col_info = engine.col_info()
print(col_info)
# To do inference, we intialize some cross-categorization states with
# `init_models` then `run` the inference. We intitialize many models to hedge
# the inferences we make. Every model is a draw from the posterior. We want to
# make inference about the data given the posterior distribution of states, so
# we take several models.
print('Initializing 32 models...')
engine.init_models()
print('Running models for 200 iterations...')
engine.run(200, checkpoint=5)
# To check whether inference has converges, we plot the log score for each
# model as a function of time and make sure they all have leveled out.
engine.convergence_plot()
plt.show()
# We can view which columns are dependent on which other columns by plotting
# a n_cols by n_cols matrix where each cell is the dependence probability
# between two columns. Note that the dependence probability is simply the
# probability that a dependence exists, not the strength of the dependence.
engine.heatmap('dependence_probability', plot_kwargs={'figsize': (10, 10,)})
plt.show()
engine.heatmap('row_similarity', plot_kwargs={'figsize': (10, 10,)})
plt.show()
# The paint job is an important part of what makes a pine wood derby car fast,
# but does it matter for animals? We'll use the linfoot information to
# determine how predictive variables are of whether an animal is fast. Linfoot
28,
28,
))
return pixels
assert __name__ == "__main__"
exdir = os.path.dirname(os.path.realpath(__file__))
df = pd.read_csv(os.path.join(exdir, 'mnist.csv.gz'), compression='gzip')
df = df.sample(2000)
testdata = df['label'][1500:]
df['label'][1500:] = float('NaN')
engine = Engine(df)
engine.init_models(4)
engine.run(1000, checkpoint=4, verbose=True)
engine.convergence_plot()
plt.show()
_, m = engine.eval(testdata, metric=Accuracy())
print('Acuracy = %f' % (m, ))
# engine.heatmap('row_similarity')
# plt.show()
# engine.heatmap('dependence_probability')
# plt.show()
