作业：利用XGBoost实现对鸢尾花数据集（Iris.csv）的分类预测

数据集
提取码：krry

• 前4/5作为训练集，后1/5作为测试集，分割数据

data = pd.read_csv('ensemble/Iris.csv')
#前4/5作为训练集，后1/5作为测试集
data_training = data[0:int(len(data)*4/5)]
data_test = data[int(len(data)*4/5):len(data)]
#分割
train_x = np.array(data_training.iloc[:, [i for i in range(data_training.shape[1]-1)]])
train_y = np.array(data_training['Species'])
test_x = np.array(data_test.iloc[:, [i for i in range(data_test.shape[1]-1)]])
test_y = np.array(data_test['Species'])

• 训练模型

clf=XGBClassifier(base_score=0.5, booster='gbtree', learning_rate=0.05, max_depth=8, n_estimators=50)
clf.fit(train_x, train_y)

• 测试

print(clf.score(test_x, test_y))

• 完整代码

from xgboost import XGBClassifier
import pandas as pd
import numpy as np

def load_data():
    data = pd.read_csv('ensemble/Iris.csv')
    #前4/5作为训练集，后1/5作为测试集
    data_training = data[0:int(len(data)*4/5)]
    data_test = data[int(len(data)*4/5):len(data)]
    #分割
    train_x = np.array(data_training.iloc[:, [i for i in range(data_training.shape[1]-1)]])
    train_y = np.array(data_training['Species'])
    test_x = np.array(data_test.iloc[:, [i for i in range(data_test.shape[1]-1)]])
    test_y = np.array(data_test['Species'])

    return train_x, train_y, test_x, test_y


def XGBoost():
    train_x, train_y, test_x, test_y = load_data()
    #训练
    clf=XGBClassifier(base_score=0.5, booster='gbtree', learning_rate=0.05, max_depth=8, n_estimators=50)
    clf.fit(train_x, train_y)
    #测试
    print(clf.score(test_x, test_y))


if __name__ == '__main__':
    XGBoost()