作业：利用AdaBoost对马疝病数据集（horseColic）进行分类预测

数据集
提取码：krry

• 先利用pandas读入csv文件，以DataFrame形式存储；然后将数据转成list（其实也可以直接操作，不过本人习惯这样做）：
  data = np.array(data).tolist()

• 分割数据，最后一列作为标签类别y，其余列为x：

x = []; y = []
for i in range(len(data)):
     y.append(data[i][-1])
     del data[i][-1]
     x.append(data[i])

• 训练模型

clf = AdaBoostClassifier(base_estimator=DecisionTreeClassifier(max_depth=7, min_samples_leaf=7), n_estimators=100, algorithm='SAMME', learning_rate=0.95)
clf.fit(train_x, train_y)

• 测试

print(clf.score(test_x, test_y))

• 完整代码：

from sklearn.ensemble import AdaBoostClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import cross_val_score
import pandas as pd
import numpy as np

def load_data(path):
    data = pd.read_csv(path, sep='\t', names=[i for i in range(22)])
    data = np.array(data).tolist()
    x = []; y = []
    for i in range(len(data)):
        y.append(data[i][-1])
        del data[i][-1]
        x.append(data[i])

    x = np.array(x)
    y = np.array(y)

    return x, y

def AdaBoost():
    train_x, train_y = load_data('ensemble/horseColicTraining.txt')
    test_x, test_y = load_data('ensemble/horseColicTest.txt')
    #训练
    clf = AdaBoostClassifier(base_estimator=DecisionTreeClassifier(max_depth=7, min_samples_leaf=7), n_estimators=100, algorithm='SAMME', learning_rate=0.95)
    clf.fit(train_x, train_y)
    #测试
    print(clf.score(test_x, test_y))


if __name__ == '__main__':
    AdaBoost()