import pandas as pd from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.neighbors import KNeighborsClassifier df = pd.read_csv('datatest.csv', names=['出行', '游戏时间', '冰激凌', '配对结果']) print(df) # 取所有的行,1,2,3列作为特征,4列标签结果 feature = df.iloc[:, 0:3] print(feature) target = df.iloc[:, -1] print(target) # 划分数据集test_size:测试集占比 random_state:随机数种子 # 训练集的特征数据,测试集的特征数据,训练集的目标数据,测试集的目标数据 x_train, x_test, y_train, y_test = train_test_split(feature, target, test_size=0.21, random_state=1500) print(x_train.shape, x_test.shape) # 标准化 ss = StandardScaler() x_train = ss.fit_transform(x_train) print(x_train) # 创建KMN算法对象,指定K值 knn = KNeighborsClassifier(n_neighbors=3) # 训练模型(训练集的特征数据和目标数据) knn.fit(x_train, y_train) # 用测试集验证数据,得到评价指标 # 测试集数据也必须标准化,但是不需要再计算均值和方差,训练集进行标准化的时候已经找到了均值和方差 # 已经找到转换规则,我们把这个规则用在了训练集上,同样我们可以直接用在测试集上,所以在测试集上的处理,我们只需要标准化 x_test = ss.transform(x_test) score = knn.score(x_test, y_test) print(f'模型评分{score}') # 预测 x_test1 = [[80000, 2.99, 5.65], [901, 3, 2.1]] x_test1 = ss.transform(x_test1) y_predict = knn.predict(x_test1) print(y_predict)
实验一喜好程度预测(源代码)
于 2022-03-23 16:22:15 首次发布