def sparsen(df,
aggregator=mean_or_last,
date=None,
time=None,
datetime=None,
bucket='date',
new_bucket_column=None,
fix_kind='last',
fix_time=None,
fix_points=10,
min_fix_point_count=None,
max_fix_point_count=None,
min_min_fix_point_time=None,
max_min_fix_point_time=None,
min_max_fix_point_time=None,
max_max_fix_point_time=None,
already_sorted=False,
aggregators_apply_to_df=False,
exclude_original_temporal_columns=True,
columns_to_exclude=None,
return_extra_info=False):
checks.is_at_least_one_not_none(datetime, date, time)
if bucket == 'date':
bucket = lambda x: conv.to_python_date(x, allow_datetimes=True)
elif bucket == 'week':
bucket = lambda x: tsatimes.first_day_of_week(x)
columns_to_exclude = set() if columns_to_exclude is None else set(
columns_to_exclude)
if datetime is not None:
checks.check_all_none(date, time)
if isinstance(datetime, str):
if exclude_original_temporal_columns:
columns_to_exclude.add(datetime)
if new_bucket_column is None and exclude_original_temporal_columns:
new_bucket_column = datetime
datetime = df[datetime].values
temporals = datetime
else:
if isinstance(date, str):
if exclude_original_temporal_columns: columns_to_exclude.add(date)
if new_bucket_column is None and exclude_original_temporal_columns:
new_bucket_column = date
date = df[date].values
if isinstance(time, str):
if exclude_original_temporal_columns: columns_to_exclude.add(time)
if new_bucket_column is None and exclude_original_temporal_columns:
new_bucket_column = time
time = df[time].values
if date is not None and time is not None:
temporals = [dt.datetime.combine(d, t) for d, t in zip(date, time)]
elif date is not None:
temporals = date
else: # time is not None
temporals = time
if new_bucket_column is None: new_bucket_column = 'bucket'
if fix_kind in ('first', 'after'): comparison = 'ge'
elif fix_kind == 'after_exclusive': comparison = 'gt'
elif fix_kind in ('last', 'before'): comparison = 'le'
elif fix_kind == 'before_exclusive': comparison = 'lt'
else: raise ValueError('Unfamiliar fix_kind: "%s"' % str(fix_kind))
if fix_kind in ('first', 'last'): checks.check_none(fix_time)
else: checks.check_not_none(fix_time)
numeric_fix_points = checks.is_some_number(fix_points)
if not numeric_fix_points:
fix_points = conv.to_python_timedelta(fix_points)
grouping_df = pd.DataFrame({'temporals': temporals})
grouped_df = grouping_df.groupby(bucket(temporals))
columns = [new_bucket_column]
data = {new_bucket_column: []}
aggs = {}
if checks.is_some_dict(aggregator): column_agg_pairs = aggregator.items()
elif checks.is_iterable(aggregator): column_agg_pairs = aggregator
else: column_agg_pairs = zip(df.columns, utils.xconst(aggregator))
for column, agg in column_agg_pairs:
if column not in columns_to_exclude:
columns.append(column)
data[column] = []
aggs[column] = agg
dates_with_no_points = []
dates_with_fix_point_limits_breached = col.OrderedDict()
fix_point_counts = col.OrderedDict()
for bucket, group_df in grouped_df:
if len(group_df) == 0: dates_with_no_points.append(bucket)
if not already_sorted:
group_df = group_df.copy()
group_df.sort_values('temporals', inplace=True)
if fix_kind == 'first': fix_time = group_df['temporals'].values[0]
elif fix_kind == 'last': fix_time = group_df['temporals'].values[-1]
if numeric_fix_points:
if comparison == 'ge':
fix_point_indices = group_df.index[tsatimes.temporal_ge(
group_df['temporals'], fix_time)][0:fix_points]
elif comparison == 'gt':
fix_point_indices = group_df.index[tsatimes.temporal_gt(
group_df['temporals'], fix_time)][0:fix_points]
elif comparison == 'le':
fix_point_indices = group_df.index[tsatimes.temporal_le(
group_df['temporals'], fix_time)][-fix_points:]
