the countries to study, various criteria such as geographic location, population, culture, and musical activity on Spotify have been taken into account. This data provides the user with more representative and comprehensive reports. The collected data is extracted from the Spotify® platform using its official web API. This data is stored in the Amazon Web Services® (AWS) cloud, specifically in an Amazon DynamoDB database. To perform this process of data extraction, storage, and transformation, AWS Lambda service is used, allowing code execution in the cloud without the need for a server, and Amazon S3 (Simple Storage Services) provide cloud storage service. The data presentation is carried out through Power BI, a Microsoft® tool that allows for graphical representation of the stored information, making it easier for the user to interpret the data. In summary, the project aims to create an automated system that integrates current technologies such as AWS cloud services, Spotify web API, and Power BI in order to enable users to intuitively visualize the data and use it according to their needs.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.014 | 0.004 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".