def add_history(month, panel_store=None, frame=None):
"""
Add the 3 month history for every employee working.
Will return one of {1, 0, -1}
{True, False NaN} where
- (1) True if kind anytime in past 3 months and employed today (new hire)
- (0) False if employed past 3 months and employed today
- (-1) NaN if un/non employed today.
"""
# TODO: Chcek this...
if frame is None:
_wp = panel_store.select('m' + month)
else:
_wp = frame
wp = get_useful(_wp.copy())
e_types = ['either', 'unemployed', 'nonemployed']
# inplace
[_add_employment_status_last_period(wp, kind=x) for x in e_types]
_wp['unemployed_history'] = wp['unemployed']
_wp['nonemployed_history'] = wp['nonemployed']
_wp['either_history'] = wp['either']
return _wp
def add_history(month, panel_store=None, frame=None):
"""
Add the 3 month history for every employee working.
Will return one of {1, 0, -1}
{True, False NaN} where
- (1) True if kind anytime in past 3 months and employed today (new hire)
- (0) False if employed past 3 months and employed today
- (-1) NaN if un/non employed today.
"""
# TODO: Chcek this...
if frame is None:
_wp = panel_store.select('m' + month)
else:
_wp = frame
wp = get_useful(_wp.copy())
e_types = ['either', 'unemployed', 'nonemployed']
# inplace
[_add_employment_status_last_period(wp, kind=x) for x in e_types]
_wp['unemployed_history'] = wp['unemployed']
_wp['nonemployed_history'] = wp['nonemployed']
_wp['either_history'] = wp['either']
return _wp
def is_recently_unemployed(wp, month='both'):
"""
Checks each row for unemployed/nonemployed in the last 3 months.
month can be 4, 8, or 'both'.
(I wonder if groupby().filter could handle this...)
Returns
-------
{timestamp: { labor_stats : DataFrame } }
A list (MIS=4, 8) of dicts of labor status to DataFrames containing just
that group.
aggfuncs should be able to ignore Nones
"""
wp = get_useful(wp)
wp = wp.loc[:, ((wp['age'] >= 22) & (wp['age'] <= 65)).any(1)]
if month == 'both':
months = [4, 8]
elif month in (4, '4'):
months == [4]
elif month in (8, '8'):
months = [8]
else:
raise ValueError
if 8 not in wp.minor_axis:
months = [4]
if 4 not in wp.minor_axis:
return None
df = wp['labor_status']
es = [df[df[x].isin([1, 2])] for x in months]
employed_idx = [x[x.loc[:, 1:3].isin([1, 2]).all(1)].index for x in es]
unemployed_idx = [x[x.loc[:, 1:3].isin([3, 4]).all(1)].index for x in es]
nonemployed_idx = [
x[x.loc[:, 1:3].isin([5, 6, 7]).all(1)].index for x in es
]
idxes = zip(['employed', 'unemployed', 'nonemployed'],
[employed_idx, unemployed_idx, nonemployed_idx])
res = {}
for i, m in enumerate(months):
stamp = pd.Timestamp(
pd.datetime(int(wp['year'][m].dropna().values[0]),
int(wp['month'][m].dropna().values[0]), 1))
res[stamp] = {k: wp.loc[:, idx[i], m] for k, idx in idxes}
return res
def is_recently_unemployed(wp, month='both'):
"""
Checks each row for unemployed/nonemployed in the last 3 months.
month can be 4, 8, or 'both'.
(I wonder if groupby().filter could handle this...)
Returns
-------
{timestamp: { labor_stats : DataFrame } }
A list (MIS=4, 8) of dicts of labor status to DataFrames containing just
that group.
aggfuncs should be able to ignore Nones
"""
wp = get_useful(wp)
wp = wp.loc[:, ((wp['age'] >= 22) & (wp['age'] <= 65)).any(1)]
if month == 'both':
months = [4, 8]
elif month in (4, '4'):
months == [4]
elif month in (8, '8'):
months = [8]
else:
raise ValueError
if 8 not in wp.minor_axis:
months = [4]
if 4 not in wp.minor_axis:
return None
df = wp['labor_status']
es = [df[df[x].isin([1, 2])] for x in months]
employed_idx = [x[x.loc[:, 1:3].isin([1, 2]).all(1)].index for x in es]
unemployed_idx = [x[x.loc[:, 1:3].isin([3, 4]).all(1)].index for x in es]
nonemployed_idx = [x[x.loc[:, 1:3].isin([5, 6, 7]).all(1)].index for x in es]
idxes = zip(['employed', 'unemployed', 'nonemployed'],
[employed_idx, unemployed_idx, nonemployed_idx])
res = {}
for i, m in enumerate(months):
stamp = pd.Timestamp(pd.datetime(int(wp['year'][m].dropna().values[0]),
int(wp['month'][m].dropna().values[0]), 1))
res[stamp] = {k: wp.loc[:, idx[i], m] for k, idx in idxes}
return res
def add_flows(month, panel_store=None, frame=None):
"""
Add the *montly* flows for each worker, for each month (2 :: 8).
The flows are: ee, eu, en, ue, uu, un, ne, nu, nn/
"""
if frame is None:
_wp = panel_store.select('m' + month)
else:
_wp = frame
wp = get_useful(_wp.copy())
try:
_add_flows_panel(wp, inplace=True)
_wp['flow'] = wp['flow']
return _wp
except Exception as e:
print("Skipping {}, because of {}".format(month, e))
raise KeyError(e)
def add_flows(month, panel_store=None, frame=None):
"""
Add the *montly* flows for each worker, for each month (2 :: 8).
The flows are: ee, eu, en, ue, uu, un, ne, nu, nn/
"""
if frame is None:
_wp = panel_store.select('m' + month)
else:
_wp = frame
wp = get_useful(_wp.copy())
try:
_add_flows_panel(wp, inplace=True)
_wp['flow'] = wp['flow']
return _wp
except Exception as e:
print("Skipping {}, because of {}".format(month, e))
raise KeyError(e)