第1关:分析红酒数据
import numpy as np
def alcohol_mean(data):
'''
返回红酒数据中红酒的酒精平均含量
:param data: 红酒数据对象
:return: 酒精平均含量,类型为float
'''
return np.mean(data['data'],axis = 0)[0]
第2关:对数据进行标准化
from sklearn.preprocessing import StandardScaler
def scaler(data):
'''
返回标准化后的红酒数据
:param data: 红酒数据对象
:return: 标准化后的红酒数据,类型为ndarray
'''
scaler = StandardScaler()
return scaler.fit_transform(data['data'])
第3关:使用kNN算法进行预测
from sklearn.neighbors import KNeighborsClassifier
from sklearn.preprocessing import StandardScaler
def classification(train_feature, train_label, test_feature):
'''
对test_feature进行红酒分类
:param train_feature: 训练集数据,类型为ndarray
:param train_label: 训练集标签,类型为ndarray
:param test_feature: 测试集数据,类型为ndarray
:return: 测试集数据的分类结果
'''
scaler = StandardScaler()
tr_feature = scaler.fit_transform(train_feature)
te_feature = scaler.transform(test_feature)
clf = KNeighborsClassifier()
clf.fit(tr_feature, train_label)
predict_result = clf.predict(te_feature)
return predict_result