goyetc

#get a single influence-sensitivity plot (ISP)
RF_explainer.plot_isp("Age")

#get all ISPs
RF_explainer.plot_isps()

goyetc

#retrieve existing segment groups that have been created in project
#Note: segment groups can also be created programmatically, see Python SDK reference
tru.get_segment_groups()

#create a new explainer object that is set to data and segment of interest
segment_explainer = tru.get_explainer('train')
segment_explainer.set_comparison_data_splits(tru.get_data_splits())
segment_explainer.set_segment('Gender', 'Male')

#observe performance for male segment

goyetc

#Drift metrics -- select metric of interest with optional parameter. Defaults to project setting.
RF_explainer.compute_model_score_instability()

#feature contributions to score drift -- related to shifts in influence density, not feature value
RF_explainer.compute_feature_contributors_to_instability().transpose().sort_values(by='test', ascending=False)

goyetc

#get avg(abs(feature influences)), per feature, and sort highest to lowest
RF_explainer.get_global_feature_importances().transpose().sort_values(by=0, ascending=False)

goyetc

#feature influences, row level
#returns results based on current truera workspace context (tru), as dataframe
RF_explainer.get_feature_influences()

goyetc

#Hotspots: error analysis / performance debugging
#note ability to select performance metric of interest
RF_explainer.find_hotspots(metric_of_interest='RECALL', 
                           max_num_responses=3)
                           
#alternatively, also include what-if performance analyses, if hotspot were eliminated
RF_explainer.find_hotspots(metric_of_interest='CLASSIFICATION_ACCURACY', 
                           show_what_if_performance=True, 
                           max_num_responses=3)

goyetc

#for quick performance comparison, let's set set a base and comparison split
RF_explainer.set_base_data_split("train")

#optional: check which splits are available
tru.get_data_splits()

#TruEra will automatically ignore any splits already set as the base data, e.g., training data
RF_explainer.set_comparison_data_splits(tru.get_data_splits())

#optional: list available performance metrics

goyetc

#instantiate truera workspace, if not already active in your current python kernel/environment
tru = explainer.get_truera_workspace()

tru.set_environment("remote") #retrieve project information from TruEra Web App

#set truera worksapce context
tru.set_project("Titanic Survival")
tru.set_data_collection("Titanic Passenger Data")
tru.set_model("Random Forest")
tru.set_data_split("Train")

goyetc

#Note: TruEra's use of an ID column / unique identifier enables proper type handling, higher data volume limits, and delayed addition of data such as labels or extra data for segmentation
#Note 2: by specifying a "split name", we automatically add this data, and corresponding Shapley values, to the project created in the TruSHAP explainer step 

GBM_shap_values = GBM_explainer(X_train, 
                           y=y_df, 
                           id_col_name='index',
                           data_split_name = "train"
                           )

goyetc

#import trushap as shap
from truera.client.experimental.trushap import trushap as shap

#TruEra Web App - connection details
CONNECTION_STRING = os.getenv('url')
TOKEN = os.getenv('token')

#use connection string and token as arguments in shap.Explainer method
#define project resource names, as desired
GBM_explainer = shap.Explainer(GBM,