UCI Wine Quality Dataset
A dataset related to red and white variants of Portuguese "Vinho Verde" wine. The dataset includes various physicochemical properties and quality ratings, making it perfect for regression and classification tasks.
- Input variables: fixed acidity, volatile acidity, citric acid, residual sugar, chlorides, free sulfur dioxide, total sulfur dioxide, density, pH, sulphates, alcohol
- Output variable: quality (score between 0 and 10)
- Number of instances: 4,898 (1,599 red wines, 3,299 white wines)
Dimensionality Reduction and Clustering
An interactive exploration of dimensionality reduction techniques (t-SNE and PCA) for data visualization and clustering. This example demonstrates:
- Applying PCA and t-SNE for dimensionality reduction
- Visualizing high-dimensional data in 2D and 3D
- Comparing different clustering approaches
- Interactive parameter tuning and analysis
Movie Descriptions TFIDF Analysis
This dataset demonstrates the application of TF-IDF (Term Frequency-Inverse Document Frequency) on movie descriptions, showing how to:
- Process and clean text data from movie descriptions
- Implement and apply TF-IDF vectorization
- Analyze similarity between movies based on their descriptions
- Visualize relationships between movies using TF-IDF features
Explore the implementation in this Colab notebook →