def test_normalize(self):
preprocessor = Preprocessor(COLS_NUM, ["merchantZip"], PATH_READ_X,
PATH_READ_y, DIR_EDA)
preprocessor.run(normalize=True)
def test_run(self):
preprocessor = Preprocessor(COLS_NUM, ["merchantZip"], PATH_READ_X,
PATH_READ_y, DIR_EDA)
preprocessor.run(hot_encode=False, normalize=False)
def test_one_hot_encoding(self):
preprocessor = Preprocessor(COLS_NUM, ["merchantZip"], PATH_READ_X,
PATH_READ_y, DIR_EDA)
preprocessor.run(hot_encode=True)
eda_runner = EDA(COLS_NUM, PATH_READ_X, PATH_READ_y, DIR_EDA)
preprocessor = Preprocessor(COLS_NUM, ["merchantZip"], PATH_READ_X,
PATH_READ_y, DIR_EDA)
eda_runner.run()
# Log results
results = {
"accuracy": [],
"f1": [],
"precision": [],
"recall": [],
"model": []
}
# Iterate over different models
for model_name, model_dict in pipeline_dict.items():
data = preprocessor.run(**model_dict["preprocessing_params"])
# Define X and y
y = data["fraud"]
X = data.drop(columns=COLS_OTHER + ["fraud"])
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=0.4)
# Train and predict
model = model_dict["model"]
clf = GridSearchCV(model, model_dict["model_params"])
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
# Get scores
results["accuracy"].append(accuracy_score(y_test, y_pred))