def set_sample(self):
sample_cols = tuple(
[self.__dict__[x] for x in self.sample_cols_labels])
self.sample = flag_sample(self.df, *sample_cols)
if self.nosingles and self.fe_name:
self.sample &= flag_nonsingletons(self.df, self.fe_name,
self.sample)
sample_vars = set_sample(self.df, self.sample, sample_cols)
self.__dict__.update(dict(zip(self.sample_store_labels, sample_vars)))
self.x = force_df(self.x)
self.y = self.y.squeeze()
# Force regression variables to float64
for var in self.vars_in_reg:
self.__dict__[var] = self.__dict__[var].astype(np.float64)
# Demean or add constant
if self.fe_name is not None:
self._demean_sample()
elif self.addcons:
_cons = np.ones(self.y.shape[0])
x = self.__dict__[self.add_constant_to]
if x.empty:
x = pd.DataFrame(_cons, columns=['_cons'], index=self.y.index)
else:
x['_cons'] = _cons
self.__dict__[self.add_constant_to] = x
# Re-weight sample
if self.AWT is not None:
self._weight_sample()
def set_sample(self):
sample_cols = tuple(
[self.__dict__[x] for x in self.sample_cols_labels])
self.sample = flag_sample(self.df, *sample_cols)
if self.nosingles and self.fe_name:
self.sample &= flag_nonsingletons(self.df, self.fe_name,
self.sample)
sample_vars = set_sample(self.df, self.sample, sample_cols)
self.__dict__.update(dict(zip(self.sample_store_labels, sample_vars)))
self.x = force_df(self.x)
self.y = self.y.squeeze()
# Force regression variables to float64
for var in self.vars_in_reg:
self.__dict__[var] = self.__dict__[var].astype(np.float64)
# Demean or add constant
if self.fe_name is not None:
self._demean_sample()
elif self.addcons:
_cons = np.ones(self.y.shape[0])
x = self.__dict__[self.add_constant_to]
if x.empty:
x = pd.DataFrame(_cons, columns=['_cons'], index=self.y.index)
else:
x['_cons'] = _cons
self.__dict__[self.add_constant_to] = x
# Re-weight sample
if self.AWT is not None:
self._weight_sample()