Trends and Export Analysis of Cava, Champagne, and Prosecco: Global Overview (2017–2024)

This repository focuses on both the analysis and clustering of the global sparkling wine trade. The first part involves data cleaning, analysis and visualization of global cava, prosecco and champagne exports, along with the evolution and trends during the 2017-2024 period, on a monthly base. The second part applies socio-economic variables to the yearly exports data, in order to get insights outside the pure trade that helps to find key trends and correlation factors that can influence the market and the sparkling wines compsuption. Finally, with the application of preprocessing and data science algorithms it has been performed a clustering analysis on a country level to help to classify the countries according to their market behaviour., with the goal of providing valuable insights for stakeholders in the cava industry.

• URL EN: 📝 | Portfolio article

• URL ES: 📝 | Portfolio article

• URL EN: 📊 | Tableau Dashboard

• URL EN: 👨🏻‍💻 | Code process explanation

Sub-Projects:

• 📊 | 01. Data Analysis

  • Part 1: Cava - monthly analysis (2017-2024)

    • Description: Data cleaning, analysis, & visualization of the monthly evolution of Cava exports over the period 2017-2024. A temporal breakdown by global, region and country has been applied for a more detailed analysis of export trends on a global scale

  • Part 2: Sparkling wine - monthly analysis (2020-2024)

    • Description: Data cleaning, analysis, & visualization of the monthly evolution of Cava, Prosecco, and Champagne exports over the period 2020-2024. A temporal breakdown by global, region and country has been applied for a more detailed analysis of export trends on a global scale.

  • Part 3: Sparkling wine - yearly analysis (2020-2024)

    • Description: Data cleaning, analysis, & visualization of the yearly evolution of Cava, Prosecco, and Champagne exports and consumption over the period 2020-2024. A temporal breakdown by global, region and country has been applied for a more detailed analysis of export trends on a global scale.

  • Folder: DA

• 🔬 | 02. Preprocessing & Clustering

  • Title: Country clustering based on sparkling wine comsuption

  • Description: Unsupervised Machine Learning within to cluster countries based on trends from 2020 to 2024. The first model focuses on sparkling wine export data, while the second integrates both trade and socio-economic indicators to reveal meaningful country groupings.

  • Folder: DS

Tools

• 📓 | Notebooks: Google Colab
• 📊 | Visualization: Tableau Public
• 🐍 | Python: Pandas, Numpy, Matplotlib, Seaborn, Scikit-learn, Sklearn (StandardScaler, PCA, KMeans)