INNER CODE UNIT · Python
y
SalvatoreRa/tutorial · machine learning/scripts/MNAR.py:87
X, y = df.iloc[:, :-1], df.iloc[:, -1]
lb = LabelBinarizer()
y =lb.fit_transform(y)
print(datasets_name)
# first we just start with the baseline
# here we use as a classifier XGBoost but you can change with another on
# we do 5 fold cross validation
kf = KFold(n_splits=fold_splits)
X = np.array(X)
for train_index, test_index in kf.split(X):
algo_time = time.time()
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
clf = xgb.XGBClassifier(random_state=42)
clf.fit(X_train, y_train)
y_test_pred = clf.predict(X_test)