def _post_pred_summary_bottom_node(bottom_node,
samples=500,
stats=None,
plot=False,
bins=100,
evals=None):
"""Create posterior predictive check for a single bottom node."""
def _calc_stats(data, stats):
out = {}
for name, func in stats.iteritems():
out[name] = func(data)
return out
if stats is None:
stats = OrderedDict((('mean', np.mean), ('std', np.std)))
############################
# Compute stats over data
data = bottom_node.value
data_stats = _calc_stats(data, stats)
###############################################
# Initialize posterior sample stats container
sampled_stats = {}
for name in stats.iterkeys():
sampled_stats[name] = np.empty(samples)
##############################
# Sample and generate stats
for sample in range(samples):
_parents_to_random_posterior_sample(bottom_node)
# Generate data from bottom node
sampled = bottom_node.random()
sampled_stat = _calc_stats(sampled, stats)
# Add it the results container
for name, value in sampled_stat.iteritems():
sampled_stats[name][sample] = value
if plot:
from pymc.Matplot import gof_plot
for name, value in sampled_stats.iteritems():
gof_plot(value, data_stats[name], nbins=bins, name=name, verbose=0)
result = _evaluate_post_pred(sampled_stats, data_stats, evals=evals)
return result
def _post_pred_summary_bottom_node(bottom_node, samples=500, stats=None, plot=False, bins=100, evals=None):
"""Create posterior predictive check for a single bottom node."""
def _calc_stats(data, stats):
out = {}
for name, func in stats.iteritems():
out[name] = func(data)
return out
if stats is None:
stats = OrderedDict((('mean', np.mean), ('std', np.std)))
############################
# Compute stats over data
data = bottom_node.value
data_stats = _calc_stats(data, stats)
###############################################
# Initialize posterior sample stats container
sampled_stats = {}
for name in stats.iterkeys():
sampled_stats[name] = np.empty(samples)
##############################
# Sample and generate stats
for sample in range(samples):
_parents_to_random_posterior_sample(bottom_node)
# Generate data from bottom node
sampled = bottom_node.random()
sampled_stat = _calc_stats(sampled, stats)
# Add it the results container
for name, value in sampled_stat.iteritems():
sampled_stats[name][sample] = value
if plot:
from pymc.Matplot import gof_plot
for name, value in sampled_stats.iteritems():
gof_plot(value, data_stats[name], nbins=bins, name=name, verbose=0)
result = _evaluate_post_pred(sampled_stats, data_stats, evals=evals)
return result
def post_pred_stats(data,
sim_datasets,
stats=None,
plot=False,
bins=100,
evals=None,
call_compare=True):
"""Calculate a set of summary statistics over posterior predictives.
:Arguments:
data : pandas.Series
sim_data : pandas.Series
:Optional:
bins : int
How many bins to use for computing the histogram.
stats : dict or function
User-defined statistics to compute (by default mean and std are computed)
and evaluate over the samples.
:Example:
* {'mean': np.mean, 'median': np.median}
* lambda x: np.mean(x)
evals : dict
User-defined evaluations of the statistics (by default 95 percentile and SEM).
:Example: {'percentile': scoreatpercentile}
plot : bool
Whether to plot the posterior predictive distributions.
progress_bar : bool
Display progress bar while sampling.
field : string
Which column name to run the stats on
call_com,pare : bool (default=True)
Whether to call post_pred_compare_stats. If False, return stats directly.
"""
def _calc_stats(data, stats):
out = {}
for name, func in stats.items():
out[name] = func(data)
return out
if stats is None:
stats = OrderedDict((('mean', np.mean), ('std', np.std)))
if isinstance(stats, FunctionType):
stats = OrderedDict((('stat', stats), ))
data_stats = _calc_stats(data, stats)
###############################################
# Initialize posterior sample stats container
samples = len(sim_datasets)
sampled_stats = {}
sampled_stats = pd.DataFrame(
index=sim_datasets.index.droplevel(2).unique(),
columns=list(stats.keys()),
dtype=np.float32)
for i, sim_dataset in sim_datasets.groupby(level=(0, 1)):
sampled_stat = _calc_stats(sim_dataset.values, stats)
# Add it to the results container
for name, value in sampled_stat.items():
sampled_stats[name][i] = value
if plot:
from pymc.Matplot import gof_plot
for name, value in sampled_stats.items():
gof_plot(value, data_stats[name], bins=bins, name=name, verbose=0)
if call_compare:
return post_pred_compare_stats(sampled_stats, data_stats, evals=evals)
else:
return sampled_stats
def post_pred_stats(data, sim_datasets, stats=None, plot=False, bins=100, evals=None, call_compare=True):
"""Calculate a set of summary statistics over posterior predictives.
:Arguments:
data : pandas.Series
sim_data : pandas.Series
:Optional:
bins : int
How many bins to use for computing the histogram.
stats : dict or function
User-defined statistics to compute (by default mean and std are computed)
and evaluate over the samples.
:Example:
* {'mean': np.mean, 'median': np.median}
* lambda x: np.mean(x)
evals : dict
User-defined evaluations of the statistics (by default 95 percentile and SEM).
:Example: {'percentile': scoreatpercentile}
plot : bool
Whether to plot the posterior predictive distributions.
progress_bar : bool
Display progress bar while sampling.
field : string
Which column name to run the stats on
call_com,pare : bool (default=True)
Whether to call post_pred_compare_stats. If False, return stats directly.
"""
def _calc_stats(data, stats):
out = {}
for name, func in stats.iteritems():
out[name] = func(data)
return out
if stats is None:
stats = OrderedDict((('mean', np.mean), ('std', np.std)))
if isinstance(stats, FunctionType):
stats = OrderedDict((('stat', stats),))
data_stats = _calc_stats(data, stats)
###############################################
# Initialize posterior sample stats container
samples = len(sim_datasets)
sampled_stats = {}
sampled_stats = pd.DataFrame(index=sim_datasets.index.droplevel(2).unique(),
columns=stats.keys(),
dtype=np.float32)
for i, sim_dataset in sim_datasets.groupby(level=(0, 1)):
sampled_stat = _calc_stats(sim_dataset.values, stats)
# Add it to the results container
for name, value in sampled_stat.iteritems():
sampled_stats[name][i] = value
if plot:
from pymc.Matplot import gof_plot
for name, value in sampled_stats.iteritems():
gof_plot(value, data_stats[name], bins=bins, name=name, verbose=0)
if call_compare:
return post_pred_compare_stats(sampled_stats, data_stats, evals=evals)
else:
return sampled_stats