
56 | Rozdział 2: Kompleksowy projekt uczenia maszynowego
for train_index, cv_index in k_fold.split(np.zeros(len(X_train)),
y_train.ravel()):
X_train_fold, X_cv_fold = X_train.iloc[train_index,:], \
X_train.iloc[cv_index,:]
y_train_fold, y_cv_fold = y_train.iloc[train_index], \
y_train.iloc[cv_index]
dtrain = xgb.DMatrix(data=X_train_fold, label=y_train_fold)
dCV = xgb.DMatrix(data=X_cv_fold)
bst = xgb.cv(params_xGB, dtrain, num_boost_round=2000,
nfold=5, early_stopping_rounds=200, verbose_eval=50)
best_rounds = np.argmin(bst['test-logloss-mean'])
bst = xgb.train(params_xGB, dtrain, best_rounds)
loglossTraining = log_loss(y_train_fold, ...