runner.py

import argparse
import datetime

from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble._bagging import BaggingClassifier
from sklearn.ensemble._forest import RandomForestClassifier
from sklearn.ensemble._gb import GradientBoostingClassifier
from sklearn.linear_model._logistic import LogisticRegression
from sklearn.mixture._gaussian_mixture import GaussianMixture
from sklearn.neural_network._multilayer_perceptron import MLPClassifier
from sklearn.svm._classes import SVC
from sklearn.model_selection import train_test_split
import anchor_global
import lime_global

# from anchor_global import features_contributions
from core import load_data, train_classifier, Model, evaluation, \
    find_threshold, ensemble_out

    
def main(source_name, train_size, to_drop, all_categorical_features, max_features, algo, exp):
       
    data, labels, class_names, feature_names, categorical_names = load_data(source_name, all_categorical_features)
    train, test, labels_train, labels_test = train_test_split(data, labels, train_size=train_size, test_size=1-train_size, random_state=2)
    
    print("###########\nOriginal model \n###########")
    
    model, encoder = train_classifier(algo, train, test, labels_train, [], all_categorical_features)
    original_model = Model([model],[encoder],[[]])
    
    threshold_1 = find_threshold(original_model.prob(train), labels_train)
    accuracy = evaluation(original_model.prob(test), labels_test, threshold_1)
    print(accuracy)

    is_fair ,_ = exp(original_model, train, max_features, to_drop, feature_names, class_names, all_categorical_features, categorical_names)
    
    
    if not is_fair:
        print("Original model is NOT fair")
    
        print("###########\nExpOut ensemble's model \n###########")
        ensemble = ensemble_out(algo,to_drop,train,test,labels_train, all_categorical_features)
        
        
        threshold_2 = find_threshold(ensemble.prob(train), labels_train)
        accuracy = evaluation(ensemble.prob(test), labels_test, threshold_2)
        print(accuracy)
        
        is_fair ,_ = exp(ensemble, train, max_features, to_drop, feature_names, class_names, all_categorical_features, categorical_names)
        return ensemble
    
    else:
        print("Original model is fair")
        return original_model


def algo_parser(algo_str):
    
    algo = algo_str.lower()
    
    if algo == "mlp":
        return MLPClassifier
    elif algo == "logreg":
        return LogisticRegression
    elif algo == "rf":
        return RandomForestClassifier
    elif algo == "ada":
        return AdaBoostClassifier
    elif algo == "bagging":
        return BaggingClassifier
    elif algo == "gaussianmixture":
        return GaussianMixture
    elif algo == "gradient":
        return GradientBoostingClassifier
    elif algo == "svm":
        return SVC
    else:
        return None
    
def exp_parser(algo_str):
    
    algo = algo_str.lower()
    
    if algo == "lime":
        return lime_global.fairness_eval
    elif algo == "anchors":
        return anchor_global.fairness_eval
    elif algo == "shap":
        return None
    else:
        return None

   
if __name__ == "__main__":
    
    parser = argparse.ArgumentParser(description='ExpOut: process fairness for classification')
    parser.add_argument('--data')  
    parser.add_argument('--trainsize', type=float)
    parser.add_argument('--algo')  
    parser.add_argument('--exp')  
    parser.add_argument('--max_features', type=int)  
    parser.add_argument('-cat_features', '--cat_features', action='store', dest='cat_features_list', type=int, nargs='*', default=[], help="Examples: -i ")
    parser.add_argument('-drop', '--drop', action='store', dest='drop_list', type=int, nargs='*', default=[], help="Examples: -i ")
    
    args = parser.parse_args() 
    
    now = datetime.datetime.now()
    print(now.year,'-', now.month,'-', now.day,',', now.hour,':', now.minute,':', now.second,sep='')
    
    main(args.data, args.trainsize, args.drop_list, args.cat_features_list, args.max_features, algo_parser(args.algo), exp_parser(args.exp))