def summarize(self):
"""
The summarize method allows to display the summary of local explainability.
This method can be configured with modify_mask method to summarize the explainability to suit needs.
If the user doesn't use modify_mask, the summarize method uses the mask_params parameters specified during
the initialisation of the SmartPredictor.
In classification case, The summarize method summarizes the explainability which corresponds to :
- the predicted values specified by the user or automatically computed (with add_input method)
- the right probabilities from predict_proba associated to the right predicted values
- the right contributions ranked and filtered as specify with modify_mask method
Returns
-------
pandas.DataFrame
- selected explanation of each row for classification case
Examples
--------
>>> summary_df = predictor.summarize()
>>> summary_df
pred proba feature_1 value_1 contribution_1 feature_2 value_2 contribution_2
0 0 0.756416 Sex 1.0 0.322308 Pclass 3.0 0.155069
1 3 0.628911 Sex 2.0 0.585475 Pclass 1.0 0.370504
2 0 0.543308 Sex 2.0 -0.486667 Pclass 3.0 0.255072
>>> predictor.modify_mask(max_contrib=1)
>>> summary_df = predictor.summarize()
>>> summary_df
pred proba feature_1 value_1 contribution_1
0 0 0.756416 Sex 1.0 0.322308
1 3 0.628911 Sex 2.0 0.585475
2 0 0.543308 Sex 2.0 -0.486667
"""
# data is needed : add_input() method must be called at least once
if not hasattr(self, "data"):
raise ValueError("You have to specify dataset x and y_pred arguments. Please use add_input() method.")
self.summary = assign_contributions(
rank_contributions(
self.data["contributions"],
self.data["x_postprocessed"]
)
)
# Apply filter method with mask_params attributes parameters
self.filter()
# Summarize information
self.data['summary'] = summarize(self.summary['contrib_sorted'],
self.summary['var_dict'],
self.summary['x_sorted'],
self.mask,
self.columns_dict,
self.features_dict)
# Matching with y_pred
return pd.concat([self.data["ypred"], self.data['summary']], axis=1)
def assign_contributions(self, ranked):
"""
Turn a list of results into a dict.
Parameters
----------
ranked : list
The output of rank_contributions.
Returns
-------
dict
Same data but rearrange into a dict with explicit names.
Raises
------
ValueError
The output of rank_contributions should always be of length three.
"""
return assign_contributions(ranked)
def summarize(self, use_groups=None):
"""
The summarize method allows to display the summary of local explainability.
This method can be configured with modify_mask method to summarize the explainability to suit needs.
If the user doesn't use modify_mask, the summarize method uses the mask_params parameters specified during
the initialisation of the SmartPredictor.
In classification case, The summarize method summarizes the explainability which corresponds to :
- the predicted values specified by the user or automatically computed (with add_input method)
- the right probabilities from predict_proba associated to the right predicted values
- the right contributions ranked and filtered as specify with modify_mask method
Parameters
----------
use_groups : bool (optional)
Whether or not to compute groups of features contributions.
Returns
-------
pandas.DataFrame
- selected explanation of each row for classification case
Examples
--------
>>> summary_df = predictor.summarize()
>>> summary_df
pred proba feature_1 value_1 contribution_1 feature_2 value_2 contribution_2
0 0 0.756416 Sex 1.0 0.322308 Pclass 3.0 0.155069
1 3 0.628911 Sex 2.0 0.585475 Pclass 1.0 0.370504
2 0 0.543308 Sex 2.0 -0.486667 Pclass 3.0 0.255072
>>> predictor.modify_mask(max_contrib=1)
>>> summary_df = predictor.summarize()
>>> summary_df
pred proba feature_1 value_1 contribution_1
0 0 0.756416 Sex 1.0 0.322308
1 3 0.628911 Sex 2.0 0.585475
2 0 0.543308 Sex 2.0 -0.486667
"""
# data is needed : add_input() method must be called at least once
use_groups = True if (use_groups is not False
and self.features_groups is not None) else False
if not hasattr(self, "data"):
raise ValueError(
"You have to specify dataset x and y_pred arguments. Please use add_input() method."
)
if use_groups is True:
data = self.data_groups
else:
data = self.data
if self._drop_option is not None:
columns_to_keep = [
x for x in self._drop_option["columns_dict_op"].values()
if x in data["x_postprocessed"].columns
]
if use_groups:
columns_to_keep += list(self.features_groups.keys())
x_preprocessed = data["x_postprocessed"][columns_to_keep]
else:
x_preprocessed = data["x_postprocessed"]
columns_dict = {i: col for i, col in enumerate(x_preprocessed.columns)}
features_dict = {
k: v
for k, v in self.features_dict.items()
if k in x_preprocessed.columns
}
self.summary = assign_contributions(
rank_contributions(data["contributions"], x_preprocessed))
# Apply filter method with mask_params attributes parameters
self.filter()
# Summarize information
data['summary'] = summarize(self.summary['contrib_sorted'],
self.summary['var_dict'],
self.summary['x_sorted'], self.mask,
columns_dict, features_dict)
# Matching with y_pred
return pd.concat([data["ypred"], data['summary']], axis=1)