def _read_panel_table(self, group, where=None):
from pandas.core.panel import _make_long_index
table = getattr(group, 'table')
# create the selection
sel = Selection(table, where)
sel.select()
fields = table._v_attrs.fields
columns = _maybe_convert(sel.values['column'],
table._v_attrs.columns_kind)
index = _maybe_convert(sel.values['index'],
table._v_attrs.index_kind)
# reconstruct
long_index = _make_long_index(np.asarray(index),
np.asarray(columns))
lp = LongPanel(sel.values['values'], index=long_index,
columns=fields)
lp = lp.sortlevel(level=0)
wp = lp.to_wide()
if sel.column_filter:
new_minor = sorted(set(wp.minor_axis) & sel.column_filter)
wp = wp.reindex(minor=new_minor)
return wp
def _read_panel_table(self, group, where=None):
from pandas.core.common import _asarray_tuplesafe
table = getattr(group, 'table')
# create the selection
sel = Selection(table, where)
sel.select()
fields = table._v_attrs.fields
columns = _maybe_convert(sel.values['column'],
table._v_attrs.columns_kind)
index = _maybe_convert(sel.values['index'],
table._v_attrs.index_kind)
# reconstruct
long_index = MultiIndex.from_arrays([index, columns])
lp = LongPanel(sel.values['values'], index=long_index,
columns=fields)
if lp.consistent:
lp = lp.sortlevel(level=0)
wp = lp.to_wide()
else:
if not self._quiet: # pragma: no cover
print ('Duplicate entries in table, taking most recently '
'appended')
# need a better algorithm
tuple_index = long_index.get_tuple_index()
index_map = lib.map_indices_object(tuple_index)
unique_tuples = lib.fast_unique(tuple_index)
unique_tuples = _asarray_tuplesafe(unique_tuples)
indexer = lib.merge_indexer_object(unique_tuples, index_map)
new_index = long_index.take(indexer)
new_values = lp.values.take(indexer, axis=0)
lp = LongPanel(new_values, index=new_index, columns=lp.columns)
wp = lp.to_wide()
if sel.column_filter:
new_minor = sorted(set(wp.minor_axis) & sel.column_filter)
wp = wp.reindex(minor=new_minor)
return wp
def _read_long(self, group, where=None):
from pandas.core.index import MultiIndex
items = self._read_index(group, 'items')
major_axis = self._read_index(group, 'major_axis')
minor_axis = self._read_index(group, 'minor_axis')
major_labels = _read_array(group, 'major_labels')
minor_labels = _read_array(group, 'minor_labels')
values = _read_array(group, 'values')
index = MultiIndex(levels=[major_axis, minor_axis],
labels=[major_labels, minor_labels])
return LongPanel(values, index=index, columns=items)
def _read_panel_table(self, group, where=None):
from pandas.core.common import _asarray_tuplesafe
table = getattr(group, 'table')
# create the selection
sel = Selection(table, where)
sel.select()
fields = table._v_attrs.fields
columns = _maybe_convert(sel.values['column'],
table._v_attrs.columns_kind)
index = _maybe_convert(sel.values['index'], table._v_attrs.index_kind)
# reconstruct
long_index = MultiIndex.from_arrays([index, columns])
lp = LongPanel(sel.values['values'], index=long_index, columns=fields)
if lp.consistent:
lp = lp.sortlevel(level=0)
wp = lp.to_wide()
else:
if not self._quiet: # pragma: no cover
print(
'Duplicate entries in table, taking most recently '
'appended')
# need a better algorithm
tuple_index = long_index.get_tuple_index()
index_map = lib.map_indices_object(tuple_index)
unique_tuples = lib.fast_unique(tuple_index)
unique_tuples = _asarray_tuplesafe(unique_tuples)
indexer = lib.merge_indexer_object(unique_tuples, index_map)
new_index = long_index.take(indexer)
new_values = lp.values.take(indexer, axis=0)
lp = LongPanel(new_values, index=new_index, columns=lp.columns)
wp = lp.to_wide()
if sel.column_filter:
new_minor = sorted(set(wp.minor_axis) & sel.column_filter)
wp = wp.reindex(minor=new_minor)
return wp
import pandas
pandas.version >= .1
except:
raise ImportError, "pandas >= .10 not installed"
from pandas import LongPanel
import scikits.statsmodels as sm
import numpy.lib.recfunctions as nprf
data = sm.datasets.grunfeld.Load()
# Baltagi doesn't include American Steel
endog = data.endog[:-20]
fullexog = data.exog[:-20]
# fullexog.sort(order=['firm','year'])
panel_arr = nprf.append_fields(fullexog, 'investment', endog, float,
usemask=False)
panel_panda = LongPanel.fromRecords(panel_arr, major_field='year',
minor_field='firm')
# the most cumbersome way of doing it as far as preprocessing by hand
exog = fullexog[['value','capital']].view(float).reshape(-1,2)
exog = sm.add_constant(exog)
panel = group(fullexog['firm'])
year = fullexog['year']
panel_mod = PanelModel(endog, exog, panel, year, xtnames=['firm','year'],
equation='invest value capital')
# note that equation doesn't actually do anything but name the variables
panel_ols = panel_mod.fit(model='pooled')
panel_be = panel_mod.fit(model='between', effects='oneway')
panel_fe = panel_mod.fit(model='fixed', effects='oneway')
panel_bet = panel_mod.fit(model='between', effects='time')
pass
if __name__ == "__main__":
import pandas
from pandas import LongPanel
import statsmodels.api as sm
import numpy.lib.recfunctions as nprf
data = sm.datasets.grunfeld.load()
# Baltagi doesn't include American Steel
endog = data.endog[:-20]
fullexog = data.exog[:-20]
# fullexog.sort(order=['firm','year'])
panel_arr = nprf.append_fields(fullexog, 'investment', endog, float,
usemask=False)
panel_panda = LongPanel.fromRecords(panel_arr, major_field='year',
minor_field='firm')
# the most cumbersome way of doing it as far as preprocessing by hand
exog = fullexog[['value','capital']].view(float).reshape(-1,2)
exog = sm.add_constant(exog, prepend=False)
panel = group(fullexog['firm'])
year = fullexog['year']
panel_mod = PanelModel(endog, exog, panel, year, xtnames=['firm','year'],
equation='invest value capital')
# note that equation doesn't actually do anything but name the variables
panel_ols = panel_mod.fit(model='pooled')
panel_be = panel_mod.fit(model='between', effects='oneway')
panel_fe = panel_mod.fit(model='fixed', effects='oneway')
panel_bet = panel_mod.fit(model='between', effects='time')
