joshreini1

# register the model
tru.add_python_model(model_name_v2,
                       models[model_name_v2],
                       train_split_name='2014-CA',
                       train_parameters = train_params)

joshreini1

tru.tester.get_model_test_results(test_types = ["fairness"])

joshreini1

tru.tester.add_fairness_test(test_name = "Impact Ratio Test",
   data_split_name_regex = ".",
   all_data_collections=True,
   all_protected_segments=True,
   metric = "DISPARATE_IMPACT_RATIO",
   fail_if_outside = [0.8, 1.25])

joshreini1

tru.add_segment_group("Sex", {"Male": "Sex == 'Male'", "Female": "Sex == 'Female'"})
tru.set_as_protected_segment(segment_group_name = "Sex", segment_name = "Female")

joshreini1

# import trushap, and optionally alias as shap to preserve your SHAP code.
from truera.client.experimental.trushap import trushap as shap

# Initialize the explainer. 
# Include TruEra authentication (optional) to add the model to your TruEra deployment.
explainer = shap.Explainer(model, connection_string = CONNECTION_STRING, token = TOKEN)

# Calculate shapley values AND add data split to your TruEra deployment.
shap_values = explainer(X, id_col_name = "id")

joshreini1

data_collections = tru.get_data_collections()
for dc in data_collections:
    tru.set_data_collection(dc)
    data_splits = ["train","2010","2011","2012","2013","2014","2015","2016"]
    ref_model = "linear_" + dc
    for split in data_splits:
        tru.tester.add_performance_test(
            data_split_name = split,
            metric = 'AUC',
            warn_threshold_type = "ABSOLUTE", #this is default, specifying for clarity

joshreini1

tru.set_data_collection("data_collection")
splits = tru.get_data_splits()
for split in splits:
    tru.set_data_collection("data_collection")
    tru.set_data_split(split)
    xs = tru.get_xs()
    ys = tru.get_ys()
    tru.set_data_collection("data_collection_v2")
    ys_mean = ys.mean()
    ys_std = ys.std()

joshreini1

class target_encoder(BaseEstimator, TransformerMixin):

    def __init__(self):
        pass

    def fit(self, X, y = None):
        return self

    def transform(self, X, y = None):
        #target encode lat and long

joshreini1

class target_encoder(BaseEstimator, TransformerMixin):

    def __init__(self):
        pass

    def fit(self, X, y = None):
        return self

    def transform(self, X, y = None):
        #target encode lat and long

joshreini1

project_name = 'Fire_Party'
tru.set_environment('local')
tru.add_project(project_name, score_type='probits')
extra_data_columns = ['year']
train_split_name = 'train'
burned_fraction_th = 0.01
for window_size in range(1,11):
    key = f'{window_size}year_window'
    print(key)
    tru.add_data_collection(key)