This lesson is part of the course
Discovering Unsupervised Learning Methods in Python
short_training6 chapters · 54 lessons
Discover unsupervised learning in Python.
1. Welcome message1 lesson
The training platformsubscribers
2. Explore data using clustering techniques12 lessons
Unsupervised learningsubscribers Determine the optimal number of clusterssubscribers Cluster points in two dimensionssubscribers Analyze the clustering resultssubscribers Measure the quality of the clusters obtainedsubscribers Choose the number of clusters for the seedssubscribers Evaluate the clusters formed from the seedssubscribers Prepare variables for better clustering resultssubscribers Standardize fish data before clusteringsubscribers Identify clusters among fishsubscribers Grouping stocks with K-meansyou are here Spot stocks with similar trendssubscribers
3. Explore data with hierarchical clustering and t-SNE visualization12 lessons
Visualize the hierarchical structures of datasubscribers Determine the number of merges neededsubscribers Group seed data using hierarchical classificationsubscribers Analyze hierarchical relationships between stockssubscribers Assign labels to clusters from hierarchical clusteringsubscribers Identify the closest data groupssubscribers Compare hierarchical groupings by linkage methodssubscribers Study clustering at different levels of the hierarchysubscribers Extract the labels of the groups formedsubscribers Project the data into two dimensions with t-SNEsubscribers Visualize the cereal data with t-SNEsubscribers Map the similarities between stocks with t-SNEsubscribers
4. Reduce the dimensionality of the data and remove redundant correlations13 lessons
Visualize how PCA workssubscribers Spot the natural correlations in the datasubscribers Decorrelate seed measurements with PCAsubscribers Identify the principal componentssubscribers Determine the intrinsic dimension of the datasubscribers Analyze the role of the first principal componentsubscribers Study the variance explained by the PCA componentssubscribers Estimate the intrinsic dimensionality of the fish datasubscribers Reduce the number of dimensions with PCAsubscribers Simplify fish measurements through dimensionality reductionsubscribers Represent words with TF-IDF scoressubscribers Cluster Wikipedia articles, part onesubscribers Continue clustering Wikipedia articles, part twosubscribers
5. Identify easy-to-interpret features15 lessons
Discover non-negative matrix factorization (NMF)subscribers Identify data made up of non-negative valuessubscribers Apply NMF to Wikipedia articlessubscribers Extract features from Wikipedia articles with NMFsubscribers Reconstructing data from NMF componentssubscribers Breaking data down into interpretable elements with NMFsubscribers Identifying document topics with NMFsubscribers Exploring the dataset of digits represented by LEDssubscribers Extracting image components with NMFsubscribers Understanding why PCA cannot identify distinct partssubscribers Building recommendation systems with NMFsubscribers Finding articles similar to Cristiano Ronaldo'ssubscribers Recommending music artists, part onesubscribers Improving music artist recommendations, part twosubscribers Taking stock of methods for discovering interpretable featuressubscribers
6. Conclusion1 lesson
Course conclusionsubscribers