def test_bad_model(self):
X = data.sim_data(10)
Y = models.bad_model(X)
assert pl.allclose(Y.sum(axis=2), 1), 'should be all ones, (%s found)' % str(Y.sum(axis=2))
# test again for 10x2x3 dataset
X = data.sim_data(10, [[.1, .4, .5]], [.1, .1, .1])
Y = models.bad_model(X)
assert pl.allclose(Y.sum(axis=2), 1), 'should be all ones, (%s found)' % str(Y.sum(axis=2))
def test_bad_model(self):
X = data.sim_data(10)
Y = models.bad_model(X)
assert pl.allclose(
Y.sum(axis=2),
1), 'should be all ones, (%s found)' % str(Y.sum(axis=2))
# test again for 10x2x3 dataset
X = data.sim_data(10, [[.1, .4, .5]], [.1, .1, .1])
Y = models.bad_model(X)
assert pl.allclose(
Y.sum(axis=2),
1), 'should be all ones, (%s found)' % str(Y.sum(axis=2))
def validate_once(true_cf = [pl.ones(3)/3.0, pl.ones(3)/3.0], true_std = 0.01*pl.ones(3), std_bias = [1., 1., 1.], save=False, dir='', i=0):
"""
Generate a set of simulated estimates for the provided true cause fractions; Fit the bad model and
the latent simplex model to this simulated data and calculate quality metrics.
"""
# generate simulation data
X = data.sim_data_for_validation(1000, true_cf, true_std, std_bias)
# fit bad model, calculate fit metrics
bad_model = models.bad_model(X)
bad_model_metrics = calc_quality_metrics(true_cf, true_std, std_bias, bad_model)
retrieve_estimates(bad_model, True, 'bad_model', dir, i)
# fit latent simplex model, calculate fit metrics
m, latent_simplex = models.fit_latent_simplex(X)
latent_simplex_metrics = calc_quality_metrics(true_cf, true_std, std_bias, latent_simplex)
retrieve_estimates(latent_simplex, True, 'latent_simplex', dir, i)
# either write results to disk or return them
if save:
pl.rec2csv(bad_model_metrics, '%s/metrics_bad_model_%i.csv' % (dir, i))
pl.rec2csv(latent_simplex_metrics, '%s/metrics_latent_simplex_%i.csv' % (dir, i))
else:
return bad_model_metrics, latent_simplex_metrics
def validate_once(true_cf=[pl.ones(3) / 3.0,
pl.ones(3) / 3.0],
true_std=0.01 * pl.ones(3),
std_bias=[1., 1., 1.],
save=False,
dir='',
i=0):
"""
Generate a set of simulated estimates for the provided true cause fractions; Fit the bad model and
the latent simplex model to this simulated data and calculate quality metrics.
"""
# generate simulation data
X = data.sim_data_for_validation(1000, true_cf, true_std, std_bias)
# fit bad model, calculate fit metrics
bad_model = models.bad_model(X)
bad_model_metrics = calc_quality_metrics(true_cf, true_std, std_bias,
bad_model)
retrieve_estimates(bad_model, True, 'bad_model', dir, i)
# fit latent simplex model, calculate fit metrics
m, latent_simplex = models.fit_latent_simplex(X)
latent_simplex_metrics = calc_quality_metrics(true_cf, true_std, std_bias,
latent_simplex)
retrieve_estimates(latent_simplex, True, 'latent_simplex', dir, i)
# either write results to disk or return them
if save:
pl.rec2csv(bad_model_metrics, '%s/metrics_bad_model_%i.csv' % (dir, i))
pl.rec2csv(latent_simplex_metrics,
'%s/metrics_latent_simplex_%i.csv' % (dir, i))
else:
return bad_model_metrics, latent_simplex_metrics
