def individual_utilities(
persons,
cdap_indiv_spec,
locals_d,
trace_hh_id=None, trace_label=None):
"""
Calculate CDAP utilities for all individuals.
Parameters
----------
persons : pandas.DataFrame
DataFrame of individual persons data.
cdap_indiv_spec : pandas.DataFrame
CDAP spec applied to individuals.
Returns
-------
utilities : pandas.DataFrame
Will have index of `persons` and columns for each of the alternatives.
plus some 'useful columns' [_hh_id_, _ptype_, 'cdap_rank', _hh_size_]
"""
# calculate single person utilities
indiv_utils = simulate.eval_utilities(cdap_indiv_spec, persons, locals_d, trace_label=trace_label)
# add columns from persons to facilitate building household interactions
useful_columns = [_hh_id_, _ptype_, 'cdap_rank', _hh_size_]
indiv_utils[useful_columns] = persons[useful_columns]
if trace_hh_id:
tracing.trace_df(indiv_utils, '%s.indiv_utils' % trace_label,
column_labels=['activity', 'person'])
return indiv_utils
def individual_utilities(
persons,
cdap_indiv_spec,
locals_d,
trace_hh_id=None, trace_label=None):
"""
Calculate CDAP utilities for all individuals.
Parameters
----------
persons : pandas.DataFrame
DataFrame of individual persons data.
cdap_indiv_spec : pandas.DataFrame
CDAP spec applied to individuals.
Returns
-------
utilities : pandas.DataFrame
Will have index of `persons` and columns for each of the alternatives.
plus some 'useful columns' [_hh_id_, _ptype_, 'cdap_rank', _hh_size_]
"""
# calculate single person utilities
indiv_utils = simulate.eval_utilities(cdap_indiv_spec, persons, locals_d, trace_label)
# add columns from persons to facilitate building household interactions
useful_columns = [_hh_id_, _ptype_, 'cdap_rank', _hh_size_]
indiv_utils[useful_columns] = persons[useful_columns]
if trace_hh_id:
tracing.trace_df(indiv_utils, '%s.indiv_utils' % trace_label,
column_labels=['activity', 'person'])
return indiv_utils
def compute_utilities(network_los,
model_settings,
choosers,
model_constants,
trace_label,
trace=False,
trace_column_names=None):
"""
Compute utilities
"""
with chunk.chunk_log(f'tvpb compute_utilities'):
trace_label = tracing.extend_trace_label(trace_label, 'compute_utils')
logger.debug(
f"{trace_label} Running compute_utilities with {choosers.shape[0]} choosers"
)
locals_dict = {'np': np, 'los': network_los}
locals_dict.update(model_constants)
# we don't grok coefficients, but allow them to use constants in spec alt columns
spec = simulate.read_model_spec(file_name=model_settings['SPEC'])
for c in spec.columns:
if c != simulate.SPEC_LABEL_NAME:
spec[c] = spec[c].map(
lambda s: model_constants.get(s, s)).astype(float)
with chunk.chunk_log(f'compute_utilities'):
# - run preprocessor to annotate choosers
preprocessor_settings = model_settings.get('PREPROCESSOR')
if preprocessor_settings:
# don't want to alter caller's dataframe
choosers = choosers.copy()
expressions.assign_columns(
df=choosers,
model_settings=preprocessor_settings,
locals_dict=locals_dict,
trace_label=trace_label)
utilities = simulate.eval_utilities(
spec,
choosers,
locals_d=locals_dict,
trace_all_rows=trace,
trace_label=trace_label,
trace_column_names=trace_column_names)
return utilities
def household_activity_choices(indiv_utils, interaction_coefficients, hhsize,
trace_hh_id=None, trace_label=None):
"""
Calculate household utilities for each activity pattern alternative for households of hhsize
The resulting activity pattern for each household will be coded as a string of activity codes.
