def Snippet_188():
print()
print(format('Hoe to evaluate XGBoost model with learning curves','*^82'))
import warnings
warnings.filterwarnings("ignore")
# load libraries
import numpy as np
from xgboost import XGBClassifier
import matplotlib.pyplot as plt
plt.style.use('ggplot')
from sklearn import datasets
import matplotlib.pyplot as plt
from sklearn.model_selection import learning_curve
# load the datasets
dataset = datasets.load_breast_cancer()
X = dataset.data; y = dataset.target
# Create CV training and test scores for various training set sizes
train_sizes, train_scores, test_scores = learning_curve(XGBClassifier(),
X, y, cv=10, scoring='accuracy', n_jobs=-1,
# 50 different sizes of the training set
train_sizes=np.linspace(0.01, 1.0, 50))
# Create means and standard deviations of training set scores
train_mean = np.mean(train_scores, axis=1)
train_std = np.std(train_scores, axis=1)
# Create means and standard deviations of test set scores
test_mean = np.mean(test_scores, axis=1)
test_std = np.std(test_scores, axis=1)
# Draw lines
plt.subplots(figsize=(12,12))
plt.plot(train_sizes, train_mean, '--', color="#111111", label="Training score")
plt.plot(train_sizes, test_mean, color="#111111", label="Cross-validation score")
# Draw bands
plt.fill_between(train_sizes, train_mean - train_std, train_mean + train_std, color="#DDDDDD")
plt.fill_between(train_sizes, test_mean - test_std, test_mean + test_std, color="#DDDDDD")
# Create plot
plt.title("Learning Curve")
plt.xlabel("Training Set Size"), plt.ylabel("Accuracy Score"), plt.legend(loc="best")
plt.tight_layout(); plt.show()
Snippet_188()