def main_global(model_name):
"""Main function for the global explanations."""
X_train_encoded, y_train, X_test_encoded, y_test, encoder = data_loading.load_encoded_data()
print(X_train_encoded)
print(type(X_train_encoded))
X_test, y_test = data_loading.load_data(type="testing")
model = model_training.load_trained_model(model_name)
# categorical_features_indices = dataset["german_credit_dataset"]["categorical_features_indices"]
categorical_features_names, categorical_features_indices, feature_names = data_loading.analyze_dataset()
df_credit = data_loading.load_data(type="raw")
df_credit = data_loading.data_preparation(df_credit)
df_credit, categorical_encoding, categorical_encoding_label = data_loading.encoding(df_credit)
explain_with_shap_global(X_test_encoded , model, model_name)
def main_init_xai(model_name, chosen_instance=4):
"""Prepare plots and data for the xai-dashboard"""
X_train_encoded, y_train, X_test_encoded, y_test, encoder = data_loading.load_encoded_data()
X_test, y_test = data_loading.load_data(type="testing")
model = model_training.load_trained_model(model_name)
# categorical_features_indices = dataset["german_credit_dataset"]["categorical_features_indices"]
categorical_features_names, categorical_features_indices, feature_names = data_loading.analyze_dataset()
df_credit = data_loading.load_data(type="raw")
df_credit = data_loading.data_preparation(df_credit)
df_credit, categorical_encoding, categorical_encoding_label = data_loading.encoding(df_credit)
#explain_with_lime(X_test, model, model_name, encoder, categorical_features_indices,
# categorical_encoding, categorical_encoding_label,
# feature_names, test_instance=chosen_instance)
explain_with_shap_global(X_train_encoded, model, model_name)
def main_local(model_name, chosen_instance=1):
"""Main function for local explanations"""
X_train_encoded, y_train, X_test_encoded, y_test, encoder = data_loading.load_encoded_data()
X_test, y_test = data_loading.load_data(type="testing")
model = model_training.load_trained_model(model_name)
categorical_features_names, categorical_features_indices, feature_names = data_loading.analyze_dataset()
df_credit = data_loading.load_data(type="raw")
df_credit = data_loading.data_preparation(df_credit)
df_credit, categorical_encoding, categorical_encoding_label = data_loading.encoding(df_credit)
explain_with_lime(X_test, model, model_name, encoder, categorical_features_indices, categorical_encoding,
categorical_encoding_label, feature_names, test_instance=chosen_instance)
explain_with_shap_local(X_test_encoded, model, model_name, feature_names=X_test_encoded.columns.tolist()
, test_instance=chosen_instance)
def post(self):
reqparse_args = reqparse.RequestParser()
reqparse_args.add_argument("chosen_instance", type=int)
args = reqparse_args.parse_args()
print(args["chosen_instance"])
X_test = data_loading.load_data(type="testing")
dataTable(X_test, chosen_instance=args["chosen_instance"])
return "data table created successfully"
def dataTable(X_test, test_instance=10):
"""Save data table for chosen instance"""
X_test, y_test = data_loading.load_data(type="testing")
x_num = X_test.iloc[test_instance, :]
data_table = pd.DataFrame(X_test.iloc[test_instance, :])
dfi.export(data_table, PATHS["03_data_outputs"] + "_data_table.png")
from backend.util.static import PATHS, dataset, params
from backend.util.util import get_the_filenames
from backend.inference.predict import predict
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
from xgboost import plot_importance
from xgboost import XGBClassifier
import matplotlib.pyplot as plt
from backend.xai_cockpit.model_explaining import *
from backend.inference.predict import *
import dataframe_image as dfi
if __name__ == '__main__':
s = (input("Type 'start' to initialize: "))
initialize()
df = load_data(type="raw")
s
# explore_data(df)
data_exploration(df)
X_train_encoded, y_train, X_test_encoded, y_test, encoder = data_loading.load_encoded_data(
)
# Choose a model and train it
model, model_name = model_training.model_selection(input("Select Model: "))
print("Trained model: ", model_name)
X_test = data_loading.train_test_split(df)
model = model_training.train_model(X_train_encoded, y_train, model)
model_training.save_trained_model(model, model_name)
print("Training score data: ")
print(model.score(X_train_encoded, y_train))
#good: 20, bad:35
def get(self):
X_train, y_train = data_loading.load_data(type="training")
data_loading.explore_data(X_train)
return "done"