diff options
Diffstat (limited to 'python/exploration/dispersion.py')
| -rw-r--r-- | python/exploration/dispersion.py | 21 |
1 files changed, 14 insertions, 7 deletions
diff --git a/python/exploration/dispersion.py b/python/exploration/dispersion.py index c9f219cf..c7bc33d9 100644 --- a/python/exploration/dispersion.py +++ b/python/exploration/dispersion.py @@ -119,18 +119,25 @@ def create_models(conn, df) -> (pd.DataFrame, float): return (df, model) -def create_models_v2(conn, df) -> (pd.DataFrame, float): +def create_models_v2(conn, df, weights=None) -> (pd.DataFrame, float): # Takes the output of get_tranche_data attach_max = df.index.get_level_values("attach").max() bottom_stack = df[df.index.get_level_values("attach") != attach_max] - model = smf.ols( + if weights is None: + weights = np.ones(len(bottom_stack)) + else: + weights.name = "resids" + bottom_stack = bottom_stack.merge(weights, left_index=True, right_index=True) + weights = np.array(bottom_stack.resids) + model = smf.wls( "logit(tranche_loss_per) ~ " - "np.log(index_duration) + " - "np.log(moneyness) * gini + " - "np.log(index_expected_loss)* gini + " - "expit(att_moneyness) +" - "expit(det_moneyness)", + "np.log(index_duration) * np.log(gini)+ " + "np.log(moneyness) * np.log(gini) + " + "I(np.log(gini)**2) +" + "expit(att_moneyness) + I(expit(att_moneyness)**2) +" + "expit(det_moneyness) + I(expit(det_moneyness)**2)", data=bottom_stack, + weights=weights, ) f = model.fit() df.loc[ |