"""
利用XBGoost预测乳腺癌的例子
20221113 byp
"""

from xgboost import XGBClassifier
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score


# 导入训练数据
data = load_breast_cancer()

# split data into X and y
X, y = data['data'], data['target']
X_train, X_test, y_train, y_test = train_test_split(
    X, y, train_size=0.8, random_state=0
)

model = XGBClassifier(num_class=3,
                      learning_rate=0.2,
                      n_estimators=1000,          # 树的个数--1000棵树建立xgboost
                      max_depth=1,                # 树的深度
                      min_child_weight=4,         # 叶子节点最小权重
                      gamma=0.,                   # 惩罚项中叶子结点个数前的参数
                      subsample=0.8,              # 随机选择80%样本建立决策树
                      colsample_btree=0.8,        # 随机选择80%特征建立决策树
                      objective='multi:softmax',  # 指定损失函数
                      scale_pos_weight=1,         # 解决样本个数不平衡的问题
                      random_state=27,            # 随机数
                      reg_alpha=0.01,
                      reg_lambda=3,
                      verbosity=0                 # 最新的xgboost(1.6.2)已经移除了silent参数，换成verbosity
                      )


# model = XGBClassifier()
model.fit(X_train, y_train)
# 保存模型
# model.save_model('Pima_Indians_Diabetes_Model.model')

# make predictions for test data
y_pred = model.predict(X)
prediction = [round(value) for value in y_pred]
# evaluate predictions
accuracy = accuracy_score(y, prediction)
# print(prediction, end='\n')
# for i in prediction:
#     print(i)

print("Accuracy:%.2f%%" % (accuracy * 100.0))