e.g. 'MNHH' for a 4 person household with activities Mandatory, NonMandatory, Home, Home
Parameters
----------
indiv_utils : pandas.DataFrame
CDAP utilities for each individual, ignoring interactions
ind_utils has index of _persons_index_ and a column for each alternative
i.e. three columns 'M' (Mandatory), 'N' (NonMandatory), 'H' (Home)
interaction_coefficients : pandas.DataFrame
Rules and coefficients for generating interaction specs for different household sizes
hhsize : int
the size of household for which activity perttern should be calculated (1..MAX_HHSIZE)
Returns
-------
choices : pandas.Series
the chosen cdap activity pattern for each household represented as a string (e.g. 'MNH')
with same index (_hh_index_) as utils
"""
if hhsize == 1:
# for 1 person households, there are no interactions to account for
# and the household utils are the same as the individual utils
choosers = vars = None
# extract the individual utilities for individuals from hhsize 1 households
utils = indiv_utils.loc[indiv_utils[_hh_size_] == 1, [_hh_id_, 'M', 'N', 'H']]
# index on household_id, not person_id
set_hh_index(utils)
else:
choosers = hh_choosers(indiv_utils, hhsize=hhsize)
spec = build_cdap_spec(interaction_coefficients, hhsize,
trace_spec=(trace_hh_id in choosers.index),
trace_label=trace_label)
utils = simulate.eval_utilities(spec, choosers, trace_label=trace_label)
if len(utils.index) == 0:
return pd.Series(dtype='float64')
probs = logit.utils_to_probs(utils, trace_label=trace_label)
# select an activity pattern alternative for each household based on probability
# result is a series indexed on _hh_index_ with the (0 based) index of the column from probs
idx_choices, rands = logit.make_choices(probs, trace_label=trace_label)
# convert choice expressed as index into alternative name from util column label
choices = pd.Series(utils.columns[idx_choices].values, index=utils.index)
if trace_hh_id:
if hhsize > 1:
tracing.trace_df(choosers, '%s.hhsize%d_choosers' % (trace_label, hhsize),
column_labels=['expression', 'person'])
tracing.trace_df(utils, '%s.hhsize%d_utils' % (trace_label, hhsize),
column_labels=['expression', 'household'])
tracing.trace_df(probs, '%s.hhsize%d_probs' % (trace_label, hhsize),
column_labels=['expression', 'household'])
tracing.trace_df(choices, '%s.hhsize%d_activity_choices' % (trace_label, hhsize),
column_labels=['expression', 'household'])
tracing.trace_df(rands, '%s.hhsize%d_rands' % (trace_label, hhsize),
columns=[None, 'rand'])
return choices
def household_activity_choices(indiv_utils, interaction_coefficients, hhsize,
trace_hh_id=None, trace_label=None):
"""
Calculate household utilities for each activity pattern alternative for households of hhsize
The resulting activity pattern for each household will be coded as a string of activity codes.
e.g. 'MNHH' for a 4 person household with activities Mandatory, NonMandatory, Home, Home
Parameters
----------
indiv_utils : pandas.DataFrame
CDAP utilities for each individual, ignoring interactions
ind_utils has index of _persons_index_ and a column for each alternative
i.e. three columns 'M' (Mandatory), 'N' (NonMandatory), 'H' (Home)
interaction_coefficients : pandas.DataFrame
Rules and coefficients for generating interaction specs for different household sizes
hhsize : int
the size of household for which activity perttern should be calculated (1..MAX_HHSIZE)
Returns
-------
choices : pandas.Series
the chosen cdap activity pattern for each household represented as a string (e.g. 'MNH')
with same index (_hh_index_) as utils
"""
if hhsize == 1:
# for 1 person households, there are no interactions to account for
# and the household utils are the same as the individual utils
choosers = vars = None
# extract the individual utilities for individuals from hhsize 1 households
utils = indiv_utils.loc[indiv_utils[_hh_size_] == 1, [_hh_id_, 'M', 'N', 'H']]
# index on household_id, not person_id
set_hh_index(utils)
else:
choosers = hh_choosers(indiv_utils, hhsize=hhsize)
spec = build_cdap_spec(interaction_coefficients, hhsize,
trace_spec=(trace_hh_id in choosers.index),
trace_label=trace_label)
utils = simulate.eval_utilities(spec, choosers, trace_label=trace_label)
if len(utils.index) == 0:
return pd.Series()
probs = logit.utils_to_probs(utils, trace_label=trace_label)
# select an activity pattern alternative for each household based on probability
# result is a series indexed on _hh_index_ with the (0 based) index of the column from probs
idx_choices, rands = logit.make_choices(probs, trace_label=trace_label)
# convert choice expressed as index into alternative name from util column label
choices = pd.Series(utils.columns[idx_choices].values, index=utils.index)
if trace_hh_id:
if hhsize > 1:
tracing.trace_df(choosers, '%s.hhsize%d_choosers' % (trace_label, hhsize),
column_labels=['expression', 'person'])
tracing.trace_df(utils, '%s.hhsize%d_utils' % (trace_label, hhsize),
column_labels=['expression', 'household'])
tracing.trace_df(probs, '%s.hhsize%d_probs' % (trace_label, hhsize),
column_labels=['expression', 'household'])
tracing.trace_df(choices, '%s.hhsize%d_activity_choices' % (trace_label, hhsize),
column_labels=['expression', 'household'])
tracing.trace_df(rands, '%s.hhsize%d_rands' % (trace_label, hhsize),
columns=[None, 'rand'])
return choices