else: # comparison == 'lt'
fix_point_indices = group_df.index[tsatimes.temporal_lt(
group_df['temporals'], fix_time)][-fix_points:]
else:
if comparison == 'ge':
fix_point_indices = group_df.index[(tsatimes.temporal_ge(group_df['temporals'], fix_time)) & \
(tsatimes.temporal_le(group_df['temporals'], tsatimes.plus_timedelta(fix_time, fix_points)))]
elif comparison == 'gt':
fix_point_indices = group_df.index[(tsatimes.temporal_gt(group_df['temporals'], fix_time)) & \
(tsatimes.temporal_le(group_df['temporals'], tsatimes.plus_timedelta(fix_time, fix_points)))]
elif comparison == 'le':
fix_point_indices = group_df.index[(tsatimes.temporal_le(group_df['temporals'], fix_time)) & \
(tsatimes.temporal_ge(group_df['temporals'], tsatimes.plus_timedelta(fix_time, -fix_points)))]
else: # comparison == 'lt':
fix_point_indices = group_df.index[(tsatimes.temporal_lt(group_df['temporals'], fix_time)) & \
(tsatimes.temporal_ge(group_df['temporals'], tsatimes.plus_timedelta(fix_time, -fix_points)))]
fix_point_limits_breached = set()
if min_fix_point_count is not None and len(
fix_point_indices) < min_fix_point_count:
fix_point_limits_breached.add('min_fix_point_count')
if max_fix_point_count is not None and len(
fix_point_indices) > max_fix_point_count:
fix_point_limits_breached.add('max_fix_point_count')
if min_min_fix_point_time is not None:
if checks.is_some_timedelta(min_min_fix_point_time):
the_min_min_fix_point_time = fix_time + min_min_fix_point_time if comparison in (
'ge', 'gt') else fix_time - min_min_fix_point_time
else:
the_min_min_fix_point_time = min_min_fix_point_time
if tsatimes.temporal_lt(
min(grouping_df['temporals'].values[fix_point_indices]),
the_min_min_fix_point_time):
fix_point_limits_breached.add('min_min_fix_point_time')
if max_min_fix_point_time is not None:
if checks.is_some_timedelta(max_min_fix_point_time):
the_max_min_fix_point_time = fix_time + max_min_fix_point_time if comparison in (
'ge', 'gt') else fix_time - max_min_fix_point_time
else:
the_max_min_fix_point_time = max_min_fix_point_time
if tsatimes.temporal_gt(
min(grouping_df['temporals'].values[fix_point_indices]),
the_max_min_fix_point_time):
fix_point_limits_breached.add('max_min_fix_point_time')
if min_max_fix_point_time is not None:
if checks.is_some_timedelta(min_max_fix_point_time):
the_min_max_fix_point_time = fix_time + min_max_fix_point_time if comparison in (
'ge', 'gt') else fix_time - min_max_fix_point_time
else:
the_min_max_fix_point_time = min_max_fix_point_time
if tsatimes.temporal_lt(
max(grouping_df['temporals'].values[fix_point_indices]),
the_min_max_fix_point_time):
fix_point_limits_breached.add('min_max_fix_point_time')
if max_max_fix_point_time is not None:
if checks.is_some_timedelta(max_max_fix_point_time):
the_max_max_fix_point_time = fix_time + max_max_fix_point_time if comparison in (
'ge', 'gt') else fix_time - max_max_fix_point_time
else:
the_max_max_fix_point_time = max_max_fix_point_time
if tsatimes.temporal_gt(
max(grouping_df['temporals'].values[fix_point_indices]),
the_max_max_fix_point_time):
fix_point_limits_breached.add('max_max_fix_point_time')
if len(fix_point_limits_breached) > 0:
dates_with_fix_point_limits_breached[
bucket] = fix_point_limits_breached
else:
data[new_bucket_column].append(bucket)
for column in columns[1:]:
if column not in columns_to_exclude:
arg = df.iloc[
fix_point_indices] if aggregators_apply_to_df else df.iloc[
fix_point_indices][column].values
data[column].append(aggs[column](arg))
fix_point_counts[bucket] = len(fix_point_indices)
df = pd.DataFrame(data, columns=columns)
if return_extra_info:
return {
'df': df,
'dates_with_no_points': dates_with_no_points,
