In [1]:
from IPython.display import Image; 

Gaussian Toy Data Demos

In [2]:
Image('AsteriskData.png', width=200)
Out[2]:

A quick hello world example for beginners to bnpy.

In [3]:
Image('GaussianToyData-LearnedClusters.png', width=200)
Out[3]:

Experiment showing how bnpy makes it easy to compare different initialization routines across many algorithm runs.

In [4]:
Image('GaussianToyData-CompareInitMethods.png', width=200)
Out[4]:

Experiment showing how births and merges can find the ideal set of clusters, no matter how many we have initially.

In [5]:
Image('GaussianToyData-BirthMergeKvsTime.png', width=200)
Out[5]:

Bag-of-words Toy Data Demos

In [6]:
Image('BarsData.png', width=200)
Out[6]:

Experiment showing how births and merges add and remove clusters to find the ideal set of bars.

In [7]:
Image('BarsData-BirthMergeKvsTime.png', width=200)
Out[7]:

Experiment shows the basics for training a topic model, comparing different number of topics.

In [8]:
Image('BarsToyData-LearnedTopicsFixedK=10.png', width=200)
Out[8]:

Use merge and delete moves for topic models to identify the 10 true bars topics from initializations with many more.

In [9]:
Image('BarsToyData-LearnedTopics-MergeDelete.png', width=200)
Out[9]: