for step in steps:
fi_dict = model.extras.feature_importances[period][step]
step_df = pd.DataFrame(fi.reorder_fi_dict(fi_dict))
step_df = step_df.rename(columns={"importance": f"s={step}"})
step_df.set_index("feature", inplace=True)
df = df.join(step_df) if step > steps[0] else step_df.copy()
df = df.sort_values(by=[f"s={sort_step}"], ascending=False)
df = df[0:top + 1]
return df
# Paramaters.
sort_step = 3
top = 30
period = "test"
for model in models:
model.extras._get_feature_importances()
fi_cm = featimp_by_steps(model=model,
period=period,
steps=model.steps,
sort_step=sort_step,
top=top,
cols=model.cols_features)
fi.write_fi_tex(
pd.DataFrame(fi_cm),
os.path.join(
out_paths["features"],
f"impurity_imp_task{task}_{model.name}_{level}_dummy.tex"))
"""
tex = meta + tex
path_out = os.path.join(out_paths["evaluation"],
f"{model.name}_{level}_{calib}_scores.tex")
with open(path_out, "w") as f:
f.write(tex)
print(f"Wrote scores table to {path_out}.")
for model in models:
fi_cm = featimp_by_steps(model=model,
steps=steps,
sort_step=sort_step,
top=top,
cols=model.cols_features)
fi.write_fi_tex(
pd.DataFrame(fi_cm),
os.path.join(out_paths["features"],
f"impurity_imp_{model.name}_{level}.tex"))
sort_step = 3
top = 30
for model in models:
for step in steps:
pi_dict = model.extras.permutation_importances["test"][step]["test"]
step_df = pd.DataFrame(fi.reorder_fi_dict(pi_dict))
step_df = step_df.rename(columns={"importance": f"s={step}"})
step_df.set_index("feature", inplace=True)
pi_df = pi_df.join(step_df) if step > steps[0] else step_df.copy()
pi_df = pi_df.sort_values(by=[f"s={sort_step}"], ascending=False)
pi_df = pi_df[0:top + 1]
print(models[0].name)
# Period B step 1
models[0].scores["B"][1]
# Notice all features and predictions in the same dataframe, no more a/b/c
# Instead we subset by the periods when needed
cols_predict = [model.col_sc_calibrated for model in models] + [ensemble.col_sc for ensemble in ensembles]
# All calibrated predictions for period C
df.loc[period_c.times_predict, cols_predict]
sort_step = 3
top = 30
for model in models:
for step in steps:
pi_dict = model.extras.permutation_importances["test"][step]["test"]
step_df = pd.DataFrame(fi.reorder_fi_dict(pi_dict))
step_df = step_df.rename(columns={"importance": f"s={step}"})
step_df.set_index("feature", inplace=True)
pi_df = pi_df.join(step_df) if step > steps[0] else step_df.copy()
pi_df = pi_df.sort_values(by=[f"s={sort_step}"], ascending=False)
pi_df = pi_df[0:top + 1]
fi.write_fi_tex(
pi_df,
os.path.join(out_paths["features"], f"permutation_imp_{model.name}.tex")
)