'dates_with_fix_point_limits_breached':
dates_with_fix_point_limits_breached,
'fix_point_counts': fix_point_counts
}
else:
return df
def run(observable,
obss=None,
times=None,
obs_covs=None,
true_values=None,
df=None,
fun=None,
return_df=False):
if df is not None:
if obss is not None and (checks.is_string(obss)
or checks.is_int(obss)):
obss = df[obss]
if times is None:
if isinstance(obss, pd.Series): times = obss.index.values
elif (checks.is_string(times) or checks.is_int(times)):
times = df[times].values
if isinstance(obss, pd.Series): obss = obss.values
if obs_covs is not None and (checks.is_string(obs_covs)
or checks.is_int(obs_covs)):
obs_covs = df[obs_covs].values
if true_values is not None and (checks.is_string(true_values)
or checks.is_int(true_values)):
true_values = df[true_values].values
checks.check_not_none(obss)
if not checks.is_iterable_not_string(observable):
observable = utils.xconst(observable)
if not checks.is_iterable_not_string(obss): obss = [obss]
if not checks.is_iterable_not_string(times): times = utils.xconst(times)
if not checks.is_iterable_not_string(obs_covs):
obs_covs = utils.xconst(obs_covs)
if not checks.is_iterable_not_string(true_values):
true_values = utils.xconst(true_values)
obs_result = None
cumulative_log_likelihood = 0.
if return_df:
time = []
filter_name = []
filter_type = []
observable_name = []
accepted = []
obs_mean = []
obs_cov = []
predicted_obs_mean = []
predicted_obs_cov = []
cross_cov = []
innov_mean = []
innov_cov = []
prior_state_mean = []
prior_state_cov = []
posterior_state_mean = []
posterior_state_cov = []
true_value = []
log_likelihood = []
gain = []
last_time = None
for an_observable, an_obs, a_time, an_obs_cov, a_true_value in zip(
observable, obss, times, obs_covs, true_values):
if a_time is None:
if last_time is None: a_time = 0
else: a_time = last_time + 1
last_time = a_time
if checks.is_callable(an_observable):
an_observable = an_observable(an_obs)
if fun is not None: an_obs = fun(an_obs)
if an_obs_cov is not None:
if isinstance(an_obs, (Obs, distrs.Distr)):
raise ValueError(
'An observation covariance is provided while the observation is given by a distribution --- conflicting arguments'
)
an_obs = distrs.NormalDistr(an_obs, an_obs_cov)
if return_df and len(time) == 0:
an_initial_state_mean = an_observable.filter.state.state_distr.mean
an_initial_state_cov = an_observable.filter.state.state_distr.cov
time.append(an_observable.filter.time)
filter_name.append(an_observable.filter.name)
filter_type.append(type(an_observable.filter))
observable_name.append(None)
accepted.append(None)
obs_mean.append(None)
obs_cov.append(None)
predicted_obs_mean.append(None)
predicted_obs_cov.append(None)
cross_cov.append(None)
innov_mean.append(None)
innov_cov.append(None)
prior_state_mean.append(
npu.to_scalar(an_initial_state_mean, raise_value_error=False))
prior_state_cov.append(
npu.to_scalar(an_initial_state_cov, raise_value_error=False))
posterior_state_mean.append(
npu.to_scalar(an_initial_state_mean, raise_value_error=False))
posterior_state_cov.append(
npu.to_scalar(an_initial_state_cov, raise_value_error=False))
true_value.append(None)
log_likelihood.append(None)
gain.append(None)
if isinstance(an_obs, Obs):
a_time, _ = _time_and_obs_distr(an_obs, a_time,
an_observable.filter.time)
predicted_obs = an_observable.predict(time=a_time,
true_value=a_true_value)
a_prior_state_mean = an_observable.filter.state.state_distr.mean
a_prior_state_cov = an_observable.filter.state.state_distr.cov
obs_result = an_observable.observe(obs=an_obs,
time=a_time,
true_value=a_true_value,
predicted_obs=predicted_obs)
if obs_result.accepted:
