cluster2

cluster2, given 4 sets of data, use the K-means algorithm to identify clusters.

• cluster2.pdf

• exercise1.py, plots the student medical records, with red rings at 1, 2 and 3 standard deviations from the mean.
• hw_data.txt, a dataset of student medical records. Each record is a student index number, a height, and a weight.

• exercise2.py, uses kmeans2() to sort the Old Faithful data into 1, 2 or 3 clusters.
• faithful_data.txt, the original 272 pairs of eruption and wait times for a geyser.

• exercise3.py, uses kmeans2() to cluster the Ruspini data into 1 through 10 clusters, and plots the resulting "energy" of each clustering.
• ruspini_data.txt, a set of 2D data.

• exercise4.py, uses kmean2() to cluster the colors used in a JPEG image, reducing the number of colors from almost 300,000 to 10 or 15.
• swim.jpg, an image of a swimmer.