cumulative_log_likelihood += obs_result.log_likelihood
a_posterior_state_mean = an_observable.filter.state.state_distr.mean
a_posterior_state_cov = an_observable.filter.state.state_distr.cov
if return_df:
time.append(obs_result.obs.time)
filter_name.append(an_observable.filter.name)
filter_type.append(type(an_observable.filter))
observable_name.append(an_observable.name)
accepted.append(obs_result.accepted)
obs_mean.append(
npu.to_scalar(obs_result.obs.distr.mean,
raise_value_error=False))
obs_cov.append(
npu.to_scalar(obs_result.obs.distr.cov,
raise_value_error=False))
predicted_obs_mean.append(
npu.to_scalar(obs_result.predicted_obs.distr.mean,
raise_value_error=False))
predicted_obs_cov.append(
npu.to_scalar(obs_result.predicted_obs.distr.cov,
raise_value_error=False))
cross_cov.append(
npu.to_scalar(obs_result.predicted_obs.cross_cov,
raise_value_error=False))
innov_mean.append(
npu.to_scalar(obs_result.innov_distr.mean,
raise_value_error=False))
innov_cov.append(
npu.to_scalar(obs_result.innov_distr.cov,
raise_value_error=False))
prior_state_mean.append(
npu.to_scalar(a_prior_state_mean, raise_value_error=False))
prior_state_cov.append(
npu.to_scalar(a_prior_state_cov, raise_value_error=False))
posterior_state_mean.append(
npu.to_scalar(a_posterior_state_mean, raise_value_error=False))
posterior_state_cov.append(
npu.to_scalar(a_posterior_state_cov, raise_value_error=False))
true_value.append(
npu.to_scalar(a_true_value, raise_value_error=False))
log_likelihood.append(
npu.to_scalar(obs_result.log_likelihood,
raise_value_error=False))
gain.append(
obs_result.gain if hasattr(obs_result, 'gain') else None)
df = None
if return_df:
df = pd.DataFrame(
{
'time': time,
'filter_name': filter_name,
'filter_type': filter_type,
'observable_name': observable_name,
'accepted': accepted,
'obs_mean': obs_mean,
'obs_cov': obs_cov,
'predicted_obs_mean': predicted_obs_mean,
'predicted_obs_cov': predicted_obs_cov,
'cross_cov': cross_cov,
'innov_mean': innov_mean,
'innov_cov': innov_cov,
'prior_state_mean': prior_state_mean,
'prior_state_cov': prior_state_cov,
'posterior_state_mean': prior_state_mean,
'posterior_state_cov': prior_state_cov,
'true_value': true_value,
'log_likelihood': log_likelihood,
'gain': gain
},
columns=('time', 'filter_name', 'filter_type', 'observable_name',
'accepted', 'obs_mean', 'obs_cov', 'predicted_obs_mean',
'predicted_obs_cov', 'cross_cov', 'innov_mean',
'innov_cov', 'prior_state_mean', 'prior_state_cov',
'posterior_state_mean', 'posterior_state_cov',
'true_value', 'log_likelihood', 'gain'))
return FilterRunResult(obs_result, cumulative_log_likelihood, df)
def run(observable,
obss=None,
times=None,
obs_covs=None,
true_values=None,
df=None,
fun=None,
return_df=False):
if df is not None:
if obss is not None and checks.is_string(obss):
obss = df[obss].values
if times is not None and checks.is_string(times):
times = df[times].values
if obs_covs is not None and checks.is_string(obs_covs):
obs_covs = df[obs_covs].values
if true_values is not None and checks.is_string(true_values):
true_values = df[true_values].values
checks.check_not_none(obss)
if not checks.is_iterable_not_string(observable):
observable = utils.xconst(observable)
if not checks.is_iterable_not_string(obss): obss = [obss]
if not checks.is_iterable_not_string(times): times = utils.xconst(times)
if not checks.is_iterable_not_string(obs_covs):
obs_covs = utils.xconst(obs_covs)
if not checks.is_iterable_not_string(true_values):
true_values = utils.xconst(true_values)
obs_result = None
if return_df:
time = []
accepted = []
obs_mean = []
obs_cov = []
predicted_obs_mean = []
predicted_obs_cov = []
innov_mean = []
innov_cov = []
prior_state_mean = []
prior_state_cov = []
posterior_state_mean = []
posterior_state_cov = []
log_likelihood = []
for an_observable, an_obs, a_time, an_obs_cov, a_true_value in zip(
observable, obss, times, obs_covs, true_values):
if checks.is_callable(an_observable):
an_observable = an_observable(an_obs)
if fun is not None: an_obs = fun(an_obs)
if an_obs_cov is not None:
if isinstance(an_obs, (Obs, distrs.Distr)):
raise ValueError(
'An observation covariance is provided while the observation is given by a distribution --- conflicting arguments'
)
an_obs = distrs.NormalDistr(an_obs, an_obs_cov)
if return_df and len(time) == 0:
an_initial_state_mean = an_observable.filter.state.state_distr.mean
an_initial_state_cov = an_observable.filter.state.state_distr.cov
time.append(an_observable.filter.time)
accepted.append(None)
obs_mean.append(None)
obs_cov.append(None)
predicted_obs_mean.append(None)
predicted_obs_cov.append(None)
innov_mean.append(None)
innov_cov.append(None)
prior_state_mean.append(
npu.to_scalar(an_initial_state_mean, raise_value_error=False))
prior_state_cov.append(
npu.to_scalar(an_initial_state_cov, raise_value_error=False))
posterior_state_mean.append(
npu.to_scalar(an_initial_state_mean, raise_value_error=False))
posterior_state_cov.append(
npu.to_scalar(an_initial_state_cov, raise_value_error=False))
log_likelihood.append(None)
if isinstance(an_obs, Obs):
a_time, _ = _time_and_obs_distr(an_obs, a_time,
an_observable.filter.time)
predicted_obs = an_observable.predict(time=a_time,
true_value=a_true_value)
a_prior_state_mean = an_observable.filter.state.state_distr.mean
a_prior_state_cov = an_observable.filter.state.state_distr.cov
obs_result = an_observable.observe(obs=an_obs,
time=a_time,
true_value=a_true_value,
predicted_obs=predicted_obs)
a_posterior_state_mean = an_observable.filter.state.state_distr.mean
a_posterior_state_cov = an_observable.filter.state.state_distr.cov
if return_df:
time.append(obs_result.obs.time)
accepted.append(obs_result.accepted)
obs_mean.append(
npu.to_scalar(obs_result.obs.distr.mean,
raise_value_error=False))
obs_cov.append(
npu.to_scalar(obs_result.obs.distr.cov,
raise_value_error=False))
predicted_obs_mean.append(
npu.to_scalar(obs_result.predicted_obs.distr.mean,
raise_value_error=False))
predicted_obs_cov.append(
npu.to_scalar(obs_result.predicted_obs.distr.cov,
raise_value_error=False))
innov_mean.append(
npu.to_scalar(obs_result.innov_distr.mean,
raise_value_error=False))
innov_cov.append(
npu.to_scalar(obs_result.innov_distr.cov,
raise_value_error=False))
prior_state_mean.append(
npu.to_scalar(a_prior_state_mean, raise_value_error=False))
prior_state_cov.append(
npu.to_scalar(a_prior_state_cov, raise_value_error=False))
posterior_state_mean.append(
npu.to_scalar(a_posterior_state_mean, raise_value_error=False))
posterior_state_cov.append(
npu.to_scalar(a_posterior_state_cov, raise_value_error=False))
log_likelihood.append(
npu.to_scalar(obs_result.log_likelihood,
raise_value_error=False))
if return_df:
return pd.DataFrame(
{
'time': time,
'accepted': accepted,
'obs_mean': obs_mean,
'obs_cov': obs_cov,
'predicted_obs_mean': predicted_obs_mean,
'predicted_obs_cov': predicted_obs_cov,
'innov_mean': innov_mean,
'innov_cov': innov_cov,
'prior_state_mean': prior_state_mean,
'prior_state_cov': prior_state_cov,
'posterior_state_mean': prior_state_mean,
'posterior_state_cov': prior_state_cov,
'log_likelihood': log_likelihood
},
columns=('time', 'accepted', 'obs_mean', 'obs_cov',
'predicted_obs_mean', 'predicted_obs_cov', 'innov_mean',
'innov_cov', 'prior_state_mean', 'prior_state_cov',
'posterior_state_mean', 'posterior_state_cov',
'log_likelihood'))
return obs_result